bot: update RSS feed
This commit is contained in:
github-actions[bot]
176
feed.xml
176
feed.xml
@@ -7,153 +7,69 @@
|
||||
<docs>http://www.rssboard.org/rss-specification</docs>
|
||||
<generator>python-feedgen</generator>
|
||||
<language>en</language>
|
||||
<lastBuildDate>Mon, 28 Jul 2025 00:02:42 +0000</lastBuildDate>
|
||||
<lastBuildDate>Tue, 29 Jul 2025 00:02:49 +0000</lastBuildDate>
|
||||
<item>
|
||||
<title>nablaNABLA: Neighborhood Adaptive Block-Level Attention</title>
|
||||
<link>https://arxiv.org/abs/2507.13546</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.13546.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Dmitrii Mikhailov, Aleksey Letunovskiy, Maria Kovaleva, Vladimir Arkhipkin, Vladimir Korviakov, Vladimir Polovnikov, Viacheslav Vasilev, Evelina Sidorova, Denis Dimitrov</p><p><b>Upvotes:</b> 100</p><p><b>Summary:</b> Recent progress in transformer-based architectures has demonstrated remarkable success in video generation tasks. However, the quadratic complexity of full attention mechanisms remains a critical bottleneck, particularly for high-resolution and long-duration video sequences. In this paper, we propose NABLA, a novel Neighborhood Adaptive Block-Level Attention mechanism that dynamically adapts to sparsity patterns in video diffusion transformers (DiTs). By leveraging block-wise attention with adaptive sparsity-driven threshold, NABLA reduces computational overhead while preserving generative quality. Our method does not require custom low-level operator design and can be seamlessly integrated with PyTorch's Flex Attention operator. Experiments demonstrate that NABLA achieves up to 2.7x faster training and inference compared to baseline almost without compromising quantitative metrics (CLIP score, VBench score, human evaluation score) and visual quality drop. The code and model weights are available here: https://github.com/gen-ai-team/Wan2.1-NABLA</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2507.13546</guid>
|
||||
<pubDate>Thu, 17 Jul 2025 21:36:36 +0000</pubDate>
|
||||
<title>Chat with AI: The Surprising Turn of Real-time Video Communication from Human to AI</title>
|
||||
<link>https://arxiv.org/abs/2507.10510</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.10510.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiangkai Wu, Zhiyuan Ren, Liming Liu, Xinggong Zhang</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> AI Video Chat emerges as a new paradigm for Real-time Communication (RTC), where one peer is not a human, but a Multimodal Large Language Model (MLLM). This makes interaction between humans and AI more intuitive, as if chatting face-to-face with a real person. However, this poses significant challenges to latency, because the MLLM inference takes up most of the response time, leaving very little time for video streaming. Due to network uncertainty and instability, transmission latency becomes a critical bottleneck preventing AI from being like a real person. To address this, we propose Artic, an AI-oriented Real-time Communication framework, exploring the network requirement shift from "humans watching video" to "AI understanding video". To reduce bitrate dramatically while maintaining MLLM accuracy, we propose Context-Aware Video Streaming that recognizes the importance of each video region for chat and allocates bitrate almost exclusively to chat-important regions. To avoid packet retransmission, we propose Loss-Resilient Adaptive Frame Rate that leverages previous frames to substitute for lost/delayed frames while avoiding bitrate waste. To evaluate the impact of video streaming quality on MLLM accuracy, we build the first benchmark, named Degraded Video Understanding Benchmark (DeViBench). Finally, we discuss some open questions and ongoing solutions for AI Video Chat.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2507.10510</guid>
|
||||
<pubDate>Mon, 14 Jul 2025 17:34:49 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>MUR: Momentum Uncertainty guided Reasoning for Large Language Models</title>
|
||||
<link>https://arxiv.org/abs/2507.14958</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.14958.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Hang Yan, Fangzhi Xu, Rongman Xu, Yifei Li, Jian Zhang, Haoran Luo, Xiaobao Wu, Luu Anh Tuan, Haiteng Zhao, Qika Lin, Jun Liu</p><p><b>Upvotes:</b> 37</p><p><b>Summary:</b> Large Language Models (LLMs) have achieved impressive performance on reasoning-intensive tasks, yet optimizing their reasoning efficiency remains an open challenge. While Test-Time Scaling (TTS) improves reasoning quality, it often leads to overthinking, wasting tokens on redundant computations. This work investigates how to efficiently and adaptively guide LLM test-time scaling without additional training. Inspired by the concept of momentum in physics, we propose Momentum Uncertainty-guided Reasoning (MUR), which dynamically allocates thinking budgets to critical reasoning steps by tracking and aggregating stepwise uncertainty over time. To support flexible inference-time control, we introduce gamma-control, a simple mechanism that tunes the reasoning budget via a single hyperparameter. We provide in-depth theoretical proof to support the superiority of MUR in terms of stability and biases. MUR is comprehensively evaluated against various TTS methods across four challenging benchmarks (MATH-500, AIME24, AIME25, and GPQA-diamond) using different sizes of recent Qwen3 models (1.7B, 4B, and 8B). Results demonstrate that MUR reduces computation by over 50% on average while improving accuracy by 0.62-3.37%.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2507.14958</guid>
|
||||
<pubDate>Sun, 20 Jul 2025 13:36:19 +0000</pubDate>
|
||||
<title>Deep Researcher with Test-Time Diffusion</title>
|
||||
<link>https://arxiv.org/abs/2507.16075</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.16075.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Rujun Han, Yanfei Chen, Zoey CuiZhu, Lesly Miculicich, Guan Sun, Yuanjun Bi, Weiming Wen, Hui Wan, Chunfeng Wen, Solène Maître, George Lee, Vishy Tirumalashetty, Emily Xue, Zizhao Zhang, Salem Haykal, Burak Gokturk, Tomas Pfister, Chen-Yu Lee</p><p><b>Upvotes:</b> 23</p><p><b>Summary:</b> Deep research agents, powered by Large Language Models (LLMs), are rapidly advancing; yet, their performance often plateaus when generating complex, long-form research reports using generic test-time scaling algorithms. Drawing inspiration from the iterative nature of human research, which involves cycles of searching, reasoning, and revision, we propose the Test-Time Diffusion Deep Researcher (TTD-DR). This novel framework conceptualizes research report generation as a diffusion process. TTD-DR initiates this process with a preliminary draft, an updatable skeleton that serves as an evolving foundation to guide the research direction. The draft is then iteratively refined through a "denoising" process, which is dynamically informed by a retrieval mechanism that incorporates external information at each step. The core process is further enhanced by a self-evolutionary algorithm applied to each component of the agentic workflow, ensuring the generation of high-quality context for the diffusion process. This draft-centric design makes the report writing process more timely and coherent while reducing information loss during the iterative search process. We demonstrate that our TTD-DR achieves state-of-the-art results on a wide array of benchmarks that require intensive search and multi-hop reasoning, significantly outperforming existing deep research agents.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2507.16075</guid>
