作者位次 #3/3ICLR 2026Poster· General Machine Learning / Transfer, Multitask and Meta-learning
BA-LoRA: Bias-Alleviating Low-Rank Adaptation to Mitigate Catastrophic Inheritance in Large Language Models
Yupeng Chang · Yi Chang · Yuan Wu
首次获取该候选人的完整档案及 StartLux 评估共 20 积分；每位用户单独解锁，之后查看免费。主动刷新 20 积分。
实时查找电子邮箱，费用不超过20积分；未找到邮箱不扣费。
Yupeng Chang · Yi Chang · Yuan Wu
Yupeng Chang · Yuan Wu · Yi Chang
Low-Rank Adaptation (LoRA) is a widely used parameter-efficient fine-tuning (PEFT) method for large language models. Under a fixed rank budget, LoRA parameterizes each adapted weight through a single low-dimensional input-side pathway, which may couple heterogeneous behaviors through shared input...
Yupeng Chang · Yuan Wu · Yi Chang
Critic-free reinforcement learning with verifiable rewards (RLVR), exemplified by Group Relative Policy Optimization (GRPO), avoids training a value function (critic) and reduces memory and compute overhead relative to critic-based PPO pipelines for aligning large language models. However, GRPO-s...
Haiqi Yang · Zhiyuan Li · Yi Chang · Yuan Wu
The Retentive Network (RetNet) has recently emerged as a formidable successor to the Transformer architecture. Although the self-attention mechanism excels at capturing global dependencies, its inherent quadratic complexity imposes significant memory constraints and inhibits scalability during lo...
Zhiyuan Li · Yuan Wu · Yi Chang
To stabilize the training of Large Language Models (LLMs), gradient clipping is a nearly ubiquitous heuristic used to alleviate exploding gradients. However, traditional global norm clipping erroneously presupposes gradient homogeneity across different functional modules, leading to an adverse “s...