5 papers
CForce: Boosting Parallel Decoding for dLLMs via Consistency Forcing
Yuji Ren, Chenkai Xu, Zhuocheng Gong +2
Diffusion large language models (dLLMs) accelerate language generation by predicting multiple masks in a single forward pass. However, existing dLLMs can suffer from unreliable pre…
EntroRouter: Learning Efficient Model Routing via Entropy Regulation
Kaiyi Zhang, Xueliang Zhao, Zhuocheng Gong +2
Model routing balances solution accuracy and computational cost by selecting among models of varying capabilities. While recent multi-round frameworks interleave reasoning and plan…
Shorten After You're Right: Lazy Length Penalties for Reasoning RL
Danlong Yuan, Tian Xie, Shaohan Huang +5
Large reasoning models, such as OpenAI o1 or DeepSeek R1, have demonstrated remarkable performance on reasoning tasks but often incur a long reasoning path with significant memory…
PromptCoT 2.0: Scaling Prompt Synthesis for Large Language Model Reasoning
Xueliang Zhao, Wei Wu, Jian Guan +2
Large language models (LLMs) are evolving from conversational systems into strong reasoners for tasks such as Olympiad mathematics and competitive programming. While scaling parame…
Latent Preference Coding: Aligning Large Language Models via Discrete Latent Codes
Zhuocheng Gong, Jian Guan, Wei Wu +2
Large language models (LLMs) have achieved remarkable success, yet aligning their generations with human preferences remains a critical challenge. Existing approaches to preference…