Wenxuan Luo's picture

5 5

Wenxuan Luo

MateoAdams2

AI & ML interests

Research on LLM agents and evaluation. Mostly focused on experiments.

Recent Activity

liked a dataset 4 days ago

rkmr07/tourism-prediction

upvoted a paper 5 days ago

Rethinking Generalization in Reasoning SFT: A Conditional Analysis on Optimization, Data, and Model Capability

upvoted a paper 5 days ago

Graph-Based Chain-of-Thought Pruning for Reducing Redundant Reflections in Reasoning LLMs

View all activity

Organizations

None yet

upvoted 2 papers 5 days ago

Rethinking Generalization in Reasoning SFT: A Conditional Analysis on Optimization, Data, and Model Capability

Paper • 2604.06628 • Published 8 days ago • 309

Graph-Based Chain-of-Thought Pruning for Reducing Redundant Reflections in Reasoning LLMs

Paper • 2604.05643 • Published 9 days ago • 13

upvoted a paper 6 days ago

GrandCode: Achieving Grandmaster Level in Competitive Programming via Agentic Reinforcement Learning

Paper • 2604.02721 • Published 13 days ago • 354

upvoted a paper 7 days ago

UniMixer: A Unified Architecture for Scaling Laws in Recommendation Systems

Paper • 2604.00590 • Published 15 days ago • 8

upvoted a paper 15 days ago

TAPS: Task Aware Proposal Distributions for Speculative Sampling

Paper • 2603.27027 • Published 19 days ago • 142