collaborators

17 papers

cs.CV2026

Vision-OPD: Learning to See Fine Details for Multimodal LLMs via On-Policy Self-Distillation

Qianhao Yuan, Jie Lou, Xing Yu +4

Multimodal Large Language Models (MLLMs) still struggle with fine-grained visual understanding, where answers often depend on small but decisive evidence in the full image. We obse…

cs.CL2026

Your Teacher Can't Help You Here: Combating Supervision Fidelity Decay in On-Policy Distillation

Yanjiang Liu, Jie Lou, Xinyan Guan +7

On-policy distillation transfers reasoning capabilities by training a student model on its own generated trajectories using token-level feedback from a teacher. However, we identif…

cs.CL2026

Coupled Variational Reinforcement Learning for Language Model General Reasoning

Xueru Wen, Jie Lou, Yanjiang Liu +6

While reinforcement learning has achieved impressive progress in language model reasoning, it is constrained by the requirement for verifiable rewards. Recent verifier-free RL meth…

cs.CL2026

Learning from Failures: Correction-Oriented Policy Optimization with Verifiable Rewards

Mengjie Ren, Jie Lou, Boxi Cao +6

Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as an effective paradigm for improving the reasoning capabilities of large language models. However, RLVR training…

cs.CL2026

MemSearcher: Training LLMs to Reason, Search and Manage Memory via End-to-End Reinforcement Learning

Qianhao Yuan, Jie Lou, Zichao Li +6

LLM-based search agents often concatenate the full interaction history into the context, producing long and noisy inputs, and increasing compute cost and GPU memory overhead. To ad…

cs.LG2026

Nemotron 3 Super: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning

NVIDIA, :, Aakshita Chandiramani +544

We describe the pre-training, post-training, and quantization of Nemotron 3 Super, a 120 billion (active 12 billion) parameter hybrid Mamba-Attention Mixture-of-Experts model. Nemo…