Changsong

maybe1possible's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted 3 papers 4 months ago

The Past Is Not Past: Memory-Enhanced Dynamic Reward Shaping

Paper • 2604.11297 • Published Apr 13 • 144

Speed by Simplicity: A Single-Stream Architecture for Fast Audio-Video Generative Foundation Model

Paper • 2603.21986 • Published Mar 23 • 125

AI Can Learn Scientific Taste

Paper • 2603.14473 • Published Mar 15 • 432

upvoted 4 papers 6 months ago

TL-GRPO: Turn-Level RL for Reasoning-Guided Iterative Optimization

Paper • 2601.16480 • Published Jan 23 • 50

HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding

Paper • 2601.14724 • Published Jan 21 • 75

FutureOmni: Evaluating Future Forecasting from Omni-Modal Context for Multimodal LLMs

Paper • 2601.13836 • Published Jan 20 • 37

ArenaRL: Scaling RL for Open-Ended Agents via Tournament-based Relative Ranking

Paper • 2601.06487 • Published Jan 10 • 54