Browse State-of-the-Art › Token Reduction
Token Reduction
37 papers with code · 0 benchmarks · 0 datasets archive 2025-07-28
Benchmarks archive 2025-07-28
No benchmark for this task in the archive.
Libraries
Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.
Datasets archive 2025-07-28
No dataset record in the archive lists this task.
Subtasks archive 2025-07-28
No subtask under this task in the archive's task tree.
Parent tasks archive 2025-07-28
Papers archive 2025-07-28
archive papers tagged: 78 · with a code link: 37 · where Syntology ran a sample: 21 (15 with a run with no instrument failure, 6 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (21 of 78 tagged: 15 with a run with no instrument failure, 6 where every run was a failure of Syntology's instrument)
Page 1 of 1: papers 1 to 78 of 78, in archive order: by repositories listed in the archive (most first), then newest first, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers that list no repository come after every paper that lists one.
Papers without a page here are shown as plain text. A Syntology line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code); hover it for the repositories the samples that ran came from. The first sentence of the abstract is shown for the first 30 papers; every abstract is on its paper's page.
-
8 Jun 2025 1 repository listedSpecifically, we propose a Spatial Token Fusion (STF) method to learn compact vision tokens for short vision token sequence, where spatial-adjacent tokens are fused into one.
-
30 May 2025 1 repository listedIn the second stage, language descriptions are fed into a powerful reasoning LLM to solve complex video-language understanding tasks.
-
29 May 2025 1 repository listedWe introduce grounded video tokenization, a paradigm that organizes tokens based on panoptic sub-object trajectories rather than fixed patches.
-
26 May 2025 1 repository listed Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample)However, as the interaction between tokens and layers is complicated, this raises a basic question: Is such a simple single-layer criterion sufficient to identify redundancy?
-
23 May 2025 1 repository listed Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 2 harvested samples)Modern reasoning models, such as OpenAI's o1 and DeepSeek-R1, exhibit impressive problem-solving capabilities but suffer from critical inefficiencies: high inference latency, excessive computational resource…
-
23 May 2025 1 repository listedWe highlight its potential to drive new model architectures and learning strategies that improve robustness, increase interpretability, and better align with the objectives of generative modeling.
-
22 May 2025 1 repository listedIn this paper, we introduce CrossLMM, decoupling long video sequences from LMMs via a dual cross-attention mechanism, which substantially reduces visual token quantity with minimal performance degradation.
-
21 May 2025 1 repository listed Syntology official (archive's flag): 1 ran · 5 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 4 unverified (of 9 harvested samples) · 4 pointer-only (licence)Unlike token reduction methods that focus on token-level redundancy, we identify and study the computation-level redundancy on vision tokens to ensure no information loss.
-
11 Apr 2025 1 repository listed Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified (of 2 harvested samples)Visual Language Models require substantial computational resources for inference due to the additional input tokens needed to represent visual information.
-
5 Apr 2025 1 repository listedTo further enhance the performance on fine-grained visual understanding tasks, we introduce WiCo+, which decomposes the visual tokens in later layers of the LLM.
-
26 Mar 2025 1 repository listedParameter-efficient tuning (PET) aims to transfer pre-trained foundation models to downstream tasks by learning a small number of parameters.
-
10 Mar 2025 1 repository listedTo preserve image details while reducing computational complexity, we propose a text-guided token pruning method with Dynamic Image Pyramid (DIP) integration.
-
5 Jan 2025 1 repository listedRecently, Multi-modal Large Language Models (MLLMs) have shown remarkable effectiveness for multi-modal tasks due to their abilities to generate and understand cross-modal data.
-
1 Jan 2025 1 repository listed Syntology official (archive's flag): 5 ran · 5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified (of 5 harvested samples) · 5 pointer-only (licence)Diffusion models have emerged as a promising approach for generating high-quality, high-dimensional images.
-
1 Jan 2025 1 repository listedParameter-efficient fine-tuning (PEFT) adapts pre-trained models to new tasks by updating only a small subset of parameters, achieving efficiency but still facing significant inference costs driven by input token length.
-
31 Dec 2024 1 repository listedUltra-fine-grained image recognition (UFGIR) is a challenging task that involves classifying images within a macro-category.
-
30 Dec 2024 1 repository listed Syntology official (archive's flag): 10 ran · 10 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified (of 13 harvested samples) · 1 pointer-only (licence)Leveraging the unique properties of similarity over importance, we introduce FrameFusion, a novel approach that combines similarity-based merging with importance-based pruning for better token reduction in LVLMs.
-
17 Dec 2024 1 repository listedRe-training the token-reduced model enhances the performance of Mamba, by effectively rebuilding the key knowledge.
