Copertina

Thinking Diffusion: Penalize and Guide Visual-Grounded Reasoning in Diffusion Multimodal Language Models

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Kim, Keuntae, Kang, Mingyu, Choi, Yong Suk
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Artificial Intelligence Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Editable Noise Map Inversion: Encoding Target-image into Noise For High-Fidelity Image Manipulation
di: Kang, Mingyu, et al.
Pubblicazione: (2025)

The Thinking Pixel: Recursive Sparse Reasoning in Multimodal Diffusion Latents
di: Sun, Yuwei, et al.
Pubblicazione: (2026)

Objective and Interpretable Breast Cosmesis Evaluation with Attention Guided Denoising Diffusion Anomaly Detection Model
di: Park, Sangjoon, et al.
Pubblicazione: (2024)

Dynamic VLM-Guided Negative Prompting for Diffusion Models
di: Chang, Hoyeon, et al.
Pubblicazione: (2025)

DiffExp: Efficient Exploration in Reward Fine-tuning for Text-to-Image Diffusion Models
di: Chae, Daewon, et al.
Pubblicazione: (2025)

Visual Funnel: Resolving Contextual Blindness in Multimodal Large Language Models
di: Jung, Woojun, et al.
Pubblicazione: (2025)

Understand, Think, and Answer: Advancing Visual Reasoning with Large Multimodal Models
di: Zhan, Yufei, et al.
Pubblicazione: (2025)

Real-Time Visual Attribution Streaming in Thinking Model
di: Kang, Seil, et al.
Pubblicazione: (2026)

H2-Cache: A Novel Hierarchical Dual-Stage Cache for High-Performance Acceleration of Generative Diffusion Models
di: Sung, Mingyu, et al.
Pubblicazione: (2025)

Diffusion Fuzzy System: Fuzzy Rule Guided Latent Multi-Path Diffusion Modeling
di: Yang, Hailong, et al.
Pubblicazione: (2025)

Your Large Vision-Language Model Only Needs A Few Attention Heads For Visual Grounding
di: Kang, Seil, et al.
Pubblicazione: (2025)

Diffusion-Guided Semantic Consistency for Multimodal Heterogeneity
di: Liu, Jing, et al.
Pubblicazione: (2026)

Reinforcing Spatial Reasoning in Vision-Language Models with Interwoven Thinking and Visual Drawing
di: Wu, Junfei, et al.
Pubblicazione: (2025)

VisDoT : Enhancing Visual Reasoning through Human-Like Interpretation Grounding and Decomposition of Thought
di: Lee, Eunsoo, et al.
Pubblicazione: (2026)

Text-Guided Variational Image Generation for Industrial Anomaly Detection and Segmentation
di: Lee, Mingyu, et al.
Pubblicazione: (2024)

StableSketcher: Enhancing Diffusion Model for Pixel-based Sketch Generation via Visual Question Answering Feedback
di: Park, Jiho, et al.
Pubblicazione: (2025)

FIFO-Diffusion: Generating Infinite Videos from Text without Training
di: Kim, Jihwan, et al.
Pubblicazione: (2024)

Towards GUI Agents: Vision-Language Diffusion Models for GUI Grounding
di: Kumbhar, Shrinidhi, et al.
Pubblicazione: (2026)

AtomThink: Multimodal Slow Thinking with Atomic Step Reasoning
di: Xiang, Kun, et al.
Pubblicazione: (2024)

Reference-Guided Diffusion Inpainting For Multimodal Counterfactual Generation
di: Buburuzan, Alexandru
Pubblicazione: (2025)

Enhancing Alignment for Unified Multimodal Models via Semantically-Grounded Supervision
di: Kim, Jiyeong, et al.
Pubblicazione: (2026)

Thinking Before Looking: Improving Multimodal LLM Reasoning via Mitigating Visual Hallucination
di: Zheng, Haojie, et al.
Pubblicazione: (2024)

Paired Image Generation with Diffusion-Guided Diffusion Models
di: Zhang, Haoxuan, et al.
Pubblicazione: (2025)

How Multimodal LLMs Solve Image Tasks: A Lens on Visual Grounding, Task Reasoning, and Answer Decoding
di: Yu, Zhuoran, et al.
Pubblicazione: (2025)

Think with Grounding: Curriculum Reinforced Reasoning with Video Grounding for Long Video Understanding
di: Chen, Houlun, et al.
Pubblicazione: (2026)

Reasoning-Guided Grounding: Elevating Video Anomaly Detection through Multimodal Large Language Models
di: Agarwal, Sakshi, et al.
Pubblicazione: (2026)

VGR: Visual Grounded Reasoning
di: Wang, Jiacong, et al.
Pubblicazione: (2025)

Fusion Embedding for Pose-Guided Person Image Synthesis with Diffusion Model
di: Lee, Donghwna, et al.
Pubblicazione: (2024)

Think, Act, Build: An Agentic Framework with Vision Language Models for Zero-Shot 3D Visual Grounding
di: Wang, Haibo, et al.
Pubblicazione: (2026)

Think Before You Drive: World Model-Inspired Multimodal Grounding for Autonomous Vehicles
di: Liao, Haicheng, et al.
Pubblicazione: (2025)

See What You Are Told: Visual Attention Sink in Large Multimodal Models
di: Kang, Seil, et al.
Pubblicazione: (2025)

When Thinking Drifts: Evidential Grounding for Robust Video Reasoning
di: Luo, Mi, et al.
Pubblicazione: (2025)

Language Model Beats Diffusion -- Tokenizer is Key to Visual Generation
di: Yu, Lijun, et al.
Pubblicazione: (2023)

AlignDiT: Multimodal Aligned Diffusion Transformer for Synchronized Speech Generation
di: Choi, Jeongsoo, et al.
Pubblicazione: (2025)

GLYPH-SR: Can We Achieve Both High-Quality Image Super-Resolution and High-Fidelity Text Recovery via VLM-guided Latent Diffusion Model?
di: Sung, Mingyu, et al.
Pubblicazione: (2025)

Progressive Multimodal Search and Reasoning for Knowledge-Intensive Visual Question Answering
di: Choi, Changin, et al.
Pubblicazione: (2025)

Beyond Visual Safety: Jailbreaking Multimodal Large Language Models for Harmful Image Generation via Semantic-Agnostic Inputs
di: Yu, Mingyu, et al.
Pubblicazione: (2026)

VG-CoT: Towards Trustworthy Visual Reasoning via Grounded Chain-of-Thought
di: Lim, Byeonggeuk, et al.
Pubblicazione: (2026)

Visual-Noise Guided In-Context Distillation for Multimodal Large Language Model Unlearning
di: Chen, Junkai, et al.
Pubblicazione: (2026)

Safeguard Text-to-Image Diffusion Models with Human Feedback Inversion
di: Kim, Sanghyun, et al.
Pubblicazione: (2024)