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

22:50

Generalizing Test-time Compute-optimal Scaling as an...

Daily Paper Cast ·

2025/11/05

🤗 Upvotes: 34 | cs.LG, cs.AI, cs.CL, I.2.7 Authors: Fali Wang, Jihai Chen, Shuhua Yang, Runxue Bao, Tianxiang Zhao, Zhiwei Zhang, Xianfeng Tang, Hui Liu, Qi He, Suhang Wang Title: Generalizing Test-time Compute-optimal Scaling as an Optimizable Graph Arxiv: http://arxiv.org/abs/2511.00086v1 Abstract: Test-Time Scaling (TTS) improves large language models (LLMs) by allocating

en

25:56

The Underappreciated Power of Vision Models for Graph...

Daily Paper Cast ·

2025/11/05

🤗 Upvotes: 31 | cs.CV, cs.AI, cs.LG Authors: Xinjian Zhao, Wei Pang, Zhongkai Xue, Xiangru Jian, Lei Zhang, Yaoyao Xu, Xiaozhuang Song, Shu Wu, Tianshu Yu Title: The Underappreciated Power of Vision Models for Graph Structural Understanding Arxiv: http://arxiv.org/abs/2510.24788v1 Abstract: Graph Neural Networks operate through bottom-up message-passing, fundamentally differing

en

23:59

UniLumos: Fast and Unified Image and Video Relighting...

Daily Paper Cast ·

2025/11/05

🤗 Upvotes: 27 | cs.CV Authors: Ropeway Liu, Hangjie Yuan, Bo Dong, Jiazheng Xing, Jinwang Wang, Rui Zhao, Yan Xing, Weihua Chen, Fan Wang Title: UniLumos: Fast and Unified Image and Video Relighting with Physics-Plausible Feedback Arxiv: http://arxiv.org/abs/2511.01678v1 Abstract: Relighting is a crucial task with both practical demand and artistic value, and recent diffusion

en

25:34

ROVER: Benchmarking Reciprocal Cross-Modal Reasoning...

Daily Paper Cast ·

2025/11/05

🤗 Upvotes: 24 | cs.CV Authors: Yongyuan Liang, Wei Chow, Feng Li, Ziqiao Ma, Xiyao Wang, Jiageng Mao, Jiuhai Chen, Jiatao Gu, Yue Wang, Furong Huang Title: ROVER: Benchmarking Reciprocal Cross-Modal Reasoning for Omnimodal Generation Arxiv: http://arxiv.org/abs/2511.01163v1 Abstract: Unified multimodal models (UMMs) have emerged as a powerful paradigm for seamlessly unifying

en

21:26

PHUMA: Physically-Grounded Humanoid Locomotion Dataset

Daily Paper Cast ·

2025/11/05

🤗 Upvotes: 23 | cs.RO Authors: Kyungmin Lee, Sibeen Kim, Minho Park, Hyunseung Kim, Dongyoon Hwang, Hojoon Lee, Jaegul Choo Title: PHUMA: Physically-Grounded Humanoid Locomotion Dataset Arxiv: http://arxiv.org/abs/2510.26236v1 Abstract: Motion imitation is a promising approach for humanoid locomotion, enabling agents to acquire humanlike behaviors. Existing methods typically

en

23:01

UniREditBench: A Unified Reasoning-based Image...

Daily Paper Cast ·

2025/11/05

🤗 Upvotes: 22 | cs.CV Authors: Feng Han, Yibin Wang, Chenglin Li, Zheming Liang, Dianyi Wang, Yang Jiao, Zhipeng Wei, Chao Gong, Cheng Jin, Jingjing Chen, Jiaqi Wang Title: UniREditBench: A Unified Reasoning-based Image Editing Benchmark Arxiv: http://arxiv.org/abs/2511.01295v1 Abstract: Recent advances in multi-modal generative models have driven substantial improvements in

en

29:01

World Simulation with Video Foundation Models for...

Daily Paper Cast ·

2025/11/05

🤗 Upvotes: 22 | cs.CV, cs.AI, cs.LG, cs.RO Authors: NVIDIA, :, Arslan Ali, Junjie Bai, Maciej Bala, Yogesh Balaji, Aaron Blakeman, Tiffany Cai, Jiaxin Cao, Tianshi Cao, Elizabeth Cha, Yu-Wei Chao, Prithvijit Chattopadhyay, Mike Chen, Yongxin Chen, Yu Chen, Shuai Cheng, Yin Cui, Jenna Diamond, Yifan Ding, Jiaojiao Fan, Linxi Fan, Liang Feng, Francesco Ferroni, Sanja Fidler, Xiao Fu, Ruiyuan Gao, Yunhao Ge, Jinwei Gu, Aryaman Gupta, Siddharth Gururani,

en

22:48

ThinkMorph: Emergent Properties in Multimodal...

