3 papers
cs.CL2026
Selective Latent Thinking: Adaptive Compression of LLM Reasoning Chains
Hui Xie, Jie Liu, Ziyue Qiao +1
Explicit chain-of-thought (CoT) reasoning substantially improves the reasoning ability of large language models (LLMs), but incurs high inference cost due to lengthy autoregressive…
cs.LG2025
Train with Perturbation, Infer after Merging: A Two-Stage Framework for Continual Learning
Haomiao Qiu, Miao Zhang, Ziyue Qiao +1
Continual Learning (CL) aims to enable models to continuously acquire new knowledge from a sequence of tasks with avoiding the forgetting of learned information. However, existing…
cs.LG2025
SplitLoRA: Balancing Stability and Plasticity in Continual Learning Through Gradient Space Splitting
Haomiao Qiu, Miao Zhang, Ziyue Qiao +3
Continual Learning requires a model to learn multiple tasks in sequence while maintaining both stability:preserving knowledge from previously learned tasks, and plasticity:effectiv…