Papers19

#GRPO

ThinkRL-Edit: Thinking in Reinforcement Learning for Reasoning-Centric Image Editing

Hengjia Li, Liming Jiang et al.Jan 6arXiv

ThinkRL-Edit teaches an image editor to think first and draw second, which makes tricky, reasoning-heavy edits much more accurate.

#reasoning-centric image editing#reinforcement learning#chain-of-thought

One Sample to Rule Them All: Extreme Data Efficiency in RL Scaling

Beginner

Yiyuan Li, Zhen Huang et al.Jan 6arXiv

This paper shows that training a language model with reinforcement learning on just one super well-designed example can boost reasoning across many school subjects, not just math.

#polymath learning#one-shot reinforcement learning#GRPO

Falcon-H1R: Pushing the Reasoning Frontiers with a Hybrid Model for Efficient Test-Time Scaling

Beginner

Falcon LLM Team, Iheb Chaabane et al.Jan 5arXiv

Falcon-H1R is a small (7B) AI model that thinks really well without needing giant computers.

#Falcon-H1R#Hybrid Transformer-Mamba#Chain-of-Thought

Bottom-up Policy Optimization: Your Language Model Policy Secretly Contains Internal Policies

Beginner

Yuqiao Tan, Minzheng Wang et al.Dec 22arXiv

Large language models (LLMs) don’t act as a single brain; inside, each layer and module quietly makes its own mini-decisions called internal policies.

#Bottom-up Policy Optimization#internal layer policy#internal modular policy

Robust-R1: Degradation-Aware Reasoning for Robust Visual Understanding

Beginner

Jiaqi Tang, Jianmin Chen et al.Dec 19arXiv

Robust-R1 teaches vision-language models to notice how a picture is damaged, think through what that damage hides, and then answer as if the picture were clear.

#Robust-R1#degradation-aware reasoning#multimodal large language models

On the Interplay of Pre-Training, Mid-Training, and RL on Reasoning Language Models

Beginner

Charlie Zhang, Graham Neubig et al.Dec 8arXiv

The paper asks when reinforcement learning (RL) really makes language models better at reasoning beyond what they learned in pre-training.

#edge of competence#process-verified evaluation#process-level rewards

COOPER: A Unified Model for Cooperative Perception and Reasoning in Spatial Intelligence

Beginner

Zefeng Zhang, Xiangzhao Hao et al.Dec 4arXiv

COOPER is a single AI model that both “looks better” (perceives depth and object boundaries) and “thinks smarter” (reasons step by step) to answer spatial questions about images.

#COOPER#multimodal large language model#unified model

1 2