x

75% of people globally want unbiased news (Pew Research) but are concerned they're not getting that.

Get balanced coverage with Symby. See how stories are covered across diverse outlets and spot when one side covers a story the other skips.

PODCAST

Daily Paper Cast

Jingwen Liang, Gengyu Wang

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:

science

All Episodes

25:36

RAGEN-2: Reasoning Collapse in Agentic RL

Daily Paper Cast ·

2026/04/10

🤗 Upvotes: 44 | cs.LGAuthors: Zihan Wang, Chi Gui, Xing Jin, Qineng Wang, Licheng Liu, Kangrui Wang, Shiqi Chen, Linjie Li, Zhengyuan Yang, Pingyue Zhang, Yiping Lu, Jiajun Wu, Li Fei-Fei, Lijuan Wang, Yejin Choi, Manling Li Title: RAGEN-2: Reasoning Collapse in Agentic RL Arxiv: http://arxiv.org/abs/2604.06268v1 Abstract: RL training of multi-turn LLM agents is inherently

en

23:23

MARS: Enabling Autoregressive Models Multi-Token...

Daily Paper Cast ·

2026/04/10

🤗 Upvotes: 25 | cs.CL Authors: Ziqi Jin, Lei Wang, Ziwei Luo, Aixin Sun Title: MARS: Enabling Autoregressive Models Multi-Token Generation Arxiv: http://arxiv.org/abs/2604.07023v1 Abstract: Autoregressive (AR) language models generate text one token at a time, even when consecutive tokens are highly predictable given earlier context. We introduce MARS (Mask AutoRegreSsion), a

en

21:56

Combee: Scaling Prompt Learning for Self-Improving...

Daily Paper Cast ·

2026/04/10

🤗 Upvotes: 22 | cs.AI, cs.CL, cs.LG Authors: Hanchen Li, Runyuan He, Qizheng Zhang, Changxiu Ji, Qiuyang Mang, Xiaokun Chen, Lakshya A Agrawal, Wei-Liang Liao, Eric Yang, Alvin Cheung, James Zou, Kunle Olukotun, Ion Stoica, Joseph E. Gonzalez Title: Combee: Scaling Prompt Learning for Self-Improving Language Model Agents Arxiv: http://arxiv.org/abs/2604.04247v1 Abstract: Recent

en

24:54

Video-MME-v2: Towards the Next Stage in Benchmarks...

Daily Paper Cast ·

2026/04/09

🤗 Upvotes: 201 | cs.CVAuthors: Chaoyou Fu, Haozhi Yuan, Yuhao Dong, Yi-Fan Zhang, Yunhang Shen, Xiaoxing Hu, Xueying Li, Jinsen Su, Chengwu Long, Xiaoyao Xie, Yongkang Xie, Xiawu Zheng, Xue Yang, Haoyu Cao, Yunsheng Wu, Ziwei Liu, Xing Sun, Caifeng Shan, Ran He Title: Video-MME-v2: Towards the Next Stage in Benchmarks for Comprehensive Video Understanding Arxiv: http://arxiv.org/abs/2604.05015v1

en

22:39

Claw-Eval: Toward Trustworthy Evaluation of...

Daily Paper Cast ·

2026/04/09

🤗 Upvotes: 98 | cs.AI Authors: Bowen Ye, Rang Li, Qibin Yang, Yuanxin Liu, Linli Yao, Hanglong Lv, Zhihui Xie, Chenxin An, Lei Li, Lingpeng Kong, Qi Liu, Zhifang Sui, Tong Yang Title: Claw-Eval: Toward Trustworthy Evaluation of Autonomous Agents Arxiv: http://arxiv.org/abs/2604.06132v1 Abstract: Large language models are increasingly deployed as autonomous agents executing

en

22:27

Learning to Retrieve from Agent Trajectories

Daily Paper Cast ·

2026/04/09

🤗 Upvotes: 55 | cs.IR, cs.AI, cs.CL Authors: Yuqi Zhou, Sunhao Dai, Changle Qu, Liang Pang, Jun Xu, Ji-Rong Wen Title: Learning to Retrieve from Agent Trajectories Arxiv: http://arxiv.org/abs/2604.04949v1 Abstract: Information retrieval (IR) systems have traditionally been designed and trained for human users, with learning-to-rank methods relying heavily on large-scale human

en

24:22

ACES: Who Tests the Tests? Leave-One-Out AUC...

