Episodes

MemPrivacy: Privacy-Preserving Personalized Memory Management for Edge-Cloud Agents

Episode 1869 · May 13, 2026 · 24:27

🤗 Upvotes: 128 | cs.CR, cs.CL Authors: Yining Chen, Jihao Zhao, Bo Tang, Haofen Wang, Yue Zhang, Fei Huang, Feiyu Xiong, Zhiyu Li T...

SenseNova-U1: Unifying Multimodal Understanding and Generation with NEO-unify Architecture

Episode 1868 · May 13, 2026 · 25:32

🤗 Upvotes: 114 | cs.CV Authors: Haiwen Diao, Penghao Wu, Hanming Deng, Jiahao Wang, Shihao Bai, Silei Wu, Weichen Fan, Wenjie Ye, Wenwen Tong, X...

$δ$-mem: Efficient Online Memory for Large Language Models

Episode 1867 · May 13, 2026 · 24:31

🤗 Upvotes: 90 | cs.AI Authors: Jingdi Lei, Di Zhang, Junxian Li, Weida Wang, Kaixuan Fan, Xiang Liu, Qihan Liu, Xiaoteng Ma, Baian Chen, Soujany...

RubricEM: Meta-RL with Rubric-guided Policy Decomposition beyond Verifiable Rewards

Episode 1866 · May 13, 2026 · 22:37

🤗 Upvotes: 66 | cs.CL, cs.LG Authors: Gaotang Li, Bhavana Dalvi Mishra, Zifeng Wang, Jun Yan, Yanfei Chen, Chun-Liang Li, Long T. Le, Rujun Han,...

Do Enterprise Systems Need Learned World Models? The Importance of Context to Infer Dynamics

Episode 1865 · May 13, 2026 · 22:41

🤗 Upvotes: 53 | cs.AI, cs.CL, cs.LG Authors: Jishnu Sethumadhavan Nair, Patrice Bechard, Rishabh Maheshwary, Surajit Dasgupta, Sravan Ramachandr...

World Action Models: The Next Frontier in Embodied AI

Episode 1864 · May 13, 2026 · 24:43

🤗 Upvotes: 51 | cs.RO, cs.CL, cs.CV Authors: Siyin Wang, Junhao Shi, Zhaoyang Fu, Xinzhe He, Feihong Liu, Chenchen Yang, Yikang Zhou, Zhaoye Fei...

Beyond the Last Layer: Multi-Layer Representation Fusion for Visual Tokenization

Episode 1863 · May 13, 2026 · 25:20

🤗 Upvotes: 30 | cs.CV, cs.AI Authors: Xuanyu Zhu, Yan Bai, Yang Shi, Yihang Lou, Yuanxing Zhang, Jing Jin, Yuan Zhou Title: ...

Efficient Pre-Training with Token Superposition

Episode 1862 · May 13, 2026 · 24:35

🤗 Upvotes: 30 | cs.CL Authors: Bowen Peng, Théo Gigant, Jeffrey Quesnelle Title: Efficient Pre-Training with Token Supe...

AlphaGRPO: Unlocking Self-Reflective Multimodal Generation in UMMs via Decompositional Verifiable Reward

Episode 1861 · May 13, 2026 · 23:59

🤗 Upvotes: 28 | cs.CV, cs.AI, cs.LG Authors: Runhui Huang, Jie Wu, Rui Yang, Zhe Liu, Hengshuang Zhao Title: AlphaGRPO:...

MCP-Cosmos: World Model-Augmented Agents for Complex Task Execution in MCP Environments

Episode 1860 · May 13, 2026 · 21:44

🤗 Upvotes: 27 | cs.AI, cs.MA Authors: Giridhar Ganapavarapu, Dhaval Patel Title: MCP-Cosmos: World Model-Augmented Agen...

Qwen-Image-2.0 Technical Report

Episode 1859 · May 12, 2026 · 23:03

🤗 Upvotes: 78 | cs.CV Authors: Bing Zhao, Chenfei Wu, Deqing Li, Hao Meng, Jiahao Li, Jie Zhang, Jingren Zhou, Junyang Lin, Kaiyuan Gao, Kuan Ca...

Soohak: A Mathematician-Curated Benchmark for Evaluating Research-level Math Capabilities of LLMs

Episode 1858 · May 12, 2026 · 23:59

🤗 Upvotes: 66 | cs.CL Authors: Guijin Son, Seungone Kim, Catherine Arnett, Hyunwoo Ko, Hyein Lee, Hyeonah Kang, Jiang Longxi, Jin Yun, JungYup L...

CollabVR: Collaborative Video Reasoning with Vision-Language and Video Generation Models

Episode 1857 · May 12, 2026 · 25:26

🤗 Upvotes: 54 | cs.CV Authors: Joowon Kim, Seungho Shin, Joonhyung Park, Eunho Yang Title: CollabVR: Collaborative Vide...

TMAS: Scaling Test-Time Compute via Multi-Agent Synergy

Episode 1856 · May 12, 2026 · 23:17

🤗 Upvotes: 44 | cs.AI Authors: George Wu, Nan Jing, Qing Yi, Chuan Hao, Ming Yang, Feng Chang, Yuan Wei, Jian Yang, Ran Tao, Bryan Dai ...

PaperFit: Vision-in-the-Loop Typesetting Optimization for Scientific Documents

Episode 1855 · May 12, 2026 · 22:55

🤗 Upvotes: 29 | cs.AI, cs.SE Authors: Bihui Yu, Xinglong Xu, Junjie Jiang, Jiabei Cheng, Caijun Jia, Siyuan Li, Conghui He, Jingxuan Wei, Cheng ...

Model Merging Scaling Laws in Large Language Models

Episode 1854 · May 12, 2026 · 21:44

🤗 Upvotes: 26 | cs.AI Authors: Yuanyi Wang, Yanggan Gu, Yiming Zhang, Qi Zhou, Zhaoyi Yan, Congkai Xie, Xinyao Wang, Jianbo Yuan, Hongxia Yang ...

SEIF: Self-Evolving Reinforcement Learning for Instruction Following

Episode 1853 · May 12, 2026 · 21:27

🤗 Upvotes: 25 | cs.CL Authors: Qingyu Ren, Qianyu He, Jiajie Zhu, Xingzhou Chen, Jingwen Chang, Zeye Sun, Han Xia, Fei Yu, Jiaqing Liang, Yanghu...

WorldReasonBench: Human-Aligned Stress Testing of Video Generators as Future World-State Predictors

Episode 1852 · May 12, 2026 · 22:26

🤗 Upvotes: 24 | cs.CV Authors: Keming Wu, Yijing Cui, Wenhan Xue, Qijie Wang, Xuan Luo, Zhiyuan Feng, Zuhao Yang, Sudong Wang, Sicong Jiang, Hao...

Memory-Efficient Looped Transformer: Decoupling Compute from Memory in Looped Language Models

Episode 1851 · May 12, 2026 · 22:29

🤗 Upvotes: 21 | cs.CL, cs.AI, cs.LG Authors: Victor Conchello Vendrell, Arnau Padres Masdemont, Niccolò Grillo, Jordi Ros-Giralt, Arash Behboodi...

Mean Mode Screaming: Mean--Variance Split Residuals for 1000-Layer Diffusion Transformers

Episode 1850 · May 11, 2026 · 21:53

🤗 Upvotes: 106 | cs.LG, cs.CV Authors: Pengqi Lu Title: Mean Mode Screaming: Mean--Variance Split Residuals for 1000-La...