collaborators

5 papers

cs.AI2026

DASH: Divergence-Adaptive Supervision Horizons for On-Policy Self-Distillation of Reasoning Models

ZhiYan Hou, Xinyu Tang, Hongyan An +9

Reinforcement learning with verifiable rewards (RLVR) improves the reasoning capabilities of large language models using automatically verifiable outcome signals, but these signals…

cs.LG2026

Continual Learning in Transition

Zhiyan Hou, Dan Zhang, Tao Feng +11

Classical continual learning (CL) has primarily focused on enabling models to update and retain knowledge through parameter-centric mechanisms, e.g., training strategies, architect…

cs.CL2026

ResMerge: Residual-based Spectral Merging of Large Language Models

Yandu Sun, Zhiyan Hou, Haokai Ma +7

Model merging offers a training-free way to combine multiple post-trained expert models, but merging experts obtained through reinforcement learning (RL) remains challenging. Exist…

cs.CL2026

MLLM-CTBench: A Benchmark for Continual Instruction Tuning with Reasoning Process Diagnosis

Haiyun Guo, Zhiyan Hou, Yandu Sun +6

Continual instruction tuning(CIT) during the post-training phase is crucial for adapting multimodal large language models (MLLMs) to evolving real-world demands. However, the progr…

cs.LG2026

PASs-MoE: Mitigating Misaligned Co-drift among Router and Experts via Pathway Activation Subspaces for Continual Learning

Zhiyan Hou, Haiyun Guo, Haokai Ma +3

Continual instruction tuning (CIT) requires multimodal large language models (MLLMs) to adapt to a stream of tasks without forgetting prior capabilities. A common strategy is to is…