activity
20242026
collaborators

7 papers

cs.CV2026

Future Optical Flow Prediction Improves Robot Control & Video Generation

Kanchana Ranasinghe, Honglu Zhou, Yu Fang +7

Future motion representations, such as optical flow, offer immense value for control and generative tasks. However, forecasting generalizable spatially dense motion representations…

cs.RO2025

Robotic VLA Benefits from Joint Learning with Motion Image Diffusion

Yu Fang, Kanchana Ranasinghe, Le Xue +10

Vision-Language-Action (VLA) models have achieved remarkable progress in robotic manipulation by mapping multimodal observations and instructions directly to actions. However, they…

cs.CL2025

SMILE: A Composite Lexical-Semantic Metric for Question-Answering Evaluation

Shrikant Kendre, Austin Xu, Honglu Zhou +3

Traditional evaluation metrics for textual and visual question answering, like ROUGE, METEOR, and Exact Match (EM), focus heavily on n-gram based lexical similarity, often missing…

cs.CV2025

Strefer: Empowering Video LLMs with Space-Time Referring and Reasoning via Synthetic Instruction Data

Honglu Zhou, Xiangyu Peng, Shrikant Kendre +4

Next-generation AI companions must go beyond general video understanding to resolve spatial and temporal references in dynamic, real-world environments. Existing Video Large Langua…

cs.CL2025

LAM SIMULATOR: Advancing Data Generation for Large Action Model Training via Online Exploration and Trajectory Feedback

Thai Hoang, Kung-Hsiang Huang, Shirley Kokane +12

Large Action Models (LAMs) for AI Agents offer incredible potential but face challenges due to the need for high-quality training data, especially for multi-steps tasks that involv…

cs.LG2025

VLM Q-Learning: Aligning Vision-Language Models for Interactive Decision-Making

Jake Grigsby, Yuke Zhu, Michael Ryoo +1

Recent research looks to harness the general knowledge and reasoning of large language models (LLMs) into agents that accomplish user-specified goals in interactive environments. V…