4 papers
MemBuilder: Reinforcing LLMs for Long-Term Memory Construction via Attributed Dense Rewards
Zhiyu Shen, Ziming Wu, Fuming Lai +2
Maintaining consistency in long-term dialogues remains a fundamental challenge for LLMs, as standard retrieval mechanisms often fail to capture the temporal evolution of historical…
DiffuSpeech: Silent Thought, Spoken Answer via Unified Speech-Text Diffusion
Yuxuan Lou, Ziming Wu, Yaochen Wang +6
Current speech language models generate responses directly without explicit reasoning, leading to errors that cannot be corrected once audio is produced. We introduce \textbf{``Sil…
DART: Distilling Autoregressive Reasoning to Silent Thought
Nan Jiang, Ziming Wu, De-Chuan Zhan +2
Chain-of-Thought (CoT) reasoning has significantly advanced Large Language Models (LLMs) in solving complex tasks. However, its autoregressive paradigm leads to significant computa…
SynAdapt: Learning Adaptive Reasoning in Large Language Models via Synthetic Continuous Chain-of-Thought
Jianwei Wang, Ziming Wu, Fuming Lai +2
While Chain-of-Thought (CoT) reasoning improves model performance, it incurs significant time costs due to the generation of discrete CoT tokens (DCoT). Continuous CoT (CCoT) offer…