|
||||
<pubDate>Mon, 21 Jul 2025 21:23:21 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>DMOSpeech 2: Reinforcement Learning for Duration Prediction in Metric-Optimized Speech Synthesis</title>
|
||||
<link>https://arxiv.org/abs/2507.14988</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.14988.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yinghao Aaron Li, Xilin Jiang, Fei Tao, Cheng Niu, Kaifeng Xu, Juntong Song, Nima Mesgarani</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> Diffusion-based text-to-speech (TTS) systems have made remarkable progress in zero-shot speech synthesis, yet optimizing all components for perceptual metrics remains challenging. Prior work with DMOSpeech demonstrated direct metric optimization for speech generation components, but duration prediction remained unoptimized. This paper presents DMOSpeech 2, which extends metric optimization to the duration predictor through a reinforcement learning approach. The proposed system implements a novel duration policy framework using group relative preference optimization (GRPO) with speaker similarity and word error rate as reward signals. By optimizing this previously unoptimized component, DMOSpeech 2 creates a more complete metric-optimized synthesis pipeline. Additionally, this paper introduces teacher-guided sampling, a hybrid approach leveraging a teacher model for initial denoising steps before transitioning to the student model, significantly improving output diversity while maintaining efficiency. Comprehensive evaluations demonstrate superior performance across all metrics compared to previous systems, while reducing sampling steps by half without quality degradation. These advances represent a significant step toward speech synthesis systems with metric optimization across multiple components. The audio samples, code and pre-trained models are available at https://dmospeech2.github.io/.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2507.14988</guid>
|
||||
<pubDate>Sun, 20 Jul 2025 14:48:48 +0000</pubDate>
|
||||
<title>Frontier AI Risk Management Framework in Practice: A Risk Analysis Technical Report</title>
|
||||
<link>https://arxiv.org/abs/2507.16534</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.16534.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shanghai AI Lab, Xiaoyang Chen, Yunhao Chen, Zeren Chen, Zhiyun Chen, Hanyun Cui, Yawen Duan, Jiaxuan Guo, Qi Guo, Xuhao Hu, Hong Huang, Lige Huang, Chunxiao Li, Juncheng Li, Qihao Lin, Dongrui Liu, Xinmin Liu, Zicheng Liu, Chaochao Lu, Xiaoya Lu, Jingjing Qu, Qibing Ren, Jing Shao, Jingwei Shi, Jingwei Sun, Peng Wang, Weibing Wang, Jia Xu, Lewen Yan, Xiao Yu, Yi Yu, Boxuan Zhang, Jie Zhang, Weichen Zhang, Zhijie Zheng, Tianyi Zhou, Bowen Zhou</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> To understand and identify the unprecedented risks posed by rapidly advancing artificial intelligence (AI) models, this report presents a comprehensive assessment of their frontier risks. Drawing on the E-T-C analysis (deployment environment, threat source, enabling capability) from the Frontier AI Risk Management Framework (v1.0) (SafeWork-F1-Framework), we identify critical risks in seven areas: cyber offense, biological and chemical risks, persuasion and manipulation, uncontrolled autonomous AI R\&D, strategic deception and scheming, self-replication, and collusion. Guided by the "AI-45^circ Law," we evaluate these risks using "red lines" (intolerable thresholds) and "yellow lines" (early warning indicators) to define risk zones: green (manageable risk for routine deployment and continuous monitoring), yellow (requiring strengthened mitigations and controlled deployment), and red (necessitating suspension of development and/or deployment). Experimental results show that all recent frontier AI models reside in green and yellow zones, without crossing red lines. Specifically, no evaluated models cross the yellow line for cyber offense or uncontrolled AI R\&D risks. For self-replication, and strategic deception and scheming, most models remain in the green zone, except for certain reasoning models in the yellow zone. In persuasion and manipulation, most models are in the yellow zone due to their effective influence on humans. For biological and chemical risks, we are unable to rule out the possibility of most models residing in the yellow zone, although detailed threat modeling and in-depth assessment are required to make further claims. This work reflects our current understanding of AI frontier risks and urges collective action to mitigate these challenges.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2507.16534</guid>
|
||||
<pubDate>Tue, 22 Jul 2025 12:44:38 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>SegDT: A Diffusion Transformer-Based Segmentation Model for Medical Imaging</title>
|
||||
<link>https://arxiv.org/abs/2507.15595</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.15595.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Salah Eddine Bekhouche, Gaby Maroun, Fadi Dornaika, Abdenour Hadid</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Medical image segmentation is crucial for many healthcare tasks, including disease diagnosis and treatment planning. One key area is the segmentation of skin lesions, which is vital for diagnosing skin cancer and monitoring patients. In this context, this paper introduces SegDT, a new segmentation model based on diffusion transformer (DiT). SegDT is designed to work on low-cost hardware and incorporates Rectified Flow, which improves the generation quality at reduced inference steps and maintains the flexibility of standard diffusion models. Our method is evaluated on three benchmarking datasets and compared against several existing works, achieving state-of-the-art results while maintaining fast inference speeds. This makes the proposed model appealing for real-world medical applications. This work advances the performance and capabilities of deep learning models in medical image analysis, enabling faster, more accurate diagnostic tools for healthcare professionals. The code is made publicly available at https://github.com/Bekhouche/SegDT{GitHub}.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2507.15595</guid>
|
||||
<pubDate>Mon, 21 Jul 2025 13:18:05 +0000</pubDate>
|
||||
<title>PRIX: Learning to Plan from Raw Pixels for End-to-End Autonomous Driving</title>
|
||||
