collaborators

6 papers

cs.RO2026

On-the-Fly VLA Adaptation via Test-Time Reinforcement Learning

Changyu Liu, Yiyang Liu, Taowen Wang +7

Vision-Language-Action models have recently emerged as a powerful paradigm for general-purpose robot learning, enabling agents to map visual observations and natural-language instr…

cs.CV2026

A-SelecT: Automatic Timestep Selection for Diffusion Transformer Representation Learning

Changyu Liu, James Chenhao Liang, Wenhao Yang +6

Diffusion models have significantly reshaped the field of generative artificial intelligence and are now increasingly explored for their capacity in discriminative representation l…

cs.CL2025

All You Need is One: Capsule Prompt Tuning with a Single Vector

Yiyang Liu, James C. Liang, Heng Fan +7

Prompt-based learning has emerged as a parameter-efficient finetuning (PEFT) approach to facilitate Large Language Model (LLM) adaptation to downstream tasks by conditioning genera…

cs.CL2025

Probabilistic Token Alignment for Large Language Model Fusion

Runjia Zeng, James Chenhao Liang, Cheng Han +8

Training large language models (LLMs) from scratch can yield models with unique functionalities and strengths, but it is costly and often leads to redundant capabilities. A more co…

cs.RO2025

Exploring the Adversarial Vulnerabilities of Vision-Language-Action Models in Robotics

Taowen Wang, Cheng Han, James Chenhao Liang +6

Recently in robotics, Vision-Language-Action (VLA) models have emerged as a transformative approach, enabling robots to execute complex tasks by integrating visual and linguistic i…

cs.LG2025

Re-Imagining Multimodal Instruction Tuning: A Representation View

Yiyang Liu, James Chenhao Liang, Ruixiang Tang +8

Multimodal instruction tuning has proven to be an effective strategy for achieving zero-shot generalization by fine-tuning pre-trained Large Multimodal Models (LMMs) with instructi…