SWE-Universe: Scale Real-World Verifiable Environments to Millions
Paper • 2602.02361 • Published • 60
AI & ML interests
Pretraining, Multimodality, NLP, CV, etc.
Recent Activity
View all activity
Losin94
authored a
paper about 1 month ago
yangapku
authored a
paper about 2 months ago
yangapku
authored a
paper 3 months ago
yangapku
authored 5
papers 4 months ago
Stabilizing Reinforcement Learning with LLMs: Formulation and Practices
Paper • 2512.01374 • Published • 106
Qwen-Image Technical Report
Paper • 2508.02324 • Published • 273
Qwen3Guard Technical Report
Paper • 2510.14276 • Published • 15
RMTBench: Benchmarking LLMs Through Multi-Turn User-Centric Role-Playing
Paper • 2507.20352 • Published
Soft Adaptive Policy Optimization
Paper • 2511.20347 • Published • 43
Losin94
authored a
paper 6 months ago
faychu
authored a
paper 6 months ago
jklj077
published a
model 7 months ago
jklj077
published a
dataset 7 months ago
jklj077
updated a
dataset 7 months ago
jklj077
updated a
model 7 months ago
Losin94
authored a
paper 8 months ago
yangapku
authored a
paper 8 months ago
yangapku
authored 3
papers 10 months ago
Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning
Paper • 2506.01939 • Published • 190
Rationales Are Not Silver Bullets: Measuring the Impact of Rationales on Model Performance and Reliability
Paper • 2505.24147 • Published
Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models
Paper • 2506.05176 • Published • 80
mingfengxue
authored a
paper 10 months ago