Cover Image

FocusDiff: Advancing Fine-Grained Text-Image Alignment for Autoregressive Visual Generation through RL

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Pan, Kaihang, Bu, Wendong, Wu, Yuruo, Wu, Yang, Shen, Kai, Li, Yunfei, Zhao, Hang, Li, Juncheng, Tang, Siliang, Zhuang, Yueting
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Janus-Pro-R1: Advancing Collaborative Visual Comprehension and Generation via Reinforcement Learning
by: Pan, Kaihang, et al.
Published: (2025)

SpatialFusion: Endowing Unified Image Generation with Intrinsic 3D Geometric Awareness
by: Qiu, Haiyi, et al.
Published: (2026)

What Limits Virtual Agent Application? OmniBench: A Scalable Multi-Dimensional Benchmark for Essential Virtual Agent Capabilities
by: Bu, Wendong, et al.
Published: (2025)

Generalist Virtual Agents: A Survey on Autonomous Agents Across Digital Platforms
by: Gao, Minghe, et al.
Published: (2024)

OmniMoGen: Unifying Human Motion Generation via Learning from Interleaved Text-Motion Instructions
by: Bu, Wendong, et al.
Published: (2025)

Momentor: Advancing Video Large Language Model with Fine-Grained Temporal Reasoning
by: Qian, Long, et al.
Published: (2024)

T2S-GPT: Dynamic Vector Quantization for Autoregressive Sign Language Production from Text
by: Yin, Aoxiong, et al.
Published: (2024)

Iris: Breaking GUI Complexity with Adaptive Focus and Self-Refining
by: Ge, Zhiqi, et al.
Published: (2024)

Mastering Collaborative Multi-modal Data Selection: A Focus on Informativeness, Uniqueness, and Representativeness
by: Yu, Qifan, et al.
Published: (2024)

Fine-tuning Multimodal LLMs to Follow Zero-shot Demonstrative Instructions
by: Li, Juncheng, et al.
Published: (2023)

CORE: Code-based Inverse Self-Training Framework with Graph Expansion for Virtual Agents
by: Wang, Keyu, et al.
Published: (2026)

WiseEdit: Benchmarking Cognition- and Creativity-Informed Image Editing
by: Pan, Kaihang, et al.
Published: (2025)

Bridging Local Details and Global Context in Text-Attributed Graphs
by: Wang, Yaoke, et al.
Published: (2024)

AnyEdit: Mastering Unified High-Quality Image Editing for Any Idea
by: Yu, Qifan, et al.
Published: (2024)

Towards Meta-Cognitive Knowledge Editing for Multimodal LLMs
by: Fan, Zhaoyu, et al.
Published: (2025)

Auto-Encoding Morph-Tokens for Multimodal LLM
by: Pan, Kaihang, et al.
Published: (2024)

InstructVid2Vid: Controllable Video Editing with Natural Language Instructions
by: Qin, Bosheng, et al.
Published: (2023)

STEP: Enhancing Video-LLMs' Compositional Reasoning by Spatio-Temporal Graph-guided Self-Training
by: Qiu, Haiyi, et al.
Published: (2024)

GMFVAD: Using Grained Multi-modal Feature to Improve Video Anomaly Detection
by: Dai, Guangyu, et al.
Published: (2025)

Boosting Virtual Agent Learning and Reasoning: A Step-Wise, Multi-Dimensional, and Generalist Reward Model with Benchmark
by: Miao, Bingchen, et al.
Published: (2025)

Benchmarking Multimodal CoT Reward Model Stepwise by Visual Program
by: Gao, Minghe, et al.
Published: (2025)

Ask Questions with Double Hints: Visual Question Generation with Answer-awareness and Region-reference
by: Shen, Kai, et al.
Published: (2024)

KCM: KAN-Based Collaboration Models Enhance Pretrained Large Models
by: Dai, Guangyu, et al.
Published: (2025)

Advancing Fine-Grained Visual Understanding with Multi-Scale Alignment in Multi-Modal Models
by: Wang, Wei, et al.
Published: (2024)

HalluciDoctor: Mitigating Hallucinatory Toxicity in Visual Instruction Data
by: Yu, Qifan, et al.
Published: (2023)

WorldGPT: Empowering LLM as Multimodal World Model
by: Ge, Zhiqi, et al.
Published: (2024)

Robust Modality-incomplete Anomaly Detection: A Modality-instructive Framework with Benchmark
by: Miao, Bingchen, et al.
Published: (2024)

LASER: Tuning-Free LLM-Driven Attention Control for Efficient Text-conditioned Image-to-Animation
by: Zheng, Haoyu, et al.
Published: (2024)

MoA: Heterogeneous Mixture of Adapters for Parameter-Efficient Fine-Tuning of Large Language Models
by: Cao, Jie, et al.
Published: (2025)

Align$^2$LLaVA: Cascaded Human and Large Language Model Preference Alignment for Multi-modal Instruction Curation
by: Huang, Hongzhe, et al.
Published: (2024)

De-fine: Decomposing and Refining Visual Programs with Auto-Feedback
by: Gao, Minghe, et al.
Published: (2023)

Chart-HQA: A Benchmark for Hypothetical Question Answering in Charts
by: Chen, Xiangnan, et al.
Published: (2025)

SOYO: A Tuning-Free Approach for Video Style Morphing via Style-Adaptive Interpolation in Diffusion Models
by: Zheng, Haoyu, et al.
Published: (2025)

InstructSAM: Segment Any Instance with Any Instructions
by: Yuan, Yuqian, et al.
Published: (2026)

Learning to Adapt: Self-Improving Web Agent via Cognitive-Aware Exploration
by: Chen, Weile, et al.
Published: (2026)

TAlignDiff: Automatic Tooth Alignment assisted by Diffusion-based Transformation Learning
by: Liu, Yunbi, et al.
Published: (2025)

FineLIP: Extending CLIP's Reach via Fine-Grained Alignment with Longer Text Inputs
by: Asokan, Mothilal, et al.
Published: (2025)

Generative Multimodal Pretraining with Discrete Diffusion Timestep Tokens
by: Pan, Kaihang, et al.
Published: (2025)

Towards Unified Multimodal Editing with Enhanced Knowledge Collaboration
by: Pan, Kaihang, et al.
Published: (2024)

Chart-FR1: Visual Focus-Driven Fine-Grained Reasoning on Dense Charts
by: Pan, Hongkun, et al.
Published: (2026)