InfiniPot-V: Memory-Constrained KV Cache Compression for Streaming Video Understanding

• URL: http://arxiv.org/abs/2506.15745v2
• Date: Fri, 24 Oct 2025 05:39:03 GMT
• Title: InfiniPot-V: Memory-Constrained KV Cache Compression for Streaming Video Understanding
• Authors: Minsoo Kim, Kyuhong Shim, Jungwook Choi, Simyung Chang,
• Abstract summary: InfiniPot-V is the first training-free, query-agnostic framework that enforces a hard, length-independent memory cap for streaming video understanding.<n>It cuts peak GPU memory by up to 94%, sustains real-time generation, and matches or surpasses full-cache accuracy-even in multi-turn dialogues.
• Score: 26.408842739663346
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Modern multimodal large language models (MLLMs) can reason over hour-long video, yet their key-value (KV) cache grows linearly with time-quickly exceeding the fixed memory of phones, AR glasses, and edge robots. Prior compression schemes either assume the whole video and user query are available offline or must first build the full cache, so memory still scales with stream length. InfiniPot-V is the first training-free, query-agnostic framework that enforces a hard, length-independent memory cap for streaming video understanding. During video encoding it monitors the cache and, once a user-set threshold is reached, runs a lightweight compression pass that (i) removes temporally redundant tokens via Temporal-axis Redundancy (TaR) metric and (ii) keeps semantically significant tokens via Value-Norm (VaN) ranking. Across four open-source MLLMs and four long-video and streaming-video benchmarks, InfiniPot-V cuts peak GPU memory by up to 94%, sustains real-time generation, and matches or surpasses full-cache accuracy-even in multi-turn dialogues. By dissolving the KV cache bottleneck without retraining or query knowledge, InfiniPot-V closes the gap for on-device streaming video assistants.

