collaborators

7 papers

cs.LG2026

A Coin Flip Per Token: Bernoulli Sparse Steering of Large Language Models

Nima Eshraghi, Lovedeep Gondara, Yuqing Huang +5

Activation steering via sparse autoencoders (SAEs) enables behavioral control of large language models without task-specific fine-tuning, but standard methods apply the steering si…

cond-mat.mtrl-sci2026

From Knowledge to Action: Outcomes of the 2025 Large Language Model (LLM) Hackathon for Applications in Materials Science and Chemistry

Aritra Roy, Kevin Shen, Andrew MacBride +350

Large language models (LLMs) are rapidly changing how researchers in materials science and chemistry discover, organize, and act on scientific knowledge. This paper analyzes a broa…

cs.AI2026

HELP: HyperNode Expansion and Logical Path-Guided Evidence Localization for Accurate and Efficient GraphRAG

Yuqi Huang, Ning Liao, Kai Yang +4

Large Language Models (LLMs) often struggle with inherent knowledge boundaries and hallucinations, limiting their reliability in knowledge-intensive tasks. While Retrieval-Augmente…

cs.LG2026

On Predictability of Reinforcement Learning Dynamics for Large Language Models

Yuchen Cai, Ding Cao, Xin Xu +7

Recent advances in reasoning capabilities of large language models (LLMs) are largely driven by reinforcement learning (RL), yet the underlying parameter dynamics during RL trainin…

cs.CL2025

On the Superimposed Noise Accumulation Problem in Sequential Knowledge Editing of Large Language Models

Ding Cao, Yuchen Cai, Yuqing Huang +4

Sequential knowledge editing techniques aim to continuously update knowledge in large language models at low cost, preventing models from generating outdated or incorrect informati…

cs.IR2025

RAG-IGBench: Innovative Evaluation for RAG-based Interleaved Generation in Open-domain Question Answering

Rongyang Zhang, Yuqing Huang, Chengqiang Lu +8

In real-world scenarios, providing user queries with visually enhanced responses can considerably benefit understanding and memory, underscoring the great value of interleaved imag…