Deep Learning

FineEdit: Unlock Instruction-Based Text Editing for LLMs
Large Language Models (LLMs) have significantly advanced natural language processing, demonstrating strong capabilities in tasks such …
Yiming Zeng, Wanhao Yu, Zexin Li, Tao Ren, Yu Ma, Jinghan Cao, Xiyan Chen, Tingting Yu
PDF Cite
Mixtraining: A Better Trade-Off Between Compute and Performance
Incorporating self-supervised learning (SSL) before standard supervised learning (SL) has become a widely used strategy to enhance …
Zexin Li - "Equal Contribution", Jiancheng Zhang - "Equal Contribution", Yufei Li, Yinglun Zhu, Cong Liu
PDF Cite
Recent Advances in Large Langauge Model Benchmarks against Data Contamination: From Static to Dynamic Evaluation
Data contamination has received increasing attention in the era of large language models (LLMs) due to their reliance on vast …
Simin Chen, Yiming Chen, Zexin Li, Yifan Jiang, Zhongwei Wan, Yixin He, Dezhi Ran, Tianle Gu, Haizhou Li, Tao Xie, Baishakhi Ray
PDF Cite
BOXR: Body and head motion Optimization framework for eXtended Reality
The emergence of standalone Extended Reality (XR) systems has enhanced user mobility, accommodating both subtle, frequent head motions …
Ziliang Zhang, Zexin Li, Hyoseung Kim, Cong Liu
PDF Cite Code DOI
DuoJoule: Accurate On-Device Deep Reinforcement Learning for Energy and Timeliness
Deep Reinforcement Learning (DRL) is critical for autonomous systems to continuously learn and adapt in dynamic environments. However, …
Soheil Shirvani, Aritra Samanta, Zexin Li, Cong Liu
PDF Cite DOI
Transferable Adversarial Attacks against ASR
Given the extensive research and real-world applications of automatic speech recognition (ASR), ensuring the robustness of ASR models …
Xiaoxue Gao, Zexin Li, Yiming Chen, Cong Liu, Haizhou Li
PDF Cite Project DOI
DeciX: Explain Deep Learning Based Code Generation Applications
Deep learning-based code generation (DL-CG) applications have shown great potential for assisting developers in programming with …
Simin Chen, Zexin Li, Wei Yang, Cong Liu
PDF Cite Code DOI
Genie: Smart ROS-based Caching for Connected Autonomous Robots
To appear soon.
Zexin Li, Soroush Bateni, Cong Liu
PDF Cite
RT-LM: Uncertainty-Aware Resource Management for Real-Time On-Device Language Models
Recent advancements in language models~(LMs) have gained substantial attentions on their capability to generate human-like responses. …
Yufei Li, Zexin Li, Wei Yang, Cong Liu
PDF Cite DOI
R^3: On-device Real-Time Deep Reinforcement Learning for Autonomous Robotics
Autonomous robotic systems, like autonomous vehicles and robotic search and rescue, require efficient on-device training for continuous …
Zexin Li, Aritra Samanta, Yufei Li, Andrea Soltoggio, Hyoseung Kim, Cong Liu
PDF Cite Code DOI