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

22:36

When to Ensemble: Identifying Token-Level Points for...

Daily Paper Cast ·

2025/10/22

🤗 Upvotes: 27 | cs.CL, cs.AI Authors: Heecheol Yun, Kwangmin Ki, Junghyun Lee, Eunho Yang Title: When to Ensemble: Identifying Token-Level Points for Stable and Fast LLM Ensembling Arxiv: http://arxiv.org/abs/2510.15346v1 Abstract: Ensembling Large Language Models (LLMs) has gained attention as a promising approach to surpass the performance of individual models by leveraging

en

20:07

A Theoretical Study on Bridging Internal Probability...

Daily Paper Cast ·

2025/10/21

🤗 Upvotes: 112 | cs.LG, cs.AI Authors: Zhi Zhou, Yuhao Tan, Zenan Li, Yuan Yao, Lan-Zhe Guo, Yu-Feng Li, Xiaoxing Ma Title: A Theoretical Study on Bridging Internal Probability and Self-Consistency for LLM Reasoning Arxiv: http://arxiv.org/abs/2510.15444v1 Abstract: Test-time scaling seeks to improve the reasoning performance of large language models (LLMs) by adding

en

25:05

OmniVinci: Enhancing Architecture and Data for...

Daily Paper Cast ·

2025/10/21

🤗 Upvotes: 56 | cs.CV, cs.AI, cs.CL Authors: Hanrong Ye, Chao-Han Huck Yang, Arushi Goel, Wei Huang, Ligeng Zhu, Yuanhang Su, Sean Lin, An-Chieh Cheng, Zhen Wan, Jinchuan Tian, Yuming Lou, Dong Yang, Zhijian Liu, Yukang Chen, Ambrish Dantrey, Ehsan Jahangiri, Sreyan Ghosh, Daguang Xu, Ehsan Hosseini-Asl, Danial Mohseni Taheri, Vidya Murali, Sifei Liu, Jason Lu, Oluwatobi Olabiyi, Frank Wang, Rafael Valle, Bryan Catanzaro, Andrew Tao, Song Han, Jan

en

22:45

NANO3D: A Training-Free Approach for Efficient 3D...

Daily Paper Cast ·

2025/10/21

🤗 Upvotes: 50 | cs.CV Authors: Junliang Ye, Shenghao Xie, Ruowen Zhao, Zhengyi Wang, Hongyu Yan, Wenqiang Zu, Lei Ma, Jun Zhu Title: NANO3D: A Training-Free Approach for Efficient 3D Editing Without Masks Arxiv: http://arxiv.org/abs/2510.15019v1 Abstract: 3D object editing is essential for interactive content creation in gaming, animation, and robotics, yet current approaches

en

20:28

Emergent Misalignment via In-Context Learning: Narrow...

Daily Paper Cast ·

2025/10/21

🤗 Upvotes: 39 | cs.CL Authors: Nikita Afonin, Nikita Andriyanov, Nikhil Bageshpura, Kyle Liu, Kevin Zhu, Sunishchal Dev, Ashwinee Panda, Alexander Panchenko, Oleg Rogov, Elena Tutubalina, Mikhail Seleznyov Title: Emergent Misalignment via In-Context Learning: Narrow in-context examples can produce broadly misaligned LLMs Arxiv: http://arxiv.org/abs/2510.11288v1 Abstract: Recent

en

20:07

Scaling Instruction-Based Video Editing with a...

Daily Paper Cast ·

2025/10/21

🤗 Upvotes: 37 | cs.CV Authors: Qingyan Bai, Qiuyu Wang, Hao Ouyang, Yue Yu, Hanlin Wang, Wen Wang, Ka Leong Cheng, Shuailei Ma, Yanhong Zeng, Zichen Liu, Yinghao Xu, Yujun Shen, Qifeng Chen Title: Scaling Instruction-Based Video Editing with a High-Quality Synthetic Dataset Arxiv: http://arxiv.org/abs/2510.15742v1 Abstract: Instruction-based video editing promises to democratize

en

25:28

Skyfall-GS: Synthesizing Immersive 3D Urban Scenes...

