Cover Image

ReasonGen-R1: CoT for Autoregressive Image generation models through SFT and RL

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhang, Yu, Li, Yunqi, Yang, Yifan, Wang, Rui, Yang, Yuqing, Qi, Dai, Bao, Jianmin, Chen, Dongdong, Luo, Chong, Qiu, Lili
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Empowering Lightweight MLLMs with Reasoning via Long CoT SFT
by: Ou, Linyu, et al.
Published: (2025)

The Synergy Dilemma of Long-CoT SFT and RL: Investigating Post-Training Techniques for Reasoning VLMs
by: Chen, Jierun, et al.
Published: (2025)

HiTVideo: Hierarchical Tokenizers for Enhancing Text-to-Video Generation with Autoregressive Large Language Models
by: Zhou, Ziqin, et al.
Published: (2025)

AVGen-Bench: A Task-Driven Benchmark for Multi-Granular Evaluation of Text-to-Audio-Video Generation
by: Zhou, Ziwei, et al.
Published: (2026)

SimpleAR: Pushing the Frontier of Autoregressive Visual Generation through Pretraining, SFT, and RL
by: Wang, Junke, et al.
Published: (2025)

AceReason-Nemotron 1.1: Advancing Math and Code Reasoning through SFT and RL Synergy
by: Liu, Zihan, et al.
Published: (2025)

MageBench: Bridging Large Multimodal Models to Agents
by: Zhang, Miaosen, et al.
Published: (2024)

REDUCIO! Generating 1K Video within 16 Seconds using Extremely Compressed Motion Latents
by: Tian, Rui, et al.
Published: (2024)

ImageGen-CoT: Enhancing Text-to-Image In-context Learning with Chain-of-Thought Reasoning
by: Liao, Jiaqi, et al.
Published: (2025)

How Likely Do LLMs with CoT Mimic Human Reasoning?
by: Bao, Guangsheng, et al.
Published: (2024)

Ada-R1: Hybrid-CoT via Bi-Level Adaptive Reasoning Optimization
by: Luo, Haotian, et al.
Published: (2025)

LLM2CLIP: Powerful Language Model Unlocks Richer Cross-Modality Representation
by: Huang, Weiquan, et al.
Published: (2024)

Improve Student's Reasoning Generalizability through Cascading Decomposed CoTs Distillation
by: Dai, Chengwei, et al.
Published: (2024)

BizGenEval: A Systematic Benchmark for Commercial Visual Content Generation
by: Li, Yan, et al.
Published: (2026)

GRASP: Grounded CoT Reasoning with Dual-Stage Optimization for Multimodal Sarcasm Target Identification
by: Wan, Faxian, et al.
Published: (2026)

Investigating CoT Monitorability in Large Reasoning Models
by: Yang, Shu, et al.
Published: (2025)

Parrot: A Training Pipeline Enhances Both Program CoT and Natural Language CoT for Reasoning
by: Jin, Senjie, et al.
Published: (2025)

Video-in-the-Loop: Span-Grounded Long Video QA with Interleaved Reasoning
by: Wang, Chendong, et al.
Published: (2025)

CoT Vectors: Transferring and Probing the Reasoning Mechanisms of LLMs
by: Li, Li, et al.
Published: (2025)

SFT or RL? An Early Investigation into Training R1-Like Reasoning Large Vision-Language Models
by: Chen, Hardy, et al.
Published: (2025)

Beyond Two-Stage Training: Cooperative SFT and RL for LLM Reasoning
by: Chen, Liang, et al.
Published: (2025)

Metis-RISE: RL Incentivizes and SFT Enhances Multimodal Reasoning Model Learning
by: Qiu, Haibo, et al.
Published: (2025)

VidGuard-R1: AI-Generated Video Detection and Explanation via Reasoning MLLMs and RL
by: Park, Kyoungjun, et al.
Published: (2025)

Efficient Long CoT Reasoning in Small Language Models
by: Wang, Zhaoyang, et al.
Published: (2025)

SFT-then-RL Outperforms Mixed-Policy Methods for LLM Reasoning
by: Limozin, Alexis, et al.
Published: (2026)

OpenVLThinker: Complex Vision-Language Reasoning via Iterative SFT-RL Cycles
by: Deng, Yihe, et al.
Published: (2025)

Blockwise SFT for Diffusion Language Models: Reconciling Bidirectional Attention and Autoregressive Decoding
by: Sun, Bowen, et al.
Published: (2025)

Mol-R1: Towards Explicit Long-CoT Reasoning in Molecule Discovery
by: Li, Jiatong, et al.
Published: (2025)

Beyond SFT-to-RL: Pre-alignment via Black-Box On-Policy Distillation for Multimodal RL
by: Wang, Sudong, et al.
Published: (2026)

DeReason: A Difficulty-Aware Curriculum Improves Decoupled SFT-then-RL Training for General Reasoning
by: Hu, Hanxu, et al.
Published: (2026)

MIND: From Passive Mimicry to Active Reasoning through Capability-Aware Multi-Perspective CoT Distillation
by: Cui, Jin, et al.
Published: (2026)

GenCLS++: Pushing the Boundaries of Generative Classification in LLMs Through Comprehensive SFT and RL Studies Across Diverse Datasets
by: He, Mingqian, et al.
Published: (2025)

Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond
by: Wen, Liang, et al.
Published: (2025)

Can Pruning Improve Reasoning? Revisiting Long-CoT Compression with Capability in Mind for Better Reasoning
by: Zhao, Shangziqi, et al.
Published: (2025)

ViaRL: Adaptive Temporal Grounding via Visual Iterated Amplification Reinforcement Learning
by: Xu, Ziqiang, et al.
Published: (2025)

Expressive and Generalizable Low-rank Adaptation for Large Models via Slow Cascaded Learning
by: Li, Siwei, et al.
Published: (2024)

Delving into RL for Image Generation with CoT: A Study on DPO vs. GRPO
by: Tong, Chengzhuo, et al.
Published: (2025)

CoT-Kinetics: A Theoretical Modeling Assessing LRM Reasoning Process
by: Bi, Jinhe, et al.
Published: (2025)

NoisyGRPO: Incentivizing Multimodal CoT Reasoning via Noise Injection and Bayesian Estimation
by: Qiu, Longtian, et al.
Published: (2025)

Patch the Distribution Mismatch: RL Rewriting Agent for Stable Off-Policy SFT
by: Wang, Jiacheng, et al.
Published: (2026)