影响力指数
96.67/100
前 0.2%
全站排名 #109
发表论文64
平均评分5.3
年均产出21.3 篇/年

Kun Wang

Postdoc@Nanyang Technological University·新加坡·OpenReview
研究方向

Large Language Model based Agent · Model interpretability · pruning alogrithm · Graph Neural Networks · Spatio-temporal learning

6.8
26

AudioTrust: Benchmarking The Multifaceted Trustworthiness of Audio Large Language Models

ICLR 2026Poster
6.0
14

AgenTracer: Who Is Inducing Failure in the LLM Agentic Systems?

ICLR 2026Poster
5.5
22

MAS$^2$: Self-Generative, Self-Configuring, Self-Rectifying Multi-Agent Systems

ICLR 2026Poster
一作
5.5
24

OrthAlign: Orthogonal Subspace Decomposition for Non-Interfering Multi-Objective Alignment

ICLR 2026Poster
通讯
5.3
21

$A^{4}$-MLRM: Fourfold Attention for Adaptive Hallucination Suppression in Multimodal Large Reasoning Model

ICLR 2026Rejected
二作
5.2
28

DiffuGuard: How Intrinsic Safety is Lost and Found in Diffusion Large Language Models

ICLR 2026Poster
5.0
19

SaFeR-VLM: Toward Safety-aware Fine-grained Reasoning in Multimodal Models

ICLR 2026Rejected
二作
5.0
27

LatentEvolve: Self-Evolving Test-Time Scaling in Latent Space

ICLR 2026Rejected
5.0
19

Goal-Aware Identification and Rectification of Misinformation in Multi-Agent Systems

ICLR 2026Poster
5.0
36

Uni-NTFM: A Unified Foundation Model for EEG Signal Representation Learning

ICLR 2026Poster
5.0
34

Towards Self-Evolving Agent Benchmarks : Validatable Agent Trajectory via Test-Time Exploration

ICLR 2026Poster
5.0
31

MME-Emotion: A Holistic Evaluation Benchmark for Emotional Intelligence in Multimodal Large Language Models

ICLR 2026Poster
5.0
22

DD-Ranking: Rethinking the Evaluation of Dataset Distillation

ICLR 2026Rejected
4.5
36

Time Is All It Takes: Spike-Retiming Attacks on Event-Driven Spiking Neural Networks

ICLR 2026Poster
4.5
6

Fire on Motion: Optimizing Video Pass-bands for Efficient Spiking Action Recognition

ICLR 2026Rejected
4.5
19

Resource Consumption Red-Teaming for Large Vision-Language Models

ICLR 2026Rejected
4.0
35

Backdoor Attribution: Elucidating and Controlling Backdoor in Language Models

ICLR 2026Withdrawn
4.0
14

Direct Preference Optimization for Dynamical System Modeling

ICLR 2026Rejected
4.0
6

Unraveling Hallucination in Large Reasoning Models: A Topological Perspective

ICLR 2026Rejected
3.5
6

Differential-Integral Neural Operator for Long-Term Turbulence Forecasting

ICLR 2026Rejected
3.5
5

Minutes to Converage: Dataset Distillation for Rapid SNN Training on Event Streams

ICLR 2026Withdrawn
3.5
17

Spatiotemporal Forecasting as Planning: A Model-Based Reinforcement Learning Approach with Generative World Models

ICLR 2026Rejected
3.3
4

VISION: Prompting Ocean Vertical Velocity Reconstruction from Incomplete Observations

ICLR 2026Withdrawn
3.3
4

Mitigating Hallucination in Multimodal Reasoning via Functional Attention Control

ICLR 2026Withdrawn
通讯
3.0
16

Learning Asymmetric Phase Dynamics via Clinically-Guided Spatiotemporal Fusion

ICLR 2026Rejected
2.7
4

MAAT: Multi-timestep Alternating Adversarial Training Against Personalized Content Security in Diffusion Models

ICLR 2026Withdrawn
2.5
5

Test-Time Safety Alignment with Dynamic Intervention for Jailbreak Defense in LLMs

