影响力指数
论文质量、代表作、近期表现、广度与样本量置信度综合计算
91.74/100
前 0.5%
全站排名 #292
发表论文28 篇
平均评分
年均产出9.3 篇/年
Huan Sun
研究方向
Large Language Modeling and Analysis of Large Language Models · Language Agents · Question Answering and Dialogue Systems
16
Agent Data Protocol: Unifying Datasets for Diverse, Effective Fine-tuning of LLM Agents
ICLR 2026Oral
19
RedTeamCUA: Realistic Adversarial Testing of Computer-Use Agents in Hybrid Web-OS Environments
ICLR 2026Oral
通讯17
Improving Code Localization with Repository Memory
ICLR 2026Poster
26
REMem: Reasoning with Episodic Memory in Language Agent
ICLR 2026Poster
24
Holistic Agent Leaderboard: The Missing Infrastructure for AI Agent Evaluation
ICLR 2026Poster
15
Is the Reversal Curse a Binding Problem? Uncovering Limitations of Transformers from a Basic Generalization Failure
ICLR 2026Poster
二作17
SciNav: A General Agent Framework for Scientific Coding Tasks
ICLR 2026Poster
二作25
TrustGen: A Platform of Dynamic Benchmarking on the Trustworthiness of Generative Foundation Models
ICLR 2026Poster
15
Agent Learning via Early Experience
ICLR 2026Rejected
5
Beyond Clicking: A Step Towards Generalist GUI Grounding via Text Dragging
ICLR 2026Withdrawn
27
ScholarEval: Research Idea Evaluation Grounded in Literature
ICLR 2026Withdrawn
5
WebGuard: Building a Generalizable Guardrail for Web Agents
ICLR 2026Withdrawn
32
Navigating the Digital World as Humans Do: Universal Visual Grounding for GUI Agents
ICLR 2025Oral
41
AutoDAN-Turbo: A Lifelong Agent for Strategy Self-Exploration to Jailbreak LLMs
ICLR 2025Spotlight
25
An Illusion of Progress? Assessing the Current State of Web Agents
COLM 2025Poster
42
EIA: ENVIRONMENTAL INJECTION ATTACK ON GENERALIST WEB AGENTS FOR PRIVACY LEAKAGE
ICLR 2025Poster
通讯12
AdvAgent: Controllable Blackbox Red-teaming on Web Agents
ICML 2025Poster
19
ScienceAgentBench: Toward Rigorous Assessment of Language Agents for Data-Driven Scientific Discovery
ICLR 2025Poster
通讯35
MMMU-Pro: A More Robust Multi-discipline Multimodal Understanding Benchmark
ICLR 2025Rejected
5
Simulate Before Act: Model-Based Planning for Web Agents
ICLR 2025Withdrawn
23
AdvWeb: Controllable Black-box Attacks on VLM-powered Web Agents
ICLR 2025Rejected
13
EVOSCHEMA: TOWARDS TEXT-TO-SQL ROBUSTNESS AGAINST SCHEMA EVOLUTION
ICLR 2025Withdrawn
-1
Tooling or Not Tooling? The Impact of Tools on Language Agents for Chemistry Problem Solving
ICLR 2025Withdrawn
通讯