11 papers
ChunkAct: Action Chunking for Agentic Robotics
Bingxin Xu, Wenrui Bao, Xinxin Liu +3
Agentic robotics places a large language model (LLM) agent in the robot control loop, where it composes perception, motion, and vision-language-action (VLA) tools under the guidanc…
Recursive Video In-Context Learning for Agentic Robot
Wenrui Bao, Xinxin Liu, Bingxin Xu +1
LLM agents that orchestrate frozen vision-language-action (VLA) policies improve across episodes through text memory, which records what the agent did but not how the task is done.…
Coding Agents with Harness for Safe Robot Control
Bingxin Xu, Yuzhang Shang, Zhen Dong +1
Coding agents have emerged as a promising paradigm for robot manipulation: a language model writes the robot controller as a program, and agents built in this way now operate robot…
Don't Drop the BATON: Long-Horizon Robot Manipulation via Agentic Subtask Exploration and Transition-aware Memory
Bingxin Xu, Yuzhang Shang, Emilio Ferrara
Long-horizon robot manipulation chains many contact-rich skills into one multi-stage task. Vision-language-action (VLA) and world-action models (WAMs) increasingly master individua…
VLA-Thinker: Boosting Vision-Language-Action Models through Thinking-with-Image Reasoning
Chaoyang Wang, Wenrui Bao, Sicheng Gao +5
Vision-Language-Action (VLA) models have shown promising capabilities for embodied intelligence, but most existing approaches rely on text-based chain-of-thought reasoning where vi…
SilentDrift: Exploiting Action Chunking for Stealthy Backdoor Attacks on Vision-Language-Action Models
Bingxin Xu, Yuzhang Shang, Binghui Wang +1
Vision-Language-Action (VLA) models are increasingly deployed in safety-critical robotic applications, yet their security vulnerabilities remain underexplored. We identify a fundam…
ButterflyQuant: Ultra-low-bit LLM Quantization through Learnable Orthogonal Butterfly Transforms
Bingxin Xu, Zhen Dong, Oussama Elachqar +1
Large language models require massive memory footprints, severely limiting deployment on consumer hardware. Quantization reduces memory through lower numerical precision, but extre…
E-CAR: Efficient Continuous Autoregressive Image Generation via Multistage Modeling
Zhihang Yuan, Yuzhang Shang, Hanling Zhang +7
Recent advances in autoregressive (AR) models with continuous tokens for image generation show promising results by eliminating the need for discrete tokenization. However, these m…
freePruner: A Training-free Approach for Large Multimodal Model Acceleration
Bingxin Xu, Yuzhang Shang, Yunhao Ge +2
Large Multimodal Models (LMMs) have demonstrated impressive capabilities in visual-language tasks but face significant deployment challenges due to their high computational demands…
Interpolating Video-LLMs: Toward Longer-sequence LMMs in a Training-free Manner
Yuzhang Shang, Bingxin Xu, Weitai Kang +7
Advancements in Large Language Models (LLMs) inspire various strategies for integrating video modalities. A key approach is Video-LLMs, which incorporate an optimizable interface l…
LLaVA-PruMerge: Adaptive Token Reduction for Efficient Large Multimodal Models
Yuzhang Shang, Mu Cai, Bingxin Xu +2
Large Multimodal Models (LMMs) have shown significant visual reasoning capabilities by connecting a visual encoder and a large language model. LMMs typically take in a fixed and la…