activity
20232026
most citedPrioritized Information Bottleneck Theoretic Framework with Distributed Online Learning for Edge Video Analytics

41 citations · 68 across the 35 of their papers we have counts for

collaborators
Showing 2026Show all

18 papers · 1 filter

cs.CV2026

Mobility Helps Learning: Unsupervised Model Adaptation for Object Recognition via Movement

Yanan Ma, Yihang Tao, Zhengru Fang +3

Movable agents, such as autonomous vehicles and robots, should be able to autonomously adapt their pre-trained object recognition models to new environments without human annotatio…

cs.NI2026

Edge-Assisted Multi-View Localization for Low-Altitude Economy under GPS-Challenged Environments

Zhengru Fang, Huanhuan Lou, Senkang Hu +5

Unmanned aerial vehicles (UAVs) serving the low-altitude economy require reliable localization in urban canyons, indoor facilities, and other GPS-challenged environments. Visual ma…

cs.NI2026

Update the Unseen Only: Minimizing AoI for Collaborative Perception through Online Learning

Yanan Ma, Zhuoyi Zhao, Zhengru Fang +3

While collaborative perception (CP) enhances the safety of autonomous driving, limited bandwidth can cause severe shared data staleness in CP systems. Existing age-of-information (…

cs.RO2026

Harness VLA: Steering Frozen VLAs into Reliable Manipulation Primitives via Memory-Guided Agents

Yixian Zhang, Huanming Zhang, Feng Gao +14

Language-conditioned manipulation requires both precise contact-rich control and robust reasoning over language, scenes, and long horizons. End-to-end Vision-Language-Action (VLA)…

cs.CV2026

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…

cs.RO2026

Multi-Agent Embodied Autonomous Driving (MAEAD): From V2X Information Exchange to Shared World Models

Senkang Hu, Zhengru Fang, Yihang Tao +3

Autonomous driving is shifting from isolated vehicle intelligence toward multi-agent embodied systems that share perception, infer intent, and coordinate action under uncertainty.…

cs.CV2026

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…

cs.RO2026

Agent-Centric Observation Adaptation for Robust Visual Control under Dynamic Perturbations

Zhengru Fang, Yu Guo, Fei Liu +6

Visual control maps visual streams to actions in reinforcement learning and vision-language-action (VLA) policies. Changing weather, noise, blur, and compression can obscure differ…

cs.AI2026

AGPO: Asymmetric Group Policy Optimization for Verifiable Reasoning and Search Ads Relevance at JD

Yang Xu, Kun Yao, Yiming Deng +3

Reinforcement Learning with Verifiable Rewards (RLVR) has demonstrated notable success in enhancing the reasoning performance of large language models (LLMs). However, recent studi…

cs.CV2026

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…

cs.AI2026

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…

cs.LG2026

Self-Induced Outcome Potential: Turn-Level Credit Assignment for Agents without Verifiers

Senkang Hu, Yong Dai, Xudong Han +4

Long-horizon LLM agents depend on intermediate information-gathering turns, yet training feedback is usually observed only at the final answer, because process-level rewards requir…

cs.NI2026

SparKV: Overhead-Aware KV Cache Loading for Efficient On-Device LLM Inference

Hongyao Liu, Liuqun Zhai, Junyi Wang +3

Efficient inference for on-device Large Language Models (LLMs) remains challenging due to limited hardware resources and the high cost of the prefill stage, which processes the ful…

cs.NI2026

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…

cs.CV2026

Learning Mutual View Information Graph for Adaptive Adversarial Collaborative Perception

Yihang Tao, Senkang Hu, Haonan An +3

Collaborative perception (CP) enables data sharing among connected and autonomous vehicles (CAVs) to enhance driving safety. However, CP systems are vulnerable to adversarial attac…

cs.AI2026

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…

cs.NI2026★ 2 cited

UAV-enabled Computing Power Networks: Design and Performance Analysis under Energy Constraints

Yiqin Deng, Zhengru Fang, Senkang Hu +4

This paper presents an innovative framework that boosts computing power by utilizing ubiquitous computing power distribution and enabling higher computing node accessibility via ad…

cs.NI2026

UAV-enabled Computing Power Networks: Task Completion Probability Analysis

Yiqin Deng, Zhengru Fang, Senkang Hu +3

This paper presents an innovative framework that synergistically enhances computing performance through ubiquitous computing power distribution and dynamic computing node accessibi…