Podcast Episodes

Genius: A Generalizable and Purely Unsupervised Self-Training Framework For Advanced Reasoning

Episode 685

🤗 Upvotes: 41 | cs.CL, cs.AI, cs.LG

Authors:
Fangzhi Xu, Hang Yan, Chang Ma, Haiteng Zhao, Qiushi Sun, Kanzhi Ch…

11 months ago

View Episode

How Instruction and Reasoning Data shape Post-Training: Data Quality through the Lens of Layer-wise Gradients

Episode 684

🤗 Upvotes: 30 | cs.LG, cs.AI, cs.CL

Authors:
Ming Li, Yanhong Li, Ziyue Li, Tianyi Zhou

Title:
…

11 months ago

View Episode

Heimdall: test-time scaling on the generative verification

Episode 683

🤗 Upvotes: 28 | cs.AI, I.2.7

Authors:
Wenlei Shi, Xing Jin

Title:
Heimdall: test-time sc…

11 months ago

View Episode

Pixel-SAIL: Single Transformer For Pixel-Grounded Understanding

Episode 682

🤗 Upvotes: 23 | cs.CV

Authors:
Tao Zhang, Xiangtai Li, Zilong Huang, Yanwei Li, Weixian Lei, Xueqing Deng, Shiha…

11 months ago

View Episode

TextArena

Episode 681

🤗 Upvotes: 21 | cs.CL, cs.AI, cs.LG, cs.MA

Authors:
Leon Guertler, Bobby Cheng, Simon Yu, Bo Liu, Leshem Choshen…

11 months ago

View Episode

InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models

Episode 680

🤗 Upvotes: 172 | cs.CV

Authors:
Jinguo Zhu, Weiyun Wang, Zhe Chen, Zhaoyang Liu, Shenglong Ye, Lixin Gu, Yuchen …

11 months ago

View Episode

PRIMA.CPP: Speeding Up 70B-Scale LLM Inference on Low-Resource Everyday Home Clusters

Episode 679

🤗 Upvotes: 95 | cs.DC, cs.AI, 68T50, I.2.7; I.2.11

Authors:
Zonghang Li, Tao Li, Wenjiao Feng, Mohsen Guizani, H…

11 months ago

View Episode

VL-Rethinker: Incentivizing Self-Reflection of Vision-Language Models with Reinforcement Learning

Episode 678

🤗 Upvotes: 36 | cs.LG, cs.AI

Authors:
Haozhe Wang, Chao Qu, Zuming Huang, Wei Chu, Fangzhen Lin, Wenhu Chen

…

11 months ago

View Episode

FUSION: Fully Integration of Vision-Language Representations for Deep Cross-Modal Understanding

Episode 677

🤗 Upvotes: 35 | cs.CV

Authors:
Zheng Liu, Mengjie Liu, Jingzhou Chen, Jingwei Xu, Bin Cui, Conghui He, Wentao Zh…

11 months ago

View Episode

Iterative Self-Training for Code Generation via Reinforced Re-Ranking

Episode 676

🤗 Upvotes: 29 | cs.CL, cs.IR, cs.SE

Authors:
Nikita Sorokin, Ivan Sedykh, Valentin Malykh

Title:
…

11 months ago

View Episode