Jia Li

Exposing Weaknesses of Large Reasoning Models through Graph Algorithm Problems

RLVER: Reinforcement Learning with Verifiable Emotion Rewards for Empathetic Agents

Towards Anomaly-Aware Pre-Training and Fine-Tuning for Graph Anomaly Detection

Rethinking Graph Out-Of-Distribution Generalization: A Learnable Random Walk Perspective

Mitigating the Safety Alignment Tax with Null-Space Constrained Policy Optimization

Can LLMs Alleviate Catastrophic Forgetting in Graph Continual Learning? A Systematic Study

Are Time-Series Foundation Models Deployment-Ready? A Systematic Study of Adversarial Robustness Across Domains

Toward Protein Docking-oriented De Novo Ligand Design via Gradient Inversion

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

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

SynopticMind: An Instruction Tuning MLLM For Weather Forecasting Report Generation

GraphArena: Evaluating and Exploring Large Language Models on Graph Computation

Improving LLMs‘ Generalized Reasoning Abilities by Graph Problems

InversionGNN: A Dual Path Network for Multi-Property Molecular Optimization

Mesh Interpolation Graph Network for Dynamic and Spatially Irregular Global Weather Forecasting

SimXRD-4M: Big Simulated X-ray Diffraction Data and Crystal Symmetry Classification Benchmark

CirT: Global Subseasonal-to-Seasonal Forecasting with Geometry-inspired Transformer

Non-stationary Equivariant Graph Neural Networks for Physical Dynamics Simulation

DualTime: A Dual-Adapter Language Model for Time Series Multimodal Representation Learning

Parameter-Efficient Fine-Tuning via Circular Convolution

IBCircuit: Towards Holistic Circuit Discovery with Information Bottleneck

One QuantLLM for ALL: Fine-tuning Quantized LLMs Once for Efficient Deployments

LoRA Unleashed: Effortlessly Advancing from Low to Arbitrary Rank

IBCircuit: Towards Holistic Circuit Discovery with Information Bottleneck