Daily Paper Cast

Jingwen Liang, Gengyu Wang
  • 0,0 (0)
  • KHOA HỌC
  • HẰNG NGÀY

We update every weekday to discuss highest-voted papers from Huggingface Daily Paper (https://huggingface.co/papers). Both the podcast scripts and audio are generated by AI. Feedback and suggestions are welcome! Email us: dailypapercast.ai@gmail.com Creator: Jingwen Liang, 3D ML, https://www.linkedin.com/in/jingwen-liang/ Gengyu Wang, LLM ML, http://wanggengyu.com Listen on: Spotify: https://open.spotify.com/show/21nrhmdaA8qoBiH8q03NXL Apple Podcast: https://podcasts.apple.com/us/podcast/daily-paper-cast/id1777620236 Cover Image by Kawen Kuang https://kawen.art

  1. 9 GIỜ TRƯỚC

    LongCodeZip: Compress Long Context for Code Language Models

    🤗 Upvotes: 70 | cs.CL, cs.SE Authors: Yuling Shi, Yichun Qian, Hongyu Zhang, Beijun Shen, Xiaodong Gu Title: LongCodeZip: Compress Long Context for Code Language Models Arxiv: http://arxiv.org/abs/2510.00446v1 Abstract: Code generation under long contexts is becoming increasingly critical as Large Language Models (LLMs) are required to reason over extensive information in the codebase. While recent advances enable code LLMs to process long inputs, high API costs and generation latency remain substantial bottlenecks. Existing context pruning techniques, such as LLMLingua, achieve promising results for general text but overlook code-specific structures and dependencies, leading to suboptimal performance in programming tasks. In this paper, we propose LongCodeZip, a novel plug-and-play code compression framework designed specifically for code LLMs. LongCodeZip employs a dual-stage strategy: (1) coarse-grained compression, which identifies and ranks function-level chunks using conditional perplexity with respect to the instruction, retaining only the most relevant functions; and (2) fine-grained compression, which segments retained functions into blocks based on perplexity and selects an optimal subset under an adaptive token budget to maximize relevance. Evaluations across multiple tasks, including code completion, summarization, and question answering, show that LongCodeZip consistently outperforms baseline methods, achieving up to a 5.6x compression ratio without degrading task performance. By effectively reducing context size while preserving essential information, LongCodeZip enables LLMs to better scale to real-world, large-scale code scenarios, advancing the efficiency and capability of code intelligence applications.

    30 phút

  2. 10 GIỜ TRƯỚC

    Self-Forcing++: Towards Minute-Scale High-Quality Video Generation

    🤗 Upvotes: 61 | cs.CV, cs.AI Authors: Justin Cui, Jie Wu, Ming Li, Tao Yang, Xiaojie Li, Rui Wang, Andrew Bai, Yuanhao Ban, Cho-Jui Hsieh Title: Self-Forcing++: Towards Minute-Scale High-Quality Video Generation Arxiv: http://arxiv.org/abs/2510.02283v1 Abstract: Diffusion models have revolutionized image and video generation, achieving unprecedented visual quality. However, their reliance on transformer architectures incurs prohibitively high computational costs, particularly when extending generation to long videos. Recent work has explored autoregressive formulations for long video generation, typically by distilling from short-horizon bidirectional teachers. Nevertheless, given that teacher models cannot synthesize long videos, the extrapolation of student models beyond their training horizon often leads to pronounced quality degradation, arising from the compounding of errors within the continuous latent space. In this paper, we propose a simple yet effective approach to mitigate quality degradation in long-horizon video generation without requiring supervision from long-video teachers or retraining on long video datasets. Our approach centers on exploiting the rich knowledge of teacher models to provide guidance for the student model through sampled segments drawn from self-generated long videos. Our method maintains temporal consistency while scaling video length by up to 20x beyond teacher's capability, avoiding common issues such as over-exposure and error-accumulation without recomputing overlapping frames like previous methods. When scaling up the computation, our method shows the capability of generating videos up to 4 minutes and 15 seconds, equivalent to 99.9% of the maximum span supported by our base model's position embedding and more than 50x longer than that of our baseline model. Experiments on standard benchmarks and our proposed improved benchmark demonstrate that our approach substantially outperforms baseline methods in both fidelity and consistency. Our long-horizon videos demo can be found at https://self-forcing-plus-plus.github.io/