Daily Paper Cast ·

2025/10/21

🤗 Upvotes: 33 | cs.CV Authors: Jie-Ying Lee, Yi-Ruei Liu, Shr-Ruei Tsai, Wei-Cheng Chang, Chung-Ho Wu, Jiewen Chan, Zhenjun Zhao, Chieh Hubert Lin, Yu-Lun Liu Title: Skyfall-GS: Synthesizing Immersive 3D Urban Scenes from Satellite Imagery Arxiv: http://arxiv.org/abs/2510.15869v1 Abstract: Synthesizing large-scale, explorable, and geometrically accurate 3D urban scenes is a

en

25:07

Latent Diffusion Model without Variational Autoencoder

Daily Paper Cast ·

2025/10/21

🤗 Upvotes: 30 | cs.CV, cs.AI Authors: Minglei Shi, Haolin Wang, Wenzhao Zheng, Ziyang Yuan, Xiaoshi Wu, Xintao Wang, Pengfei Wan, Jie Zhou, Jiwen Lu Title: Latent Diffusion Model without Variational Autoencoder Arxiv: http://arxiv.org/abs/2510.15301v2 Abstract: Recent progress in diffusion-based visual generation has largely relied on latent diffusion models with variational

en

23:54

When Models Lie, We Learn: Multilingual Span-Level...

Daily Paper Cast ·

2025/10/18

🤗 Upvotes: 81 | cs.CLAuthors: Elisei Rykov, Kseniia Petrushina, Maksim Savkin, Valerii Olisov, Artem Vazhentsev, Kseniia Titova, Alexander Panchenko, Vasily Konovalov, Julia Belikova Title: When Models Lie, We Learn: Multilingual Span-Level Hallucination Detection with PsiloQA Arxiv: http://arxiv.org/abs/2510.04849v1 Abstract: Hallucination detection remains a fundamental

en

23:52

Agentic Entropy-Balanced Policy Optimization

Daily Paper Cast ·

2025/10/18

🤗 Upvotes: 78 | cs.LG, cs.AI, cs.CL, cs.IR Authors: Guanting Dong, Licheng Bao, Zhongyuan Wang, Kangzhi Zhao, Xiaoxi Li, Jiajie Jin, Jinghan Yang, Hangyu Mao, Fuzheng Zhang, Kun Gai, Guorui Zhou, Yutao Zhu, Ji-Rong Wen, Zhicheng Dou Title: Agentic Entropy-Balanced Policy Optimization Arxiv: http://arxiv.org/abs/2510.14545v1 Abstract: Recently, Agentic Reinforcement Learning

en

23:15

WithAnyone: Towards Controllable and ID Consistent...

Daily Paper Cast ·

2025/10/18

🤗 Upvotes: 65 | cs.CV, cs.AI Authors: Hengyuan Xu, Wei Cheng, Peng Xing, Yixiao Fang, Shuhan Wu, Rui Wang, Xianfang Zeng, Daxin Jiang, Gang Yu, Xingjun Ma, Yu-Gang Jiang Title: WithAnyone: Towards Controllable and ID Consistent Image Generation Arxiv: http://arxiv.org/abs/2510.14975v1 Abstract: Identity-consistent generation has become an important focus in text-to-image

en

24:04

AI for Service: Proactive Assistance with AI Glasses

Daily Paper Cast ·

2025/10/18

🤗 Upvotes: 60 | cs.AI, cs.CL, cs.CV Authors: Zichen Wen, Yiyu Wang, Chenfei Liao, Boxue Yang, Junxian Li, Weifeng Liu, Haocong He, Bolong Feng, Xuyang Liu, Yuanhuiyi Lyu, Xu Zheng, Xuming Hu, Linfeng Zhang Title: AI for Service: Proactive Assistance with AI Glasses Arxiv: http://arxiv.org/abs/2510.14359v1 Abstract: In an era where AI is evolving from a passive tool into an

en

20:41

From Pixels to Words -- Towards Native...

Daily Paper Cast ·

2025/10/18

🤗 Upvotes: 51 | cs.CV, cs.AI Authors: Haiwen Diao, Mingxuan Li, Silei Wu, Linjun Dai, Xiaohua Wang, Hanming Deng, Lewei Lu, Dahua Lin, Ziwei Liu Title: From Pixels to Words -- Towards Native Vision-Language Primitives at Scale Arxiv: http://arxiv.org/abs/2510.14979v1 Abstract: The edifice of native Vision-Language Models (VLMs) has emerged as a rising contender to typical

en

21:12

ImagerySearch: Adaptive Test-Time Search for Video...

Daily Paper Cast ·

2025/10/18

🤗 Upvotes: 46 | cs.CV Authors: Meiqi Wu, Jiashu Zhu, Xiaokun Feng, Chubin Chen, Chen Zhu, Bingze Song, Fangyuan Mao, Jiahong Wu, Xiangxiang Chu, Kaiqi Huang Title: ImagerySearch: Adaptive Test-Time Search for Video Generation Beyond Semantic Dependency Constraints Arxiv: http://arxiv.org/abs/2510.14847v1 Abstract: Video generation models have achieved remarkable progress,

en

25:04

Information Gain-based Policy Optimization: A Simple...

Daily Paper Cast ·

2025/10/18

🤗 Upvotes: 30 | cs.CL, cs.AI, cs.LG Authors: Guoqing Wang, Sunhao Dai, Guangze Ye, Zeyu Gan, Wei Yao, Yong Deng, Xiaofeng Wu, Zhenzhe Ying Title: Information Gain-based Policy Optimization: A Simple and Effective Approach for Multi-Turn LLM Agents Arxiv: http://arxiv.org/abs/2510.14967v1 Abstract: Large language model (LLM)-based agents are increasingly trained with

en

19:44

LaSeR: Reinforcement Learning with Last-Token...

Daily Paper Cast ·

2025/10/18

🤗 Upvotes: 30 | cs.CL, cs.AI, cs.LG Authors: Wenkai Yang, Weijie Liu, Ruobing Xie, Yiju Guo, Lulu Wu, Saiyong Yang, Yankai Lin Title: LaSeR: Reinforcement Learning with Last-Token Self-Rewarding Arxiv: http://arxiv.org/abs/2510.14943v1 Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has recently emerged as a core paradigm for enhancing the reasoning capabilities

en

20:48

TokDrift: When LLM Speaks in Subwords but Code Speaks...

Daily Paper Cast ·

2025/10/18

🤗 Upvotes: 27 | cs.CL, cs.AI, cs.LG, cs.PL, cs.SE Authors: Yinxi Li, Yuntian Deng, Pengyu Nie Title: TokDrift: When LLM Speaks in Subwords but Code Speaks in Grammar Arxiv: http://arxiv.org/abs/2510.14972v1 Abstract: Large language models (LLMs) for code rely on subword tokenizers, such as byte-pair encoding (BPE), learned from mixed natural language text and programming

en

22:18

BitNet Distillation

Daily Paper Cast ·

2025/10/18

🤗 Upvotes: 26 | cs.LG, cs.CL Authors: Xun Wu, Shaohan Huang, Wenhui Wang, Ting Song, Li Dong, Yan Xia, Furu Wei Title: BitNet Distillation Arxiv: http://arxiv.org/abs/2510.13998v1 Abstract: In this paper, we present BitNet Distillation (BitDistill), a lightweight pipeline that fine-tunes off-the-shelf full-precision LLMs (e.g., Qwen) into 1.58-bit precision (i.e., ternary

en

22:32

Spatial Forcing: Implicit Spatial Representation...

Daily Paper Cast ·

2025/10/16

🤗 Upvotes: 133 | cs.ROAuthors: Fuhao Li, Wenxuan Song, Han Zhao, Jingbo Wang, Pengxiang Ding, Donglin Wang, Long Zeng, Haoang Li Title: Spatial Forcing: Implicit Spatial Representation Alignment for Vision-language-action Model Arxiv: http://arxiv.org/abs/2510.12276v1 Abstract: Vision-language-action (VLA) models have recently shown strong potential in enabling robots to follow

en

23:30

Advancing End-to-End Pixel Space Generative Modeling...

Daily Paper Cast ·

2025/10/16

🤗 Upvotes: 91 | cs.CV Authors: Jiachen Lei, Keli Liu, Julius Berner, Haiming Yu, Hongkai Zheng, Jiahong Wu, Xiangxiang Chu Title: Advancing End-to-End Pixel Space Generative Modeling via Self-supervised Pre-training Arxiv: http://arxiv.org/abs/2510.12586v1 Abstract: Pixel-space generative models are often more difficult to train and generally underperform compared to their

en

1,351 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