Daily Paper Cast ·

2025/11/04

🤗 Upvotes: 56 | cs.CV Authors: Jiawei Gu, Yunzhuo Hao, Huichen Will Wang, Linjie Li, Michael Qizhe Shieh, Yejin Choi, Ranjay Krishna, Yu Cheng Title: ThinkMorph: Emergent Properties in Multimodal Interleaved Chain-of-Thought Reasoning Arxiv: http://arxiv.org/abs/2510.27492v1 Abstract: Multimodal reasoning requires iterative coordination between language and vision, yet it

en

20:54

INT v.s. FP: A Comprehensive Study of Fine-Grained...

Daily Paper Cast ·

2025/11/04

🤗 Upvotes: 49 | cs.LG, cs.AI Authors: Mengzhao Chen, Meng Wu, Hui Jin, Zhihang Yuan, Jing Liu, Chaoyi Zhang, Yunshui Li, Jie Huang, Jin Ma, Zeyue Xue, Zhiheng Liu, Xingyan Bin, Ping Luo Title: INT v.s. FP: A Comprehensive Study of Fine-Grained Low-bit Quantization Formats Arxiv: http://arxiv.org/abs/2510.25602v1 Abstract: Modern AI hardware, such as Nvidia's Blackwell

en

25:27

Spatial-SSRL: Enhancing Spatial Understanding via...

Daily Paper Cast ·

2025/11/04

🤗 Upvotes: 21 | cs.CV, cs.AI Authors: Yuhong Liu, Beichen Zhang, Yuhang Zang, Yuhang Cao, Long Xing, Xiaoyi Dong, Haodong Duan, Dahua Lin, Jiaqi Wang Title: Spatial-SSRL: Enhancing Spatial Understanding via Self-Supervised Reinforcement Learning Arxiv: http://arxiv.org/abs/2510.27606v1 Abstract: Spatial understanding remains a weakness of Large Vision-Language Models (LVLMs)

en

22:34

The End of Manual Decoding: Towards Truly End-to-End...

Daily Paper Cast ·

2025/11/01

🤗 Upvotes: 70 | cs.CL, cs.AIAuthors: Zhichao Wang, Dongyang Ma, Xinting Huang, Deng Cai, Tian Lan, Jiahao Xu, Haitao Mi, Xiaoying Tang, Yan Wang Title: The End of Manual Decoding: Towards Truly End-to-End Language Models Arxiv: http://arxiv.org/abs/2510.26697v1 Abstract: The "end-to-end" label for LLMs is a misnomer. In practice, they depend on a non-differentiable decoding

en

23:11

Kimi Linear: An Expressive, Efficient Attention...

Daily Paper Cast ·

2025/11/01

🤗 Upvotes: 40 | cs.CL, cs.LG Authors: Kimi Team, Yu Zhang, Zongyu Lin, Xingcheng Yao, Jiaxi Hu, Fanqing Meng, Chengyin Liu, Xin Men, Songlin Yang, Zhiyuan Li, Wentao Li, Enzhe Lu, Weizhou Liu, Yanru Chen, Weixin Xu, Longhui Yu, Yejie Wang, Yu Fan, Longguang Zhong, Enming Yuan, Dehao Zhang, Yizhi Zhang, T. Y. Liu, Haiming Wang, Shengjun Fang, Weiran He, Shaowei Liu, Yiwei Li, Jianlin Su, Jiezhong Qiu, Bo Pang, Junjie Yan, Zhejun Jiang, Weixiao Huang,

en

23:45

Surfer 2: The Next Generation of Cross-Platform...

Daily Paper Cast ·

2025/11/01

🤗 Upvotes: 28 | cs.AI Authors: Mathieu Andreux, Märt Bakler, Yanael Barbier, Hamza Benchekroun, Emilien Biré, Antoine Bonnet, Riaz Bordie, Nathan Bout, Matthias Brunel, Aleix Cambray, Pierre-Louis Cedoz, Antoine Chassang, Gautier Cloix, Ethan Connelly, Alexandra Constantinou, Ramzi De Coster, Hubert de la Jonquiere, Aurélien Delfosse, Maxime Delpit, Alexis Deprez, Augustin Derupti, Mathieu Diaz, Shannon D'Souza, Julie Dujardin, Abai Edmund, Michael

en

25:05

Are Video Models Ready as Zero-Shot Reasoners? An...

