Cover Image

XStreamVGGT: Extremely Memory-Efficient Streaming Vision Geometry Grounded Transformer with KV Cache Compression

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Su, Zunhai, Ye, Weihao, Feng, Hansen, Fan, Keyu, Zhang, Jing, Yu, Dahai, Liu, Zhengwu, Wong, Ngai
Format:	Preprint
Published:	2026
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

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

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

KVSink: Understanding and Enhancing the Preservation of Attention Sinks in KV Cache Quantization for LLMs
by: Su, Zunhai, et al.
Published: (2025)

CodeComp: Structural KV Cache Compression for Agentic Coding
by: Chen, Qiujiang, et al.
Published: (2026)

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

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

VGGT: Visual Geometry Grounded Transformer
by: Wang, Jianyuan, et al.
Published: (2025)

AKVQ-VL: Attention-Aware KV Cache Adaptive 2-Bit Quantization for Vision-Language Models
by: Su, Zunhai, et al.
Published: (2025)

Binary Weight Multi-Bit Activation Quantization for Compute-in-Memory CNN Accelerators
by: Zhou, Wenyong, et al.
Published: (2025)

NestedKV: Nested Memory Routing for Long-Context KV Cache Compression
by: Chen, Hong, et al.
Published: (2026)

InfiniPot-V: Memory-Constrained KV Cache Compression for Streaming Video Understanding
by: Kim, Minsoo, et al.
Published: (2025)

Training Transformers for KV Cache Compressibility
by: Gelberg, Yoav, et al.
Published: (2026)

RotateKV: Accurate and Robust 2-Bit KV Cache Quantization for LLMs via Outlier-Aware Adaptive Rotations
by: Su, Zunhai, et al.
Published: (2025)

StreamKV: Streaming Video Question-Answering with Segment-based KV Cache Retrieval and Compression
by: Chen, Yilong, et al.
Published: (2025)

LiteVGGT: Boosting Vanilla VGGT via Geometry-aware Cached Token Merging
by: Shu, Zhijian, et al.
Published: (2025)

Reloc-VGGT: Visual Re-localization with Geometry Grounded Transformer
by: Deng, Tianchen, et al.
Published: (2025)

Time and Memory Trade-off of KV-Cache Compression in Tensor Transformer Decoding
by: Chen, Yifang, et al.
Published: (2025)

Decomposing Densification in Gaussian Splatting for Faster 3D Scene Reconstruction
by: Huang, Binxiao, et al.
Published: (2025)

DoPE: Denoising Rotary Position Embedding
by: Xiong, Jing, et al.
Published: (2025)

VGGT-World: Transforming VGGT into an Autoregressive Geometry World Model
by: Sun, Xiangyu, et al.
Published: (2026)

OmniVGGT: Omni-Modality Driven Visual Geometry Grounded Transformer
by: Peng, Haosong, et al.
Published: (2025)

CacheGen: KV Cache Compression and Streaming for Fast Large Language Model Serving
by: Liu, Yuhan, et al.
Published: (2023)

StreamMem: Query-Agnostic KV Cache Memory for Streaming Video Understanding
by: Yang, Yanlai, et al.
Published: (2025)

MuKV: Multi-Grained KV Cache Compression for Long Streaming Video Question-Answering
by: Xiao, Junbin, et al.
Published: (2026)

FlashVGGT: Efficient and Scalable Visual Geometry Transformers with Compressed Descriptor Attention
by: Wang, Zipeng, et al.
Published: (2025)

4DLangVGGT: 4D Language-Visual Geometry Grounded Transformer
by: Wu, Xianfeng, et al.
Published: (2025)

HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding
by: Zhang, Haowei, et al.
Published: (2026)

Q-Filters: Leveraging QK Geometry for Efficient KV Cache Compression
by: Godey, Nathan, et al.
Published: (2025)

Unveiling Super Experts in Mixture-of-Experts Large Language Models
by: Su, Zunhai, et al.
Published: (2025)

Exploring Layer-wise Information Effectiveness for Post-Training Quantization in Small Language Models
by: Xiao, He, et al.
Published: (2025)

The Pitfalls of KV Cache Compression
by: Chen, Alex, et al.
Published: (2025)

HCAttention: Extreme KV Cache Compression via Heterogeneous Attention Computing for LLMs
by: Yang, Dongquan, et al.
Published: (2025)

Mamba-VGGT: Persistent Long-Sequence Video Geometry Grounded Transformer via External Sliding Window Mamba Memory
by: Deng, Tianchen, et al.
Published: (2026)

CaliDrop: KV Cache Compression with Calibration
by: Su, Yi, et al.
Published: (2025)

PackKV: Reducing KV Cache Memory Footprint through LLM-Aware Lossy Compression
by: Jiang, Bo, et al.
Published: (2025)

CktFormalizer: Autoformalization of Natural Language into Circuit Representations
by: Xiong, Jing, et al.
Published: (2026)

GoldFinch: High Performance RWKV/Transformer Hybrid with Linear Pre-Fill and Extreme KV-Cache Compression
by: Goldstein, Daniel, et al.
Published: (2024)

SwiftVGGT: A Scalable Visual Geometry Grounded Transformer for Large-Scale Scenes
by: Lee, Jungho, et al.
Published: (2025)

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

AirCache: Activating Inter-modal Relevancy KV Cache Compression for Efficient Large Vision-Language Model Inference
by: Huang, Kai, et al.
Published: (2025)