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

24:35

More Thought, Less Accuracy? On the Dual Nature of...

Daily Paper Cast ·

2025/10/02

🤗 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

en

23:19

Thinking-Free Policy Initialization Makes Distilled...

Daily Paper Cast ·

2025/10/02

🤗 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

en

25:33

DC-VideoGen: Efficient Video Generation with Deep...

Daily Paper Cast ·

2025/10/02

🤗 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

en

24:35

SLA: Beyond Sparsity in Diffusion Transformers via...

Daily Paper Cast ·

2025/10/01

🤗 Upvotes: 98 | cs.LG, cs.AI, cs.CVAuthors: Jintao Zhang, Haoxu Wang, Kai Jiang, Shuo Yang, Kaiwen Zheng, Haocheng Xi, Ziteng Wang, Hongzhou Zhu, Min Zhao, Ion Stoica, Joseph E. Gonzalez, Jun Zhu, Jianfei Chen Title: SLA: Beyond Sparsity in Diffusion Transformers via Fine-Tunable Sparse-Linear Attention Arxiv: http://arxiv.org/abs/2509.24006v1 Abstract: In Diffusion Transformer

en

21:00

StableToken: A Noise-Robust Semantic Speech Tokenizer...

Daily Paper Cast ·

2025/10/01

🤗 Upvotes: 58 | cs.CL Authors: Yuhan Song, Linhao Zhang, Chuhan Wu, Aiwei Liu, Wei Jia, Houfeng Wang, Xiao Zhou Title: StableToken: A Noise-Robust Semantic Speech Tokenizer for Resilient SpeechLLMs Arxiv: http://arxiv.org/abs/2509.22220v1 Abstract: Prevalent semantic speech tokenizers, designed to capture linguistic content, are surprisingly fragile. We find they are not robust

en

26:13

Multiplayer Nash Preference Optimization

Daily Paper Cast ·

2025/10/01

🤗 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, Jure Leskovec, Yejin Choi Title: Multiplayer Nash Preference Optimization Arxiv: http://arxiv.org/abs/2509.23102v1 Abstract: Reinforcement learning from human feedback (RLHF) has emerged as the standard paradigm for aligning large language

en

25:04

RealUnify: Do Unified Models Truly Benefit from...

Daily Paper Cast ·

2025/10/01

🤗 Upvotes: 41 | cs.AI Authors: Yang Shi, Yuhao Dong, Yue Ding, Yuran Wang, Xuanyu Zhu, Sheng Zhou, Wenting Liu, Haochen Tian, Rundong Wang, Huanqian Wang, Zuyan Liu, Bohan Zeng, Ruizhe Chen, Qixun Wang, Zhuoran Zhang, Xinlong Chen, Chengzhuo Tong, Bozhou Li, Chaoyou Fu, Qiang Liu, Haotian Wang, Wenjing Yang, Yuanxing Zhang, Pengfei Wan, Yi-Fan Zhang, Ziwei Liu Title: RealUnify: Do Unified Models Truly Benefit from Unification

en

24:39

Beyond the Exploration-Exploitation Trade-off: A...

Daily Paper Cast ·

2025/10/01

🤗 Upvotes: 39 | cs.LG, cs.CL Authors: Fanding Huang, Guanbo Huang, Xiao Fan, Yi He, Xiao Liang, Xiao Chen, Qinting Jiang, Faisal Nadeem Khan, Jingyan Jiang, Zhi Wang Title: Beyond the Exploration-Exploitation Trade-off: A Hidden State Approach for LLM Reasoning in RLVR Arxiv: http://arxiv.org/abs/2509.23808v1 Abstract: A prevailing view in Reinforcement Learning for Verifiable

en

19:35

OpenGPT-4o-Image: A Comprehensive Dataset for...

Daily Paper Cast ·

2025/10/01

🤗 Upvotes: 38 | cs.CV, cs.AI Authors: Zhihong Chen, Xuehai Bai, Yang Shi, Chaoyou Fu, Huanyu Zhang, Haotian Wang, Xiaoyan Sun, Zhang Zhang, Liang Wang, Yuanxing Zhang, Pengfei Wan, Yi-Fan Zhang Title: OpenGPT-4o-Image: A Comprehensive Dataset for Advanced Image Generation and Editing Arxiv: http://arxiv.org/abs/2509.24900v1 Abstract: The performance of unified multimodal models

en

26:23

SANA-Video: Efficient Video Generation with Block...

Daily Paper Cast ·

2025/10/01

🤗 Upvotes: 36 | cs.CV, cs.AI Authors: Junsong Chen, Yuyang Zhao, Jincheng Yu, Ruihang Chu, Junyu Chen, Shuai Yang, Xianbang Wang, Yicheng Pan, Daquan Zhou, Huan Ling, Haozhe Liu, Hongwei Yi, Hao Zhang, Muyang Li, Yukang Chen, Han Cai, Sanja Fidler, Ping Luo, Song Han, Enze Xie Title: SANA-Video: Efficient Video Generation with Block Linear Diffusion Transformer Arxiv: http://arxiv.org/abs/2509.24695v1