Daily Paper Cast ·

2025/11/01

🤗 Upvotes: 27 | cs.CV, cs.AI, cs.CL Authors: Ziyu Guo, Xinyan Chen, Renrui Zhang, Ruichuan An, Yu Qi, Dongzhi Jiang, Xiangtai Li, Manyuan Zhang, Hongsheng Li, Pheng-Ann Heng Title: Are Video Models Ready as Zero-Shot Reasoners? An Empirical Study with the MME-CoF Benchmark Arxiv: http://arxiv.org/abs/2510.26802v1 Abstract: Recent video generation models can produce

en

22:48

The Quest for Generalizable Motion Generation: Data,...

Daily Paper Cast ·

2025/11/01

🤗 Upvotes: 25 | cs.CV Authors: Jing Lin, Ruisi Wang, Junzhe Lu, Ziqi Huang, Guorui Song, Ailing Zeng, Xian Liu, Chen Wei, Wanqi Yin, Qingping Sun, Zhongang Cai, Lei Yang, Ziwei Liu Title: The Quest for Generalizable Motion Generation: Data, Model, and Evaluation Arxiv: http://arxiv.org/abs/2510.26794v1 Abstract: Despite recent advances in 3D human motion generation (MoGen) on

en

23:09

Concerto: Joint 2D-3D Self-Supervised Learning...

Daily Paper Cast ·

2025/10/29

🤗 Upvotes: 147 | cs.CVAuthors: Yujia Zhang, Xiaoyang Wu, Yixing Lao, Chengyao Wang, Zhuotao Tian, Naiyan Wang, Hengshuang Zhao Title: Concerto: Joint 2D-3D Self-Supervised Learning Emerges Spatial Representations Arxiv: http://arxiv.org/abs/2510.23607v1 Abstract: Humans learn abstract concepts through multisensory synergy, and once formed, such representations can often be

en

23:06

Every Attention Matters: An Efficient Hybrid...

Daily Paper Cast ·

2025/10/24

🤗 Upvotes: 79 | cs.LG, cs.AI, cs.CLAuthors: Ling Team, Bin Han, Caizhi Tang, Chen Liang, Donghao Zhang, Fan Yuan, Feng Zhu, Jie Gao, Jingyu Hu, Longfei Li, Meng Li, Mingyang Zhang, Peijie Jiang, Peng Jiao, Qian Zhao, Qingyuan Yang, Wenbo Shen, Xinxing Yang, Yalin Zhang, Yankun Ren, Yao Zhao, Yibo Cao, Yixuan Sun, Yue Zhang, Yuchen Fang, Zibin Lin, Zixuan Cheng, Jun Zhou Title: Every Attention Matters: An Efficient Hybrid

en

21:40

BAPO: Stabilizing Off-Policy Reinforcement Learning...

Daily Paper Cast ·

2025/10/24

🤗 Upvotes: 68 | cs.LG, cs.AI, cs.CL Authors: Zhiheng Xi, Xin Guo, Yang Nan, Enyu Zhou, Junrui Shen, Wenxiang Chen, Jiaqi Liu, Jixuan Huang, Zhihao Zhang, Honglin Guo, Xun Deng, Zhikai Lei, Miao Zheng, Guoteng Wang, Shuo Zhang, Peng Sun, Rui Zheng, Hang Yan, Tao Gui, Qi Zhang, Xuanjing Huang Title: BAPO: Stabilizing Off-Policy Reinforcement Learning for LLMs via Balanced Policy Optimization with Adaptive Clipping

en

21:23

LoongRL:Reinforcement Learning for Advanced Reasoning...

Daily Paper Cast ·

2025/10/24

🤗 Upvotes: 44 | cs.CL Authors: Siyuan Wang, Gaokai Zhang, Li Lyna Zhang, Ning Shang, Fan Yang, Dongyao Chen, Mao Yang Title: LoongRL:Reinforcement Learning for Advanced Reasoning over Long Contexts Arxiv: http://arxiv.org/abs/2510.19363v1 Abstract: Reasoning over long contexts is essential for large language models. While reinforcement learning (RL) enhances short-context

en

24:03

Language Models are Injective and Hence Invertible

Daily Paper Cast ·

2025/10/24

🤗 Upvotes: 42 | cs.LG, cs.AI Authors: Giorgos Nikolaou, Tommaso Mencattini, Donato Crisostomi, Andrea Santilli, Yannis Panagakis, Emanuele Rodolà Title: Language Models are Injective and Hence Invertible Arxiv: http://arxiv.org/abs/2510.15511v3 Abstract: Transformer components such as non-linear activations and normalization are inherently non-injective, suggesting that

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