Wenxuan Luo

MateoAdams2

AI & ML interests

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

Recent Activity

upvoted a paper 2 days ago

Speaker-Aware Temporal Aggregation Strategies on Segment Representations for Depression Detection in Dyadic Interaction: A Benchmark Study

liked a dataset 6 days ago

sun158/hermes-dataset

liked a dataset 7 days ago

rk000000/eval_smolvla-take-20260706

View all activity

Organizations

None yet

upvoted a paper 2 days ago

Speaker-Aware Temporal Aggregation Strategies on Segment Representations for Depression Detection in Dyadic Interaction: A Benchmark Study

Paper • 2607.02904 • Published 10 days ago • 4

upvoted 2 papers about 1 month ago

ABot-Earth 0.5: Generative 3D Earth Model

Paper • 2606.09967 • Published Jun 8 • 486

Recovering Policy-Induced Errors: Benchmarking and Trajectory Synthesis for Robust GUI Agents

Paper • 2605.29447 • Published May 28 • 21

upvoted a paper 2 months ago

How Fast Should a Model Commit to Supervision? Training Reasoning Models on the Tsallis Loss Continuum

Paper • 2604.25907 • Published Apr 28 • 4

upvoted 5 papers 3 months ago

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

Paper • 2604.06628 • Published Apr 8 • 329

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

Paper • 2604.05643 • Published Apr 7 • 14

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

Paper • 2604.02721 • Published Apr 3 • 639

UniMixer: A Unified Architecture for Scaling Laws in Recommendation Systems

Paper • 2604.00590 • Published Apr 1 • 8

TAPS: Task Aware Proposal Distributions for Speculative Sampling

Paper • 2603.27027 • Published Mar 27 • 146