Pan Li

Scalable Spatio-Temporal SE(3) Diffusion for Long-Horizon Protein Dynamics

Reducing Belief Deviation in Reinforcement Learning for Active Reasoning of LLM Agents

Measuring Physical-World Privacy Awareness of Large Language Models: An Evaluation Benchmark

Struc-EMB: The Potential of Structure-Aware Encoding in Language Embeddings

$\nabla$-Reasoner: LLM Reasoning via Test-Time Gradient Descent in Latent Space

MoEEdit: Efficient and Routing-Stable Knowledge Editing for Mixture-of-Experts LLMs

Baleen: Self‑Interpretable, Robust SSMs with Stochastic Selective Memory

Weak-to-Strong GraphRAG: Aligning Weak Retrievers with Large Language Models for Graph-based Retrieval Augmented Generation

Rethinking the Value of Multi-Agent Workflow: A Strong Single Agent Baseline

Haystack Engineering: Context Engineering for Heterogeneous and Agentic Long-Context Evaluation

ParamAgent: Language Agents with Parametric Knowledge

STRIDE: Structure and Embedding Distillation with Attention for Graph Neural Networks

REL-RAG: Relation-Aware Retrieval-Augmented Generation for Generalizable Knowledge Graph Question Answering

Can LLM Agents Assist Dynamic Network Simulation? A Case Study on Email Networks and Phishing Synthesis

LayerDAG: A Layerwise Autoregressive Diffusion Model for Directed Acyclic Graph Generation

Graph-KV: Breaking Sequence via Injecting Structural Biases into Large Language Models

Do LLMs Really Forget? Evaluating Unlearning with Knowledge Correlation and Confidence Awareness

Convergent Privacy Loss of Noisy-SGD without Convexity and Smoothness

Rethinking Addressing in Language Models via Contextualized Equivariant Positional Encoding

What Are Good Positional Encodings for Directed Graphs?

Differentially Private Relational Learning with Entity-level Privacy Guarantees

Privately Learning from Graphs with Applications in Fine-tuning Large Language Models

Underestimated Privacy Risks for Minority Populations in Large Language Model Unlearning

Simple is Effective: The Roles of Graphs and Large Language Models in Knowledge-Graph-Based Retrieval-Augmented Generation

Rethinking Addressing in Language Models via Contextualized Equivariant Positional Encoding

Understanding and Mitigating Bottlenecks of State Space Models through the Lens of Recency and Over-smoothing

A Benchmark on Directed Graph Representation Learning in Hardware Designs

Underestimated Privacy Risks for Minority Populations in Large Language Model Unlearning

Generalization Principles for Inference over Text-Attributed Graphs with Large Language Models

Towards Stable, Globally Expressive Graph Representations with Laplacian Eigenvectors

RoFt-Mol: Benchmarking Robust Fine-tuning with Molecular Graph Foundation Models

GFSE: A Foundational Model For Graph Structural Encoding

What Can We Learn from State Space Models for Machine Learning on Graphs?

Privately Learning from Graphs with Applications in Fine-tuning Large Pretrained Models