en

26:05

Democratizing AI scientists using ToolUniverse

Daily Paper Cast ·

2025/10/01

🤗 Upvotes: 33 | cs.AI, cs.LG Authors: Shanghua Gao, Richard Zhu, Pengwei Sui, Zhenglun Kong, Sufian Aldogom, Yepeng Huang, Ayush Noori, Reza Shamji, Krishna Parvataneni, Theodoros Tsiligkaridis, Marinka Zitnik Title: Democratizing AI scientists using ToolUniverse Arxiv: http://arxiv.org/abs/2509.23426v1 Abstract: AI scientists are emerging computational systems that serve as

en

23:16

Visual Jigsaw Post-Training Improves MLLMs

Daily Paper Cast ·

2025/10/01

🤗 Upvotes: 33 | cs.CV Authors: Penghao Wu, Yushan Zhang, Haiwen Diao, Bo Li, Lewei Lu, Ziwei Liu Title: Visual Jigsaw Post-Training Improves MLLMs Arxiv: http://arxiv.org/abs/2509.25190v1 Abstract: Reinforcement learning based post-training has recently emerged as a powerful paradigm for enhancing the alignment and reasoning capabilities of multimodal large language models

en

24:47

When Does Reasoning Matter? A Controlled Study of...

Daily Paper Cast ·

2025/10/01

🤗 Upvotes: 29 | cs.CL Authors: Nicolas Boizard, Hippolyte Gisserot-Boukhlef, Kevin El-Haddad, Céline Hudelot, Pierre Colombo Title: When Does Reasoning Matter? A Controlled Study of Reasoning's Contribution to Model Performance Arxiv: http://arxiv.org/abs/2509.22193v1 Abstract: Large Language Models (LLMs) with reasoning capabilities have achieved state-of-the-art performance on

en

24:54

LongLive: Real-time Interactive Long Video Generation

Daily Paper Cast ·

2025/09/30

🤗 Upvotes: 136 | cs.CV Authors: Shuai Yang, Wei Huang, Ruihang Chu, Yicheng Xiao, Yuyang Zhao, Xianbang Wang, Muyang Li, Enze Xie, Yingcong Chen, Yao Lu, Song Han, Yukang Chen Title: LongLive: Real-time Interactive Long Video Generation Arxiv: http://arxiv.org/abs/2509.22622v1 Abstract: We present LongLive, a frame-level autoregressive (AR) framework for real-time and

en

23:16

Quantile Advantage Estimation for Entropy-Safe Reasoning

Daily Paper Cast ·

2025/09/30

🤗 Upvotes: 102 | cs.LG, cs.AI Authors: Junkang Wu, Kexin Huang, Jiancan Wu, An Zhang, Xiang Wang, Xiangnan He Title: Quantile Advantage Estimation for Entropy-Safe Reasoning Arxiv: http://arxiv.org/abs/2509.22611v1 Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) strengthens LLM reasoning, but training often oscillates between {entropy collapse} and {entropy

en

27:27

EPO: Entropy-regularized Policy Optimization for LLM...

Daily Paper Cast ·

2025/09/30

🤗 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 Dimitris Title: EPO: Entropy-regularized Policy Optimization for LLM Agents Reinforcement Learning Arxiv: http://arxiv.org/abs/2509.22576v1 Abstract: Training LLM agents in multi-turn environments with sparse rewards, where completing a single

en

25:00

MinerU2.5: A Decoupled Vision-Language Model for...

Daily Paper Cast ·

2025/09/30

🤗 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, Qintong Zhang, Zhenjiang Jin, Guang Liang, Rui Zhang, Wenzheng Zhang, Yuan Qu, Zhifei Ren, Yuefeng Sun, Yuanhong Zheng, Dongsheng Ma, Zirui Tang, Boyu Niu, Ziyang Miao, Hejun Dong, Siyi Qian, Junyuan Zhang, Jingzhou Chen, Fangdong Wang, Xiaomeng Zhao, Liqun Wei, Wei Li, Shasha Wang, Ruiliang Xu, Yuanyuan Cao, Lu

en

21:58

ReviewScore: Misinformed Peer Review Detection with...

Daily Paper Cast ·

2025/09/30

🤗 Upvotes: 54 | cs.CL Authors: Hyun Ryu, Doohyuk Jang, Hyemin S. Lee, Joonhyun Jeong, Gyeongman Kim, Donghyeon Cho, Gyouk Chu, Minyeong Hwang, Hyeongwon Jang, Changhun Kim, Haechan Kim, Jina Kim, Joowon Kim, Yoonjeon Kim, Kwanhyung Lee, Chanjae Park, Heecheol Yun, Gregor Betz, Eunho Yang Title: ReviewScore: Misinformed Peer Review Detection with Large Language Models Arxiv:

en

22:33

Variational Reasoning for Language Models

Daily Paper Cast ·

2025/09/30

🤗 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 Title: Variational Reasoning for Language Models Arxiv: http://arxiv.org/abs/2509.22637v1 Abstract: We introduce a variational reasoning framework for language models that treats thinking traces as latent variables and optimizes them

en

23:30

Language Models Can Learn from Verbal Feedback...

Daily Paper Cast ·

2025/09/30

🤗 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 Title: Language Models Can Learn from Verbal Feedback Without Scalar Rewards Arxiv: http://arxiv.org/abs/2509.22638v1 Abstract: LLMs are often trained with RL from human or AI feedback, yet such methods typically compress nuanced feedback into

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