Cover Image

Evict3R: Training-Free Token Eviction for Memory-Bounded Streaming Visual Geometry Transformers

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Mahdi, Soroush, Ayar, Fardin, Javanmardi, Ehsan, Tsukada, Manabu, Javanmardi, Mahdi
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

LiDAR-Camera Fusion for Video Panoptic Segmentation without Video Training
by: Ayar, Fardin, et al.
Published: (2024)

Towards Robust LiDAR Localization: Deep Learning-based Uncertainty Estimation
by: Dolatabadi, Minoo, et al.
Published: (2025)

Neural Error Covariance Estimation for Precise LiDAR Localization
by: Dolatabadi, Minoo, et al.
Published: (2025)

Where Do You Go? Pedestrian Trajectory Prediction using Scene Features
by: Rezaei, Mohammad Ali, et al.
Published: (2025)

You Share Beliefs, I Adapt: Progressive Heterogeneous Collaborative Perception
by: Si, Hao, et al.
Published: (2025)

Accurate Cooperative Localization Utilizing LiDAR-equipped Roadside Infrastructure for Autonomous Driving
by: Jiang, Yuze, et al.
Published: (2024)

UTrice: Unifying Primitives in Differentiable Ray Tracing and Rasterization via Triangles for Particle-Based 3D Scenes
by: Liu, Changhe, et al.
Published: (2025)

Training-Free Diffusion Framework for Stylized Image Generation with Identity Preservation
by: Rezaei, Mohammad Ali, et al.
Published: (2025)

SUG-Occ: Explicit Semantics and Uncertainty Guided Sparse Learning for Efficient 3D Occupancy Prediction
by: Wu, Hanlin, et al.
Published: (2026)

A Synthetic Benchmark for Collaborative 3D Semantic Occupancy Prediction in V2X-Enabled Autonomous Driving
by: Wu, Hanlin, et al.
Published: (2025)

Trust, Don't Trust, or Flip: Robust Preference-Based Reinforcement Learning with Multi-Expert Feedback
by: Hosseini, Seyed Amir, et al.
Published: (2026)

G3FA: Geometry-guided GAN for Face Animation
by: Javanmardi, Alireza, et al.
Published: (2024)

GHOST: Geometry-Hierarchical Online Streaming Token Eviction for Efficient 3D Reconstruction
by: Chen, Leyang, et al.
Published: (2026)

Masked Autoencoder Self Pre-Training for Defect Detection in Microelectronics
by: Röhrich, Nikolai, et al.
Published: (2025)

FastVGGT: Training-Free Acceleration of Visual Geometry Transformer
by: Shen, You, et al.
Published: (2025)

FrameVGGT: Geometry-Aligned Frame-Level Memory for Bounded Streaming VGGT
by: Xu, Zhisong, et al.
Published: (2026)

StereoVGGT: A Training-Free Visual Geometry Transformer for Stereo Vision
by: Chen, Ziyang, et al.
Published: (2026)

An Innovative Framework for Breast Cancer Detection Using Pyramid Adaptive Atrous Convolution, Transformer Integration, and Multi-Scale Feature Fusion
by: Pour, Ehsan Sadeghi, et al.
Published: (2026)

InfiniteVGGT: Visual Geometry Grounded Transformer for Endless Streams
by: Yuan, Shuai, et al.
Published: (2026)

StreamCacheVGGT: Streaming Visual Geometry Transformers with Robust Scoring and Hybrid Cache Compression
by: Liu, Xuanyi, et al.
Published: (2026)

Token Transforming: A Unified and Training-Free Token Compression Framework for Vision Transformer Acceleration
by: Zeng, Fanhu, et al.
Published: (2025)

OVGGT: O(1) Constant-Cost Streaming Visual Geometry Transformer
by: Lu, Si-Yu, et al.
Published: (2026)

Recurrent Attention-based Token Selection for Efficient Streaming Video-LLMs
by: Dorovatas, Vaggelis, et al.
Published: (2025)

Lightweight RGB-T Tracking with Mobile Vision Transformers
by: Falaki, Mahdi, et al.
Published: (2025)

Mem3R: Streaming 3D Reconstruction with Hybrid Memory via Test-Time Training
by: Liu, Changkun, et al.
Published: (2026)

PaceVGGT: Pre-Alternating-Attention Token Pruning for Visual Geometry Transformers
by: Li, Haotang, et al.
Published: (2026)

LongStream: Long-Sequence Streaming Autoregressive Visual Geometry
by: Cheng, Chong, et al.
Published: (2026)

QVGGT: Post-Training Quantized Visual Geometry Grounded Transformer
by: Pan, Zhizhen, et al.
Published: (2026)

Streaming 4D Visual Geometry Transformer
by: Zhuo, Dong, et al.
Published: (2025)

XStreamVGGT: Extremely Memory-Efficient Streaming Vision Geometry Grounded Transformer with KV Cache Compression
by: Su, Zunhai, et al.
Published: (2026)

XStreamVGGT: Extremely Memory-Efficient Streaming Vision Geometry Grounded Transformer with KV Cache Compression
by: Su, Zunhai, et al.
Published: (2026)

TalkingPose: Efficient Face and Gesture Animation with Feedback-guided Diffusion Model
by: Javanmardi, Alireza, et al.
Published: (2025)

Memory-Efficient Vision Transformers: An Activation-Aware Mixed-Rank Compression Strategy
by: Azizi, Seyedarmin, et al.
Published: (2024)

TTSA3R: Training-Free Temporal-Spatial Adaptive Persistent State for Streaming 3D Reconstruction
by: Zheng, Zhijie, et al.
Published: (2026)

vid-TLDR: Training Free Token merging for Light-weight Video Transformer
by: Choi, Joonmyung, et al.
Published: (2024)

MemRoPE: Training-Free Infinite Video Generation via Evolving Memory Tokens
by: Kim, Youngrae, et al.
Published: (2026)

Geometry-Guided 3D Visual Token Pruning for Video-Language Models
by: Li, Han, et al.
Published: (2026)

GC-KBVQA: A New Four-Stage Framework for Enhancing Knowledge Based Visual Question Answering Performance
by: Moradi, Mohammad Mahdi, et al.
Published: (2025)

ConceptPose: Training-Free Zero-Shot Object Pose Estimation using Concept Vectors
by: Kuang, Liming, et al.
Published: (2025)

SSR: A Training-Free Approach for Streaming 3D Reconstruction
by: Deng, Hui, et al.
Published: (2026)