Hui Xiong

GoldenStart: Q-Guided Priors and Entropy Control for Distilling Flow Policies

Enhancing Multivariate Time Series Forecasting with Global Temporal Retrieval

Forest-Based Graph Learning for Semi-Supervised Node Classification

You only need 4 extra tokens: Synergistic Test-time Adaptation for LLMs

Agentic Analogical Reasoning for Large Language Models

Virne: A Comprehensive Benchmark for RL-based Network Resource Allocation in NFV

AutoFly: Vision-Language-Action Model for UAV Autonomous Navigation in the Wild

Towards Generalizable PDE Dynamics Forecasting via Physics-Guided Invariant Learning

SARSteer: Safeguarding Large Audio Language Models via Safe-Ablated Refusal Steering

SchemaRAG: Enhancing Knowledge-Intensive Reasoning of LLMs via Inference-Time Adaptive Schema

Real-time Routing under Partial Observability: Information-Efficient Policies for Connected Vehicles

Towards the Explainability of Temporal Graph Networks via Memory Backtracking

Disentangle, Gate, and Optimize: Cross Domain Transfer power by Multi Objective Bayesian Optimization

Beyond the Known: An Unknown-Aware Large Language Model for Open-Set Text Classification

SkyEvents: A Large-Scale Event-enhanced UAV Dataset for Robust 3D Scene Reconstruction

SELECT2REASON: Efficient Instruction-Tuning Data Selection for Long-CoT Reasoning

RETuning: Upgrading Inference-Time Scaling for Stock Movement Prediction with Large Language Models

LeGIT: LLM Guided Intervention Targeting for Online Causal Discovery

GraphSearch: An Agentic Deep Searching Workflow for Graph Retrieval-Augmented Generation

Protap: A Benchmark for Protein Modeling on Realistic Downstream Applications

Think-on-Graph 3.0: Efficient and Adaptive LLM Reasoning on Heterogeneous Graphs via Multi-Agent Dual-Evolving Context Retrieval

Distributionally Robust Conditional Conformal Prediction

ST$^2$360D: Spatial-to-Temporal Consistency for Training-free 360 Monocular Depth Estimation

Optimizing the Unknown: Black Box Bayesian Optimization with Energy-Based Model and Reinforcement Learning

Robust Explanations of Graph Neural Networks via Graph Curvatures

Learning to Think: Information-Theoretic Reinforcement Fine-Tuning for LLMs

Multimodal 3D Genome Pre-training

SePer: Measure Retrieval Utility Through The Lens Of Semantic Perplexity Reduction

Editable Concept Bottleneck Models

Towards the Causal Complete Cause of Multi-Modal Representation Learning

Logic-in-Frames: Dynamic Keyframe Search via Visual Semantic-Logical Verification for Long Video Understanding

GVPO: Group Variance Policy Optimization for Large Language Model Post-Training

GCAL: Adapting Graph Models to Evolving Domain Shifts

OneForecast: A Universal Framework for Global and Regional Weather Forecasting

Unveiling the Learning Mind of Language Models: A Cognitive Framework and Empirical Study

Revisiting Noise Resilience Strategies in Gesture Recognition: Short-Term Enhancement in sEMG Analysis

CATCH: Channel-Aware Multivariate Time Series Anomaly Detection via Frequency Patching

Structure-Enhanced Protein Instruction Tuning: Towards General-Purpose Protein Understanding

See&Trek: Training-Free Spatial Prompting for Multimodal Large Language Model

Towards Continuous Reuse of Graph Models via Holistic Memory Diversification

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

Revisiting Noise Resilience Strategies in Gesture Recognition: Short-Term Enhancement in Surface Electromyographic Signal Analysis

RGB-Event ISP: The Dataset and Benchmark

Editable Concept Bottleneck Models

SAFER: A Calibrated Risk-Aware Multimodal Recommendation Model for Dynamic Treatment Regimes

Language Model Preference Evaluation with Multiple Weak Evaluators

Towards Constraint-aware Learning for Resource Allocation in NFV-enabled Networks

Continuous Space-Time Video Super-Resolution via Event Camera

MAD: Multi-Alignment MEG-to-Text Decoding

Detecting Out-of-Context Misinformation via Multi-Agent and Multi-Grained Retrieval

Channel-aware Contrastive Conditional Diffusion for Multivariate Probabilistic Time Series Forecasting

SEAL: SEmantic-Augmented Imitation Learning via Language Model

Enhancing Conversational Recommender Systems with Tree-Structured Knowledge and Pretrained Language Models

SEE: See Everything Every Time - Broader Light Range Image Enhancement via Events

Efficient Skill Discovery via Regret-Aware Optimization

Can Large Language Models Help Experimental Design for Causal Discovery?