Papers134

All Beginner Intermediate Advanced

All Sources arXiv

#GRPO

Rethinking Chain-of-Thought Reasoning for Videos

Intermediate

Yiwu Zhong, Zi-Yuan Hu et al.Dec 10arXiv

The paper shows that video AIs do not need long, human-like chains of thought to reason well.

#video reasoning#chain-of-thought#concise reasoning

Learning Unmasking Policies for Diffusion Language Models

Intermediate

Metod Jazbec, Theo X. Olausson et al.Dec 9arXiv

Diffusion language models write by gradually unmasking hidden words, so deciding which blanks to reveal next is a big deal for both speed and accuracy.

#diffusion language models#masked diffusion#unmasking policy

Thinking with Images via Self-Calling Agent

Intermediate

Wenxi Yang, Yuzhong Zhao et al.Dec 9arXiv

This paper teaches a vision-language model to think about images by talking to copies of itself, using only words to plan and decide.

#Self-Calling Chain-of-Thought#sCoT#interleaved multimodal chain-of-thought

TreeGRPO: Tree-Advantage GRPO for Online RL Post-Training of Diffusion Models

Intermediate

Zheng Ding, Weirui YeDec 9arXiv

TreeGRPO teaches image generators using a smart branching tree so each training run produces many useful learning signals instead of just one.

#TreeGRPO#reinforcement learning#diffusion 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

Beyond Token-level Supervision: Unlocking the Potential of Decoding-based Regression via Reinforcement Learning

Intermediate

Ming Chen, Sheng Tang et al.Dec 6arXiv

The paper shows that making a model write a number as a sequence of digits and then grading the whole number at the end works better than grading each digit separately.

#decoding-based regression#sequence-level reward#reinforcement learning

EtCon: Edit-then-Consolidate for Reliable Knowledge Editing

Intermediate

Ruilin Li, Yibin Wang et al.Dec 4arXiv

Large language models forget or misuse new facts if you only poke their weights once; EtCon fixes this with a two-step plan.

#knowledge editing#EtCon#TPSFT

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

SPARK: Stepwise Process-Aware Rewards for Reference-Free Reinforcement Learning

Intermediate

Salman Rahman, Sruthi Gorantla et al.Dec 2arXiv

SPARK teaches AI to grade its own steps without needing the right answers written down anywhere.

#SPARK#Process Reward Model#PRM-CoT

ReVSeg: Incentivizing the Reasoning Chain for Video Segmentation with Reinforcement Learning

Intermediate

Yifan Li, Yingda Yin et al.Dec 2arXiv

ReVSeg teaches an AI to segment objects in videos by thinking step-by-step instead of guessing everything at once.

#Reasoning Video Object Segmentation#Vision-Language Models#Temporal Grounding

PaCo-RL: Advancing Reinforcement Learning for Consistent Image Generation with Pairwise Reward Modeling

Intermediate

Bowen Ping, Chengyou Jia et al.Dec 2arXiv

This paper teaches image models to keep things consistent across multiple pictures—like the same character, art style, and story logic—using reinforcement learning (RL).

#consistent image generation#pairwise reward modeling#reinforcement learning

From Imitation to Discrimination: Toward A Generalized Curriculum Advantage Mechanism Enhancing Cross-Domain Reasoning Tasks

Intermediate

Changpeng Yang, Jinyang Wu et al.Dec 2arXiv

This paper teaches AI models to reason better by first copying only good examples and later learning from mistakes too.

#Curriculum Advantage Policy Optimization#advantage-based RL#imitation learning

8 9 10 11 12