<link>https://arxiv.org/abs/2507.17596</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.17596.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Maciej K. Wozniak, Lianhang Liu, Yixi Cai, Patric Jensfelt</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> While end-to-end autonomous driving models show promising results, their practical deployment is often hindered by large model sizes, a reliance on expensive LiDAR sensors and computationally intensive BEV feature representations. This limits their scalability, especially for mass-market vehicles equipped only with cameras. To address these challenges, we propose PRIX (Plan from Raw Pixels). Our novel and efficient end-to-end driving architecture operates using only camera data, without explicit BEV representation and forgoing the need for LiDAR. PRIX leverages a visual feature extractor coupled with a generative planning head to predict safe trajectories from raw pixel inputs directly. A core component of our architecture is the Context-aware Recalibration Transformer (CaRT), a novel module designed to effectively enhance multi-level visual features for more robust planning. We demonstrate through comprehensive experiments that PRIX achieves state-of-the-art performance on the NavSim and nuScenes benchmarks, matching the capabilities of larger, multimodal diffusion planners while being significantly more efficient in terms of inference speed and model size, making it a practical solution for real-world deployment. Our work is open-source and the code will be at https://maxiuw.github.io/prix.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2507.17596</guid>
|
||||
<pubDate>Wed, 23 Jul 2025 15:28:23 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>LAPO: Internalizing Reasoning Efficiency via Length-Adaptive Policy Optimization</title>
|
||||
<link>https://arxiv.org/abs/2507.15758</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.15758.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xingyu Wu, Yuchen Yan, Shangke Lyu, Linjuan Wu, Yiwen Qiu, Yongliang Shen, Weiming Lu, Jian Shao, Jun Xiao, Yueting Zhuang</p><p><b>Upvotes:</b> 30</p><p><b>Summary:</b> Large reasoning models have achieved remarkable performance through extended chain-of-thought sequences, yet this computational freedom leads to excessive token generation even for simple problems. We present Length-Adaptive Policy Optimization (LAPO), a novel framework that transforms reasoning length control from an external constraint into an intrinsic model capability. Unlike existing approaches that impose rigid limits or rely on post-hoc interventions, LAPO enables models to internalize an understanding of appropriate reasoning depth through a two-stage reinforcement learning process. In the first stage, models learn natural reasoning patterns by discovering the statistical distribution of successful solution lengths. The second stage leverages these patterns as meta-cognitive guidance, embedding them directly within the model's reasoning context to ensure inference-time flexibility. Experiments on mathematical reasoning benchmarks demonstrate that LAPO reduces token usage by up to 40.9\% while improving accuracy by 2.3\%. Our analysis reveals that models trained with LAPO develop emergent abilities to allocate computational resources based on problem complexity, achieving efficient reasoning without sacrificing quality.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2507.15758</guid>
|
||||
<pubDate>Mon, 21 Jul 2025 16:14:41 +0000</pubDate>
|
||||
<title>CLEAR: Error Analysis via LLM-as-a-Judge Made Easy</title>
|
||||
<link>https://arxiv.org/abs/2507.18392</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.18392.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Asaf Yehudai, Lilach Eden, Yotam Perlitz, Roy Bar-Haim, Michal Shmueli-Scheuer</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> The evaluation of Large Language Models (LLMs) increasingly relies on other LLMs acting as judges. However, current evaluation paradigms typically yield a single score or ranking, answering which model is better but not why. While essential for benchmarking, these top-level scores obscure the specific, actionable reasons behind a model's performance. To bridge this gap, we introduce CLEAR, an interactive, open-source package for LLM-based error analysis. CLEAR first generates per-instance textual feedback, then it creates a set of system-level error issues, and quantifies the prevalence of each identified issue. Our package also provides users with an interactive dashboard that allows for a comprehensive error analysis through aggregate visualizations, applies interactive filters to isolate specific issues or score ranges, and drills down to the individual instances that exemplify a particular behavioral pattern. We demonstrate CLEAR analysis for RAG and Math benchmarks, and showcase its utility through a user case study.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2507.18392</guid>
|
||||
<pubDate>Thu, 24 Jul 2025 13:15:21 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>True Multimodal In-Context Learning Needs Attention to the Visual Context</title>
|
||||
<link>https://arxiv.org/abs/2507.15807</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.15807.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shuo Chen, Jianzhe Liu, Zhen Han, Yan Xia, Daniel Cremers, Philip Torr, Volker Tresp, Jindong Gu</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Multimodal Large Language Models (MLLMs), built on powerful language backbones, have enabled Multimodal In-Context Learning (MICL)-adapting to new tasks from a few multimodal demonstrations consisting of images, questions, and answers. Despite showing noticeable improvement on standard vision-language datasets, current MLLMs struggle to leverage visual information in the demonstrations. Specifically, they tend to neglect visual cues and over-rely on textual patterns, leading to mere text imitation rather than genuine multimodal adaptation. This behavior makes MICL still unimodal and largely restricts its practical utility. More importantly, this limitation is often concealed by the improved performance on tasks that do not require understanding the visual context. As a result, how to effectively enhance MICL ability and reliably evaluate the MICL performance remains underexplored. To address these issues, we first introduce Dynamic Attention Reallocation (DARA), an efficient fine-tuning strategy that encourages models to attend to the visual context by rebalancing attention across visual and textual tokens. In addition, we present TrueMICL, an MICL-dedicated dataset with both support and test sets that explicitly requires the integration of multimodal information-particularly visual content-for correct task completion. Extensive experiments demonstrate the effectiveness of our holistic solution, showcasing substantial improvements in the true multimodal in-context learning capabilities. Code and datasets are available at https://chenxshuo.github.io/true-micl-colm .</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2507.15807</guid>
|
||||
<pubDate>Mon, 21 Jul 2025 17:08:18 +0000</pubDate>
|
||||
<title>The Geometry of LLM Quantization: GPTQ as Babai's Nearest Plane Algorithm</title>
|
||||
