conftrace_

token pruning

81 papers

Explore in graph

Co-occurring keywords

model compression (3302) efficient computing (781) vision transformer (1106) vision language model (767) inference acceleration (244) multimodal large language model (966) model efficiency (206) vision-language model (2348) efficient inference (233) multimodal learning (4645)

Papers

METEOR: Multi-Encoder Collaborative Token Pruning for Efficient Vision Language Models ICCV 2025
Skip-Vision: Efficient and Scalable Acceleration of Vision-Language Models via Adaptive Token Skipping ICCV 2025
Pruning All-Rounder: Rethinking and Improving Inference Efficiency for Large Vision Language Models ICCV 2025
Training-Free and Hardware-Friendly Acceleration for Diffusion Models via Similarity-based Token Pruning AAAI 2025
Token Pruning in Multimodal Large Language Models: Are We Solving the Right Problem? ACL 2025
Lifting the Veil on Visual Information Flow in MLLMs: Unlocking Pathways to Faster Inference CVPR 2025
LEANCODE: Understanding Models Better for Code Simplification of Pre-trained Large Language Models ACL 2025
Towards Storage-Efficient Visual Document Retrieval: An Empirical Study on Reducing Patch-Level Embeddings ACL 2025
AIM: Adaptive Inference of Multi-Modal LLMs via Token Merging and Pruning ICCV 2025
Keyframe-oriented Vision Token Pruning: Enhancing Efficiency of Large Vision Language Models on Long-Form Video Processing ICCV 2025
When Large Vision-Language Model Meets Large Remote Sensing Imagery: Coarse-to-Fine Text-Guided Token Pruning ICCV 2025
SparseVILA: Decoupling Visual Sparsity for Efficient VLM Inference ICCV 2025
Representing 3D Shapes with 64 Latent Vectors for 3D Diffusion Models ICCV 2025
FastVAR: Linear Visual Autoregressive Modeling via Cached Token Pruning ICCV 2025
SpecVLM: Enhancing Speculative Decoding of Video LLMs via Verifier-Guided Token Pruning EMNLP 2025
Stop Looking for “Important Tokens” in Multimodal Language Models: Duplication Matters More EMNLP 2025
VisiPruner: Decoding Discontinuous Cross-Modal Dynamics for Efficient Multimodal LLMs EMNLP 2025
Walk and Read Less: Improving the Efficiency of Vision-and-Language Navigation via Tuning-Free Multimodal Token Pruning EMNLP 2025
Token Cropr: Faster ViTs for Quite a Few Tasks CVPR 2025
Fit and Prune: Fast and Training-free Visual Token Pruning for Multi-modal Large Language Models AAAI 2025
A Hidden Stumbling Block in Generalized Category Discovery: Distracted Attention ICCV 2025
Beyond Text-Visual Attention: Exploiting Visual Cues for Effective Token Pruning in VLMs ICCV 2025
Harnessing Input-Adaptive Inference for Efficient VLN ICCV 2025
AdaTP: Attention-Debiased Token Pruning for Video Large Language Models EMNLP 2025
CoViPAL: Layer-wise Contextualized Visual Token Pruning for Large Vision-Language Models EMNLP 2025