-
ZimaBlue: Evolving Generalizable World Action Models through Scalable Video Pre-training
score 10
入选 HF Daily Papers; HF 热度: 47 upvotes (+4); 有代码实现; 关键词(7): scaling, lightweight, deployment, real-time, pre-training
-
Safin-1: Safety from Within through Memory-Native State Evolution
score 10
入选 HF Daily Papers; HF 热度: 20 upvotes (+4); 有代码实现; 关键词(1): fine-tuning
-
Qwen-Drive-1.0: An Initial Step towards a Vision-Language Foundation Model for Autonomous Driving
score 8
入选 HF Daily Papers; HF 热度: 369 upvotes (+4); 关键词(1): vision-language
-
UI-Venus-2 Technical Report
score 8
入选 HF Daily Papers; HF 热度: 59 upvotes (+4); 关键词(3): deployment, reasoning, open-source
-
From Production Traffic to Post-Training: Building a Self-Hosted LLM That Covers the Corporate Request Mix
score 8
入选 HF Daily Papers; HF 热度: 33 upvotes (+4); 关键词(5): production, serving, GRPO, post-training, reasoning
-
DiagEvo: Diagnosis-Guided Self-Evolution via Hierarchical Error Memory
score 7
入选 HF Daily Papers; HF 热度: 19 upvotes (+3); 关键词(1): reasoning
-
It Takes Two to Match: Co-Evolving Generative Retriever with Reinforcement Learning
score 8
入选 HF Daily Papers; HF 热度: 70 upvotes (+4); 关键词(2): fine-tuning, GRPO
-
Recursive Criticality of AI Self-Improvement
score 7
入选 HF Daily Papers; HF 热度: 6 upvotes (+2); 有代码实现
-
On the Design Fundamentals of Pixel Text Representation Learning
score 10
入选 HF Daily Papers; HF 热度: 32 upvotes (+4); 有代码实现; 关键词(2): compression, pretraining
-
Knowledge Distillation During Mid-Training Favors Reasoning over Factual Recall
score 7
入选 HF Daily Papers; HF 热度: 4 upvotes (+1); 有代码实现; 关键词(5): lightweight, distillation, post-training, pre-training, reasoning