<link>https://arxiv.org/abs/2507.18553</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.18553.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jiale Chen, Torsten Hoefler, Dan Alistarh</p><p><b>Upvotes:</b> 17</p><p><b>Summary:</b> Quantizing the weights of large language models (LLMs) from 16-bit to lower bitwidth is the de facto approach to deploy massive transformers onto more affordable accelerators. GPTQ emerged as one of the standard methods for one-shot post-training quantization at LLM scale. Yet, its inner workings are described as a sequence of ad-hoc algebraic updates that obscure any geometric meaning or worst-case guarantees. In this work, we show that, when executed back-to-front (from the last to first dimension) for a linear layer, GPTQ is mathematically identical to Babai's nearest plane algorithm for the classical closest vector problem (CVP) on a lattice defined by the Hessian matrix of the layer's inputs. This equivalence is based on a sophisticated mathematical argument, and has two analytical consequences: (i) the GPTQ error propagation step gains an intuitive geometric interpretation; (ii) GPTQ inherits the error upper bound of Babai's algorithm under the no-clipping condition. Taken together, these results place GPTQ on firm theoretical footing and open the door to importing decades of progress in lattice algorithms towards the design of future quantization algorithms for billion-parameter models.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2507.18553</guid>
|
||||
<pubDate>Thu, 24 Jul 2025 16:22:18 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Hierarchical Budget Policy Optimization for Adaptive Reasoning</title>
|
||||
<link>https://arxiv.org/abs/2507.15844</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.15844.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shangke Lyu, Linjuan Wu, Yuchen Yan, Xingyu Wu, Hao Li, Yongliang Shen, Peisheng Jiang, Weiming Lu, Jun Xiao, Yueting Zhuang</p><p><b>Upvotes:</b> 15</p><p><b>Summary:</b> Large reasoning models achieve remarkable performance through extensive chain-of-thought generation, yet exhibit significant computational inefficiency by applying uniform reasoning strategies regardless of problem complexity. We present Hierarchical Budget Policy Optimization (HBPO), a reinforcement learning framework that enables models to learn problem-specific reasoning depths without sacrificing capability. HBPO addresses the fundamental challenge of exploration space collapse in efficiency-oriented training, where penalties on long output length systematically bias models away from necessary long reasoning paths. Through hierarchical budget exploration, our approach partitions rollout samples into multiple subgroups with distinct token budgets, aiming to enable efficient resource allocation while preventing degradation of capability. We introduce differentiated reward mechanisms that create budget-aware incentives aligned with the complexity of the problem, allowing models to discover natural correspondences between task requirements and computational effort. Extensive experiments demonstrate that HBPO reduces average token usage by up to 60.6% while improving accuracy by 3.14% across four reasoning benchmarks. Unlike existing methods that impose external constraints or rely on discrete mode selection, HBPO exhibits emergent adaptive behavior where models automatically adjust reasoning depth based on problem complexity. Our results suggest that reasoning efficiency and capability are not inherently conflicting, and can be simultaneously optimized through appropriately structured hierarchical training that preserves exploration diversity.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2507.15844</guid>
|
||||
<pubDate>Mon, 21 Jul 2025 17:52:34 +0000</pubDate>
|
||||
<title>Specification Self-Correction: Mitigating In-Context Reward Hacking Through Test-Time Refinement</title>
|
||||
<link>https://arxiv.org/abs/2507.18742</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.18742.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Víctor Gallego</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Language models (LMs) are susceptible to in-context reward hacking, where they exploit flaws in tainted or faulty written specifications or rubrics to achieve high scores without fulfilling the user's true intent. We introduce Specification Self-Correction (SSC), a novel, test-time framework that enables an LM to identify and correct flaws within its own guiding specification. SSC employs a multi-step inference process where the model first generates a response based on a potentially tainted specification, critiques its output, and then revises the specification itself to remove the exploitable loophole. A final, more robust response is then generated using this self-corrected specification. Across experiments spanning creative writing and agentic coding tasks with several LMs, we demonstrate that while models initially game tainted specifications in 50-70\% of cases, the SSC process reduces this vulnerability by over 90\%. This dynamic repair occurs at inference time, requires no weight modification, and leads to more robustly aligned model behavior. Code at https://github.com/vicgalle/specification-self-correction .</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2507.18742</guid>
|
||||
<pubDate>Thu, 24 Jul 2025 18:44:28 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Discovering and using Spelke segments</title>
|
||||
<link>https://arxiv.org/abs/2507.16038</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.16038.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Rahul Venkatesh, Klemen Kotar, Lilian Naing Chen, Seungwoo Kim, Luca Thomas Wheeler, Jared Watrous, Ashley Xu, Gia Ancone, Wanhee Lee, Honglin Chen, Daniel Bear, Stefan Stojanov, Daniel Yamins</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> Segments in computer vision are often defined by semantic considerations and are highly dependent on category-specific conventions. In contrast, developmental psychology suggests that humans perceive the world in terms of Spelke objects--groupings of physical things that reliably move together when acted on by physical forces. Spelke objects thus operate on category-agnostic causal motion relationships which potentially better support tasks like manipulation and planning. In this paper, we first benchmark the Spelke object concept, introducing the SpelkeBench dataset that contains a wide variety of well-defined Spelke segments in natural images. Next, to extract Spelke segments from images algorithmically, we build SpelkeNet, a class of visual world models trained to predict distributions over future motions. SpelkeNet supports estimation of two key concepts for Spelke object discovery: (1) the motion affordance map, identifying regions likely to move under a poke, and (2) the expected-displacement map, capturing how the rest of the scene will move. These concepts are used for "statistical counterfactual probing", where diverse "virtual pokes" are applied on regions of high motion-affordance, and the resultant expected displacement maps are used define Spelke segments as statistical aggregates of correlated motion statistics. We find that SpelkeNet outperforms supervised baselines like SegmentAnything (SAM) on SpelkeBench. Finally, we show that the Spelke concept is practically useful for downstream applications, yielding superior performance on the 3DEditBench benchmark for physical object manipulation when used in a variety of off-the-shelf object manipulation models.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2507.16038</guid>
|
||||
