Imagen de Portada

Sparsity Forcing: Reinforcing Token Sparsity of MLLMs

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Chen, Feng, He, Yefei, Lin, Lequan, Gou, Chenhui, Liu, Jing, Zhuang, Bohan, Wu, Qi
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

ZipCache: Accurate and Efficient KV Cache Quantization with Salient Token Identification
por: He, Yefei, et al.
Publicado: (2024)

STS: Efficient Sparse Attention with Speculative Token Sparsity
por: Xu, Ceyu, et al.
Publicado: (2026)

Reinforcement Learning With Sparse-Executing Actions via Sparsity Regularization
por: Pang, Jing-Cheng, et al.
Publicado: (2021)

MiniCache: KV Cache Compression in Depth Dimension for Large Language Models
por: Liu, Akide, et al.
Publicado: (2024)

Evaluating and Advancing Multimodal Large Language Models in Perception Ability Lens
por: Chen, Feng, et al.
Publicado: (2024)

Activity Sparsity Complements Weight Sparsity for Efficient RNN Inference
por: Mukherji, Rishav, et al.
Publicado: (2023)

Sparsity and Out-of-Distribution Generalization
por: Aaronson, Scott, et al.
Publicado: (2026)

ME-Switch: A Memory-Efficient Expert Switching Framework for Large Language Models
por: Liu, Jing, et al.
Publicado: (2024)

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

Dynamic Sparsity: Challenging Common Sparsity Assumptions for Learning World Models in Robotic Reinforcement Learning Benchmarks
por: Pandaram, Muthukumar, et al.
Publicado: (2025)

Outlier Weighed Layerwise Sparsity (OWL): A Missing Secret Sauce for Pruning LLMs to High Sparsity
por: Yin, Lu, et al.
Publicado: (2023)

Boosting Robustness in Preference-Based Reinforcement Learning with Dynamic Sparsity
por: Muslimani, Calarina, et al.
Publicado: (2024)

On the Interplay Between Sparsity and Training in Deep Reinforcement Learning
por: Davelouis, Fatima, et al.
Publicado: (2025)

Sparsity-Driven Plasticity in Multi-Task Reinforcement Learning
por: Todorov, Aleksandar, et al.
Publicado: (2025)

VLM-Pruner: Buffering for Spatial Sparsity in an Efficient VLM Centrifugal Token Pruning Paradigm
por: Wu, Zhenkai, et al.
Publicado: (2025)

Spark Transformer: Reactivating Sparsity in FFN and Attention
por: You, Chong, et al.
Publicado: (2025)

Model Sparsity Can Simplify Machine Unlearning
por: Jia, Jinghan, et al.
Publicado: (2023)

Improving Decision Sparsity
por: Sun, Yiyang, et al.
Publicado: (2024)

Homeostasis and Sparsity in Transformer
por: Kotyuzanskiy, Leonid, et al.
Publicado: (2024)

Sparsity-Induced Global Matrix Autoregressive Model with Auxiliary Network Data
por: Wu, Sanyou, et al.
Publicado: (2025)

Polar Sparsity: High Throughput Batched LLM Inferencing with Scalable Contextual Sparsity
por: Shrestha, Susav, et al.
Publicado: (2025)

SAUC: Sparsity-Aware Uncertainty Calibration for Spatiotemporal Prediction with Graph Neural Networks
por: Zhuang, Dingyi, et al.
Publicado: (2024)

Network Sparsity Unlocks the Scaling Potential of Deep Reinforcement Learning
por: Ma, Guozheng, et al.
Publicado: (2025)

Sparsity-based Safety Conservatism for Constrained Offline Reinforcement Learning
por: Cho, Minjae, et al.
Publicado: (2024)

Weight Sparsity Complements Activity Sparsity in Neuromorphic Language Models
por: Mukherji, Rishav, et al.
Publicado: (2024)

Sparsity-Constraint Optimization via Splicing Iteration
por: Zhu, Jin, et al.
Publicado: (2024)

Sparsity-Aware Evolution for Model Merging
por: Zhang, Huan, et al.
Publicado: (2026)

Efficient Reward Identification In Max Entropy Reinforcement Learning with Sparsity and Rank Priors
por: Shehab, Mohamad Louai, et al.
Publicado: (2025)

Investigating Sparsity in Recurrent Neural Networks
por: Darji, Harshil
Publicado: (2024)

Empowering Distributed Training with Sparsity-driven Data Synchronization
por: Wang, Zhuang, et al.
Publicado: (2023)

Scaling Attention via Feature Sparsity
por: Xie, Yan, et al.
Publicado: (2026)

Towards the Connection between Activation Sparsity and Flat Minima
por: Peng, Ze, et al.
Publicado: (2026)

Sparsity and Superposition in Mixture of Experts
por: Chaudhari, Marmik, et al.
Publicado: (2025)

Leveraging Sparsity for Sample-Efficient Preference Learning: A Theoretical Perspective
por: Yao, Yunzhen, et al.
Publicado: (2025)

Accelerating Transformer Pre-training with 2:4 Sparsity
por: Hu, Yuezhou, et al.
Publicado: (2024)

skscope: Fast Sparsity-Constrained Optimization in Python
por: Wang, Zezhi, et al.
Publicado: (2024)

Learnable Permutation for Structured Sparsity on Transformer Models
por: Li, Zekai, et al.
Publicado: (2026)

Compositional Sparsity as an Inductive Bias for Neural Architecture Design
por: Lin, Hongyu, et al.
Publicado: (2026)

Topolow: Force-Directed Euclidean Embedding of Dissimilarity Data with Robustness Against Non-Metricity and Sparsity
por: Arhami, Omid, et al.
Publicado: (2025)

Robot Learning with Sparsity and Scarcity
por: Xu, Jingxi
Publicado: (2025)