activity
20242026
collaborators

5 papers

cs.CV2026

video-SALMONN-R: Learning to ReWatch, ReAsk, and ReAnswer for Efficient Video Understanding

Yixuan Li, Guangzhi Sun, Yudong Yang +1

Video large language models (LLMs) are often constrained by computation and memory budgets, leading them to use reduced frame rates and spatial resolutions, which may cause them to…

cs.CY2026

Uncertainty-based Debiasing and Unlearning for Decontamination

Guangzhi Sun, Xiao Zhan, Mark Gales

Benchmark-based evaluation is the dominant paradigm for assessing large language model (LLM) capabilities, yet data contamination inflates reported performance and undermines fair…

cs.LG2025

Evaluating Sparse Autoencoders for Monosemantic Representation

Moghis Fereidouni, Muhammad Umair Haider, Peizhong Ju +1

A key barrier to interpreting large language models is polysemanticity, where neurons activate for multiple unrelated concepts. Sparse autoencoders (SAEs) have been proposed to mit…

q-bio.NC2024

Large language models surpass human experts in predicting neuroscience results

Xiaoliang Luo, Akilles Rechardt, Guangzhi Sun +36

Scientific discoveries often hinge on synthesizing decades of research, a task that potentially outstrips human information processing capacities. Large language models (LLMs) offe…

q-bio.NC2024

Matching domain experts by training from scratch on domain knowledge

Xiaoliang Luo, Guangzhi Sun, Bradley C. Love

Recently, large language models (LLMs) have outperformed human experts in predicting the results of neuroscience experiments (Luo et al., 2024). What is the basis for this performa…