<pubDate>Mon, 21 Jul 2025 20:11:57 +0000</pubDate>
|
||||
<title>GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning</title>
|
||||
<link>https://arxiv.org/abs/2507.19457</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.19457.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Lakshya A Agrawal, Shangyin Tan, Dilara Soylu, Noah Ziems, Rishi Khare, Krista Opsahl-Ong, Arnav Singhvi, Herumb Shandilya, Michael J Ryan, Meng Jiang, Christopher Potts, Koushik Sen, Alexandros G. Dimakis, Ion Stoica, Dan Klein, Matei Zaharia, Omar Khattab</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Large language models (LLMs) are increasingly adapted to downstream tasks via reinforcement learning (RL) methods like Group Relative Policy Optimization (GRPO), which often require thousands of rollouts to learn new tasks. We argue that the interpretable nature of language can often provide a much richer learning medium for LLMs, compared with policy gradients derived from sparse, scalar rewards. To test this, we introduce GEPA (Genetic-Pareto), a prompt optimizer that thoroughly incorporates natural language reflection to learn high-level rules from trial and error. Given any AI system containing one or more LLM prompts, GEPA samples system-level trajectories (e.g., reasoning, tool calls, and tool outputs) and reflects on them in natural language to diagnose problems, propose and test prompt updates, and combine complementary lessons from the Pareto frontier of its own attempts. As a result of GEPA's design, it can often turn even just a few rollouts into a large quality gain. Across four tasks, GEPA outperforms GRPO by 10% on average and by up to 20%, while using up to 35x fewer rollouts. GEPA also outperforms the leading prompt optimizer, MIPROv2, by over 10% across two LLMs, and demonstrates promising results as an inference-time search strategy for code optimization.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2507.19457</guid>
|
||||
<pubDate>Fri, 25 Jul 2025 17:42:32 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>EarthCrafter: Scalable 3D Earth Generation via Dual-Sparse Latent Diffusion</title>
|
||||
<link>https://arxiv.org/abs/2507.16535</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.16535.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Shang Liu, Chenjie Cao, Chaohui Yu, Wen Qian, Jing Wang, Fan Wang</p><p><b>Upvotes:</b> 11</p><p><b>Summary:</b> Despite the remarkable developments achieved by recent 3D generation works, scaling these methods to geographic extents, such as modeling thousands of square kilometers of Earth's surface, remains an open challenge. We address this through a dual innovation in data infrastructure and model architecture. First, we introduce Aerial-Earth3D, the largest 3D aerial dataset to date, consisting of 50k curated scenes (each measuring 600m x 600m) captured across the U.S. mainland, comprising 45M multi-view Google Earth frames. Each scene provides pose-annotated multi-view images, depth maps, normals, semantic segmentation, and camera poses, with explicit quality control to ensure terrain diversity. Building on this foundation, we propose EarthCrafter, a tailored framework for large-scale 3D Earth generation via sparse-decoupled latent diffusion. Our architecture separates structural and textural generation: 1) Dual sparse 3D-VAEs compress high-resolution geometric voxels and textural 2D Gaussian Splats (2DGS) into compact latent spaces, largely alleviating the costly computation suffering from vast geographic scales while preserving critical information. 2) We propose condition-aware flow matching models trained on mixed inputs (semantics, images, or neither) to flexibly model latent geometry and texture features independently. Extensive experiments demonstrate that EarthCrafter performs substantially better in extremely large-scale generation. The framework further supports versatile applications, from semantic-guided urban layout generation to unconditional terrain synthesis, while maintaining geographic plausibility through our rich data priors from Aerial-Earth3D. Our project page is available at https://whiteinblue.github.io/earthcrafter/</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2507.16535</guid>
|
||||
<pubDate>Tue, 22 Jul 2025 12:46:48 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Agentar-Fin-R1: Enhancing Financial Intelligence through Domain Expertise, Training Efficiency, and Advanced Reasoning</title>
|
||||
<link>https://arxiv.org/abs/2507.16802</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.16802.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yanjun Zheng, Xiyang Du, Longfei Liao, Xiaoke Zhao, Zhaowen Zhou, Jingze Song, Bo Zhang, Jiawei Liu, Xiang Qi, Zhe Li, Zhiqiang Zhang, Wei Wang, Peng Zhang</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> Large Language Models (LLMs) exhibit considerable promise in financial applications; however, prevailing models frequently demonstrate limitations when confronted with scenarios that necessitate sophisticated reasoning capabilities, stringent trustworthiness criteria, and efficient adaptation to domain-specific requirements. We introduce the Agentar-Fin-R1 series of financial large language models (8B and 32B parameters), specifically engineered based on the Qwen3 foundation model to enhance reasoning capabilities, reliability, and domain specialization for financial applications. Our optimization approach integrates a high-quality, systematic financial task label system with a comprehensive multi-layered trustworthiness assurance framework. This framework encompasses high-quality trustworthy knowledge engineering, multi-agent trustworthy data synthesis, and rigorous data validation governance. Through label-guided automated difficulty-aware optimization, tow-stage training pipeline, and dynamic attribution systems, we achieve substantial improvements in training efficiency. Our models undergo comprehensive evaluation on mainstream financial benchmarks including Fineva, FinEval, and FinanceIQ, as well as general reasoning datasets such as MATH-500 and GPQA-diamond. To thoroughly assess real-world deployment capabilities, we innovatively propose the Finova evaluation benchmark, which focuses on agent-level financial reasoning and compliance verification. Experimental results demonstrate that Agentar-Fin-R1 not only achieves state-of-the-art performance on financial tasks but also exhibits exceptional general reasoning capabilities, validating its effectiveness as a trustworthy solution for high-stakes financial applications. The Finova bench is available at https://github.com/antgroup/Finova.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2507.16802</guid>
|
||||
<pubDate>Tue, 22 Jul 2025 17:52:16 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>HLFormer: Enhancing Partially Relevant Video Retrieval with Hyperbolic Learning</title>
|
||||