ICLR 2026Withdrawn
2.5
5

UniErase: Towards Balanced and Precise Unlearning in Language Models

ICLR 2026Withdrawn
2.4
6

Unlocking Clinical Potential: Beyond Single-to-Tri-Phase CT with Dynamic Fusion for Precision Liver Tumor Segmentation

ICLR 2026Withdrawn
2.0
5

CircuitProbe: Dissecting Spatiotemporal Visual Semantics with Circuit Tracing

ICLR 2026Withdrawn
-1

RAGCell: Retrieval-Augmented Generation as Supervision for Versatile Single-cell Analysis

ICLR 2026Withdrawn
二作
-1

BACKDOOR COLLAPSE: ELIMINATING UNKNOWN THREATS VIA KNOWN BACKDOOR AGGREGATION IN LANGUAGE MODELS

ICLR 2026Withdrawn
8.9
15

Multi-agent Architecture Search via Agentic Supernet

ICML 2025Oral
8.0
32

AlphaEdit: Null-Space Constrained Knowledge Editing for Language Models

ICLR 2025Oral
三作
7.8
22

G-Memory: Tracing Hierarchical Memory for Multi-Agent Systems

NeurIPS 2025Spotlight
三作
7.8
19

Unleashing Foundation Vision Models: Adaptive Transfer for Diverse Data-Limited Scientific Domains

NeurIPS 2025Poster
7.8
32

GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning

NeurIPS 2025Poster
7.3
21

Graph Sparsification via Mixture of Graphs

ICLR 2025Spotlight
7.2
13

KGMark: A Diffusion Watermark for Knowledge Graphs

ICML 2025Poster
7.2
15

G-Designer: Architecting Multi-agent Communication Topologies via Graph Neural Networks

ICML 2025Spotlight
7.0
22

Breaking the Discretization Barrier of Continuous Physics Simulation Learning

NeurIPS 2025Poster
7.0
18

On the Role of Attention Heads in Large Language Model Safety

ICLR 2025Oral
6.8
23

Auditing Meta-Cognitive Hallucinations in Reasoning Large Language Models

NeurIPS 2025Poster
通讯
6.8
34

MME-RealWorld: Could Your Multimodal LLM Challenge High-Resolution Real-World Scenarios that are Difficult for Humans?

ICLR 2025Poster
6.6
15

OneForecast: A Universal Framework for Global and Regional Weather Forecasting

ICML 2025Poster
6.3
31

Open-CK: A Large Multi-Physics Fields Coupling benchmarks in Combustion Kinetics

ICLR 2025Poster
6.0
40

Cut the Crap: An Economical Communication Pipeline for LLM-based Multi-Agent Systems

ICLR 2025Poster
6.0
19

AgentAuditor: Human-level Safety and Security Evaluation for LLM Agents

NeurIPS 2025Poster
5.8
36

SPARK: Physics-Guided Quantitative Augmentation for Dynamical System Modeling

ICLR 2025Rejected
通讯
5.8
6

ErrorRadar: Benchmarking Complex Mathematical Reasoning of Multimodal Large Language Models Via Error Detection

ICLR 2025Rejected
5.5
41

Mitigating Modality Prior-Induced Hallucinations in Multimodal Large Language Models via Deciphering Attention Causality

ICLR 2025Poster
5.5
19

FiDeLiS: Faithful Reasoning in Large Language Model for Knowledge Graph Question Answering

ICLR 2025Rejected
4.8
8

MINER: Mining the Underlying Pattern of Modality-Specific Neurons in Multimodal Large Language Models

ICLR 2025Rejected
4.3
5

P-Align: Self-Alignment in Physical Dynamical System Modeling

ICLR 2025Withdrawn
4.0
7

iAgent: LLM Agent as a Shield between User and Recommender Systems

ICLR 2025Rejected
3.0
7

MIND SCRAMBLE: UNVEILING LARGE LANGUAGE MODEL PSYCHOLOGY VIA TYPOGLYCEMIA

ICLR 2025Rejected