山下颯太

thomas-taylor's activity

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

upvoted a paper 3 days ago

Anti-Self-Distillation for Reasoning RL via Pointwise Mutual Information

Paper • 2605.11609 • Published 11 days ago • 186

upvoted a paper 5 days ago

Learning to Foresee: Unveiling the Unlocking Efficiency of On-Policy Distillation

Paper • 2605.11739 • Published 10 days ago • 55

upvoted a paper 9 days ago

Mean Mode Screaming: Mean--Variance Split Residuals for 1000-Layer Diffusion Transformers

Paper • 2605.06169 • Published 16 days ago • 186

upvoted a paper about 2 months ago

Marco DeepResearch: Unlocking Efficient Deep Research Agents via Verification-Centric Design

Paper • 2603.28376 • Published Mar 30 • 24