4 citations · 10 across the 21 of their papers we have counts for
23 papers
EvolvAttack: Backdooring self Evolving VLM Agents
Chuan Zou, Yang Xiang, Zexin Li +2
Self-evolving mechanisms let vision-language model (VLM) agents continually adapt through evolving memory, but they also allow malicious behavior to emerge only after deployment. W…
Boosting Transferable Adversarial Attacks against Deep Reinforcement Learning
Zexin Li, Ruili Yao, Yiming Zeng +1
Most adversarial attacks on deep reinforcement learning (DRL) assume white-box access to the victim policy, which rarely holds in practice. This paper studies transfer-based black-…
TetraRL: A Self-Adaptive Runtime for On-Device Deep Reinforcement Learning Systems
Zexin Li, Soheil Shirvani, Cong Liu
Autonomous robotic systems, including autonomous vehicles, drones, and mobile robots, increasingly rely on on-device Deep Reinforcement Learning (DRL) to adapt to dynamic environme…
Energy-Efficient Multimodal Inference Serving with Tri-serve
Ziyang Jia, Sara Rashidi Golrouye, Laxmi Bhuyan +5
Multimodal model inference creates substantial energy demand with growing performance requirements. Within GPUs, power is autonomously managed by an on-board power management unit…
Orion: Enabling Self-adaptive Memory Management for On-device Online Continual Learning
Zexin Li, Nikil Dutt, Cong Liu
Online continual learning (OCL) enables real-time adaptation to new data, making it crucial for dynamic robotic applications. However, its practical deployment is hindered by memor…
RED: Adaptive Real-Time DAG Scheduling for Robotic Inference under Environmental Dynamics
Zexin Li, Tao Ren, Johnathan Liu +2
Robots deployed in dynamic environments must contend with environment-driven changes that reshape computation at runtime: new tasks may appear, precedence relations can shift, and…
PIMbot: A Self-Adaptive Attack Framework for Adversarial Manipulation of Multi-Robot Reinforcement Learning
Zexin Li, Ziliang Zhang, Hyoseung Kim +1
Recent research has demonstrated the potential of reinforcement learning in effective multi-robot collaboration, particularly in social dilemmas where robots face a trade-off betwe…
LeMix: Unified Scheduling for LLM Training and Inference on Multi-GPU Systems
Yufei Li, Zexin Li, Yinglun Zhu +1
Modern deployment of large language models (LLMs) frequently involves both inference serving and continuous retraining to stay aligned with evolving data and user feedback. Common…
Policy Search, Retrieval, and Composition via Task Similarity in Collaborative Agentic Systems
Saptarshi Nath, Christos Peridis, Eseoghene Benjamin +7
Agentic AI aims to create systems that set their own goals, adapt proactively to change, and refine behavior through continuous experience. Recent advances suggest that, when facin…
Mixtraining: A Better Trade-Off Between Compute and Performance
Zexin Li, Jiancheng Zhang, Yufei Li +2
Incorporating self-supervised learning (SSL) before standard supervised learning (SL) has become a widely used strategy to enhance model performance, particularly in data-limited s…
Recent Advances in Large Langauge Model Benchmarks against Data Contamination: From Static to Dynamic Evaluation
Simin Chen, Yiming Chen, Zexin Li +8
Data contamination has received increasing attention in the era of large language models (LLMs) due to their reliance on vast Internet-derived training corpora. To mitigate the ris…
Bridging the Editing Gap in LLMs: FineEdit for Precise and Targeted Text Modifications
Yiming Zeng, Wanhao Yu, Zexin Li +5
Large Language Models (LLMs) have significantly advanced natural language processing, demonstrating strong capabilities in tasks such as text generation, summarization, and reasoni…
Transferable Adversarial Attacks against ASR
Xiaoxue Gao, Zexin Li, Yiming Chen +2
Given the extensive research and real-world applications of automatic speech recognition (ASR), ensuring the robustness of ASR models against minor input perturbations becomes a cr…
BOXR: Body and head motion Optimization framework for eXtended Reality
Ziliang Zhang, Zexin Li, Hyoseung Kim +1
The emergence of standalone XR systems has enhanced user mobility, accommodating both subtle, frequent head motions and substantial, less frequent body motions. However, the pervas…
Genie: Smart ROS-based Caching for Connected Autonomous Robots
Zexin Li, Soroush Bateni, Cong Liu
Despite the promising future of autonomous robots, several key issues currently remain that can lead to compromised performance and safety. One such issue is latency, where we find…
R^3: On-device Real-Time Deep Reinforcement Learning for Autonomous Robotics
Zexin Li, Aritra Samanta, Yufei Li +3
Autonomous robotic systems, like autonomous vehicles and robotic search and rescue, require efficient on-device training for continuous adaptation of Deep Reinforcement Learning (D…
RT-LM: Uncertainty-Aware Resource Management for Real-Time Inference of Language Models
Yufei Li, Zexin Li, Wei Yang +1
Recent advancements in language models (LMs) have gained substantial attentions on their capability to generate human-like responses. Though exhibiting a promising future for vario…
RED: A Systematic Real-Time Scheduling Approach for Robotic Environmental Dynamics
Zexin Li, Tao Ren, Xiaoxi He +1
Intelligent robots are designed to effectively navigate dynamic and unpredictable environments laden with moving mechanical elements and objects. Such environment-induced dynamics,…
PIMbot: Policy and Incentive Manipulation for Multi-Robot Reinforcement Learning in Social Dilemmas
Shahab Nikkhoo, Zexin Li, Aritra Samanta +2
Recent research has demonstrated the potential of reinforcement learning (RL) in enabling effective multi-robot collaboration, particularly in social dilemmas where robots face a t…
MIMONet: Multi-Input Multi-Output On-Device Deep Learning
Zexin Li, Xiaoxi He, Yufei Li +3
Future intelligent robots are expected to process multiple inputs simultaneously (such as image and audio data) and generate multiple outputs accordingly (such as gender and emotio…
Dynamic Transformers Provide a False Sense of Efficiency
Yiming Chen, Simin Chen, Zexin Li +4
Despite much success in natural language processing (NLP), pre-trained language models typically lead to a high computational cost during inference. Multi-exit is a mainstream appr…
White-Box Multi-Objective Adversarial Attack on Dialogue Generation
Yufei Li, Zexin Li, Yingfan Gao +1
Pre-trained transformers are popular in state-of-the-art dialogue generation (DG) systems. Such language models are, however, vulnerable to various adversarial samples as studied i…
Sibling-Attack: Rethinking Transferable Adversarial Attacks against Face Recognition
Zexin Li, Bangjie Yin, Taiping Yao +4
A hard challenge in developing practical face recognition (FR) attacks is due to the black-box nature of the target FR model, i.e., inaccessible gradient and parameter information…