activity
20242026
most citedGLBench: A Comprehensive Benchmark for Graph with Large Language Models

2 citations · 3 across the 20 of their papers we have counts for

collaborators
Showing cs.LGShow all

9 papers · 1 filter

cs.LG2026

IRDS: Interpretable RLVR Data Selection via Verifier-Coupled Sparse Autoencoder Coverage

Yuhan Li, Mingxu Zhang, Dazhong Shen +1

Reinforcement learning with verifiable rewards (RLVR) has become a key technique for en- hancing LLM reasoning, yet its data ineffi- ciency remains a major bottleneck. Existing met…

cs.LG2026

SAE-FD: Sparse Autoencoder Feature Distillation for Continual Learning of Large Language Models

Mingxu Zhang, Yuhan Li, Lujundong Li +3

Continual learning enables large language models to adapt to evolving tasks without retraining from scratch, yet catastrophic forgetting remains a central obstacle. Among continual…

cs.LG2026

SLIM: Sparse Latent Steering for Interpretable and Property-Directed LLM-Based Molecular Editing

Mingxu Zhang, Yuhan Li, Lujundong Li +3

Large language models possess strong chemical reasoning capabilities, making them effective molecular editors. However, property-relevant information is implicitly entangled across…

cs.LG2026

Unlocking the Potentials of Retrieval-Augmented Generation for Diffusion Language Models

Chuanyue Yu, Jiahui Wang, Yuhan Li +6

Diffusion Language Models (DLMs) have recently demonstrated remarkable capabilities in natural language processing tasks. However, the potential of Retrieval-Augmented Generation (…

cs.LG2025

GraphRAG-R1: Graph Retrieval-Augmented Generation with Process-Constrained Reinforcement Learning

Chuanyue Yu, Kuo Zhao, Yuhan Li +8

Graph Retrieval-Augmented Generation (GraphRAG) has shown great effectiveness in enhancing the reasoning abilities of LLMs by leveraging graph structures for knowledge representati…

cs.LG2025

Revisiting LoRA through the Lens of Parameter Redundancy: Spectral Encoding Helps

Jiashun Cheng, Aochuan Chen, Nuo Chen +4

Low-Rank Adaptation (LoRA) has emerged as a prominent technique for fine-tuning large foundation models. Despite its successes, the substantial parameter redundancy, which limits t…