109 citations · 156 across the 16 of their papers we have counts for
19 papers
Cooperative Multi-Agent Vision-Language-Action Models via Reinforced Fine Tuning
Ruixiao Xu, Wong Lik Hang Kenny, Zhiqian Liu +12
We study reinforcement learning (RL) methods for cooperative multi-agent Vision-Language-Action (VLA) models. This problem is challenging because VLAs are pretrained on large-scale…
UCoder: Unsupervised Code Generation by Internal Probing of Large Language Models
Jiajun Wu, Jian Yang, Wei Zhang +6
Large language models (LLMs) have demonstrated remarkable capabilities in code generation tasks. However, their effectiveness heavily relies on supervised training with extensive l…
SLMQuant:Benchmarking Small Language Model Quantization for Practical Deployment
Jiacheng Wang, Yejun Zeng, Jinyang Guo +3
Despite the growing interest in Small Language Models (SLMs) as resource-efficient alternatives to Large Language Models (LLMs), their deployment on edge devices remains challengin…
Empirical Study on Robustness and Resilience in Cooperative Multi-Agent Reinforcement Learning
Simin Li, Zihao Mao, Hanxiao Li +13
In cooperative Multi-Agent Reinforcement Learning (MARL), it is a common practice to tune hyperparameters in ideal simulated environments to maximize cooperative performance. Howev…
Vulnerable Agent Identification in Large-Scale Multi-Agent Reinforcement Learning
Simin Li, Zihao Mao, Zheng Yuwei +12
Partial agent failure becomes inevitable when systems scale up, making it crucial to identify the subset of agents whose failure causes worst-case system performance degradations.…
SPEAR: Structured Pruning for Spiking Neural Networks via Synaptic Operation Estimation and Reinforcement Learning
Hui Xie, Yuhe Liu, Shaoqi Yang +6
While deep spiking neural networks (SNNs) demonstrate superior performance, their deployment on resource-constrained neuromorphic hardware still remains challenging. Network prunin…
AGENTSAFE: Benchmarking the Safety of Embodied Agents on Hazardous Instructions
Zonghao Ying, Le Wang, Yisong Xiao +7
The integration of vision-language models (VLMs) is driving a new generation of embodied agents capable of operating in human-centered environments. However, as deployment expands,…
DynamicPAE: Generating Scene-Aware Physical Adversarial Examples in Real-Time
Jin Hu, Xianglong Liu, Jiakai Wang +5
Physical adversarial examples (PAEs) are regarded as whistle-blowers of real-world risks in deep-learning applications, thus worth further investigation. However, current PAE gener…
Selective Focus: Investigating Semantics Sensitivity in Post-training Quantization for Lane Detection
Yunqian Fan, Xiuying Wei, Ruihao Gong +4
Lane detection (LD) plays a crucial role in enhancing the L2+ capabilities of autonomous driving, capturing widespread attention. The Post-Processing Quantization (PTQ) could facil…
Fast and Controllable Post-training Sparsity: Learning Optimal Sparsity Allocation with Global Constraint in Minutes
Ruihao Gong, Yang Yong, Zining Wang +4
Neural network sparsity has attracted many research interests due to its similarity to biological schemes and high energy efficiency. However, existing methods depend on long-time…
Robust Multi-Agent Reinforcement Learning by Mutual Information Regularization
Simin Li, Ruixiao Xu, Jingqiao Xiu +4
In multi-agent reinforcement learning (MARL), ensuring robustness against unpredictable or worst-case actions by allies is crucial for real-world deployment. Existing robust MARL m…
Revisiting Open World Object Detection
Xiaowei Zhao, Xianglong Liu, Yifan Shen +3
Open World Object Detection (OWOD), simulating the real dynamic world where knowledge grows continuously, attempts to detect both known and unknown classes and incrementally learn…
Towards Real-world X-ray Security Inspection: A High-Quality Benchmark and Lateral Inhibition Module for Prohibited Items Detection
Renshuai Tao, Yanlu Wei, Xiangjian Jiang +6
Prohibited items detection in X-ray images often plays an important role in protecting public safety, which often deals with color-monotonous and luster-insufficient objects, resul…
A Comprehensive Evaluation Framework for Deep Model Robustness
Jun Guo, Wei Bao, Jiakai Wang +7
Deep neural networks (DNNs) have achieved remarkable performance across a wide range of applications, while they are vulnerable to adversarial examples, which motivates the evaluat…
Spatiotemporal Attacks for Embodied Agents
Aishan Liu, Tairan Huang, Xianglong Liu +5
Adversarial attacks are valuable for providing insights into the blind-spots of deep learning models and help improve their robustness. Existing work on adversarial attacks have ma…
Occluded Prohibited Items Detection: an X-ray Security Inspection Benchmark and De-occlusion Attention Module
Yanlu Wei, Renshuai Tao, Zhangjie Wu +3
Security inspection often deals with a piece of baggage or suitcase where objects are heavily overlapped with each other, resulting in an unsatisfactory performance for prohibited…
Stratified Rule-Aware Network for Abstract Visual Reasoning
Sheng Hu, Yuqing Ma, Xianglong Liu +2
Abstract reasoning refers to the ability to analyze information, discover rules at an intangible level, and solve problems in innovative ways. Raven's Progressive Matrices (RPM) te…
Region-wise Generative Adversarial ImageInpainting for Large Missing Areas
Yuqing Ma, Xianglong Liu, Shihao Bai +4
Recently deep neutral networks have achieved promising performance for filling large missing regions in image inpainting tasks. They usually adopted the standard convolutional arch…
Interpreting and Improving Adversarial Robustness of Deep Neural Networks with Neuron Sensitivity
Chongzhi Zhang, Aishan Liu, Xianglong Liu +4
Deep neural networks (DNNs) are vulnerable to adversarial examples where inputs with imperceptible perturbations mislead DNNs to incorrect results. Despite the potential risk they…