rednote-hilab

company

https://github.com/rednote-hilab

AI & ML interests

None defined yet.

Recent Activity

floyed submitted a paper about 19 hours ago

Anti-Self-Distillation for Reasoning RL via Pointwise Mutual Information

ygfrancois new activity about 1 month ago

rednote-hilab/dots.mocr:Add ParseBench evaluation results

ygfrancois new activity about 1 month ago

rednote-hilab/dots.mocr:Add MDPBench evaluation results

View all activity

Papers

Anti-Self-Distillation for Reasoning RL via Pointwise Mutual Information

Bootstrapping Exploration with Group-Level Natural Language Feedback in Reinforcement Learning

View all Papers

rednote-hilab 's Papers 8

Submitted by

floyed shen

Anti-Self-Distillation for Reasoning RL via Pointwise Mutual Information

rednote-hilab

Submitted by

HuangMeow

Bootstrapping Exploration with Group-Level Natural Language Feedback in Reinforcement Learning

rednote-hilab

Submitted by

Xiao Wang

REDSearcher: A Scalable and Cost-Efficient Framework for Long-Horizon Search Agents

rednote-hilab

Submitted by

floyed shen

VESPO: Variational Sequence-Level Soft Policy Optimization for Stable Off-Policy LLM Training

rednote-hilab

dots.ocr: Multilingual Document Layout Parsing in a Single Vision-Language Model

rednote-hilab

Submitted by

taesiri

DeepEyesV2: Toward Agentic Multimodal Model

rednote-hilab

Submitted by

MikaStars39

Refusal Falls off a Cliff: How Safety Alignment Fails in Reasoning?

rednote-hilab

DeepEyes: Incentivizing "Thinking with Images" via Reinforcement Learning

rednote-hilab