arXiv Computer Vision
Video-MemComp: Taylor-Guided Sensitivity-Aware Memory Management for Streaming Video Understanding
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
arXiv AI
Jun 9
OmniMem: Perturbation-aware Memory Compression for Streaming Audio-Visual LLMs
arXiv:2606. 07577v1 Announce Type: new Abstract: Audio-visual large language models (LLMs) hold strong promise for long-form video understanding, yet their long-video inference is fundamentally limited by the linear growth of video tokens and key-value (KV) caches.
arXiv Machine Learning
Oct 12
CORAL-KV: Compact Cross-Layer Prediction and Residual Coding for Autoregressive Video KV Caches
CORAL-KV is a new framework for compressing the key‑value (KV) cache used by autoregressive video diffusion models. It predicts keys and values across cache layers using block‑diagonal‑plus‑low‑rank (block‑DPLR) predictors, then quantizes only the residuals, offering a flexible trade‑off between fidelity and memory usage. In extensive tests on HY‑WorldPlay and MAGI‑1, the reusable configuration outperforms QVG‑4 by up to 4.95 dB PSNR while reducing cache memory by 37–48 %, and the video‑adapted configuration surpasses QVG‑Pro by 3.77 dB PSNR with 33.7 % less memory, all while maintaining comparable latency and reducing temporal discontinuities.
arXiv Computer Vision
1d ago
VAR-Q: Tuning-free KV Cache Quantization for Visual Autoregressive Image and Video Generation
arXiv:2611.05380v1 Announce Type: new Abstract: Visual autoregressive generation spans two dominant paradigms: next-scale prediction for images and video, and next-frame prediction for video. Both de...
arXiv Computer Vision
1d ago
NanoKV: High-Ratio KV Cache Compression for Autoregressive Video Generation
arXiv:2611.06377v1 Announce Type: new Abstract: Autoregressive video models rely on historical key-value (KV) caches to preserve scene consistency over extended rollouts, making KV storage and repeat...
arXiv Computer Vision
Aug 31
Token-Budget Distillation: Transferring Full-Token Semantics to Compressed Video Vision-Language Models
Token-Budget Distillation (TBD) is a parameter‑efficient fine‑tuning framework that adapts video vision‑language models to a fixed token budget. It freezes the pretrained backbone, updates only LoRA adapters, and incorporates FlashVID visual token compression. TBD uses a dual‑path teacher‑student design with full‑token supervision and compressed student optimization, enabling the student to recover full‑token semantics while remaining efficient under aggressive token reduction.
arXiv Computer Vision
Sep 22
PREM: Prefix-Steered Recurrent Memory for Long-Video Understanding
arXiv:2609.23601v1 Announce Type: new Abstract: Long-video understanding must capture transient visual evidence under strict token budgets, yet existing methods compress frames, append memory tokens,...