Episodes

StableToken: A Noise-Robust Semantic Speech Tokenizer for Resilient SpeechLLMs

Episode 1203 · September 30, 2025 · 21:00

🤗 Upvotes: 58 | cs.CL Authors: Yuhan Song, Linhao Zhang, Chuhan Wu, Aiwei Liu, Wei Jia, Houfeng Wang, Xiao Zhou Title: ...

Multiplayer Nash Preference Optimization

Episode 1202 · September 30, 2025 · 26:13

🤗 Upvotes: 52 | cs.AI, cs.CL Authors: Fang Wu, Xu Huang, Weihao Xuan, Zhiwei Zhang, Yijia Xiao, Guancheng Wan, Xiaomin Li, Bing Hu, Peng Xia, Ju...

RealUnify: Do Unified Models Truly Benefit from Unification? A Comprehensive Benchmark

Episode 1201 · September 30, 2025 · 25:04

🤗 Upvotes: 41 | cs.AI Authors: Yang Shi, Yuhao Dong, Yue Ding, Yuran Wang, Xuanyu Zhu, Sheng Zhou, Wenting Liu, Haochen Tian, Rundong Wang, Huan...

Beyond the Exploration-Exploitation Trade-off: A Hidden State Approach for LLM Reasoning in RLVR

Episode 1200 · September 30, 2025 · 24:39

🤗 Upvotes: 39 | cs.LG, cs.CL Authors: Fanding Huang, Guanbo Huang, Xiao Fan, Yi He, Xiao Liang, Xiao Chen, Qinting Jiang, Faisal Nadeem Khan, Ji...

OpenGPT-4o-Image: A Comprehensive Dataset for Advanced Image Generation and Editing

Episode 1199 · September 30, 2025 · 19:35

🤗 Upvotes: 38 | cs.CV, cs.AI Authors: Zhihong Chen, Xuehai Bai, Yang Shi, Chaoyou Fu, Huanyu Zhang, Haotian Wang, Xiaoyan Sun, Zhang Zhang, Lian...

SANA-Video: Efficient Video Generation with Block Linear Diffusion Transformer

Episode 1198 · September 30, 2025 · 26:23

🤗 Upvotes: 36 | cs.CV, cs.AI Authors: Junsong Chen, Yuyang Zhao, Jincheng Yu, Ruihang Chu, Junyu Chen, Shuai Yang, Xianbang Wang, Yicheng Pan, D...

Democratizing AI scientists using ToolUniverse

Episode 1197 · September 30, 2025 · 26:05

🤗 Upvotes: 33 | cs.AI, cs.LG Authors: Shanghua Gao, Richard Zhu, Pengwei Sui, Zhenglun Kong, Sufian Aldogom, Yepeng Huang, Ayush Noori, Reza Sha...

Visual Jigsaw Post-Training Improves MLLMs

Episode 1196 · September 30, 2025 · 23:16

🤗 Upvotes: 33 | cs.CV Authors: Penghao Wu, Yushan Zhang, Haiwen Diao, Bo Li, Lewei Lu, Ziwei Liu Title: Visual Jigsaw P...

When Does Reasoning Matter? A Controlled Study of Reasoning's Contribution to Model Performance

Episode 1195 · September 30, 2025 · 24:47

🤗 Upvotes: 29 | cs.CL Authors: Nicolas Boizard, Hippolyte Gisserot-Boukhlef, Kevin El-Haddad, Céline Hudelot, Pierre Colombo Title:...

LongLive: Real-time Interactive Long Video Generation

Episode 1194 · September 29, 2025 · 24:54

🤗 Upvotes: 136 | cs.CV Authors: Shuai Yang, Wei Huang, Ruihang Chu, Yicheng Xiao, Yuyang Zhao, Xianbang Wang, Muyang Li, Enze Xie, Yingcong Chen...

Quantile Advantage Estimation for Entropy-Safe Reasoning

Episode 1193 · September 29, 2025 · 23:16

🤗 Upvotes: 102 | cs.LG, cs.AI Authors: Junkang Wu, Kexin Huang, Jiancan Wu, An Zhang, Xiang Wang, Xiangnan He Title: Qu...

EPO: Entropy-regularized Policy Optimization for LLM Agents Reinforcement Learning

Episode 1192 · September 29, 2025 · 27:27

🤗 Upvotes: 98 | cs.LG, cs.CL Authors: Xu Wujiang, Wentian Zhao, Zhenting Wang, Li Yu-Jhe, Jin Can, Jin Mingyu, Mei Kai, Wan Kun, Metaxas Dimitri...

MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing

Episode 1191 · September 29, 2025 · 25:00

🤗 Upvotes: 81 | cs.CV, cs.CL Authors: Junbo Niu, Zheng Liu, Zhuangcheng Gu, Bin Wang, Linke Ouyang, Zhiyuan Zhao, Tao Chu, Tianyao He, Fan Wu, Q...

ReviewScore: Misinformed Peer Review Detection with Large Language Models

Episode 1190 · September 29, 2025 · 21:58

🤗 Upvotes: 54 | cs.CL Authors: Hyun Ryu, Doohyuk Jang, Hyemin S. Lee, Joonhyun Jeong, Gyeongman Kim, Donghyeon Cho, Gyouk Chu, Minyeong Hwang, H...

Variational Reasoning for Language Models

Episode 1189 · September 29, 2025 · 22:33

🤗 Upvotes: 51 | cs.CL, cs.AI, cs.LG Authors: Xiangxin Zhou, Zichen Liu, Haonan Wang, Chao Du, Min Lin, Chongxuan Li, Liang Wang, Tianyu Pang ...

Language Models Can Learn from Verbal Feedback Without Scalar Rewards

Episode 1188 · September 29, 2025 · 23:30

🤗 Upvotes: 48 | cs.CL, cs.AI, cs.LG Authors: Renjie Luo, Zichen Liu, Xiangyan Liu, Chao Du, Min Lin, Wenhu Chen, Wei Lu, Tianyu Pang ...

MesaTask: Towards Task-Driven Tabletop Scene Generation via 3D Spatial Reasoning

Episode 1187 · September 29, 2025 · 25:33

🤗 Upvotes: 28 | cs.CV, cs.RO Authors: Jinkun Hao, Naifu Liang, Zhen Luo, Xudong Xu, Weipeng Zhong, Ran Yi, Yichen Jin, Zhaoyang Lyu, Feng Zheng,...

CapRL: Stimulating Dense Image Caption Capabilities via Reinforcement Learning

Episode 1186 · September 29, 2025 · 23:54

🤗 Upvotes: 28 | cs.CV, cs.AI, cs.CL Authors: Long Xing, Xiaoyi Dong, Yuhang Zang, Yuhang Cao, Jianze Liang, Qidong Huang, Jiaqi Wang, Feng Wu, D...

No Prompt Left Behind: Exploiting Zero-Variance Prompts in LLM Reinforcement Learning via Entropy-Guided Advantage Shaping

Episode 1185 · September 29, 2025 · 27:53

🤗 Upvotes: 27 | cs.CL, cs.AI, cs.LG Authors: Thanh-Long V. Le, Myeongho Jeon, Kim Vu, Viet Lai, Eunho Yang Title: No Pr...

VCRL: Variance-based Curriculum Reinforcement Learning for Large Language Models

Episode 1184 · September 26, 2025 · 22:17

🤗 Upvotes: 95 | cs.LG, cs.CL Authors: Guochao Jiang, Wenfeng Feng, Guofeng Quan, Chuzhan Hao, Yuewei Zhang, Guohua Liu, Hao Wang Ti...