    23 phút

  3. 10 GIỜ TRƯỚC

    ExGRPO: Learning to Reason from Experience

    🤗 Upvotes: 50 | cs.LG, cs.AI, cs.CL Authors: Runzhe Zhan, Yafu Li, Zhi Wang, Xiaoye Qu, Dongrui Liu, Jing Shao, Derek F. Wong, Yu Cheng Title: ExGRPO: Learning to Reason from Experience Arxiv: http://arxiv.org/abs/2510.02245v1 Abstract: Reinforcement learning from verifiable rewards (RLVR) is an emerging paradigm for improving the reasoning ability of large language models. However, standard on-policy training discards rollout experiences after a single update, leading to computational inefficiency and instability. While prior work on RL has highlighted the benefits of reusing past experience, the role of experience characteristics in shaping learning dynamics of large reasoning models remains underexplored. In this paper, we are the first to investigate what makes a reasoning experience valuable and identify rollout correctness and entropy as effective indicators of experience value. Based on these insights, we propose ExGRPO (Experiential Group Relative Policy Optimization), a framework that organizes and prioritizes valuable experiences, and employs a mixed-policy objective to balance exploration with experience exploitation. Experiments on five backbone models (1.5B-8B parameters) show that ExGRPO consistently improves reasoning performance on mathematical/general benchmarks, with an average gain of +3.5/7.6 points over on-policy RLVR. Moreover, ExGRPO stabilizes training on both stronger and weaker models where on-policy methods fail. These results highlight principled experience management as a key ingredient for efficient and scalable RLVR.

    22 phút

  4. 10 GIỜ TRƯỚC

    StealthAttack: Robust 3D Gaussian Splatting Poisoning via Density-Guided Illusions

    🤗 Upvotes: 46 | cs.CV Authors: Bo-Hsu Ke, You-Zhe Xie, Yu-Lun Liu, Wei-Chen Chiu Title: StealthAttack: Robust 3D Gaussian Splatting Poisoning via Density-Guided Illusions Arxiv: http://arxiv.org/abs/2510.02314v1 Abstract: 3D scene representation methods like Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS) have significantly advanced novel view synthesis. As these methods become prevalent, addressing their vulnerabilities becomes critical. We analyze 3DGS robustness against image-level poisoning attacks and propose a novel density-guided poisoning method. Our method strategically injects Gaussian points into low-density regions identified via Kernel Density Estimation (KDE), embedding viewpoint-dependent illusory objects clearly visible from poisoned views while minimally affecting innocent views. Additionally, we introduce an adaptive noise strategy to disrupt multi-view consistency, further enhancing attack effectiveness. We propose a KDE-based evaluation protocol to assess attack difficulty systematically, enabling objective benchmarking for future research. Extensive experiments demonstrate our method's superior performance compared to state-of-the-art techniques. Project page: https://hentci.github.io/stealthattack/

    26 phút

  5. 10 GIỜ TRƯỚC

    Interactive Training: Feedback-Driven Neural Network Optimization

    🤗 Upvotes: 33 | cs.LG, cs.AI, cs.CL Authors: Wentao Zhang, Yang Young Lu, Yuntian Deng Title: Interactive Training: Feedback-Driven Neural Network Optimization Arxiv: http://arxiv.org/abs/2510.02297v1 Abstract: Traditional neural network training typically follows fixed, predefined optimization recipes, lacking the flexibility to dynamically respond to instabilities or emerging training issues. In this paper, we introduce Interactive Training, an open-source framework that enables real-time, feedback-driven intervention during neural network training by human experts or automated AI agents. At its core, Interactive Training uses a control server to mediate communication between users or agents and the ongoing training process, allowing users to dynamically adjust optimizer hyperparameters, training data, and model checkpoints. Through three case studies, we demonstrate that Interactive Training achieves superior training stability, reduced sensitivity to initial hyperparameters, and improved adaptability to evolving user needs, paving the way toward a future training paradigm where AI agents autonomously monitor training logs, proactively resolve instabilities, and optimize training dynamics.

    21 phút

  6. 10 GIỜ TRƯỚC

    ModernVBERT: Towards Smaller Visual Document Retrievers

    🤗 Upvotes: 24 | cs.IR Authors: Paul Teiletche, Quentin Macé, Max Conti, Antonio Loison, Gautier Viaud, Pierre Colombo, Manuel Faysse Title: ModernVBERT: Towards Smaller Visual Document Retrievers Arxiv: http://arxiv.org/abs/2510.01149v1 Abstract: Multimodal embedding models are gaining prevalence, notably for document retrieval as efficient alternatives to text-only pipelines. These models are typically built by finetuning large vision-language decoders (VLMs) with contrastive losses on text-image pairs. In this work, we show that, while cost-efficient, this repurposing approach often bottlenecks retrieval performance. Through controlled experiments, we establish a principled recipe for improving visual document retrieval models. We notably measure the impact of attention masking, image resolution, modality alignment data regimes, and late interaction centered contrastive objectives which emerge as central performance factors. Building on these insights, we release ModernVBERT, a compact 250M-parameter vision-language encoder that outperforms models up to 10 times larger when finetuned on document retrieval tasks. Models and code are made available at https://huggingface.co/ModernVBERT.

    23 phút

  7. 10 GIỜ TRƯỚC

    StockBench: Can LLM Agents Trade Stocks Profitably In Real-world Markets?