<link>https://arxiv.org/abs/2507.17402</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.17402.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Li Jun, Wang Jinpeng, Tan Chaolei, Lian Niu, Chen Long, Zhang Min, Wang Yaowei, Xia Shu-Tao, Chen Bin</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Partially Relevant Video Retrieval (PRVR) addresses the critical challenge of matching untrimmed videos with text queries describing only partial content. Existing methods suffer from geometric distortion in Euclidean space that sometimes misrepresents the intrinsic hierarchical structure of videos and overlooks certain hierarchical semantics, ultimately leading to suboptimal temporal modeling. To address this issue, we propose the first hyperbolic modeling framework for PRVR, namely HLFormer, which leverages hyperbolic space learning to compensate for the suboptimal hierarchical modeling capabilities of Euclidean space. Specifically, HLFormer integrates the Lorentz Attention Block and Euclidean Attention Block to encode video embeddings in hybrid spaces, using the Mean-Guided Adaptive Interaction Module to dynamically fuse features. Additionally, we introduce a Partial Order Preservation Loss to enforce "text < video" hierarchy through Lorentzian cone constraints. This approach further enhances cross-modal matching by reinforcing partial relevance between video content and text queries. Extensive experiments show that HLFormer outperforms state-of-the-art methods. Code is released at https://github.com/lijun2005/ICCV25-HLFormer.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2507.17402</guid>
|
||||
<pubDate>Wed, 23 Jul 2025 10:59:46 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Technical Report of TeleChat2, TeleChat2.5 and T1</title>
|
||||
<link>https://arxiv.org/abs/2507.18013</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.18013.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zihan Wang, Xinzhang Liu, Yitong Yao, Chao Wang, Yu Zhao, Zhihao Yang, Wenmin Deng, Kaipeng Jia, Jiaxin Peng, Yuyao Huang, Sishi Xiong, Zhuo Jiang, Kaidong Yu, Xiaohui Hu, Fubei Yao, Ruiyu Fang, Zhuoru Jiang, Ruiting Song, Qiyi Xie, Rui Xue, Xuewei He, Yanlei Xue, Zhu Yuan, Zhaoxi Zhang, Zilu Huang, Shiquan Wang, Xin Wang, Hanming Wu, Mingyuan Wang, Xufeng Zhan, Yuhan Sun, Zhaohu Xing, Yuhao Jiang, Bingkai Yang, Shuangyong Song, Yongxiang Li, Zhongjiang He, Xuelong Li</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> We introduce the latest series of TeleChat models: TeleChat2, TeleChat2.5, and T1, offering a significant upgrade over their predecessor, TeleChat. Despite minimal changes to the model architecture, the new series achieves substantial performance gains through enhanced training strategies in both pre-training and post-training stages. The series begins with TeleChat2, which undergoes pretraining on 10 trillion high-quality and diverse tokens. This is followed by Supervised Fine-Tuning (SFT) and Direct Preference Optimization (DPO) to further enhance its capabilities. TeleChat2.5 and T1 expand the pipeline by incorporating a continual pretraining phase with domain-specific datasets, combined with reinforcement learning (RL) to improve performance in code generation and mathematical reasoning tasks. The T1 variant is designed for complex reasoning, supporting long Chain-of-Thought (CoT) reasoning and demonstrating substantial improvements in mathematics and coding. In contrast, TeleChat2.5 prioritizes speed, delivering rapid inference. Both flagship models of T1 and TeleChat2.5 are dense Transformer-based architectures with 115B parameters, showcasing significant advancements in reasoning and general task performance compared to the original TeleChat. Notably, T1-115B outperform proprietary models such as OpenAI's o1-mini and GPT-4o. We publicly release TeleChat2, TeleChat2.5 and T1, including post-trained versions with 35B and 115B parameters, to empower developers and researchers with state-of-the-art language models tailored for diverse applications.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2507.18013</guid>
|
||||
<pubDate>Thu, 24 Jul 2025 01:00:48 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Group Sequence Policy Optimization</title>
|
||||
<link>https://arxiv.org/abs/2507.18071</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.18071.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Chujie Zheng, Shixuan Liu, Mingze Li, Xiong-Hui Chen, Bowen Yu, Chang Gao, Kai Dang, Yuqiong Liu, Rui Men, An Yang, Jingren Zhou, Junyang Lin</p><p><b>Upvotes:</b> 121</p><p><b>Summary:</b> This paper introduces Group Sequence Policy Optimization (GSPO), our stable, efficient, and performant reinforcement learning algorithm for training large language models. Unlike previous algorithms that adopt token-level importance ratios, GSPO defines the importance ratio based on sequence likelihood and performs sequence-level clipping, rewarding, and optimization. We demonstrate that GSPO achieves superior training efficiency and performance compared to the GRPO algorithm, notably stabilizes Mixture-of-Experts (MoE) RL training, and has the potential for simplifying the design of RL infrastructure. These merits of GSPO have contributed to the remarkable improvements in the latest Qwen3 models.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2507.18071</guid>
|
||||
<pubDate>Thu, 24 Jul 2025 03:50:32 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>A New Pair of GloVes</title>
|
||||
<link>https://arxiv.org/abs/2507.18103</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.18103.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Riley Carlson, John Bauer, Christopher D. Manning</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> This report documents, describes, and evaluates new 2024 English GloVe (Global Vectors for Word Representation) models. While the original GloVe models built in 2014 have been widely used and found useful, languages and the world continue to evolve and we thought that current usage could benefit from updated models. Moreover, the 2014 models were not carefully documented as to the exact data versions and preprocessing that were used, and we rectify this by documenting these new models. We trained two sets of word embeddings using Wikipedia, Gigaword, and a subset of Dolma. Evaluation through vocabulary comparison, direct testing, and NER tasks shows that the 2024 vectors incorporate new culturally and linguistically relevant words, perform comparably on structural tasks like analogy and similarity, and demonstrate improved performance on recent, temporally dependent NER datasets such as non-Western newswire data.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2507.18103</guid>
|
||||
<pubDate>Thu, 24 Jul 2025 05:29:18 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>TeEFusion: Blending Text Embeddings to Distill Classifier-Free Guidance</title>
|
||||
