Daily Paper Cast

🤗 Upvotes: 30 | cs. CV Authors: Zichen Wen, Shaobo Wang, Yufa Zhou, Junyuan Zhang, Qintong Zhang, Yifeng Gao, Zhaorun Chen, Bin Wang, Weijia Li, Conghui He, Linfeng Zhang Title: Efficient Multi-modal Large Language Models via Progressive Consistency Distillation Arxiv: http://arxiv.org/abs/2510.00515v1 Abstract: Visual tokens consume substantial computational resources in multi-modal large 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 re...

🤗 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 tr...

🤗 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 o...

🤗 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 pr...

🤗 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...

🤗 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 t...

🤗 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...

🤗 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...

🤗 Upvotes: 53 | cs. LG, cs. AI, cs. CL Authors: Zichen Liu, Anya Sims, Keyu Duan, Changyu Chen, Simon Yu, Xiangxin Zhou, Haotian Xu, Shaopan Xiong, Bo Liu, Chenmien Tan, Chuen Yang Beh, Weixun Wang, Hao Zhu, Weiyan Shi, Diyi Yang, Michael Shieh, Yee Whye Teh, Wee Sun Lee, Min Lin Title: GEM: A Gym for Agentic LLMs Arxiv: http://arxiv.org/abs/2510.01051v1 Abstract: The training paradigm for large...

🤗 Upvotes: 52 | cs. RO, cs. CV Authors: Hengtao Li, Pengxiang Ding, Runze Suo, Yihao Wang, Zirui Ge, Dongyuan Zang, Kexian Yu, Mingyang Sun, Hongyin Zhang, Donglin Wang, Weihua Su Title: VLA-RFT: Vision-Language-Action Reinforcement Fine-tuning with Verified Rewards in World Simulators Arxiv: http://arxiv.org/abs/2510.00406v1 Abstract: Vision-Language-Action (VLA) models enable embodied decision-...

🤗 Upvotes: 32 | cs. LG, cs. AI, cs. CL Authors: Ziniu Li, Congliang Chen, Tianyun Yang, Tian Ding, Ruoyu Sun, Ge Zhang, Wenhao Huang, Zhi-Quan Luo Title: Knapsack RL: Unlocking Exploration of LLMs via Optimizing Budget Allocation Arxiv: http://arxiv.org/abs/2509.25849v1 Abstract: Large Language Models (LLMs) can self-improve through reinforcement learning, where they generate trajectories to expl...

🤗 Upvotes: 26 | cs. SE, cs. AI, cs. LG Authors: Alexander Kovrigin, Aleksandra Eliseeva, Konstantin Grotov, Egor Bogomolov, Yaroslav Zharov Title: PIPer: On-Device Environment Setup via Online Reinforcement Learning Arxiv: http://arxiv.org/abs/2509.25455v1 Abstract: Environment setup-the process of configuring the system to work with a specific software project-represents a persistent challenge i...

🤗 Upvotes: 25 | cs. LG Authors: Lorenz K. Müller, Philippe Bich, Jiawei Zhuang, Ahmet Çelik, Luca Benfenati, Lukas Cavigelli Title: SINQ: Sinkhorn-Normalized Quantization for Calibration-Free Low-Precision LLM Weights Arxiv: http://arxiv.org/abs/2509.22944v2 Abstract: Post-training quantization has emerged as the most widely used strategy for deploying large language models at low precision. Stil...

🤗 Upvotes: 21 | cs. AI, cs. CL Authors: Minki Kang, Wei-Ning Chen, Dongge Han, Huseyin A. Inan, Lukas Wutschitz, Yanzhi Chen, Robert Sim, Saravan Rajmohan Title: ACON: Optimizing Context Compression for Long-horizon LLM Agents Arxiv: http://arxiv.org/abs/2510.00615v1 Abstract: Large language models (LLMs) are increasingly deployed as agents in dynamic, real-world environments, where success requi...

🤗 Upvotes: 124 | cs. CL, cs. AI Authors: Zijian Wu, Xiangyan Liu, Xinyuan Zhang, Lingjun Chen, Fanqing Meng, Lingxiao Du, Yiran Zhao, Fanshi Zhang, Yaoqi Ye, Jiawei Wang, Zirui Wang, Jinjie Ni, Yufan Yang, Arvin Xu, Michael Qizhe Shieh Title: MCPMark: A Benchmark for Stress-Testing Realistic and Comprehensive MCP Use Arxiv: http://arxiv.org/abs/2509.24002v1 Abstract: MCP standardizes how LLMs int...

