{"url":"/task/token-reduction","name":"Token Reduction","slug":"token-reduction","description_markdown":null,"categories":[{"name":"Adversarial","url":"/area/adversarial"},{"name":"Computer Vision","url":"/area/computer-vision"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"derived"},"counts":{"papers_tagged":78,"papers_with_code":37,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":0,"subtasks":0,"parent_tasks":1},"benchmarks":[],"datasets":[],"subtasks":[],"parent_tasks":[{"url":"/task/image-classification","name":"Image Classification"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":37,"tagged_in_all":78,"items":[{"url":"/paper/learning-compact-vision-tokens-for-efficient","title":"Learning Compact Vision Tokens for Efficient Large Multimodal Models","date":"2025-06-08","arxiv_id":"2506.07138","repositories_listed":1,"syntology":null},{"url":"/paper/silvr-a-simple-language-based-video-reasoning","title":"SiLVR: A Simple Language-based Video Reasoning Framework","date":"2025-05-30","arxiv_id":"2505.24869","repositories_listed":1,"syntology":null},{"url":"/paper/one-trajectory-one-token-grounded-video","title":"One Trajectory, One Token: Grounded Video Tokenization via Panoptic Sub-object Trajectory","date":"2025-05-29","arxiv_id":"2505.23617","repositories_listed":1,"syntology":null},{"url":"/paper/flowcut-rethinking-redundancy-via-information","title":"FlowCut: Rethinking Redundancy via Information Flow for Efficient Vision-Language Models","date":"2025-05-26","arxiv_id":"2505.19536","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/token-reduction-should-go-beyond-efficiency","title":"Token Reduction Should Go Beyond Efficiency in Generative Models -- From Vision, Language to Multimodality","date":"2025-05-23","arxiv_id":"2505.18227","repositories_listed":1,"syntology":null},{"url":"/paper/not-all-tokens-are-what-you-need-in-thinking","title":"Not All Tokens Are What You Need In Thinking","date":"2025-05-23","arxiv_id":"2505.17827","repositories_listed":1,"syntology":{"n":2,"n_ran":0,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/crosslmm-decoupling-long-video-sequences-from","title":"CrossLMM: Decoupling Long Video Sequences from LMMs via Dual Cross-Attention Mechanisms","date":"2025-05-22","arxiv_id":"2505.17020","repositories_listed":1,"syntology":null},{"url":"/paper/streamline-without-sacrifice-squeeze-out","title":"Streamline Without Sacrifice -- Squeeze out Computation Redundancy in LMM","date":"2025-05-21","arxiv_id":"2505.15816","repositories_listed":1,"syntology":{"n":9,"n_ran":5,"n_unverified":4,"n_pointer_only":4}},{"url":"/paper/pact-pruning-and-clustering-based-token","title":"PACT: Pruning and Clustering-Based Token Reduction for Faster Visual Language Models","date":"2025-04-11","arxiv_id":"2504.08966","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/window-token-concatenation-for-efficient","title":"Window Token Concatenation for Efficient Visual Large Language Models","date":"2025-04-05","arxiv_id":"2504.04024","repositories_listed":1,"syntology":null},{"url":"/paper/faster-parameter-efficient-tuning-with-token","title":"Faster Parameter-Efficient Tuning with Token Redundancy Reduction","date":"2025-03-26","arxiv_id":"2503.20282","repositories_listed":1,"syntology":null},{"url":"/paper/when-large-vision-language-model-meets-large","title":"When Large Vision-Language Model Meets Large Remote Sensing Imagery: Coarse-to-Fine Text-Guided Token Pruning","date":"2025-03-10","arxiv_id":"2503.07588","repositories_listed":1,"syntology":null},{"url":"/paper/folder-accelerating-multi-modal-large","title":"FOLDER: Accelerating Multi-modal Large Language Models with Enhanced Performance","date":"2025-01-05","arxiv_id":"2501.02430","repositories_listed":1,"syntology":null},{"url":"/paper/cached-adaptive-token-merging-dynamic-token","title":"Cached Adaptive Token Merging: Dynamic Token Reduction and Redundant Computation Elimination in Diffusion Model","date":"2025-01-01","arxiv_id":"2501.00946","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_unverified":0,"n_pointer_only":5}},{"url":"/paper/rethinking-token-reduction-with-parameter","title":"Rethinking