4 accepted papers
Reinforcement learning (RL) has emerged as a powerful framework to improve the reasoning performance of large language models (LLMs), with approaches such as Group Relative Policy Optimization (GRPO) showing promising results. However, GRPO and its variants struggle with collapsed groups (i.e., all-
Despite significant progress in multimodal large language models (MLLMs), their performance on complex, multi-page document comprehension remains inadequate, largely due to the lack of high-quality, document-level datasets. While current retrieval-augmented generation (RAG) methods offer partial sol…
Continual learning requires models to train continuously across consecutive tasks without forgetting. Most existing methods utilize linear classifiers, which struggle to maintain a stable classification space while learning new tasks. Inspired by the success of Kolmogorov-Arnold Networks (KAN) in pr…
Continual learning (CL) aims to learn from sequentially arriving tasks without catastrophic forgetting (CF). By partitioning the network into two parts based on the Lottery Ticket Hypothesis---one for holding the knowledge of the old tasks while the other for learning the knowledge of the new task--…