Tianyu Li

Litianyu2004's activity

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

upvoted a paper about 10 hours ago

What Makes World Action Models Generalize? An Empirical Study of Test-Time Future Modeling

Paper • 2609.34981 • Published 1 day ago • 57

upvoted a paper 4 months ago

Linearizing Vision Transformer with Test-Time Training

Paper • 2605.02772 • Published May 28 • 17

authored a paper 4 months ago

SiameseNorm: Breaking the Barrier to Reconciling Pre/Post-Norm

Paper • 2602.08064 • Published Feb 8

upvoted 2 papers 5 months ago

InsightTok: Improving Text and Face Fidelity in Discrete Tokenization for Autoregressive Image Generation

Paper • 2605.14333 • Published May 14 • 33

Refinement via Regeneration: Enlarging Modification Space Boosts Image Refinement in Unified Multimodal Models

Paper • 2604.25636 • Published Apr 28 • 25

upvoted a paper 6 months ago

HopChain: Multi-Hop Data Synthesis for Generalizable Vision-Language Reasoning

Paper • 2603.17024 • Published Mar 17 • 111

upvoted a paper 8 months ago

The Flexibility Trap: Why Arbitrary Order Limits Reasoning Potential in Diffusion Language Models

Paper • 2601.15165 • Published Jan 21 • 75

upvoted a paper about 1 year ago

HybridNorm: Towards Stable and Efficient Transformer Training via Hybrid Normalization

Paper • 2503.04598 • Published Mar 6, 2025 • 22

upvoted a paper over 1 year ago

Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning

Paper • 2506.01939 • Published Jun 2, 2025 • 190