Token Reduction with Parameter-Efficient Fine-Tuning in ViT for Pixel-Level Tasks","date":"2025-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/cross-layer-cache-aggregation-for-token","title":"Cross-Layer Cache Aggregation for Token Reduction in Ultra-Fine-Grained Image Recognition","date":"2024-12-31","arxiv_id":"2501.00243","repositories_listed":1,"syntology":null},{"url":"/paper/framefusion-combining-similarity-and","title":"FrameFusion: Combining Similarity and Importance for Video Token Reduction on Large Visual Language Models","date":"2024-12-30","arxiv_id":"2501.01986","repositories_listed":1,"syntology":{"n":13,"n_ran":2,"n_unverified":11,"n_pointer_only":0}},{"url":"/paper/faster-vision-mamba-is-rebuilt-in-minutes-via","title":"Faster Vision Mamba is Rebuilt in Minutes via Merged Token Re-training","date":"2024-12-17","arxiv_id":"2412.12496","repositories_listed":1,"syntology":null},{"url":"/paper/enhancing-multimodal-large-language-models-2","title":"Enhancing Multimodal Large Language Models Complex Reason via Similarity Computation","date":"2024-12-13","arxiv_id":"2412.09817","repositories_listed":1,"syntology":null},{"url":"/paper/learning-to-merge-tokens-via-decoupled","title":"Learning to Merge Tokens via Decoupled Embedding for Efficient Vision Transformers","date":"2024-12-13","arxiv_id":"2412.10569","repositories_listed":1,"syntology":{"n":34,"n_ran":4,"n_unverified":30,"n_pointer_only":4}},{"url":"/paper/token-cropr-faster-vits-for-quite-a-few-tasks","title":"Token Cropr: Faster ViTs for Quite a Few Tasks","date":"2024-12-01","arxiv_id":"2412.00965","repositories_listed":1,"syntology":null},{"url":"/paper/inference-optimal-vlms-need-only-one-visual","title":"Inference Optimal VLMs Need Fewer Visual Tokens and More Parameters","date":"2024-11-05","arxiv_id":"2411.03312","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_unverified":1,"n_pointer_only":2}},{"url":"/paper/longvu-spatiotemporal-adaptive-compression","title":"LongVU: Spatiotemporal Adaptive Compression for Long Video-Language Understanding","date":"2024-10-22","arxiv_id":"2410.17434","repositories_listed":1,"syntology":{"n":11,"n_ran":6,"n_unverified":5,"n_pointer_only":0}},{"url":"/paper/rethinking-token-reduction-for-state-space","title":"Rethinking Token Reduction for State Space Models","date":"2024-10-16","arxiv_id":"2410.14725","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":2}},{"url":"/paper/fastadasp-multitask-adapted-efficient","title":"FastAdaSP: Multitask-Adapted Efficient Inference for Large Speech Language Model","date":"2024-10-03","arxiv_id":"2410.03007","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/discovering-the-gems-in-early-layers","title":"Discovering the Gems in Early Layers: Accelerating Long-Context LLMs with 1000x Input Token Reduction","date":"2024-09-25","arxiv_id":"2409.17422","repositories_listed":1,"syntology":{"n":13,"n_ran":13,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/less-is-more-a-simple-yet-effective-token","title":"Less is More: A Simple yet Effective Token Reduction Method for Efficient Multi-modal LLMs","date":"2024-09-17","arxiv_id":"2409.10994","repositories_listed":1,"syntology":{"n":8,"n_ran":8,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/bridging-local-details-and-global-context-in","title":"Bridging Local Details and Global Context in Text-Attributed Graphs","date":"2024-06-18","arxiv_id":"2406.12608","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/algm-adaptive-local-then-global-token-merging-1","title":"ALGM: Adaptive Local-then-Global Token Merging for Efficient Semantic Segmentation with Plain Vision Transformers","date":"2024-06-14","arxiv_id":"2406.09936","repositories_listed":1,"syntology":{"n":12,"n_ran":6,"n_unverified":6,"n_pointer_only":12}},{"url":"/paper/hierarchical-context-merging-better-long","title":"Hierarchical Context Merging: Better Long Context Understanding for Pre-trained LLMs","date":"2024-04-16","arxiv_id":"2404.10308","repositories_listed":1,"syntology":{"n":15,"n_ran":12,"n_unverified":3,"n_pointer_only":15}}],"syntology_records":16,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}