Cover Image

SparseMM: Head Sparsity Emerges from Visual Concept Responses in MLLMs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wang, Jiahui, Liu, Zuyan, Rao, Yongming, Lu, Jiwen
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

Chain-of-Spot: Interactive Reasoning Improves Large Vision-Language Models
by: Liu, Zuyan, et al.
Published: (2024)

Efficient Inference of Vision Instruction-Following Models with Elastic Cache
by: Liu, Zuyan, et al.
Published: (2024)

Oryx MLLM: On-Demand Spatial-Temporal Understanding at Arbitrary Resolution
by: Liu, Zuyan, et al.
Published: (2024)

GeoVista: Web-Augmented Agentic Visual Reasoning for Geolocalization
by: Wang, Yikun, et al.
Published: (2025)

Ola: Pushing the Frontiers of Omni-Modal Language Model
by: Liu, Zuyan, et al.
Published: (2025)

X-3D: Explicit 3D Structure Modeling for Point Cloud Recognition
by: Sun, Shuofeng, et al.
Published: (2024)

Insight-V++: Towards Advanced Long-Chain Visual Reasoning with Multimodal Large Language Models
by: Dong, Yuhao, et al.
Published: (2026)

Insight-V: Exploring Long-Chain Visual Reasoning with Multimodal Large Language Models
by: Dong, Yuhao, et al.
Published: (2024)

Magic-MM-Embedding: Towards Visual-Token-Efficient Universal Multimodal Embedding with MLLMs
by: Li, Qi, et al.
Published: (2026)

Vision Generalist Model: A Survey
by: Wang, Ziyi, et al.
Published: (2025)

SparseVILA: Decoupling Visual Sparsity for Efficient VLM Inference
by: Khaki, Samir, et al.
Published: (2025)

Visual Jigsaw Post-Training Improves MLLMs
by: Wu, Penghao, et al.
Published: (2025)

DiffSparse: Accelerating Diffusion Transformers with Learned Token Sparsity
by: Zhu, Haowei, et al.
Published: (2026)

AV-Reasoner: Improving and Benchmarking Clue-Grounded Audio-Visual Counting for MLLMs
by: Lu, Lidong, et al.
Published: (2025)

Object Concepts Emerge from Motion
by: Liang, Haoqian, et al.
Published: (2025)

OmniSparse: Training-Aware Fine-Grained Sparse Attention for Long-Video MLLMs
by: Chen, Feng, et al.
Published: (2025)

Sparsity- and Hybridity-Inspired Visual Parameter-Efficient Fine-Tuning for Medical Diagnosis
by: Liu, Mingyuan, et al.
Published: (2024)

Once for Both: Single Stage of Importance and Sparsity Search for Vision Transformer Compression
by: Ye, Hancheng, et al.
Published: (2024)

TSP3D: Text-guided Sparse Voxel Pruning for Efficient 3D Visual Grounding
by: Guo, Wenxuan, et al.
Published: (2025)

LLaVA-SP: Enhancing Visual Representation with Visual Spatial Tokens for MLLMs
by: Lou, Haoran, et al.
Published: (2025)

POINTS-Long: Adaptive Dual-Mode Visual Reasoning in MLLMs
by: Wang, Haicheng, et al.
Published: (2026)

Concepts from Representations: Post-hoc Concept Bottleneck Models via Sparse Decomposition of Visual Representations
by: Gong, Shizhan, et al.
Published: (2026)

VisionPulse: Dynamic Visual Sparsity for Efficient Multimodal Reasoning
by: Xu, Hengbo, et al.
Published: (2026)

V2M: Visual 2-Dimensional Mamba for Image Representation Learning
by: Wang, Chengkun, et al.
Published: (2024)

HeSS: Head Sensitivity Score for Sparsity Redistribution in VGGT
by: Kim, Yongsung, et al.
Published: (2026)

MM-LDM: Multi-Modal Latent Diffusion Model for Sounding Video Generation
by: Sun, Mingzhen, et al.
Published: (2024)

Turbo-GoDec: Exploiting the Cluster Sparsity Prior for Hyperspectral Anomaly Detection
by: Sheng, Jiahui, et al.
Published: (2026)

Instruction-Oriented Preference Alignment for Enhancing Multi-Modal Comprehension Capability of MLLMs
by: Wang, Zitian, et al.
Published: (2025)

GRASP: Guided Region-Aware Sparse Prompting for Adapting MLLMs to Remote Sensing
by: Sun, Qigan, et al.
Published: (2026)

When MLLMs Meet Compression Distortion: A Coding Paradigm Tailored to MLLMs
by: Liu, Jinming, et al.
Published: (2025)

VisualQuest: A Benchmark for Abstract Visual Reasoning in MLLMs
by: Xiao, Kelaiti, et al.
Published: (2025)

Seek-and-Solve: Benchmarking MLLMs for Visual Clue-Driven Reasoning in Daily Scenarios
by: Li, Xiaomin, et al.
Published: (2026)

Don't Just Chase "Highlighted Tokens" in MLLMs: Revisiting Visual Holistic Context Retention
by: Zou, Xin, et al.
Published: (2025)

Exploring the Design Space of Visual Context Representation in Video MLLMs
by: Du, Yifan, et al.
Published: (2024)

DisCo: Towards Distinct and Coherent Visual Encapsulation in Video MLLMs
by: Zhao, Jiahe, et al.
Published: (2025)

Attention Sparsity is Input-Stable: Training-Free Sparse Attention for Video Generation via Offline Sparsity Profiling and Online QK Co-Clustering
by: Luo, Jiayi, et al.
Published: (2026)

Segment Anything with Motion, Geometry, and Semantic Adaptation for Complex Nonlinear Visual Object Tracking
by: Zhu, Deyi, et al.
Published: (2026)

AbductiveMLLM: Boosting Visual Abductive Reasoning Within MLLMs
by: Chang, Boyu, et al.
Published: (2026)

Dynamic Sparse Training with Structured Sparsity
by: Lasby, Mike, et al.
Published: (2023)

Bee: A High-Quality Corpus and Full-Stack Suite to Unlock Advanced Fully Open MLLMs
by: Zhang, Yi, et al.
Published: (2025)