{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/famba-v-fast-vision-mamba-with-cross-layer","title":"Famba-V: Fast Vision Mamba with Cross-Layer Token Fusion","arxiv_id":"2409.09808","date":"2024-09-15","proceeding":null,"authors":["Hui Shen","Zhongwei Wan","Xin Wang","Mi Zhang"],"abstract":"Mamba and Vision Mamba (Vim) models have shown their potential as an alternative to methods based on Transformer architecture. This work introduces Fast Mamba for Vision (Famba-V), a cross-layer token fusion technique to enhance the training efficiency of Vim models. The key idea of Famba-V is to identify and fuse similar tokens across different Vim layers based on a suit of cross-layer strategies instead of simply applying token fusion uniformly across all the layers that existing works propose. We evaluate the performance of Famba-V on CIFAR-100. Our results show that Famba-V is able to enhance the training efficiency of Vim models by reducing both training time and peak memory usage during training. Moreover, the proposed cross-layer strategies allow Famba-V to deliver superior accuracy-efficiency trade-offs. These results all together demonstrate Famba-V as a promising efficiency enhancement technique for Vim models.","url_abs":"https://arxiv.org/abs/2409.09808v3","url_pdf":"https://arxiv.org/pdf/2409.09808v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"famba-v-fast-vision-mamba-with-cross-layer","repo_url":"https://github.com/aiot-mlsys-lab/famba-v","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"mamba","task_name":"Mamba"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"mamba","method_name":"Mamba"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2409.09808","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.09808"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/aiot-mlsys-lab/famba-v","reach":{"status":"ok"}}],"summary":{"ran_fixture":1,"ran_honours":2,"ran":3,"ran_draft_wrong":1,"unverified":2},"by_repo_kind":{"official":{"samples":9,"ran":7,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"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"},"n_pointer_only_for_licence":9,"samples":[{"code_sha256_prefix":"424049f15b90678d","entry":"bipartite_soft_matching","repo":"aiot-mlsys-lab/famba-v","repo_kind":"official","path":"fambav/token_merge.py","file_url":"https://github.com/aiot-mlsys-lab/famba-v/blob/HEAD/fambav/token_merge.py","link_basis":"plan_row","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"424049f15b90678d"}},{"code_sha256_prefix":"f50a8d20efb35c68","entry":"broadcat","repo":"aiot-mlsys-lab/famba-v","repo_kind":"official","path":"fambav/rope.py","file_url":"https://github.com/aiot-mlsys-lab/famba-v/blob/HEAD/fambav/rope.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f50a8d20efb35c68"}},{"code_sha256_prefix":"0595d8b8521fd9ca","entry":"causal_conv1d_ref","repo":"aiot-mlsys-lab/famba-v","repo_kind":"official","path":"causal-conv1d/causal_conv1d/causal_conv1d_interface.py","file_url":"https://github.com/aiot-mlsys-lab/famba-v/blob/HEAD/causal-conv1d/causal_conv1d/causal_conv1d_interface.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"0595d8b8521fd9ca"}},{"code_sha256_prefix":"969e8250d805a154","entry":"do_nothing","repo":"aiot-mlsys-lab/famba-v","repo_kind":"official","path":"fambav/token_merge.py","file_url":"https://github.com/aiot-mlsys-lab/famba-v/blob/HEAD/fambav/token_merge.py","link_basis":"plan_row","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"969e8250d805a154"}},{"code_sha256_prefix":"674be50d432e8846","entry":"kth_bipartite_soft_matching","repo":"aiot-mlsys-lab/famba-v","repo_kind":"official","path":"fambav/token_merge.py","file_url":"https://github.com/aiot-mlsys-lab/famba-v/blob/HEAD/fambav/token_merge.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"674be50d432e8846"}},{"code_sha256_prefix":"4a0feeebf8ac43a8","entry":"new_data_aug_generator","repo":"aiot-mlsys-lab/famba-v","repo_kind":"official","path":"fambav/augment.py","file_url":"https://github.com/aiot-mlsys-lab/famba-v/blob/HEAD/fambav/augment.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"4a0feeebf8ac43a8"}},{"code_sha256_prefix":"58823d9435a8751b","entry":"rotate_half","repo":"aiot-mlsys-lab/famba-v","repo_kind":"official","path":"fambav/rope.py","file_url":"https://github.com/aiot-mlsys-lab/famba-v/blob/HEAD/fambav/rope.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"58823d9435a8751b"}},{"code_sha256_prefix":"80ba95ca0da5ce5f","entry":"build_dataset","repo":"aiot-mlsys-lab/famba-v","repo_kind":"official","path":"fambav/datasets.py","file_url":"https://github.com/aiot-mlsys-lab/famba-v/blob/HEAD/fambav/datasets.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"80ba95ca0da5ce5f"}},{"code_sha256_prefix":"ebeb7b6e20a434cf","entry":"build_transform","repo":"aiot-mlsys-lab/famba-v","repo_kind":"official","path":"fambav/datasets.py","file_url":"https://github.com/aiot-mlsys-lab/famba-v/blob/HEAD/fambav/datasets.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ebeb7b6e20a434cf"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}