-
13 Dec 2024 1 repository listedMultimodal large language models have experienced rapid growth, and numerous different models have emerged.
-
13 Dec 2024 1 repository listed Syntology official (archive's flag): 2 ran · 28 ran (of which 1 constructed an object rather than computing a result; 12 with no instrument failure: 1 honoured, 0 violated, 11 with no contract checked; 16 where Syntology's instrument failed) · 6 unverified (of 34 harvested samples) · 4 pointer-only (licence)Our method introduces a lightweight embedding module decoupled from the ViT forward pass to extract dedicated features for token merging, thereby addressing the restriction from using intermediate features.
-
1 Dec 2024 1 repository listedThe adoption of Vision Transformers (ViTs) in resource-constrained applications necessitates improvements in inference throughput.
-
5 Nov 2024 1 repository listed Syntology official: harvested, nothing ran · 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified (of 2 harvested samples) · 2 pointer-only (licence)Our results reveal a surprising trend: for visual reasoning tasks, the inference-optimal behavior in VLMs is achieved by using the largest LLM that fits within the inference budget while minimizing visual token count -…
-
22 Oct 2024 1 repository listed Syntology official (archive's flag): 11 ran · 11 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 8 where Syntology's instrument failed) · 0 unverified (of 11 harvested samples) · 2 pointer-only (licence)Given a light-weight LLM, our LongVU also scales effectively into a smaller size with state-of-the-art video understanding performance.
-
16 Oct 2024 1 repository listed Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified (of 2 harvested samples) · 2 pointer-only (licence)While token reduction techniques offer a straightforward post-training strategy, we find that applying existing methods directly to SSMs leads to substantial performance drops.
-
3 Oct 2024 1 repository listed Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified (of 3 harvested samples) · 3 pointer-only (licence)In this study, we aim to explore Multitask Speech Language Model (SpeechLM) efficient inference via token reduction.
-
25 Sep 2024 1 repository listed Syntology official (archive's flag): 13 ran · 13 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 1 violated, 8 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified (of 13 harvested samples) · 3 pointer-only (licence)Our research introduces a novel approach for the long context bottleneck to accelerate LLM inference and reduce GPU memory consumption.
-
17 Sep 2024 1 repository listed Syntology official (archive's flag): 8 ran · 8 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 6 where Syntology's instrument failed) · 0 unverified (of 8 harvested samples) · 1 pointer-only (licence)The rapid advancement of Multimodal Large Language Models (MLLMs) has led to remarkable performances across various domains.
-
18 Jun 2024 1 repository listed Syntology official (archive's flag): 1 ran · 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result (of 1 harvested sample) · 1 pointer-only (licence)Representation learning on text-attributed graphs (TAGs) is vital for real-world applications, as they combine semantic textual and contextual structural information.
-
14 Jun 2024 1 repository listed Syntology official (archive's flag): 7 ran · 7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 3 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified (of 12 harvested samples) · 12 pointer-only (licence)This work presents Adaptive Local-then-Global Merging (ALGM), a token reduction method for semantic segmentation networks that use plain Vision Transformers.
-
16 Apr 2024 1 repository listed Syntology official (archive's flag): 12 ran · 12 ran (of which 1 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 5 where Syntology's instrument failed) · 3 unverified (of 15 harvested samples) · 15 pointer-only (licence)Large language models (LLMs) have shown remarkable performance in various natural language processing tasks.
