Podcast Episodes

Macaron-V1: Towards Open Continual Learning with Self-Improvement and Mixture-of-LoRA

Episode 2175

🤗 Upvotes: 277 | cs.LG, cs.CL

Authors:
Mind Lab, :, Vin Bo, Asher Cai, Jingwei Cao, Song Cao, Vic Cao, Amelia Ch…

1 week ago

View Episode

BDH-CQ: In-Context Learning with Recurrent Latent Reasoning

Episode 2174

🤗 Upvotes: 253 | cs.NE, cs.AI, cs.LG, stat.ML

Authors:
Björn Engdahl, Adrian Kosowski, Jan Chorowski, Zuzanna St…

1 week ago

View Episode

SWE-Bench ProMax: Benchmarking Agents on Large-Scale Multilingual Code Refactoring

Episode 2173

🤗 Upvotes: 120 | cs.CL, cs.SE

Authors:
Yuling Shi, Jinghan Xu, Kelin Fu, Wenhao Zeng, Shilin He, Lei Zhang, Yue …

1 week ago

View Episode

On-Policy Self-Distillation without Any Supervision

Episode 2172

🤗 Upvotes: 92 | cs.LG

Authors:
Yijiang Li, Bingyang Wang, Yijun Liang, Yunjie Tian, Di Fu, Nuno Vasconcelos

…

1 week ago

View Episode

Ouroboros: A Self-Developing Frontier Coding Agent with Reviewed Core Evolution

Episode 2171

🤗 Upvotes: 68 | cs.SE, cs.AI

Authors:
Anton Razzhigaev, Andrei Gritsaev, Andrei Kaznacheev, Nikita Dragunov, Rom…

1 week ago

View Episode

Agent Memory Distillation: Empowering Small LLM Agents with Hierarchical Teacher Memory

Episode 2170

🤗 Upvotes: 37 | cs.AI, cs.LG

Authors:
Taeil Kim, Kangsan Kim, Sung Ju Hwang

Title:
Agent…

1 week ago

View Episode

Motif 3: Technical Report

Episode 2169

🤗 Upvotes: 36 | cs.AI

Authors:
Junghwan Lim, Joon Son Chung, Sungmin Lee, Wai Ting Cheung, Gihun Cho, Minsu Ha, …

1 week ago

View Episode

Sci-VBench: Evaluating Knowledge- and Reasoning-Intensive Video Generation in Science Domains

Episode 2168

🤗 Upvotes: 26 | cs.CV, cs.AI

Authors:
Diandian Zhang, Tingyu Song, Lin Fu, Zheyuan Yang, Yilun Zhao

…

1 week, 1 day ago

View Episode

What to Edit Next: Visually Aligned Image-Editing Follow-Up Suggestions in Conversational Systems

Episode 2167

🤗 Upvotes: 25 | cs.CV, cs.AI

Authors:
Zhijing Zhang, Jinpeng Yu, Xin Song, Bingnan Li, Chuyue Li, Changhui Du, X…

1 week, 1 day ago

View Episode

SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs

Episode 2166

🤗 Upvotes: 33 | cs.CL, cs.LG

Authors:
Kejian Zhu, Zhuoran Jin, Shangqing Tu, Hongbang Yuan, Yushi Bai, Kang Liu,…

1 week, 2 days ago

View Episode