Daily Paper Cast ·

2026/04/09

🤗 Upvotes: 47 | cs.LG Authors: Hui Sun, Yun-Ji Zhang, Zheng Xie, Ren-Biao Liu, Yali Du, Xin-Ye Li, Ming Li Title: ACES: Who Tests the Tests? Leave-One-Out AUC Consistency for Code Generation Arxiv: http://arxiv.org/abs/2604.03922v1 Abstract: Selecting LLM-generated code candidates using LLM-generated tests is challenging because the tests themselves may be incorrect. Existing

en

23:50

GBQA: A Game Benchmark for Evaluating LLMs as Quality...

Daily Paper Cast ·

2026/04/09

🤗 Upvotes: 37 | cs.SE, cs.AI Authors: Shufan Jiang, Chios Chen, Zhiyang Chen Title: GBQA: A Game Benchmark for Evaluating LLMs as Quality Assurance Engineers Arxiv: http://arxiv.org/abs/2604.02648v1 Abstract: The autonomous discovery of bugs remains a significant challenge in modern software development. Compared to code generation, the complexity of dynamic runtime environments

en

21:19

Beyond Accuracy: Unveiling Inefficiency Patterns in...

Daily Paper Cast ·

2026/04/09

🤗 Upvotes: 33 | cs.PF, cs.SE Authors: Qisheng Su, Shiting Huang, Zhen Fang, Ziyan Chen, Zehui Chen, Feng Zhao Title: Beyond Accuracy: Unveiling Inefficiency Patterns in Tool-Integrated Reasoning Arxiv: http://arxiv.org/abs/2604.05404v1 Abstract: In real-world Tool-Integrated Reasoning (TIR) scenarios, where LLMs interleave reasoning with external tool calls, a major source of

en

22:23

ThinkTwice: Jointly Optimizing Large Language Models...

Daily Paper Cast ·

2026/04/09

🤗 Upvotes: 32 | cs.AI Authors: Difan Jiao, Qianfeng Wen, Blair Yang, Zhenwei Tang, Ashton Anderson Title: ThinkTwice: Jointly Optimizing Large Language Models for Reasoning and Self-Refinement Arxiv: http://arxiv.org/abs/2604.01591v2 Abstract: We introduce ThinkTwice, a simple two-phase framework that jointly optimizes LLMs to solve reasoning problems and refine the answers,

en

24:53

Vanast: Virtual Try-On with Human Image Animation via...

Daily Paper Cast ·

2026/04/09

🤗 Upvotes: 31 | cs.CV Authors: Hyunsoo Cha, Wonjung Woo, Byungjun Kim, Hanbyul Joo Title: Vanast: Virtual Try-On with Human Image Animation via Synthetic Triplet Supervision Arxiv: http://arxiv.org/abs/2604.04934v1 Abstract: We present Vanast, a unified framework that generates garment-transferred human animation videos directly from a single human image, garment images, and a

en

25:12

MegaTrain: Full Precision Training of 100B+ Parameter...

Daily Paper Cast ·

2026/04/09

🤗 Upvotes: 26 | cs.CL, cs.DC, cs.OS Authors: Zhengqing Yuan, Hanchi Sun, Lichao Sun, Yanfang Ye Title: MegaTrain: Full Precision Training of 100B+ Parameter Large Language Models on a Single GPU Arxiv: http://arxiv.org/abs/2604.05091v1 Abstract: We present MegaTrain, a memory-centric system that efficiently trains 100B+ parameter large language models at full precision on a

en

20:34

Watch Before You Answer: Learning from Visually...

Daily Paper Cast ·

2026/04/09

🤗 Upvotes: 26 | cs.CV, cs.AI, cs.CL Authors: Yuxuan Zhang, EunJeong Hwang, Huaisong Zhang, Penghui Du, Yiming Jia, Dongfu Jiang, Xuan He, Shenhui Zhang, Ping Nie, Peter West, Kelsey R. Allen Title: Watch Before You Answer: Learning from Visually Grounded Post-Training Arxiv: http://arxiv.org/abs/2604.05117v1 Abstract: It is critical for vision-language models (VLMs) to

en

23:58

OpenWorldLib: A Unified Codebase and Definition of...

Daily Paper Cast ·

2026/04/08

🤗 Upvotes: 152 | cs.CVAuthors: DataFlow Team, Bohan Zeng, Daili Hua, Kaixin Zhu, Yifan Dai, Bozhou Li, Yuran Wang, Chengzhuo Tong, Yifan Yang, Mingkun Chang, Jianbin Zhao, Zhou Liu, Hao Liang, Xiaochen Ma, Ruichuan An, Junbo Niu, Zimo Meng, Tianyi Bai, Meiyi Qiang, Huanyao Zhang, Zhiyou Xiao, Tianyu Guo, Qinhan Yu, Runhao Zhao, Zhengpin Li, Xinyi Huang, Yisheng Pan, Yiwen Tang, Yang Shi, Yue Ding, Xinlong Chen, Hongcheng Gao, Minglei Shi, Jialong Wu,

en

23:52

MinerU2.5-Pro: Pushing the Limits of Data-Centric...

