3 papers
cs.LG2025
T-Graphormer: Using Transformers for Spatiotemporal Forecasting
Hao Yuan Bai, Xue Liu
Spatiotemporal data is ubiquitous, and forecasting it has important applications in many domains. However, its complex cross-component dependencies and non-linear temporal dynamics…
cs.CL2025
Improving Neuron-level Interpretability with White-box Language Models
Hao Bai, Yi Ma
Neurons in auto-regressive language models like GPT-2 can be interpreted by analyzing their activation patterns. Recent studies have shown that techniques such as dictionary learni…
cs.AI2024
Fine-Tuning Large Vision-Language Models as Decision-Making Agents via Reinforcement Learning
Yuexiang Zhai, Hao Bai, Zipeng Lin +8
Large vision-language models (VLMs) fine-tuned on specialized visual instruction-following data have exhibited impressive language reasoning capabilities across various scenarios.…