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

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

22 Nov 2024CVPR 2025 1arXiv:2411.15024archive 2025-07-28

Keda Tao, Can Qin, Haoxuan You, Yang Sui, Huan Wang

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.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2411.15024")

Code

Syntology Ran 6 of 14 code samples harvested from 1 repository linked to this paper; 8 have no recorded run. Of those that ran: 1 ran · violated contract; 3 ran · our draft was wrong; 2 ran · fixture could not drive it.

By repository: official repository: 11 samples from 1 repository, 4 ran; 3 identical to code first harvested elsewhere. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

kd-tao/dycoke officialmentioned in papermentioned on GitHubpytorchApache-2.0 report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

14 samples harvested; 6 ran; 0 honoured the contract we drafted; 8 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · violated contract
3ran · our draft was wrong
2ran · fixture could not drive it
8unverified

Licence: 3 of the 14 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from kd-tao/dycoke. Some samples are identical code Syntology first harvested from another repository; for those, this paper's copy is not located and its licence is not recorded. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

extract_patches kd-tao/dycoke/llava/mm_utils.py official repository ran · fixture could not drive it Apache-2.0 (permissive) · b0a851cae92754ff · report
get_chunk kd-tao/dycoke/llava/eval/model_vqa.py official repository ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 42a46570620cd9fa · report
split_list kd-tao/dycoke/llava/eval/model_vqa.py official repository ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 076c252c52cbb161 · report
unpad_image kd-tao/dycoke/llava/model/llava_arch.py official repository ran · fixture could not drive it fingerprinted Apache-2.0 (permissive) · 7606525af238fb64 · report
auto_pad_images kd-tao/dycoke/llava/mm_utils.py official repository unverified Apache-2.0 (permissive) · 3c8823948724e269 · report
convert_to_scalar kd-tao/dycoke/trl/core.py official repository unverified Apache-2.0 (permissive) · c32b636f13ed9ee5 · report
dycole_ttm kd-tao/dycoke/llava/model/llava_arch.py official repository unverified Apache-2.0 (permissive) · 624d0786b7143686 · report
flatten_dict kd-tao/dycoke/trl/core.py official repository unverified Apache-2.0 (permissive) · a51ae45a1f6c0b5b · report
resize_and_center_crop kd-tao/dycoke/llava/mm_utils.py official repository unverified Apache-2.0 (permissive) · c80358dff96c25ce · report
safe_load_tokenizer kd-tao/dycoke/llava/conversation.py official repository unverified Apache-2.0 (permissive) · b20705b0dfd77ffc · report
top_k_top_p_filtering kd-tao/dycoke/trl/core.py official repository unverified Apache-2.0 (permissive) · 2c3da386578af970 · report
convert_to_custom_text_state_dict identical code first harvested elsewhere ran · violated contract licence of this copy not recorded · 7bff6f3b3cb560e7 · report
get_cast_dtype identical code first harvested elsewhere ran · our draft was wrong licence of this copy not recorded · dcd422d66b0581d8 · report
build_model_from_openai_state_dict identical code first harvested elsewhere unverified licence of this copy not recorded · 275eb8fe6104bf3a · report

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Pruning

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections