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

22:14

WildWorld: A Large-Scale Dataset for Dynamic World...

Daily Paper Cast ·

2026/03/26

🤗 Upvotes: 69 | cs.CV Authors: Zhen Li, Zian Meng, Shuwei Shi, Wenshuo Peng, Yuwei Wu, Bo Zheng, Chuanhao Li, Kaipeng Zhang Title: WildWorld: A Large-Scale Dataset for Dynamic World Modeling with Actions and Explicit State toward Generative ARPG Arxiv: http://arxiv.org/abs/2603.23497v1 Abstract: Dynamical systems theory and reinforcement learning view world evolution as

en

27:57

From Static Templates to Dynamic Runtime Graphs: A...

Daily Paper Cast ·

2026/03/26

🤗 Upvotes: 43 | cs.AI, cs.CL Authors: Ling Yue, Kushal Raj Bhandari, Ching-Yun Ko, Dhaval Patel, Shuxin Lin, Nianjun Zhou, Jianxi Gao, Pin-Yu Chen, Shaowu Pan Title: From Static Templates to Dynamic Runtime Graphs: A Survey of Workflow Optimization for LLM Agents Arxiv: http://arxiv.org/abs/2603.22386v1 Abstract: Large language model (LLM)-based systems are becoming increasingly

en

21:53

SpecEyes: Accelerating Agentic Multimodal LLMs via...

Daily Paper Cast ·

2026/03/26

🤗 Upvotes: 43 | cs.CV, cs.CL Authors: Haoyu Huang, Jinfa Huang, Zhongwei Wan, Xiawu Zheng, Rongrong Ji, Jiebo Luo Title: SpecEyes: Accelerating Agentic Multimodal LLMs via Speculative Perception and Planning Arxiv: http://arxiv.org/abs/2603.23483v1 Abstract: Agentic multimodal large language models (MLLMs) (e.g., OpenAI o3 and Gemini Agentic Vision) achieve remarkable reasoning

en

22:20

PEARL: Personalized Streaming Video Understanding Model

Daily Paper Cast ·

2026/03/26

🤗 Upvotes: 36 | cs.CV, cs.AI, cs.IR Authors: Yuanhong Zheng, Ruichuan An, Xiaopeng Lin, Yuxing Liu, Sihan Yang, Huanyu Zhang, Haodong Li, Qintong Zhang, Renrui Zhang, Guopeng Li, Yifan Zhang, Yuheng Li, Wentao Zhang Title: PEARL: Personalized Streaming Video Understanding Model Arxiv: http://arxiv.org/abs/2603.20422v1 Abstract: Human cognition of new concepts is inherently a

en

20:42

DA-Flow: Degradation-Aware Optical Flow Estimation...

Daily Paper Cast ·

2026/03/26

🤗 Upvotes: 36 | cs.CV Authors: Jaewon Min, Jaeeun Lee, Yeji Choi, Paul Hyunbin Cho, Jin Hyeon Kim, Tae-Young Lee, Jongsik Ahn, Hwayeong Lee, Seonghyun Park, Seungryong Kim Title: DA-Flow: Degradation-Aware Optical Flow Estimation with Diffusion Models Arxiv: http://arxiv.org/abs/2603.23499v1 Abstract: Optical flow models trained on high-quality data often degrade severely when

en

23:43

SIMART: Decomposing Monolithic Meshes into Sim-ready...

Daily Paper Cast ·

2026/03/26

🤗 Upvotes: 33 | cs.CV, cs.GR, cs.RO Authors: Chuanrui Zhang, Minghan Qin, Yuang Wang, Baifeng Xie, Hang Li, Ziwei Wang Title: SIMART: Decomposing Monolithic Meshes into Sim-ready Articulated Assets via MLLM Arxiv: http://arxiv.org/abs/2603.23386v1 Abstract: High-quality articulated 3D assets are indispensable for embodied AI and physical simulation, yet 3D generation still

en

20:15

UniGRPO: Unified Policy Optimization for...

Daily Paper Cast ·

2026/03/26

🤗 Upvotes: 30 | cs.CV Authors: Jie Liu, Zilyu Ye, Linxiao Yuan, Shenhan Zhu, Yu Gao, Jie Wu, Kunchang Li, Xionghui Wang, Xiaonan Nie, Weilin Huang, Wanli Ouyang Title: UniGRPO: Unified Policy Optimization for Reasoning-Driven Visual Generation Arxiv: http://arxiv.org/abs/2603.23500v1 Abstract: Unified models capable of interleaved generation have emerged as a promising paradigm,

en

22:32

RealMaster: Lifting Rendered Scenes into...

Daily Paper Cast ·

2026/03/26

🤗 Upvotes: 23 | cs.CV Authors: Dana Cohen-Bar, Ido Sobol, Raphael Bensadoun, Shelly Sheynin, Oran Gafni, Or Patashnik, Daniel Cohen-Or, Amit Zohar Title: RealMaster: Lifting Rendered Scenes into Photorealistic Video Arxiv: http://arxiv.org/abs/2603.23462v1 Abstract: State-of-the-art video generation models produce remarkable photorealism, but they lack the precise control

en

23:04

Omni-WorldBench: Towards a Comprehensive...

Daily Paper Cast ·

2026/03/25

🤗 Upvotes: 110 | cs.CVAuthors: Meiqi Wu, Zhixin Cai, Fufangchen Zhao, Xiaokun Feng, Rujing Dang, Bingze Song, Ruitian Tian, Jiashu Zhu, Jiachen Lei, Hao Dou, Jing Tang, Lei Sun, Jiahong Wu, Xiangxiang Chu, Zeming Liu, Kaiqi Huang Title: Omni-WorldBench: Towards a Comprehensive Interaction-Centric Evaluation for World Models Arxiv: http://arxiv.org/abs/2603.22212v1 Abstract:

en

22:55

Speed by Simplicity: A Single-Stream Architecture for...

Daily Paper Cast ·

2026/03/25

🤗 Upvotes: 90 | cs.CV Authors: SII-GAIR, Sand. ai, :, Ethan Chern, Hansi Teng, Hanwen Sun, Hao Wang, Hong Pan, Hongyu Jia, Jiadi Su, Jin Li, Junjie Yu, Lijie Liu, Lingzhi Li, Lyumanshan Ye, Min Hu, Qiangang Wang, Quanwei Qi, Steffi Chern, Tao Bu, Taoran Wang, Teren Xu, Tianning Zhang, Tiantian Mi, Weixian Xu, Wenqiang Zhang, Wentai Zhang, Xianping Yi, Xiaojie Cai, Xiaoyang Kang, Yan Ma, Yixiu Liu, Yunbo Zhang, Yunpeng Huang, Yutong Lin, Zewei Tao,

en

22:54

LongCat-Flash-Prover: Advancing Native Formal...

Daily Paper Cast ·

2026/03/25

🤗 Upvotes: 63 | cs.AI, cs.CL Authors: Jianing Wang, Jianfei Zhang, Qi Guo, Linsen Guo, Rumei Li, Chao Zhang, Chong Peng, Cunguang Wang, Dengchang Zhao, Jiarong Shi, Jingang Wang, Liulin Feng, Mengxia Shen, Qi Li, Shengnan An, Shun Wang, Wei Shi, Xiangyu Xi, Xiaoyu Li, Xuezhi Cao, Yi Lu, Yunke Zhao, Zhengyu Chen, Zhimin Lin, Wei Wang, Peng Pei, Xunliang Cai Title: LongCat-Flash-Prover: Advancing Native Formal Reasoning via

en

26:12

Look Where It Matters: High-Resolution Crops...

Daily Paper Cast ·

2026/03/25

🤗 Upvotes: 60 | cs.CV, cs.AI Authors: Nimrod Shabtay, Moshe Kimhi, Artem Spector, Sivan Haray, Ehud Rivlin, Chaim Baskin, Raja Giryes, Eli Schwartz Title: Look Where It Matters: High-Resolution Crops Retrieval for Efficient VLMs Arxiv: http://arxiv.org/abs/2603.16932v1 Abstract: Vision-language models (VLMs) typically process images at a native high-resolution, forcing a

en

24:15

OpenResearcher: A Fully Open Pipeline for...

Daily Paper Cast ·

2026/03/25

🤗 Upvotes: 55 | cs.IR, cs.AI, cs.CL Authors: Zhuofeng Li, Dongfu Jiang, Xueguang Ma, Haoxiang Zhang, Ping Nie, Yuyu Zhang, Kai Zou, Jianwen Xie, Yu Zhang, Wenhu Chen Title: OpenResearcher: A Fully Open Pipeline for Long-Horizon Deep Research Trajectory Synthesis Arxiv: http://arxiv.org/abs/2603.20278v1 Abstract: Training deep research agents requires long-horizon trajectories

en

22:39

VideoDetective: Clue Hunting via both Extrinsic Query...

Daily Paper Cast ·

2026/03/25

🤗 Upvotes: 45 | cs.CV Authors: Ruoliu Yang, Chu Wu, Caifeng Shan, Ran He, Chaoyou Fu Title: VideoDetective: Clue Hunting via both Extrinsic Query and Intrinsic Relevance for Long Video Understanding Arxiv: http://arxiv.org/abs/2603.22285v1 Abstract: Long video understanding remains challenging for multimodal large language models (MLLMs) due to limited context windows, which

en

22:51

SpatialBoost: Enhancing Visual Representation through...

Daily Paper Cast ·

2026/03/25

🤗 Upvotes: 39 | cs.CV Authors: Byungwoo Jeon, Dongyoung Kim, Huiwon Jang, Insoo Kim, Jinwoo Shin Title: SpatialBoost: Enhancing Visual Representation through Language-Guided Reasoning Arxiv: http://arxiv.org/abs/2603.22057v1 Abstract: Despite the remarkable success of large-scale pre-trained image representation models (i.e., vision encoders) across various vision tasks, they

en

22:49

F4Splat: Feed-Forward Predictive Densification for...

Daily Paper Cast ·

2026/03/25

🤗 Upvotes: 31 | cs.CV Authors: Injae Kim, Chaehyeon Kim, Minseong Bae, Minseok Joo, Hyunwoo J. Kim Title: F4Splat: Feed-Forward Predictive Densification for Feed-Forward 3D Gaussian Splatting Arxiv: http://arxiv.org/abs/2603.21304v1 Abstract: Feed-forward 3D Gaussian Splatting methods enable single-pass reconstruction and real-time rendering. However, they typically adopt rigid

en

24:27

mSFT: Addressing Dataset Mixtures Overfitting...

Daily Paper Cast ·

2026/03/25

🤗 Upvotes: 28 | cs.LG, cs.AI Authors: Woosung Koh, Jeyoung Jeon, Youngjin Song, Yujin Cheon, Soowon Oh, Jaehyeong Choi, Se-Young Yun Title: mSFT: Addressing Dataset Mixtures Overfitting Heterogeneously in Multi-task SFT Arxiv: http://arxiv.org/abs/2603.21606v2 Abstract: Current language model training commonly applies multi-task Supervised Fine-Tuning (SFT) using a homogeneous

en

24:36

HopChain: Multi-Hop Data Synthesis for Generalizable...

Daily Paper Cast ·

2026/03/24

🤗 Upvotes: 96 | cs.CV, cs.AI, cs.CL Authors: Shenzhi Wang, Shixuan Liu, Jing Zhou, Chang Gao, Xiong-Hui Chen, Binghai Wang, An Yang, Shiji Song, Bowen Yu, Gao Huang, Junyang Lin Title: HopChain: Multi-Hop Data Synthesis for Generalizable Vision-Language Reasoning Arxiv: http://arxiv.org/abs/2603.17024v2 Abstract: Vision-language models (VLMs) show strong multimodal capabilities

en

24:19

Astrolabe: Steering Forward-Process Reinforcement...

Daily Paper Cast ·

2026/03/24

🤗 Upvotes: 87 | cs.CV Authors: Songchun Zhang, Zeyue Xue, Siming Fu, Jie Huang, Xianghao Kong, Y Ma, Haoyang Huang, Nan Duan, Anyi Rao Title: Astrolabe: Steering Forward-Process Reinforcement Learning for Distilled Autoregressive Video Models Arxiv: http://arxiv.org/abs/2603.17051v1 Abstract: Distilled autoregressive (AR) video models enable efficient streaming generation but

en

25:57

TerraScope: Pixel-Grounded Visual Reasoning for Earth...

Daily Paper Cast ·

2026/03/24

🤗 Upvotes: 42 | cs.CV Authors: Yan Shu, Bin Ren, Zhitong Xiong, Xiao Xiang Zhu, Begüm Demir, Nicu Sebe, Paolo Rota Title: TerraScope: Pixel-Grounded Visual Reasoning for Earth Observation Arxiv: http://arxiv.org/abs/2603.19039v1 Abstract: Vision-language models (VLMs) have shown promise in earth observation (EO), yet they struggle with tasks that require grounding complex

en

1,800 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