Daily Paper Cast ·

2026/04/08

🤗 Upvotes: 91 | cs.CV, cs.CL Authors: Bin Wang, Tianyao He, Linke Ouyang, Fan Wu, Zhiyuan Zhao, Tao Chu, Yuan Qu, Zhenjiang Jin, Weijun Zeng, Ziyang Miao, Bangrui Xu, Junbo Niu, Mengzhang Cai, Jiantao Qiu, Qintong Zhang, Dongsheng Ma, Yuefeng Sun, Hejun Dong, Wenzheng Zhang, Jutao Xiao, Jiayong Shi, Pengyu Liao, Xiaomeng Zhao, Huaping Zhong, Liqun Wei, Jing Yu, Jie Yang, Wei Li, Shasha Wang, Qianqian Wu, Xuanhe Zhou, Weijia Li, Zhenxiang Li, Zhongying

en

22:52

LIBERO-Para: A Diagnostic Benchmark and Metrics for...

Daily Paper Cast ·

2026/04/08

🤗 Upvotes: 72 | cs.LG Authors: Chanyoung Kim, Minwoo Kim, Minseok Kang, Hyunwoo Kim, Dahuin Jung Title: LIBERO-Para: A Diagnostic Benchmark and Metrics for Paraphrase Robustness in VLA Models Arxiv: http://arxiv.org/abs/2603.28301v1 Abstract: Vision-Language-Action (VLA) models achieve strong performance in robotic manipulation by leveraging pre-trained vision-language

en

21:22

TriAttention: Efficient Long Reasoning with...

Daily Paper Cast ·

2026/04/08

🤗 Upvotes: 70 | cs.CL, cs.CV Authors: Weian Mao, Xi Lin, Wei Huang, Yuxin Xie, Tianfu Fu, Bohan Zhuang, Song Han, Yukang Chen Title: TriAttention: Efficient Long Reasoning with Trigonometric KV Compression Arxiv: http://arxiv.org/abs/2604.04921v1 Abstract: Extended reasoning in large language models (LLMs) creates severe KV cache memory bottlenecks. Leading KV cache compression

en

22:27

Adam's Law: Textual Frequency Law on Large Language...

Daily Paper Cast ·

2026/04/08

🤗 Upvotes: 46 | cs.CL Authors: Hongyuan Adam Lu, Z. L., Victor Wei, Zefan Zhang, Zhao Hong, Qiqi Xiang, Bowen Cao, Wai Lam Title: Adam's Law: Textual Frequency Law on Large Language Models Arxiv: http://arxiv.org/abs/2604.02176v2 Abstract: While textual frequency has been validated as relevant to human cognition in reading speed, its relatedness to Large Language Models (LLMs)

en

23:35

AURA: Always-On Understanding and Real-Time...

Daily Paper Cast ·

2026/04/08

🤗 Upvotes: 39 | cs.CV Authors: Xudong Lu, Yang Bo, Jinpeng Chen, Shuhan Li, Xintong Guo, Huankang Guan, Fang Liu, Dunyuan Xu, Peiwen Sun, Heyang Sun, Rui Liu, Hongsheng Li Title: AURA: Always-On Understanding and Real-Time Assistance via Video Streams Arxiv: http://arxiv.org/abs/2604.04184v1 Abstract: Video Large Language Models (VideoLLMs) have achieved strong performance on

en

21:28

ClawArena: Benchmarking AI Agents in Evolving...

Daily Paper Cast ·

2026/04/08

🤗 Upvotes: 27 | cs.LG, cs.AI, cs.CL Authors: Haonian Ji, Kaiwen Xiong, Siwei Han, Peng Xia, Shi Qiu, Yiyang Zhou, Jiaqi Liu, Jinlong Li, Bingzhou Li, Zeyu Zheng, Cihang Xie, Huaxiu Yao Title: ClawArena: Benchmarking AI Agents in Evolving Information Environments Arxiv: http://arxiv.org/abs/2604.04202v1 Abstract: AI agents deployed as persistent assistants must maintain correct

en

1,967 results

Similar Podcasts

Classic Radio Science Fiction

solgoodmedia.com

Mission to Mars

Inception Point AI

The 365 Days of Astronomy

365DaysOfAstronomy.org

Creek Devil

william Jevning

UFO Chronicles Podcast

Nik Hunter