9 papers
HiLoRA: Hierarchical Low-Rank Adaptation for Personalized Federated Learning
Zihao Peng, Nan Zou, Jiandian Zeng +4
Vision Transformers (ViTs) have been widely adopted in vision tasks due to their strong transferability. In Federated Learning (FL), where full fine-tuning is communication heavy,…
Matrix as Plan: Structured Logical Reasoning with Feedback-Driven Replanning
Ke Chen, Jiandian Zeng, Zihao Peng +3
As knowledge and semantics on the web grow increasingly complex, enhancing Large Language Models (LLMs)' comprehension and reasoning capabilities has become particularly important.…
The Finer the Better: Towards Granular-aware Open-set Domain Generalization
Yunyun Wang, Zheng Duan, Xinyue Liao +2
Open-Set Domain Generalization (OSDG) tackles the realistic scenario where deployed models encounter both domain shifts and novel object categories. Despite impressive progress wit…
SCOUT: A Defense Against Data Poisoning Attacks in Fine-Tuned Language Models
Mohamed Afane, Abhishek Satyam, Ke Chen +3
Backdoor attacks create significant security threats to language models by embedding hidden triggers that manipulate model behavior during inference, presenting critical risks for…
ChronoForge-RL: Chronological Forging through Reinforcement Learning for Enhanced Video Understanding
Kehua Chen
Current state-of-the-art video understanding methods typically struggle with two critical challenges: (1) the computational infeasibility of processing every frame in dense video c…
Post-Hoc Split-Point Self-Consistency Verification for Efficient, Unified Quantification of Aleatoric and Epistemic Uncertainty in Deep Learning
Zhizhong Zhao, Ke Chen
Uncertainty quantification (UQ) is vital for trustworthy deep learning, yet existing methods are either computationally intensive, such as Bayesian or ensemble methods, or provide…
MetaRuleGPT: Recursive Numerical Reasoning of Language Models Trained with Simple Rules
Kejie Chen, Lin Wang, Qinghai Zhang +1
Recent studies have highlighted the limitations of large language models in mathematical reasoning, particularly their inability to capture the underlying logic. Inspired by meta-l…
Goal Exploration via Adaptive Skill Distribution for Goal-Conditioned Reinforcement Learning
Lisheng Wu, Ke Chen
Exploration efficiency poses a significant challenge in goal-conditioned reinforcement learning (GCRL) tasks, particularly those with long horizons and sparse rewards. A primary li…
Bias Resilient Multi-Step Off-Policy Goal-Conditioned Reinforcement Learning
Lisheng Wu, Ke Chen
In goal-conditioned reinforcement learning (GCRL), sparse rewards present significant challenges, often obstructing efficient learning. Although multi-step GCRL can boost this effi…