University of California at San Diego

university

https://www.ucsd.edu

Activity Feed

AI & ML interests

None defined yet.

Recent Activity

zhenwang9102 submitted a paper 1 day ago

FlashEvolve: Accelerating Agent Self-Evolution with Asynchronous Stage Orchestration

Shibo-UCSD submitted a paper 30 days ago

CocoaBench: Evaluating Unified Digital Agents in the Wild

zhenwang9102 submitted a paper 3 months ago

CellMaster: Collaborative Cell Type Annotation in Single-Cell Analysis

View all activity

Papers

FlashEvolve: Accelerating Agent Self-Evolution with Asynchronous Stage Orchestration

CocoaBench: Evaluating Unified Digital Agents in the Wild

View all Papers

UCSanDiego 's Papers 7

Submitted by

Zhen Wang

FlashEvolve: Accelerating Agent Self-Evolution with Asynchronous Stage Orchestration

University of California at San Diego

Submitted by

Shibo Hao

CocoaBench: Evaluating Unified Digital Agents in the Wild

University of California at San Diego

36 2

Submitted by

Zhen Wang

CellMaster: Collaborative Cell Type Annotation in Single-Cell Analysis

University of California at San Diego

3 2

Submitted by

Zhen Wang

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

University of California at San Diego

8 2

Submitted by

Chung-En, Sun

Steer2Edit: From Activation Steering to Component-Level Editing

University of California at San Diego

Submitted by

Suraj Ranganath

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

University of California at San Diego

12 2

Submitted by

Zhen Wang

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

University of California at San Diego

10 3

AI & ML interests

Recent Activity

Papers

Team members 1

FlashEvolve: Accelerating Agent Self-Evolution with Asynchronous Stage Orchestration

CocoaBench: Evaluating Unified Digital Agents in the Wild

CellMaster: Collaborative Cell Type Annotation in Single-Cell Analysis

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

Steer2Edit: From Activation Steering to Component-Level Editing

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

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