-
10 Jan 2024 1 repository listed
-
9 Aug 2023 1 repository listed Syntology 8 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 5 where Syntology's instrument failed) · 0 unverified (of 8 harvested samples) · 3 pointer-only (licence)
-
3 Jun 2023 1 repository listed
-
27 May 2023 1 repository listed Syntology official (archive's flag): 3 ran · 3 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 3 harvested samples)
-
14 Dec 2021 1 repository listed Syntology 6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified (of 7 harvested samples) · 7 pointer-only (licence)
-
25 May 2021 1 repository listed
-
Token Transforming: A Unified and Training-Free Token Compression Framework for Vision Transformer Acceleration6 Jun 2025 0 repositories listed
-
Astraea: A GPU-Oriented Token-wise Acceleration Framework for Video Diffusion Transformers5 Jun 2025 0 repositories listed
-
Towards Storage-Efficient Visual Document Retrieval: An Empirical Study on Reducing Patch-Level Embeddings5 Jun 2025 0 repositories listed
-
VScan: Rethinking Visual Token Reduction for Efficient Large Vision-Language Models28 May 2025 0 repositories listed
-
The Overthinker's DIET: Cutting Token Calories with DIfficulty-AwarE Training25 May 2025 0 repositories listed
-
Plan and Budget: Effective and Efficient Test-Time Scaling on Large Language Model Reasoning22 May 2025 0 repositories listed
-
DRP: Distilled Reasoning Pruning with Skill-aware Step Decomposition for Efficient Large Reasoning Models20 May 2025 0 repositories listed
-
STAR: Stage-Wise Attention-Guided Token Reduction for Efficient Large Vision-Language Models Inference18 May 2025 0 repositories listed
-
16 May 2025 0 repositories listed Syntology 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample) · 1 pointer-only (licence)
-
EcoSafeRAG: Efficient Security through Context Analysis in Retrieval-Augmented Generation16 May 2025 0 repositories listed
-
Hypernym Mercury: Token Optimization Through Semantic Field Constriction And Reconstruction From Hypernyms. A New Text Compression Method12 May 2025 0 repositories listed
-
DyMU: Dynamic Merging and Virtual Unmerging for Efficient VLMs23 Apr 2025 0 repositories listed
-
ZipR1: Reinforcing Token Sparsity in MLLMs23 Apr 2025 0 repositories listed
-
Dynamic Compressing Prompts for Efficient Inference of Large Language Models15 Apr 2025 0 repositories listed
-
Efficient LLaMA-3.2-Vision by Trimming Cross-attended Visual Features1 Apr 2025 0 repositories listed
-
Local Information Matters: Inference Acceleration For Grounded Conversation Generation Models Through Adaptive Local-Aware Token Pruning31 Mar 2025 0 repositories listed
-
Token Dynamics: Towards Efficient and Dynamic Video Token Representation for Video Large Language Models21 Mar 2025 0 repositories listed
-
Vamba: Understanding Hour-Long Videos with Hybrid Mamba-Transformers14 Mar 2025 0 repositories listed
-
Layton: Latent Consistency Tokenizer for 1024-pixel Image Reconstruction and Generation by 256 Tokens11 Mar 2025 0 repositories listed
-
Does Acceleration Cause Hidden Instability in Vision Language Models? Uncovering Instance-Level Divergence Through a Large-Scale Empirical Study9 Mar 2025 0 repositories listed
-
BatchGEMBA: Token-Efficient Machine Translation Evaluation with Batched Prompting and Prompt Compression4 Mar 2025 0 repositories listed
-
Knowing When to Stop: Dynamic Context Cutoff for Large Language Models3 Feb 2025 0 repositories listed
-
MINT: Mitigating Hallucinations in Large Vision-Language Models via Token Reduction2 Feb 2025 0 repositories listed
-
Learning Free Token Reduction for Multi-Modal Large Language Models29 Jan 2025 0 repositories listed
-
Dynamic Token Reduction during Generation for Vision Language Models24 Jan 2025 0 repositories listed
-
AdaFV: Rethinking of Visual-Language alignment for VLM acceleration16 Jan 2025 0 repositories listed
-
ImagePiece: Content-aware Re-tokenization for Efficient Image Recognition21 Dec 2024 0 repositories listed
-
Deploying Foundation Model Powered Agent Services: A Survey18 Dec 2024 0 repositories listed
-
AsymRnR: Video Diffusion Transformers Acceleration with Asymmetric Reduction and Restoration16 Dec 2024 0 repositories listed
-
TRIM: Token Reduction and Inference Modeling for Cost-Effective Language Generation10 Dec 2024 0 repositories listed
-
Accelerating Multimodal Large Language Models by Searching Optimal Vision Token Reduction30 Nov 2024 0 repositories listed
-
Efficient Multi-modal Large Language Models via Visual Token Grouping26 Nov 2024 0 repositories listed
-
Rethinking Token Reduction in MLLMs: Towards a Unified Paradigm for Training-Free Acceleration26 Nov 2024 0 repositories listed
-
freePruner: A Training-free Approach for Large Multimodal Model Acceleration23 Nov 2024 0 repositories listed
-
PAR: Prompt-Aware Token Reduction Method for Efficient Large Multimodal Models9 Oct 2024 0 repositories listed
-
Cut the Crap: An Economical Communication Pipeline for LLM-based Multi-Agent Systems3 Oct 2024 0 repositories listed
-
Vote&Mix: Plug-and-Play Token Reduction for Efficient Vision Transformer30 Aug 2024 0 repositories listed
-
FIT-RAG: Black-Box RAG with Factual Information and Token Reduction21 Mar 2024 0 repositories listed
-
TPC-ViT: Token Propagation Controller for Efficient Vision Transformer3 Jan 2024 0 repositories listed
-
25 Mar 2023 0 repositories listed
-
TORE: Token Reduction for Efficient Human Mesh Recovery with Transformer19 Nov 2022 0 repositories listed
Syntology lines on 21 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced; each line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
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