<link>https://arxiv.org/abs/2507.18192</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.18192.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Minghao Fu, Guo-Hua Wang, Xiaohao Chen, Qing-Guo Chen, Zhao Xu, Weihua Luo, Kaifu Zhang</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Recent advances in text-to-image synthesis largely benefit from sophisticated sampling strategies and classifier-free guidance (CFG) to ensure high-quality generation. However, CFG's reliance on two forward passes, especially when combined with intricate sampling algorithms, results in prohibitively high inference costs. To address this, we introduce TeEFusion (Text Embeddings Fusion), a novel and efficient distillation method that directly incorporates the guidance magnitude into the text embeddings and distills the teacher model's complex sampling strategy. By simply fusing conditional and unconditional text embeddings using linear operations, TeEFusion reconstructs the desired guidance without adding extra parameters, simultaneously enabling the student model to learn from the teacher's output produced via its sophisticated sampling approach. Extensive experiments on state-of-the-art models such as SD3 demonstrate that our method allows the student to closely mimic the teacher's performance with a far simpler and more efficient sampling strategy. Consequently, the student model achieves inference speeds up to 6times faster than the teacher model, while maintaining image quality at levels comparable to those obtained through the teacher's complex sampling approach. The code is publicly available at https://github.com/AIDC-AI/TeEFusion{github.com/AIDC-AI/TeEFusion}.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2507.18192</guid>
|
||||
<pubDate>Thu, 24 Jul 2025 08:45:40 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Iwin Transformer: Hierarchical Vision Transformer using Interleaved Windows</title>
|
||||
<link>https://arxiv.org/abs/2507.18405</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.18405.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Simin Huo, Ning Li</p><p><b>Upvotes:</b> 3</p><p><b>Summary:</b> We introduce Iwin Transformer, a novel position-embedding-free hierarchical vision transformer, which can be fine-tuned directly from low to high resolution, through the collaboration of innovative interleaved window attention and depthwise separable convolution. This approach uses attention to connect distant tokens and applies convolution to link neighboring tokens, enabling global information exchange within a single module, overcoming Swin Transformer's limitation of requiring two consecutive blocks to approximate global attention. Extensive experiments on visual benchmarks demonstrate that Iwin Transformer exhibits strong competitiveness in tasks such as image classification (87.4 top-1 accuracy on ImageNet-1K), semantic segmentation and video action recognition. We also validate the effectiveness of the core component in Iwin as a standalone module that can seamlessly replace the self-attention module in class-conditional image generation. The concepts and methods introduced by the Iwin Transformer have the potential to inspire future research, like Iwin 3D Attention in video generation. The code and models are available at https://github.com/cominder/Iwin-Transformer.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2507.18405</guid>
|
||||
<pubDate>Thu, 24 Jul 2025 13:45:48 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>DriftMoE: A Mixture of Experts Approach to Handle Concept Drifts</title>
|
||||
<link>https://arxiv.org/abs/2507.18464</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.18464.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Miguel Aspis, Sebastián A. Cajas Ordónez, Andrés L. Suárez-Cetrulo, Ricardo Simón Carbajo</p><p><b>Upvotes:</b> 8</p><p><b>Summary:</b> Learning from non-stationary data streams subject to concept drift requires models that can adapt on-the-fly while remaining resource-efficient. Existing adaptive ensemble methods often rely on coarse-grained adaptation mechanisms or simple voting schemes that fail to optimally leverage specialized knowledge. This paper introduces DriftMoE, an online Mixture-of-Experts (MoE) architecture that addresses these limitations through a novel co-training framework. DriftMoE features a compact neural router that is co-trained alongside a pool of incremental Hoeffding tree experts. The key innovation lies in a symbiotic learning loop that enables expert specialization: the router selects the most suitable expert for prediction, the relevant experts update incrementally with the true label, and the router refines its parameters using a multi-hot correctness mask that reinforces every accurate expert. This feedback loop provides the router with a clear training signal while accelerating expert specialization. We evaluate DriftMoE's performance across nine state-of-the-art data stream learning benchmarks spanning abrupt, gradual, and real-world drifts testing two distinct configurations: one where experts specialize on data regimes (multi-class variant), and another where they focus on single-class specialization (task-based variant). Our results demonstrate that DriftMoE achieves competitive results with state-of-the-art stream learning adaptive ensembles, offering a principled and efficient approach to concept drift adaptation. All code, data pipelines, and reproducibility scripts are available in our public GitHub repository: https://github.com/miguel-ceadar/drift-moe.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2507.18464</guid>
|
||||
<pubDate>Thu, 24 Jul 2025 14:39:20 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>TTS-VAR: A Test-Time Scaling Framework for Visual Auto-Regressive Generation</title>
|
||||
<link>https://arxiv.org/abs/2507.18537</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.18537.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zhekai Chen, Ruihang Chu, Yukang Chen, Shiwei Zhang, Yujie Wei, Yingya Zhang, Xihui Liu</p><p><b>Upvotes:</b> 13</p><p><b>Summary:</b> Scaling visual generation models is essential for real-world content creation, yet requires substantial training and computational expenses. Alternatively, test-time scaling has garnered growing attention due to resource efficiency and promising performance. In this work, we present TTS-VAR, the first general test-time scaling framework for visual auto-regressive (VAR) models, modeling the generation process as a path searching problem. To dynamically balance computational efficiency with exploration capacity, we first introduce an adaptive descending batch size schedule throughout the causal generation process. Besides, inspired by VAR's hierarchical coarse-to-fine multi-scale generation, our framework integrates two key components: (i) At coarse scales, we observe that generated tokens are hard for evaluation, possibly leading to erroneous acceptance of inferior samples or rejection of superior samples. Noticing that the coarse scales contain sufficient structural information, we propose clustering-based diversity search. It preserves structural variety through semantic feature clustering, enabling later selection on samples with higher potential. (ii) In fine scales, resampling-based potential selection prioritizes promising candidates using potential scores, which are defined as reward functions incorporating multi-scale generation history. Experiments on the powerful VAR model Infinity show a notable 8.7% GenEval score improvement (from 0.69 to 0.75). Key insights reveal that early-stage structural features effectively influence final quality, and resampling efficacy varies across generation scales. Code is available at https://github.com/ali-vilab/TTS-VAR.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2507.18537</guid>
|
||||
<pubDate>Thu, 24 Jul 2025 16:04:55 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>GLiNER2: An Efficient Multi-Task Information Extraction System with Schema-Driven Interface</title>
