14 papers
Embodied Operators and Benchmarking: Toward Reusable and Deployable Embodied Intelligence Systems
Junwu Xiong, Jiaxuan Gao, Wei Chai +10
Embodied intelligence systems require not only end-to-end policy models, but also reusable functional modules that transform multimodal observations, robot states, human demonstrat…
Universal Image Restoration via Internalized Chain-of-Thought Reasoning
Yu Guo, Zhengru Fang, Shengfeng He +4
Image restoration seeks to recover high-quality images from degraded inputs but becomes highly ill-posed under complex, mixed degradations. While unified all-in-one models are comm…
FRUC: Feedforward Dynamic Scene Reconstruction from Uncalibrated Collaborative Driving Views
Yihang Tao, Yu Guo, Zhengru Fang +2
We present FRUC, a feedforward 3D Gaussian Splatting framework for dynamic scene reconstruction from uncalibrated collaborative driving views. Existing multi-agent reconstruction f…
Agent-Centric Observation Adaptation for Robust Visual Control under Dynamic Perturbations
Zhengru Fang, Yu Guo, Fei Liu +5
Real-world visual systems face time-varying perturbations, including weather, sensor noise, compression artifacts, and background distractions. Existing image restoration methods a…
CXR-ContraBench: Benchmarking Negated-Option Attraction in Medical VLMs
Zhengru Fang, Yanan Ma, Yu Guo +5
When a chest X-ray shows consolidation but the question asks which finding is present, a medical vision-language model may answer "No consolidation." This is more than an incorrect…
Inference-Time Budget Control for LLM Search Agents
Zhengru Fang, Senkang Forest Hu, Zhonghao Chang +6
LLM search agents increasingly rely on tools at inference time, but their trajectories are often constrained by hard limits on both tool calls and generated tokens. Under such dual…
V2VCrafter: Consistent Street-View Image Generation Across Vehicles
Yihang Tao, Yu Guo, Senkang Hu +4
Connected and autonomous driving (CAD) systems leverage vehicle-to-vehicle (V2V) communication for multi-agent collaborative perception, yet remain constrained by scarce annotated…
CF-VLA: Efficient Coarse-to-Fine Action Generation for Vision-Language-Action Policies
Fan Du, Feng Yan, Jianxiong Wu +8
Flow-based vision-language-action (VLA) policies offer strong expressivity for action generation, but suffer from a fundamental inefficiency: multi-step inference is required to re…
Birdcast: Interest-aware BEV Multicasting for Infrastructure-assisted Collaborative Perception
Yanan Ma, Zhengru Fang, Yihang Tao +4
Vehicle-to-infrastructure collaborative perception (V2I-CP) leverages a high-vantage node to transmit supplementary information, i.e., bird's-eye-view (BEV) feature maps, to vehicl…
Optimizing Agentic Reasoning with Retrieval via Synthetic Semantic Information Gain Reward
Senkang Hu, Yong Dai, Yuzhi Zhao +5
Agentic reasoning enables large reasoning models (LRMs) to dynamically acquire external knowledge, but yet optimizing the retrieval process remains challenging due to the lack of d…
DSP-Reg: Domain-Sensitive Parameter Regularization for Robust Domain Generalization
Xudong Han, Senkang Hu, Yihang Tao +4
Domain Generalization (DG) is a critical area that focuses on developing models capable of performing well on data from unseen distributions, which is essential for real-world appl…
Shared Spatial Memory Through Predictive Coding
Zhengru Fang, Yu Guo, Yuang Zhang +3
Constructing a consistent shared spatial memory is a critical challenge in multi-agent systems, where partial observability and limited bandwidth often lead to catastrophic failure…
NWaaS: A Non-Intrusive and Privacy-Preserving Watermarking-as-a-Service System with Adaptive Resource Scheduling
Haonan An, Qianyao Ren, Guang Hua +5
Securing intellectual property (IP) in Machine Learning as a Service is critical yet challenging. While deep neural network watermarking serves as a standard defense against model…
Task-Oriented Semantic Compression for Localization at the Network Edge
Zhengru Fang, Senkang Hu, Yu Guo +2
Achieving precise visual localization in GPS-limited urban environments poses significant challenges for resource-constrained mobile platforms, particularly under strict bandwidth,…