3 papers
cs.LG2026
Local Linearity of LLMs Enables Activation Steering via Model-Based Linear Optimal Control
Julian Skifstad, Xinyue Annie Yang, Glen Chou
Inference-time LLM alignment methods, particularly activation steering, offer an alternative to fine-tuning by directly modifying activations during generation. Existing methods, h…
cs.CV2025
MAPS: Preserving Vision-Language Representations via Module-Wise Proximity Scheduling for Better Vision-Language-Action Generalization
Chengyue Huang, Mellon M. Zhang, Robert Azarcon +2
Vision-Language-Action (VLA) models inherit strong priors from pretrained Vision-Language Models (VLMs), but naive fine-tuning often disrupts these representations and harms genera…
cs.CV2025
Towards Streaming LiDAR Object Detection with Point Clouds as Egocentric Sequences
Mellon M. Zhang, Glen Chou, Saibal Mukhopadhyay
Accurate and low-latency 3D object detection is essential for autonomous driving, where safety hinges on both rapid response and reliable perception. While rotating LiDAR sensors a…