    🤗 Upvotes: 24 | cs.LG, cs.CL Authors: Yanxu Chen, Zijun Yao, Yantao Liu, Jin Ye, Jianing Yu, Lei Hou, Juanzi Li Title: StockBench: Can LLM Agents Trade Stocks Profitably In Real-world Markets? Arxiv: http://arxiv.org/abs/2510.02209v1 Abstract: Large language models (LLMs) have recently demonstrated strong capabilities as autonomous agents, showing promise in reasoning, tool use, and sequential decision-making. While prior benchmarks have evaluated LLM agents in domains such as software engineering and scientific discovery, the finance domain remains underexplored, despite its direct relevance to economic value and high-stakes decision-making. Existing financial benchmarks primarily test static knowledge through question answering, but they fall short of capturing the dynamic and iterative nature of trading. To address this gap, we introduce StockBench, a contamination-free benchmark designed to evaluate LLM agents in realistic, multi-month stock trading environments. Agents receive daily market signals -- including prices, fundamentals, and news -- and must make sequential buy, sell, or hold decisions. Performance is assessed using financial metrics such as cumulative return, maximum drawdown, and the Sortino ratio. Our evaluation of state-of-the-art proprietary (e.g., GPT-5, Claude-4) and open-weight (e.g., Qwen3, Kimi-K2, GLM-4.5) models shows that while most LLM agents struggle to outperform the simple buy-and-hold baseline, several models demonstrate the potential to deliver higher returns and manage risk more effectively. These findings highlight both the challenges and opportunities in developing LLM-powered financial agents, showing that excelling at static financial knowledge tasks does not necessarily translate into successful trading strategies. We release StockBench as an open-source resource to support reproducibility and advance future research in this domain.

    31 phút

  8. 1 NGÀY TRƯỚC

    DeepSearch: Overcome the Bottleneck of Reinforcement Learning with Verifiable Rewards via Monte Carlo Tree Search

    🤗 Upvotes: 100 | cs.AI, cs.CL Authors: Fang Wu, Weihao Xuan, Heli Qi, Ximing Lu, Aaron Tu, Li Erran Li, Yejin Choi Title: DeepSearch: Overcome the Bottleneck of Reinforcement Learning with Verifiable Rewards via Monte Carlo Tree Search Arxiv: http://arxiv.org/abs/2509.25454v2 Abstract: Although RLVR has become an essential component for developing advanced reasoning skills in LLMs, contemporary studies have documented training plateaus that emerge following thousands of optimization steps, demonstrating notable decreases in performance gains despite increased computational investment. This limitation stems from the sparse exploration patterns inherent in current RLVR practices, where models rely on limited rollouts that often miss critical reasoning paths and fail to provide systematic coverage of the solution space. We present DeepSearch, a framework that integrates Monte Carlo Tree Search directly into RLVR training. In contrast to existing methods that rely on tree search only at inference, DeepSearch embeds structured search into the training loop, enabling systematic exploration and fine-grained credit assignment across reasoning steps. Through training-time exploration, DeepSearch addresses the fundamental bottleneck of insufficient exploration, which leads to diminishing performance improvements over prolonged training steps. Our contributions include: (1) a global frontier selection strategy that prioritizes promising nodes across the search tree, (2) selection with entropy-based guidance that identifies confident paths for supervision, and (3) adaptive replay buffer training with solution caching for efficiency. Experiments on mathematical reasoning benchmarks show that DeepSearch achieves 62.95% average accuracy and establishes a new state-of-the-art for 1.5B reasoning models - using 5.7x fewer GPU hours than extended training approaches. These results highlight the importance of strategic exploration over brute-force scaling and demonstrate the promise of algorithmic innovation for advancing RLVR methodologies. DeepSearch establishes a new direction for scaling reasoning capabilities through systematic search rather than prolonged computation.

    24 phút
Xem tất cả (1,2 N)

Giới Thiệu

We update every weekday to discuss highest-voted papers from Huggingface Daily Paper (https://huggingface.co/papers). Both the podcast scripts and audio are generated by AI. Feedback and suggestions are welcome! Email us: dailypapercast.ai@gmail.com Creator: Jingwen Liang, 3D ML, https://www.linkedin.com/in/jingwen-liang/ Gengyu Wang, LLM ML, http://wanggengyu.com Listen on: Spotify: https://open.spotify.com/show/21nrhmdaA8qoBiH8q03NXL Apple Podcast: https://podcasts.apple.com/us/podcast/daily-paper-cast/id1777620236 Cover Image by Kawen Kuang https://kawen.art

Thông Tin

  • Nhà sáng tạo
    Jingwen Liang, Gengyu Wang
  • Năm hoạt động
    2024 - 2025
  • Tập
    1,2 N
  • Xếp hạng
    Sạch
  • Bản quyền
    © 2025 Jingwen Liang, Gengyu Wang
  • Trang web chương trình
    Daily Paper Cast

Có Thể Bạn Cũng Thích