🤗 Upvotes: 106 | cs. NE, cs. AI, cs. LG, stat. ML Authors: Adrian Kosowski, Przemysław Uznański, Jan Chorowski, Zuzanna Stamirowska, Michał Bartoszkiewicz Title: The Dragon Hatchling: The Missing Link between the Transformer and Models of the Brain Arxiv: http://arxiv.org/abs/2509.26507v1 Abstract: The relationship between computing systems and the brain has served as motivation for pioneering th...

🤗 Upvotes: 103 | cs. CV, cs. AI Authors: Qinsi Wang, Bo Liu, Tianyi Zhou, Jing Shi, Yueqian Lin, Yiran Chen, Hai Helen Li, Kun Wan, Wentian Zhao Title: Vision-Zero: Scalable VLM Self-Improvement via Strategic Gamified Self-Play Arxiv: http://arxiv.org/abs/2509.25541v1 Abstract: Although reinforcement learning (RL) can effectively enhance the reasoning capabilities of vision-language models (VLMs)...

🤗 Upvotes: 57 | cs. CL Authors: Shaobo Wang, Jiaming Wang, Jiajun Zhang, Cong Wang, Yue Min, Zichen Wen, Fei Huang, Huiqiang Jiang, Junyang Lin, Dayiheng Liu, Linfeng Zhang Title: Winning the Pruning Gamble: A Unified Approach to Joint Sample and Token Pruning for Efficient Supervised Fine-Tuning Arxiv: http://arxiv.org/abs/2509.23873v1 Abstract: As supervised fine-tuning (SFT) evolves from a lig...

🤗 Upvotes: 45 | cs. CL, cs. AI, cs. LG Authors: Zhepei Wei, Xiao Yang, Kai Sun, Jiaqi Wang, Rulin Shao, Sean Chen, Mohammad Kachuee, Teja Gollapudi, Tony Liao, Nicolas Scheffer, Rakesh Wanga, Anuj Kumar, Yu Meng, Wen-tau Yih, Xin Luna Dong Title: TruthRL: Incentivizing Truthful LLMs via Reinforcement Learning Arxiv: http://arxiv.org/abs/2509.25760v1 Abstract: While large language models (LLMs) ha...

🤗 Upvotes: 36 | cs. LG, cs. AI, cs. CV, cs. MM Authors: Junlin Han, Shengbang Tong, David Fan, Yufan Ren, Koustuv Sinha, Philip Torr, Filippos Kokkinos Title: Learning to See Before Seeing: Demystifying LLM Visual Priors from Language Pre-training Arxiv: http://arxiv.org/abs/2509.26625v1 Abstract: Large Language Models (LLMs), despite being trained on text alone, surprisingly develop rich visual...

🤗 Upvotes: 30 | cs. CL, cs. AI, cs. CV, cs. LG, cs. RO Authors: Yida Xue, Mingjun Mao, Xiangyuan Ru, Yuqi Zhu, Baochang Ren, Shuofei Qiao, Mengru Wang, Shumin Deng, Xinyu An, Ningyu Zhang, Ying Chen, Huajun Chen Title: OceanGym: A Benchmark Environment for Underwater Embodied Agents Arxiv: http://arxiv.org/abs/2509.26536v1 Abstract: We introduce OceanGym, the first comprehensive benchmark for oce...

🤗 Upvotes: 29 | cs. CV, cs. AI Authors: Xinyu Tian, Shu Zou, Zhaoyuan Yang, Mengqi He, Fabian Waschkowski, Lukas Wesemann, Peter Tu, Jing Zhang Title: More Thought, Less Accuracy? On the Dual Nature of Reasoning in Vision-Language Models Arxiv: http://arxiv.org/abs/2509.25848v1 Abstract: Reasoning has emerged as a pivotal capability in Large Language Models (LLMs). Through Reinforcement Learning...

🤗 Upvotes: 26 | cs. LG, cs. CL Authors: Xin Xu, Cliveb AI, Kai Yang, Tianhao Chen, Yang Wang, Saiyong Yang, Can Yang Title: Thinking-Free Policy Initialization Makes Distilled Reasoning Models More Effective and Efficient Reasoners Arxiv: http://arxiv.org/abs/2509.26226v1 Abstract: Reinforcement Learning with Verifiable Reward (RLVR) effectively solves complex tasks but demands extremely long con...

🤗 Upvotes: 26 | cs. CV, cs. AI Authors: Junyu Chen, Wenkun He, Yuchao Gu, Yuyang Zhao, Jincheng Yu, Junsong Chen, Dongyun Zou, Yujun Lin, Zhekai Zhang, Muyang Li, Haocheng Xi, Ligeng Zhu, Enze Xie, Song Han, Han Cai Title: DC-VideoGen: Efficient Video Generation with Deep Compression Video Autoencoder Arxiv: http://arxiv.org/abs/2509.25182v1 Abstract: We introduce DC-VideoGen, a post-training acc...