Cover Image

CompoDistill: Attention Distillation for Compositional Reasoning in Multimodal LLMs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Kim, Jiwan, Kim, Kibum, Seo, Sangwoo, Park, Chanyoung
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Semantic Diversity-aware Prototype-based Learning for Unbiased Scene Graph Generation
by: Jeon, Jaehyeong, et al.
Published: (2024)

SIMPLOT: Enhancing Chart Question Answering by Distilling Essentials
by: Kim, Wonjoong, et al.
Published: (2024)

Adaptive Self-training Framework for Fine-grained Scene Graph Generation
by: Kim, Kibum, et al.
Published: (2024)

Why and When Visual Token Pruning Fails? A Study on Relevant Visual Information Shift in MLLMs Decoding
by: Kim, Jiwan, et al.
Published: (2026)

V.I.P. : Iterative Online Preference Distillation for Efficient Video Diffusion Models
by: Kim, Jisoo, et al.
Published: (2025)

LLM4SGG: Large Language Models for Weakly Supervised Scene Graph Generation
by: Kim, Kibum, et al.
Published: (2023)

FEAST: Fully Connected Expressive Attention for Spatial Transcriptomics
by: Jeong, Taejin, et al.
Published: (2026)

Multimodal Distribution Matching for Vision-Language Dataset Distillation
by: Jeong, Jongoh, et al.
Published: (2026)

VizECGNet: Visual ECG Image Network for Cardiovascular Diseases Classification with Multi-Modal Training and Knowledge Distillation
by: Nam, Ju-Hyeon, et al.
Published: (2024)

Global Geometry Is Not Enough for Vision Representations
by: Chung, Jiwan, et al.
Published: (2026)

Align Your Query: Representation Alignment for Multimodality Medical Object Detection
by: Seo, Ara, et al.
Published: (2025)

The Role of Teacher Calibration in Knowledge Distillation
by: Kim, Suyoung, et al.
Published: (2025)

Leveraging Textual Compositional Reasoning for Robust Change Captioning
by: Park, Kyu Ri, et al.
Published: (2025)

Multi-Level Knowledge Distillation and Dynamic Self-Supervised Learning for Continual Learning
by: Kim, Taeheon, et al.
Published: (2025)

Classifier-guided CLIP Distillation for Unsupervised Multi-label Classification
by: Kim, Dongseob, et al.
Published: (2025)

3D-Aware Vision-Language Models Fine-Tuning with Geometric Distillation
by: Lee, Seonho, et al.
Published: (2025)

Adaptive Graph Rewiring to Mitigate Over-Squashing in Mesh-Based GNNs for Fluid Dynamics Simulations
by: Seo, Sangwoo, et al.
Published: (2025)

RealCompo: Balancing Realism and Compositionality Improves Text-to-Image Diffusion Models
by: Zhang, Xinchen, et al.
Published: (2024)

Enhancing Source-Free Domain Adaptive Object Detection with Low-confidence Pseudo Label Distillation
by: Yoon, Ilhoon, et al.
Published: (2024)

DreamSampler: Unifying Diffusion Sampling and Score Distillation for Image Manipulation
by: Kim, Jeongsol, et al.
Published: (2024)

Adaptive Explicit Knowledge Transfer for Knowledge Distillation
by: Park, Hyungkeun, et al.
Published: (2024)

Active Multimodal Distillation for Few-shot Action Recognition
by: Feng, Weijia, et al.
Published: (2025)

Inference-Time Diffusion Model Distillation
by: Park, Geon Yeong, et al.
Published: (2024)

RA-SGG: Retrieval-Augmented Scene Graph Generation Framework via Multi-Prototype Learning
by: Yoon, Kanghoon, et al.
Published: (2024)

Speaking Beyond Language: A Large-Scale Multimodal Dataset for Learning Nonverbal Cues from Video-Grounded Dialogues
by: Kim, Youngmin, et al.
Published: (2025)

EditSplat: Multi-View Fusion and Attention-Guided Optimization for View-Consistent 3D Scene Editing with 3D Gaussian Splatting
by: Lee, Dong In, et al.
Published: (2024)

SiNGER: A Clearer Voice Distills Vision Transformers Further
by: Yu, Geunhyeok, et al.
Published: (2025)

VISD: Enhancing Video Reasoning via Structured Self-Distillation
by: Lin, Hao, et al.
Published: (2026)

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

Multimodal Robust Prompt Distillation for 3D Point Cloud Models
by: Gu, Xiang, et al.
Published: (2025)

Distilling Privileged Multimodal Information for Expression Recognition using Optimal Transport
by: Aslam, Muhammad Haseeb, et al.
Published: (2024)

X-Distill: Cross-Architecture Vision Distillation for Visuomotor Learning
by: Shao, Maanping, et al.
Published: (2026)

Tiled Prompts: Overcoming Prompt Misguidance in Image and Video Super-Resolution
by: Kim, Bryan Sangwoo, et al.
Published: (2026)

EgoSpeak: Learning When to Speak for Egocentric Conversational Agents in the Wild
by: Kim, Junhyeok, et al.
Published: (2025)

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

Scale Decoupled Distillation
by: Luo, Shicai Wei Chunbo Luo Yang
Published: (2024)

Accurate Scene Text Recognition with Efficient Model Scaling and Cloze Self-Distillation
by: Maracani, Andrea, et al.
Published: (2025)

Multimodal Emotion Recognition via Bi-directional Cross-Attention and Temporal Modeling
by: Byeon, Junhyeong, et al.
Published: (2026)

VGenST-Bench: A Benchmark for Spatio-Temporal Reasoning via Active Video Synthesis
by: Park, Jinho, et al.
Published: (2026)

Seeing is Understanding: Unlocking Causal Attention into Modality-Mutual Attention for Multimodal LLMs
by: Wang, Wei-Yao, et al.
Published: (2025)