Yuxuan liu

LancasterLiu's activity

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

upvoted a paper 1 day ago

One Token per Multimodal Evidence: Latent Memory for Resource-Constrained QA

Paper • 2606.10572 • Published 2 days ago • 14

liked a dataset about 1 month ago

SII-fleeeecer/PragmaSafe-Beavertails

Updated Mar 31 • 761 • 1

updated a dataset 6 months ago

LancasterLiu/MAT

Viewer • Updated Dec 13, 2025 • 1.99k • 13

published a dataset 6 months ago

LancasterLiu/MAT

Viewer • Updated Dec 13, 2025 • 1.99k • 13

upvoted a paper 7 months ago

SofT-GRPO: Surpassing Discrete-Token LLM Reinforcement Learning via Gumbel-Reparameterized Soft-Thinking Policy Optimization

Paper • 2511.06411 • Published Nov 9, 2025 • 18