14 papers
Test-Time Training as Residual Memory for Robot Policies
Haoxuan Wang, Gengyu Zhang, Ramana Rao Kompella +2
Memory is essential for long-horizon robotic manipulation, where successful actions may depend on past events that are no longer recoverable from the current observation. As episod…
ForeAct3D: Policy-Grounded Future World Modeling for VLA Policies
Zhe Tao, Feiran Wang, Gaowen Liu +3
Robots need to anticipate how their actions will change the world, since manipulation success hinges on the resulting contacts and object motions. However, existing Vision-Language…
Drop-Then-Recovery: How Redundant Are Vision-Language-Action Models?
Guoheng Sun, Kaixi Feng, Shwai He +8
Vision-Language-Action (VLA) models enable instruction-driven robotic manipulation, but they inherit oversized language backbones from pretrained VLMs whose capacity far exceeds wh…
Navigating the Clutter: Waypoint-Based Bi-Level Planning for Multi-Robot Systems
Jiabao Ji, Yongchao Chen, Yang Zhang +4
Multi-robot control in cluttered environments is a challenging problem that involves complex physical constraints, including robot-robot collisions, robot-obstacle collisions, and…
Attention-aware Inference Optimizations for Large Vision-Language Models with Memory-efficient Decoding
Fatih Ilhan, Gaowen Liu, Ramana Rao Kompella +5
Large Vision-Language Models (VLMs) have achieved remarkable success in multi-modal reasoning, but their inference time efficiency remains a significant challenge due to the memory…
A Multi-Agent Perception-Action Alliance for Efficient Long Video Reasoning
Yichang Xu, Gaowen Liu, Ramana Rao Kompella +6
This paper presents a multi-agent perception-action exploration alliance, dubbed A4VL, for efficient long-video reasoning. A4VL operates in a multi-round perception-action explorat…
Vision Verification Enhanced Fusion of VLMs for Efficient Visual Reasoning
Selim Furkan Tekin, Yichang Xu, Gaowen Liu +3
With the growing number and diversity of Vision-Language Models (VLMs), many works explore language-based ensemble, collaboration, and routing techniques across multiple VLMs to im…
When Should a Robot Think? Resource-Aware Reasoning via Reinforcement Learning for Embodied Robotic Decision-Making
Jun Liu, Pu Zhao, Zhenglun Kong +12
Embodied robotic systems increasingly rely on large language model (LLM)-based agents to support high-level reasoning, planning, and decision-making during interactions with the en…
Spectrally Distilled Representations Aligned with Instruction-Augmented LLMs for Satellite Imagery
Minh Kha Do, Wei Xiang, Kang Han +5
Vision-language foundation models (VLFMs) promise zero-shot and retrieval understanding for Earth observation. While operational satellite systems often lack full multi-spectral co…
GIFSplat: Generative Prior-Guided Iterative Feed-Forward 3D Gaussian Splatting from Sparse Views
Tianyu Chen, Wei Xiang, Kang Han +4
Feed-forward 3D reconstruction offers substantial runtime advantages over per-scene optimization, which remains slow at inference and often fragile under sparse views. However, exi…
SwiftNDC: Fast Neural Depth Correction for High-Fidelity 3D Reconstruction
Kang Han, Wei Xiang, Lu Yu +3
Depth-guided 3D reconstruction has gained popularity as a fast alternative to optimization-heavy approaches, yet existing methods still suffer from scale drift, multi-view inconsis…
VLA Knows Its Limits: Adaptive Execution Horizons for Robot Policies
Haoxuan Wang, Gengyu Zhang, Yan Yan +2
Action chunking has recently emerged as a standard practice in flow-based Vision-Language-Action (VLA) models. However, the effect and choice of the execution horizon - the number…
Compositional Caching for Training-free Open-vocabulary Attribute Detection
Marco Garosi, Alessandro Conti, Gaowen Liu +2
Attribute detection is crucial for many computer vision tasks, as it enables systems to describe properties such as color, texture, and material. Current approaches often rely on l…
MULTIFLOW: Shifting Towards Task-Agnostic Vision-Language Pruning
Matteo Farina, Massimiliano Mancini, Elia Cunegatti +3
While excellent in transfer learning, Vision-Language models (VLMs) come with high computational costs due to their large number of parameters. To address this issue, removing para…