9 papers
NaRA: Noise-Aware LoRA for Parameter-Efficient Fine-Tuning of Diffusion LLMs
Shuaidi Wang, Zhan Zhuang, Ruping Huang +1
Diffusion Large Language Models (dLLMs) have emerged as a promising non-autoregressive generative paradigm. Given the prohibitive computational cost of full fine-tuning, Parameter-…
AdaGamma: State-Dependent Discounting for Temporal Adaptation in Reinforcement Learning
Yaomin Wang, Jianting Pan, Ran Tian +4
The discount factor in reinforcement learning controls both the effective planning horizon and the strength of bootstrapping, yet most deep RL methods use a single fixed value acro…
Selective Successor Eligibility Traces for RLVR
Chaoli Mou, Zhan Zhuang, Xinning Chen +3
Reinforcement Learning with Verifiable Rewards (RLVR) has become a key approach for improving the reasoning abilities of large language models. However, widely used critic-free alg…
HAD: Heterogeneity-Aware Distillation for Lifelong Heterogeneous Learning
Xuerui Zhang, Xuehao Wang, Zhan Zhuang +5
Lifelong learning aims to preserve knowledge acquired from previous tasks while incorporating knowledge from a sequence of new tasks. However, most prior work explores only streams…
One-Token Verification for Reasoning Correctness Estimation
Zhan Zhuang, Xiequn Wang, Zebin Chen +4
Recent breakthroughs in large language models (LLMs) have led to notable successes in complex reasoning tasks, such as mathematical problem solving. A common strategy for improving…
PLAN: Proactive Low-Rank Allocation for Continual Learning
Xiequn Wang, Zhan Zhuang, Yu Zhang
Continual learning (CL) requires models to continuously adapt to new tasks without forgetting past knowledge. In this work, we propose \underline{P}roactive \underline{L}ow-rank \u…
Come Together, But Not Right Now: A Progressive Strategy to Boost Low-Rank Adaptation
Zhan Zhuang, Xiequn Wang, Wei Li +9
Low-rank adaptation (LoRA) has emerged as a leading parameter-efficient fine-tuning technique for adapting large foundation models, yet it often locks adapters into suboptimal mini…
MoPFormer: Motion-Primitive Transformer for Wearable-Sensor Activity Recognition
Hao Zhang, Zhan Zhuang, Xuehao Wang +2
Human Activity Recognition (HAR) with wearable sensors is challenged by limited interpretability, which significantly impacts cross-dataset generalization. To address this challeng…
CopRA: A Progressive LoRA Training Strategy
Zhan Zhuang, Xiequn Wang, Yulong Zhang +3
Low-Rank Adaptation (LoRA) is a parameter-efficient technique for rapidly fine-tuning foundation models. In standard LoRA training dynamics, models tend to quickly converge to a lo…