Pith. sign in

REVIEW 5 cited by

DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2411.15024 v3 pith:E3QNJ6T6 submitted 2024-11-22 cs.CV cs.LG

Keda Tao , Can Qin , Haoxuan You , Yang Sui , Huan Wang This is my paper · ORCID
classification cs.CVcs.LG
keywords tokensdycokevideocompressioninferencevllmsdecodingdifferent
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Video large language models (VLLMs) have significantly advanced recently in processing complex video content, yet their inference efficiency remains constrained because of the high computational cost stemming from the thousands of visual tokens generated from the video inputs. We empirically observe that, unlike single image inputs, VLLMs typically attend visual tokens from different frames at different decoding iterations, making a one-shot pruning strategy prone to removing important tokens by mistake. Motivated by this, we present DyCoke, a training-free token compression method to optimize token representation and accelerate VLLMs. DyCoke incorporates a plug-and-play temporal compression module to minimize temporal redundancy by merging redundant tokens across frames, and applies dynamic KV cache reduction to prune spatially redundant tokens selectively. It ensures high-quality inference by dynamically retaining the critical tokens at each decoding step. Extensive experimental results demonstrate that DyCoke can outperform the prior SoTA counterparts, achieving 1.5X inference speedup, 1.4X memory reduction against the baseline VLLM, while still improving the performance, with no training.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. CRAFT: Compression via Recursive Adaptive Fusion of Video Tokens for Vision-Language Models

    cs.CV 2026-08 conditional novelty 6.0 of 10

    CRAFT recursively merges video tokens with training-free similarity selection plus learnable gated fusion, retaining ~97% of average accuracy at 8x compression across six benchmarks.

  2. AuroraLong: Bringing RNNs Back to Efficient Open-Ended Video Understanding

    cs.CV 2025-07 conditional novelty 6.0 of 10

    A 2B-parameter video-language model using an RWKV linear-RNN backbone and sorted token merging achieves competitive long-video QA accuracy with far lower memory cost than transformer-based models.

  3. LLaVA-Scissor: Token Compression with Semantic Connected Components for Video LLMs

    cs.CV 2025-06 conditional novelty 6.0 of 10

    A training-free token compression method using semantic connected components in space and time keeps video understanding accuracy high even when retaining only 5-10% of visual tokens.

  4. AdaTP: Attention-Debiased Token Pruning for Video Large Language Models

    cs.CV 2025-05 conditional novelty 5.0 of 10

    AdaTP prunes visual tokens in video LLMs by debiasing attention scores, reducing FLOPs to about a quarter of the vanilla model at matching benchmark accuracy.

  5. DynTok: Dynamic Compression of Visual Tokens for Efficient and Effective Video Understanding

    cs.CL 2025-06 conditional novelty 4.0 of 10

    DynTok dynamically merges similar adjacent visual tokens into groups, reducing video token counts to 44.4% with comparable or better video understanding accuracy.

Pith tools