collaborators

6 papers

cs.CL2026

From Refuse to Richness: Rubric Rewards for Long-Form Hallucination Reinforcement Learning

Yudong Wang, Zhe Yang, Wenhan Ma +6

Rewards that penalize unsupported claims can improve grounding in long-form generation, but they can also teach models to answer less. We study this refusal-to-richness trade-off i…

cs.CL2026

DFlare: Scaling Up Draft Capacity for Block Diffusion Speculative Decoding

Jiebin Zhang, Zhenghan Yu, Song Liu +9

Block diffusion speculative decoding accelerates LLM inference by predicting all tokens within a block simultaneously for the target model to verify in parallel. Predicting an enti…

cs.CL2026

Reinforcement Learning for Chain of Thought Compression with One-Domain-to-All Generalization

Hanyu Li, Jiangshan Duo, Bofei Gao +4

Chain-of-thought reasoning in large language models can trigger an "overthinking trap": longer rollouts raise cost and latency yet often yield unreliable accuracy gains. Existing m…

cs.CL2026

JudgeRLVR: Judge First, Generate Second for Efficient Reasoning

Jiangshan Duo, Hanyu Li, Hailin Zhang +3

Reinforcement Learning with Verifiable Rewards (RLVR) has become a standard paradigm for reasoning in Large Language Models. However, optimizing solely for final-answer correctness…

cs.CL2026

MiMo-V2-Flash Technical Report

Core Team, Bangjun Xiao, Bingquan Xia +123

We present MiMo-V2-Flash, a Mixture-of-Experts (MoE) model with 309B total parameters and 15B active parameters, designed for fast, strong reasoning and agentic capabilities. MiMo-…

cs.CL2025

MiMo-Audio: Audio Language Models are Few-Shot Learners

Core Team, Dong Zhang, Gang Wang +97

Existing audio language models typically rely on task-specific fine-tuning to accomplish particular audio tasks. In contrast, humans are able to generalize to new audio tasks with…