Related papers

• Quant VideoGen: Auto-Regressive Long Video Generation via 2-Bit KV-Cache Quantization [83.406036390582]
  Quant VideoGen (QVG) is a training free KV cache quantization framework for autoregressive video diffusion models.<n>It reduces KV memory by up to 7.0 times with less than 4% end to end latency overhead.<n>It consistently outperforms existing baselines in generation quality.
  arXiv  Detail & Related papers  (2026-02-03T00:54:32Z)
• HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding [92.59317281526239]
  HERMES is a training-free architecture for real-time and accurate understanding of video streams.<n>Hermes reuses a compact KV cache, enabling efficient streaming understanding under resource constraints.<n>Hermes achieves superior or comparable accuracy across all benchmarks, with up to 11.4% gains on streaming datasets.
  arXiv  Detail & Related papers  (2026-01-21T07:26:15Z)
• CacheFlow: Compressive Streaming Memory for Efficient Long-Form Video Understanding [0.0]
  CacheFlow is a training-free pipeline that pairs Dynamic Token Dropping with a long-term memory.<n>Online, per-frame processing makes our approach fundamentally suited for live streaming VQA.<n>At inference, a consensus-based retrieval mechanism retrieves only the Top-K most relevant blocks.
  arXiv  Detail & Related papers  (2025-11-17T17:56:14Z)
• KVSwap: Disk-aware KV Cache Offloading for Long-Context On-device Inference [6.159622195480178]
  Language models (LMs) underpin emerging mobile and embedded AI applications like meeting and video summarization and document analysis.<n>Long-context inference quickly hits a emphmemory capacity wall as the key-value ( KV) cache grows linearly with context length and batch size.<n>We present KVSwap, a software framework to break this memory wall by offloading the KV cache to non-volatile secondary storage (disk)<n> KVSwap delivers higher throughput under tight memory budgets while maintaining the generation quality when compared with existing KV cache offloading schemes.
  arXiv  Detail & Related papers  (2025-11-14T22:37:57Z)
• video-SALMONN S: Streaming Audio-Visual LLMs Beyond Length Limits via Memory [51.03819128505358]
  Video-SALMONN S is first to process 3-hour videos at 1 FPS and 360p resolution under a fixed memory budget.<n>A test-time-training memory module continually updates token representations to capture long-range dependencies.<n>A prompt-dependent memory reader retrieves context-relevant content from fixed-size memory.
  arXiv  Detail & Related papers  (2025-10-13T08:20:15Z)
• StreamMem: Query-Agnostic KV Cache Memory for Streaming Video Understanding [14.50396424661833]
  StreamMem is a query-agnostic KV cache memory mechanism for streaming video understanding.<n>It achieves state-of-the-art performance in query-agnostic KV cache compression and is competitive with query-aware compression approaches.
  arXiv  Detail & Related papers  (2025-08-21T16:56:29Z)
• CRAM: Large-scale Video Continual Learning with Bootstrapped Compression [4.304743423080129]
  Continual learning (CL) promises to allow neural networks to learn from continuous streams of inputs, instead of IID (independent and identically distributed) sampling.<n>We focus on video CL employing a rehearsal-based approach, which reinforces past samples from a memory buffer.<n>We propose a scheme to deal with this forgetting by refreshing video codes, which requires careful decompression with a previous version of the network and recompression with a new one.
  arXiv  Detail & Related papers  (2025-08-07T03:32:20Z)
• QuickVideo: Real-Time Long Video Understanding with System Algorithm Co-Design [54.38970077613728]
  Long-video understanding has emerged as a crucial capability in real-world applications such as video surveillance, meeting summarization, educational lecture analysis, and sports broadcasting.<n>We propose QuickVideo, a system-algorithm co-design that substantially accelerates long-video understanding to support real-time downstream applications.
  arXiv  Detail & Related papers  (2025-05-22T03:26:50Z)
• dKV-Cache: The Cache for Diffusion Language Models [53.85291644298835]
  Diffusion Language Models (DLMs) have been seen as a promising competitor for autoregressive language models.<n>We propose a KV-cache-like mechanism, delayed KV-Cache, for the denoising process of DLMs.<n>Our approach is motivated by the observation that different tokens have distinct representation dynamics throughout the diffusion process.
  arXiv  Detail & Related papers  (2025-05-21T17:32:10Z)
• SpeCache: Speculative Key-Value Caching for Efficient Generation of LLMs [44.41154292836592]
  We propose SpeCache, which offloads the complete KV cache and dynamically fetches KV pairs back in each decoding step.<n> Experiments on LongBench and Needle-in-a-Haystack benchmarks verify that SpeCache effectively reduces VRAM usage.
  arXiv  Detail & Related papers  (2025-03-20T14:01:56Z)
• ReTaKe: Reducing Temporal and Knowledge Redundancy for Long Video Understanding [55.320254859515714]
  ReTaKe enables VideoLLMs to process 8 times longer frames (up to 2048), similar-sized models by 3-5% and even rivaling much larger ones on VideoMME, MLVU, LongVideoBench, and LVBench.<n>Our code is available at https://github.com/SCZwangxiao/video-ReTaKe.
  arXiv  Detail & Related papers  (2024-12-29T15:42:24Z)
• ShadowKV: KV Cache in Shadows for High-Throughput Long-Context LLM Inference [25.638980944695728]
  ShadowKV is an efficient long-context large language models (LLMs) inference system.<n>It stores the low-rank key cache and offloads the value cache to reduce the memory footprint for larger batch sizes and longer sequences.<n>It can support up to 6$times$ larger batch sizes and boost throughput by up to 3.04$times$ on an A100 GPU.
  arXiv  Detail & Related papers  (2024-10-28T19:08:12Z)
• Streaming Long Video Understanding with Large Language Models [83.11094441893435]
  VideoStreaming is an advanced vision-language large model (VLLM) for video understanding. It capably understands arbitrary-length video with a constant number of video streaming tokens encoded and propagatedly selected. Our model achieves superior performance and higher efficiency on long video benchmarks.
  arXiv  Detail & Related papers  (2024-05-25T02:22:09Z)
• Get More with LESS: Synthesizing Recurrence with KV Cache Compression for Efficient LLM Inference [78.65321721142624]
  We focus on a memory bottleneck imposed by the key-value ( KV) cache. Existing KV cache methods approach this problem by pruning or evicting large swaths of relatively less important KV pairs. We propose LESS, a simple integration of a constant sized cache with eviction-based cache methods.
  arXiv  Detail & Related papers  (2024-02-14T18:54:56Z)
• CacheGen: KV Cache Compression and Streaming for Fast Large Language Model Serving [31.766738294505767]
  CacheGen is a fast context-loading module for large language models. Uses a custom tensor encoder to encode a KV cache into compact bitstream representations. adapts the compression level of different parts of a KV cache to cope with changes in available bandwidth.
  arXiv  Detail & Related papers  (2023-10-11T07:08:20Z)
• READMem: Robust Embedding Association for a Diverse Memory in Unconstrained Video Object Segmentation [24.813416082160224]
  We present READMem, a modular framework for sVOS methods to handle unconstrained videos. We propose a robust association of the embeddings stored in the memory with query embeddings during the update process. Our approach achieves competitive results on the Long-time Video dataset (LV1) while not hindering performance on short sequences.
  arXiv  Detail & Related papers  (2023-05-22T08:31:16Z)
• MeMViT: Memory-Augmented Multiscale Vision Transformer for Efficient Long-Term Video Recognition [74.35009770905968]
  We build a memory-augmented vision transformer that has a temporal support 30x longer than existing models. MeMViT obtains state-of-the-art results on the AVA, EPIC-Kitchens-100 action classification, and action anticipation datasets.
  arXiv  Detail & Related papers  (2022-01-20T18:59:54Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.