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
96.67/100
前 0.2%
全站排名 #109
发表论文64 篇
平均评分
年均产出21.3 篇/年
Kun Wang
研究方向
Large Language Model based Agent · Model interpretability · pruning alogrithm · Graph Neural Networks · Spatio-temporal learning
26
AudioTrust: Benchmarking The Multifaceted Trustworthiness of Audio Large Language Models
ICLR 2026Poster
14
AgenTracer: Who Is Inducing Failure in the LLM Agentic Systems?
ICLR 2026Poster
22
MAS$^2$: Self-Generative, Self-Configuring, Self-Rectifying Multi-Agent Systems
ICLR 2026Poster
一作24
OrthAlign: Orthogonal Subspace Decomposition for Non-Interfering Multi-Objective Alignment
ICLR 2026Poster
通讯21
$A^{4}$-MLRM: Fourfold Attention for Adaptive Hallucination Suppression in Multimodal Large Reasoning Model
ICLR 2026Rejected
二作28
DiffuGuard: How Intrinsic Safety is Lost and Found in Diffusion Large Language Models
ICLR 2026Poster
19
SaFeR-VLM: Toward Safety-aware Fine-grained Reasoning in Multimodal Models
ICLR 2026Rejected
二作27
LatentEvolve: Self-Evolving Test-Time Scaling in Latent Space
ICLR 2026Rejected
19
Goal-Aware Identification and Rectification of Misinformation in Multi-Agent Systems
ICLR 2026Poster
36
Uni-NTFM: A Unified Foundation Model for EEG Signal Representation Learning
ICLR 2026Poster
34
Towards Self-Evolving Agent Benchmarks : Validatable Agent Trajectory via Test-Time Exploration
ICLR 2026Poster
31
MME-Emotion: A Holistic Evaluation Benchmark for Emotional Intelligence in Multimodal Large Language Models
ICLR 2026Poster
22
DD-Ranking: Rethinking the Evaluation of Dataset Distillation
ICLR 2026Rejected
36
Time Is All It Takes: Spike-Retiming Attacks on Event-Driven Spiking Neural Networks
ICLR 2026Poster
6
Fire on Motion: Optimizing Video Pass-bands for Efficient Spiking Action Recognition
ICLR 2026Rejected
19
Resource Consumption Red-Teaming for Large Vision-Language Models
ICLR 2026Rejected
35
Backdoor Attribution: Elucidating and Controlling Backdoor in Language Models
ICLR 2026Withdrawn
14
Direct Preference Optimization for Dynamical System Modeling
ICLR 2026Rejected
6
Unraveling Hallucination in Large Reasoning Models: A Topological Perspective
ICLR 2026Rejected
6
Differential-Integral Neural Operator for Long-Term Turbulence Forecasting
ICLR 2026Rejected
5
Minutes to Converage: Dataset Distillation for Rapid SNN Training on Event Streams
ICLR 2026Withdrawn
17
Spatiotemporal Forecasting as Planning: A Model-Based Reinforcement Learning Approach with Generative World Models
ICLR 2026Rejected
4
VISION: Prompting Ocean Vertical Velocity Reconstruction from Incomplete Observations
ICLR 2026Withdrawn
4
Mitigating Hallucination in Multimodal Reasoning via Functional Attention Control
ICLR 2026Withdrawn
通讯16
Learning Asymmetric Phase Dynamics via Clinically-Guided Spatiotemporal Fusion
ICLR 2026Rejected
4
MAAT: Multi-timestep Alternating Adversarial Training Against Personalized Content Security in Diffusion Models
ICLR 2026Withdrawn
5
Test-Time Safety Alignment with Dynamic Intervention for Jailbreak Defense in LLMs
ICLR 2026Withdrawn
5
UniErase: Towards Balanced and Precise Unlearning in Language Models
ICLR 2026Withdrawn
6
Unlocking Clinical Potential: Beyond Single-to-Tri-Phase CT with Dynamic Fusion for Precision Liver Tumor Segmentation
ICLR 2026Withdrawn
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
15
Multi-agent Architecture Search via Agentic Supernet
ICML 2025Oral
32
AlphaEdit: Null-Space Constrained Knowledge Editing for Language Models
ICLR 2025Oral
三作22
G-Memory: Tracing Hierarchical Memory for Multi-Agent Systems
NeurIPS 2025Spotlight
三作19
Unleashing Foundation Vision Models: Adaptive Transfer for Diverse Data-Limited Scientific Domains
NeurIPS 2025Poster
32
GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning
NeurIPS 2025Poster
21
Graph Sparsification via Mixture of Graphs
ICLR 2025Spotlight
13
KGMark: A Diffusion Watermark for Knowledge Graphs
ICML 2025Poster
15
G-Designer: Architecting Multi-agent Communication Topologies via Graph Neural Networks
ICML 2025Spotlight
22
Breaking the Discretization Barrier of Continuous Physics Simulation Learning
NeurIPS 2025Poster
18
On the Role of Attention Heads in Large Language Model Safety
ICLR 2025Oral
23
Auditing Meta-Cognitive Hallucinations in Reasoning Large Language Models
NeurIPS 2025Poster
通讯34
MME-RealWorld: Could Your Multimodal LLM Challenge High-Resolution Real-World Scenarios that are Difficult for Humans?
ICLR 2025Poster
15
OneForecast: A Universal Framework for Global and Regional Weather Forecasting
ICML 2025Poster
31
Open-CK: A Large Multi-Physics Fields Coupling benchmarks in Combustion Kinetics
ICLR 2025Poster
40
Cut the Crap: An Economical Communication Pipeline for LLM-based Multi-Agent Systems
ICLR 2025Poster
19
AgentAuditor: Human-level Safety and Security Evaluation for LLM Agents
NeurIPS 2025Poster
36
SPARK: Physics-Guided Quantitative Augmentation for Dynamical System Modeling
ICLR 2025Rejected
通讯6
ErrorRadar: Benchmarking Complex Mathematical Reasoning of Multimodal Large Language Models Via Error Detection
ICLR 2025Rejected
41
Mitigating Modality Prior-Induced Hallucinations in Multimodal Large Language Models via Deciphering Attention Causality
ICLR 2025Poster
19
FiDeLiS: Faithful Reasoning in Large Language Model for Knowledge Graph Question Answering
ICLR 2025Rejected
8
MINER: Mining the Underlying Pattern of Modality-Specific Neurons in Multimodal Large Language Models
ICLR 2025Rejected
5
P-Align: Self-Alignment in Physical Dynamical System Modeling
ICLR 2025Withdrawn
7
iAgent: LLM Agent as a Shield between User and Recommender Systems
ICLR 2025Rejected
7
MIND SCRAMBLE: UNVEILING LARGE LANGUAGE MODEL PSYCHOLOGY VIA TYPOGLYCEMIA
ICLR 2025Rejected