University of California at San Diego

university

https://www.ucsd.edu

AI & ML interests

None defined yet.

Recent Activity

nicklashansen submitted a paper about 9 hours ago

Hallucination in World Models is Predictable and Preventable

zhenwang9102 submitted a paper 1 day ago

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

zhenwang9102 submitted a paper 3 days ago

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

View all activity

Papers

Hallucination in World Models is Predictable and Preventable

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

View all Papers

UCSanDiego 's papers 16

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

Submitted by

Xin Gao

Do Text Edits Generalize to Visual Generation? Benchmarking Cross-Modal Knowledge Editing in UMMs

UCSanDiego

University of California at San Diego

Submitted by

Letian Peng

BOOKMARKS: Efficient Active Storyline Memory for Role-playing

UCSanDiego

University of California at San Diego

Submitted by

Zhen Wang

FlashEvolve: Accelerating Agent Self-Evolution with Asynchronous Stage Orchestration

UCSanDiego

University of California at San Diego

1

Submitted by

Shibo Hao

CocoaBench: Evaluating Unified Digital Agents in the Wild

UCSanDiego

University of California at San Diego

Submitted by

Zhen Wang

CellMaster: Collaborative Cell Type Annotation in Single-Cell Analysis

UCSanDiego

University of California at San Diego

Submitted by

Zhen Wang

scPilot: Large Language Model Reasoning Toward Automated Single-Cell Analysis and Discovery

UCSanDiego

University of California at San Diego

Submitted by

Chung-En, Sun

Steer2Edit: From Activation Steering to Component-Level Editing

UCSanDiego

University of California at San Diego

2

Submitted by

Suraj Ranganath

StealthRL: Reinforcement Learning Paraphrase Attacks for Multi-Detector Evasion of AI-Text Detectors

UCSanDiego

University of California at San Diego

Submitted by

Zhen Wang

FIRE-Bench: Evaluating Agents on the Rediscovery of Scientific Insights

UCSanDiego

University of California at San Diego