University of California at San Diego

university

https://www.ucsd.edu

AI & ML interests

None defined yet.

Recent Activity

williamium submitted a paper about 19 hours ago

Co-RL: Unsupervised Reasoning Emerges from Diverse Cohort in Multi-agent RL

williamium submitted a paper 3 days ago

Learn What's Left, Not What's Mastered: Saturation Aware Advantage Reweighting for Multi-Reward Policy Optimization

williamium submitted a paper 4 days ago

Self-Supervised Visual On-Policy Distillation

View all activity

Papers

Co-RL: Unsupervised Reasoning Emerges from Diverse Cohort in Multi-agent RL

Learn What's Left, Not What's Mastered: Saturation Aware Advantage Reweighting for Multi-Reward Policy Optimization

View all Papers

UCSanDiego 's papers 21

Submitted by

William Li

Co-RL: Unsupervised Reasoning Emerges from Diverse Cohort in Multi-agent RL

UCSanDiego

University of California at San Diego

Submitted by

William Li

Learn What's Left, Not What's Mastered: Saturation Aware Advantage Reweighting for Multi-Reward Policy Optimization

UCSanDiego

University of California at San Diego

Submitted by

William Li

Demystifying Agent Skills: Why They Work-Until They Don't

UCSanDiego

University of California at San Diego

Submitted by

William Li

Self-Supervised Visual On-Policy Distillation

UCSanDiego

University of California at San Diego

Submitted by

William Li

On-Policy Self-Distillation without Any Supervision

UCSanDiego

University of California at San Diego

Submitted by

Nicklas Hansen

Hallucination in World Models is Predictable and Preventable

UCSanDiego

University of California at San Diego

Submitted by

Zhen Wang

MEMPROBE: Probing Long-Term Agent Memory via Hidden User-State Recovery

UCSanDiego

University of California at San Diego

Submitted by

Zhen Wang

Demystifying Training-Time Augmentation for Data-Constrained Language Model Pretraining

UCSanDiego

University of California at San Diego

Submitted by

Darrien McKenzie

Manifold Bandits: Bayesian Curriculum Learning over the Latent Geometry of Large Language Models

UCSanDiego

University of California at San Diego

Submitted by

Hyunjin Kim

EgoPhys: Learning Generalizable Physics Models of Deformable Objects from Egocentric Video

UCSanDiego

University of California at San Diego

Submitted by

Suraj Ranganath

PIPE-Cypher: Automatic Enterprise Benchmark Generation for Text-to-Cypher Systems

UCSanDiego

University of California at San Diego

Submitted by

Yu Xia

Agentic Chain-of-Thought Steering for Efficient and Controllable LLM Reasoning

UCSanDiego

University of California at San Diego