|
||||
<link>https://arxiv.org/abs/2507.18546</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.18546.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Urchade Zaratiana, Gil Pasternak, Oliver Boyd, George Hurn-Maloney, Ash Lewis</p><p><b>Upvotes:</b> 12</p><p><b>Summary:</b> Information extraction (IE) is fundamental to numerous NLP applications, yet existing solutions often require specialized models for different tasks or rely on computationally expensive large language models. We present GLiNER2, a unified framework that enhances the original GLiNER architecture to support named entity recognition, text classification, and hierarchical structured data extraction within a single efficient model. Built pretrained transformer encoder architecture, GLiNER2 maintains CPU efficiency and compact size while introducing multi-task composition through an intuitive schema-based interface. Our experiments demonstrate competitive performance across extraction and classification tasks with substantial improvements in deployment accessibility compared to LLM-based alternatives. We release GLiNER2 as an open-source pip-installable library with pre-trained models and documentation at https://github.com/fastino-ai/GLiNER2.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2507.18546</guid>
|
||||
<pubDate>Thu, 24 Jul 2025 16:11:14 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Deep Learning-Based Age Estimation and Gender Deep Learning-Based Age Estimation and Gender Classification for Targeted Advertisement</title>
|
||||
<link>https://arxiv.org/abs/2507.18565</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.18565.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Muhammad Imran Zaman, Nisar Ahmed</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> This paper presents a novel deep learning-based approach for simultaneous age and gender classification from facial images, designed to enhance the effectiveness of targeted advertising campaigns. We propose a custom Convolutional Neural Network (CNN) architecture, optimized for both tasks, which leverages the inherent correlation between age and gender information present in facial features. Unlike existing methods that often treat these tasks independently, our model learns shared representations, leading to improved performance. The network is trained on a large, diverse dataset of facial images, carefully pre-processed to ensure robustness against variations in lighting, pose, and image quality. Our experimental results demonstrate a significant improvement in gender classification accuracy, achieving 95%, and a competitive mean absolute error of 5.77 years for age estimation. Critically, we analyze the performance across different age groups, identifying specific challenges in accurately estimating the age of younger individuals. This analysis reveals the need for targeted data augmentation and model refinement to address these biases. Furthermore, we explore the impact of different CNN architectures and hyperparameter settings on the overall performance, providing valuable insights for future research.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2507.18565</guid>
|
||||
<pubDate>Thu, 24 Jul 2025 16:41:26 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Captain Cinema: Towards Short Movie Generation</title>
|
||||
<link>https://arxiv.org/abs/2507.18634</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.18634.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Junfei Xiao, Ceyuan Yang, Lvmin Zhang, Shengqu Cai, Yang Zhao, Yuwei Guo, Gordon Wetzstein, Maneesh Agrawala, Alan Yuille, Lu Jiang</p><p><b>Upvotes:</b> 28</p><p><b>Summary:</b> We present Captain Cinema, a generation framework for short movie generation. Given a detailed textual description of a movie storyline, our approach firstly generates a sequence of keyframes that outline the entire narrative, which ensures long-range coherence in both the storyline and visual appearance (e.g., scenes and characters). We refer to this step as top-down keyframe planning. These keyframes then serve as conditioning signals for a video synthesis model, which supports long context learning, to produce the spatio-temporal dynamics between them. This step is referred to as bottom-up video synthesis. To support stable and efficient generation of multi-scene long narrative cinematic works, we introduce an interleaved training strategy for Multimodal Diffusion Transformers (MM-DiT), specifically adapted for long-context video data. Our model is trained on a specially curated cinematic dataset consisting of interleaved data pairs. Our experiments demonstrate that Captain Cinema performs favorably in the automated creation of visually coherent and narrative consistent short movies in high quality and efficiency. Project page: https://thecinema.ai</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2507.18634</guid>
|
||||
<pubDate>Thu, 24 Jul 2025 17:59:56 +0000</pubDate>
|
||||
<title>MMBench-GUI: Hierarchical Multi-Platform Evaluation Framework for GUI Agents</title>
|
||||
<link>https://arxiv.org/abs/2507.19478</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2507.19478.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Xuehui Wang, Zhenyu Wu, JingJing Xie, Zichen Ding, Bowen Yang, Zehao Li, Zhaoyang Liu, Qingyun Li, Xuan Dong, Zhe Chen, Weiyun Wang, Xiangyu Zhao, Jixuan Chen, Haodong Duan, Tianbao Xie, Chenyu Yang, Shiqian Su, Yue Yu, Yuan Huang, Yiqian Liu, Xiao Zhang, Yanting Zhang, Xiangyu Yue, Weijie Su, Xizhou Zhu, Wei Shen, Jifeng Dai, Wenhai Wang</p><p><b>Upvotes:</b> 13</p><p><b>Summary:</b> We introduce MMBench-GUI, a hierarchical benchmark for evaluating GUI automation agents across Windows, macOS, Linux, iOS, Android, and Web platforms. It comprises four levels: GUI Content Understanding, Element Grounding, Task Automation, and Task Collaboration, covering essential skills for GUI agents. In addition, we propose a novel Efficiency-Quality Area (EQA) metric to assess GUI agent execution efficiency in online automation scenarios. Through MMBench-GUI, we identify accurate visual grounding as a critical determinant of overall task success, emphasizing the substantial benefits of modular frameworks that integrate specialized grounding modules. Furthermore, to achieve reliable GUI automation, an agent requires strong task planning and cross-platform generalization abilities, with long-context memory, a broad action space, and long-term reasoning playing a critical role. More important, task efficiency remains a critically underexplored dimension, and all models suffer from substantial inefficiencies, with excessive redundant steps even when tasks are ultimately completed. The integration of precise localization, effective planning, and early stopping strategies is indispensable to enable truly efficient and scalable GUI automation. Our benchmark code, evaluation data, and running environment will be publicly available at https://github.com/open-compass/MMBench-GUI.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2507.19478</guid>
|
||||
<pubDate>Fri, 25 Jul 2025 17:59:26 +0000</pubDate>
|
||||
</item>
|
||||
</channel>
|
||||
</rss>
|
||||
|
||||
Reference in New Issue
Block a user