collaborators

6 papers

cs.RO2026

Driving Intents Amplify Planning-Oriented Reinforcement Learning

Hengtong Lu, Victor Shea-Jay Huang, Chengmin Yang +4

Continuous-action policies trained on a single demonstrated trajectory per scene suffer from mode collapse: samples cluster around the demonstrated maneuver and the policy cannot r…

cs.RO2026

MindVLA-U1: VLA Beats VA with Unified Streaming Architecture for Autonomous Driving

Yuzhou Huang, Benjin Zhu, Hengtong Lu +6

Autonomous driving has progressed from modular pipelines toward end-to-end unification, and Vision-Language-Action (VLA) models are a natural extension of this journey beyond Visio…

cs.RO2026

Action Emergence from Streaming Intent

Pengfei Jing, Victor Shea-Jay Huang, Hengtong Lu +3

We formalize action emergence as a target capability for end-to-end autonomous driving: the ability to generate physically feasible, semantically appropriate, and safety-compliant…

cs.CV2026

The Perceptual Bandwidth Bottleneck in Vision-Language Models: Active Visual Reasoning via Sequential Experimental Design

Anjie Liu, Ziqin Gong, Yan Song +6

Visual perception in modern Vision-Language Models (VLMs) is constrained by a perceptual bandwidth bottleneck: a broad field of view preserves global context but sacrifices the fin…

cs.CL2026

LexInstructEval: Lexical Instruction Following Evaluation for Large Language Models

Huimin Ren, Yan Liang, Baiqiao Su +4

The ability of Large Language Models (LLMs) to precisely follow complex and fine-grained lexical instructions is a cornerstone of their utility and controllability. However, evalua…

cs.LG2026

Breaking the Exploration Bottleneck: Rubric-Scaffolded Reinforcement Learning for General LLM Reasoning

Yang Zhou, Sunzhu Li, Shunyu Liu +11

Recent advances in Large Language Models (LLMs) have underscored the potential of Reinforcement Learning (RL) to facilitate the emergence of reasoning capabilities. Despite the enc…