PaperHub
影响力指数
88.56/100
前 0.7%
全站排名 #433
发表论文47 篇
平均评分5.3
年均产出15.7 篇/年

Lichao Sun

Assistant Professor@Lehigh University·美国·OpenReview
研究方向

Generative AI · Medical AI · Large Language Models · Federated Learning · Trustworthy AI · Security and Privacy

6.0
28

IDER: IDempotent Experience Replay for Reliable Continual Learning

ICLR 2026Poster
5.5
32

Can LLMs Move Beyond Short Exchanges to Realistic Therapy Conversations?

ICLR 2026Poster
5.5
25

EIP: Weighted Ranking of LLMs by Quantifying Question Difficulty

ICLR 2026Poster
通讯
5.0
14

CultureVLM: Characterizing and Improving Cultural Understanding of Vision-Language Models

ICLR 2026Withdrawn
5.0
18

MRAG-Corrupter: Knowledge Poisoning Attacks to Multimodal Retrieval Augmented Generation

ICLR 2026Rejected
4.8
26

NavTrust: Benchmarking Trustworthiness for Embodied Navigation

ICLR 2026Rejected
4.7
16

Causal-CoT: Causal Chain-of-Thought for Validated Reasoning

ICLR 2026Desk Rejected
通讯
4.7
25

TrustGen: A Platform of Dynamic Benchmarking on the Trustworthiness of Generative Foundation Models

ICLR 2026Poster
4.5
26

Revisiting Visual Understanding in Multimodal Reasoning through a Lens of Image Perturbation

ICLR 2026Rejected
4.5
31

Can Text-to-Video Models Generate Realistic Human Motion?

ICLR 2026Desk Rejected
4.5
21

RoboTrust: Evaluating the Interaction Trustworthiness of Multi-modal Large Language Models in Embodied Agents

ICLR 2026Rejected
通讯
4.5
25

EfficientLLM: Evaluating Large Language Models Efficiency

ICLR 2026Desk Rejected
4.0
21

RouteJudge: Benchmarking LLM-as-a-Judge with Routing Strategies

ICLR 2026Desk Rejected
通讯
4.0
5

MMLU-Reason: Benchmarking Multi-Task Multi-modal Language Understanding and Reasoning

ICLR 2026Withdrawn
通讯
3.5
5

Agentic Robot: A Brain-Inspired Framework for Vision-Language-Action Models in Embodied Agents

ICLR 2026Withdrawn
通讯
7.3
21

Analytic Energy-Guided Policy Optimization for Offline Reinforcement Learning

NeurIPS 2025Poster
7.3
23

Towards Building Model/Prompt-Transferable Attackers against Large Vision-Language Models

NeurIPS 2025Spotlight
6.8
21

BadVLA: Towards Backdoor Attacks on Vision-Language-Action Models via Objective-Decoupled Optimization

NeurIPS 2025Poster
通讯
6.8
29

First SFT, Second RL, Third UPT: Continual Improving Multi-Modal LLM Reasoning via Unsupervised Post-Training

NeurIPS 2025Poster
通讯
6.8
19

Tackling Continual Offline RL through Selective Weights Activation on Aligned Spaces

NeurIPS 2025Poster
6.7
12

Exposing and Patching the Flaws of Large Language Models in Social Character Simulation

COLM 2025Poster
6.3
22

Missing Premise exacerbates Overthinking: Are Reasoning Models losing Critical Thinking Skill?

COLM 2025Poster
三作
6.3
34

GUI-World: A Video Benchmark and Dataset for Multimodal GUI-oriented Understanding

ICLR 2025Poster
通讯
6.1
11

XAttnMark: Learning Robust Audio Watermarking with Cross-Attention

ICML 2025Poster
6.0
27

BenTo: Benchmark Reduction with In-Context Transferability

ICLR 2025Poster
三作
6.0
20

DataGen: Unified Synthetic Dataset Generation via Large Language Models

ICLR 2025Poster
5.8
25

Rethinking and Defending Protective Perturbation in Personalized Diffusion Models

ICLR 2025Rejected
通讯
5.7
36

Mora: Enabling Generalist Video Generation via A Multi-Agent Framework

ICLR 2025Rejected
通讯
5.4
21

Benchmarking Vision Language Model Unlearning via Fictitious Facial Identity Dataset

ICLR 2025Poster
5.3
35

MLP-KAN: Unifying Deep Representation and Function Learning

ICLR 2025Rejected
通讯
5.3
32

Quantifying AI Psychology: A Psychometric Benchmark for Large Language Models

ICLR 2025Rejected
通讯
4.8
30

Solving Continual Offline RL through Selective Weights Activation on Aligned Spaces

ICLR 2025Rejected
通讯
3.5
5

Are Large Vision-Language Models Robust to Adversarial Visual Transformations?

ICLR 2025Withdrawn
合作者 (20)