{"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/mixture-of-nested-experts-adaptive-processing","title":"Mixture of Nested Experts: Adaptive Processing of Visual Tokens","arxiv_id":"2407.19985","date":"2024-07-29","proceeding":null,"authors":["Gagan Jain","Nidhi Hegde","Aditya Kusupati","Arsha Nagrani","Shyamal Buch","Prateek Jain","Anurag Arnab","Sujoy Paul"],"abstract":"The visual medium (images and videos) naturally contains a large amount of information redundancy, thereby providing a great opportunity for leveraging efficiency in processing. While Vision Transformer (ViT) based models scale effectively to large data regimes, they fail to capitalize on this inherent redundancy, leading to higher computational costs. Mixture of Experts (MoE) networks demonstrate scalability while maintaining same inference-time costs, but they come with a larger parameter footprint. We present Mixture of Nested Experts (MoNE), which utilizes a nested structure for experts, wherein individual experts fall on an increasing compute-accuracy curve. Given a compute budget, MoNE learns to dynamically choose tokens in a priority order, and thus redundant tokens are processed through cheaper nested experts. Using this framework, we achieve equivalent performance as the baseline models, while reducing inference time compute by over two-fold. We validate our approach on standard image and video datasets - ImageNet-21K, Kinetics400, and Something-Something-v2. We further highlight MoNE$'$s adaptability by showcasing its ability to maintain strong performance across different inference-time compute budgets on videos, using only a single trained model.","url_abs":"https://arxiv.org/abs/2407.19985v2","url_pdf":"https://arxiv.org/pdf/2407.19985v2.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":"mixture-of-nested-experts-adaptive-processing","repo_url":"https://github.com/usryokousha/mone-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"mixture-of-experts","task_name":"Mixture-of-Experts"}],"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":"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"},{"method_slug":"vision-transformer","method_name":"Vision Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2407.19985","atlas_url":"https://app.syntology.ai/?focus=2407.19985","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.19985"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/usryokousha/mone-pytorch","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":6,"ran_fixture":1,"ran_honours":1,"unverified":6},"by_repo_kind":{"listed":{"samples":14,"ran":8,"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":0,"samples":[{"code_sha256_prefix":"e7237603e96b6121","entry":"capacity","repo":"usryokousha/mone-pytorch","repo_kind":"listed","path":"mone_pytorch/layers/routing.py","file_url":"https://github.com/usryokousha/mone-pytorch/blob/HEAD/mone_pytorch/layers/routing.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e7237603e96b6121"}},{"code_sha256_prefix":"c157f5b112b3a392","entry":"drop_path","repo":"usryokousha/mone-pytorch","repo_kind":"listed","path":"mone_pytorch/layers/block.py","file_url":"https://github.com/usryokousha/mone-pytorch/blob/HEAD/mone_pytorch/layers/block.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c157f5b112b3a392"}},{"code_sha256_prefix":"3ee734d9e881f9c6","entry":"experts_choose_masked_contract","repo":"usryokousha/mone-pytorch","repo_kind":"listed","path":"mone_pytorch/layers/experts_choose_linear.py","file_url":"https://github.com/usryokousha/mone-pytorch/blob/HEAD/mone_pytorch/layers/experts_choose_linear.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3ee734d9e881f9c6"}},{"code_sha256_prefix":"3c04490a215299f2","entry":"make_2tuple","repo":"usryokousha/mone-pytorch","repo_kind":"listed","path":"mone_pytorch/layers/mlp.py","file_url":"https://github.com/usryokousha/mone-pytorch/blob/HEAD/mone_pytorch/layers/mlp.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3c04490a215299f2"}},{"code_sha256_prefix":"dbdf6fbba8af2996","entry":"named_apply","repo":"usryokousha/mone-pytorch","repo_kind":"listed","path":"mone_pytorch/models/vision_transformer.py","file_url":"https://github.com/usryokousha/mone-pytorch/blob/HEAD/mone_pytorch/models/vision_transformer.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"dbdf6fbba8af2996"}},{"code_sha256_prefix":"d038c3fd8fece745","entry":"nested_linear_expand","repo":"usryokousha/mone-pytorch","repo_kind":"listed","path":"mone_pytorch/layers/nested_experts_linear.py","file_url":"https://github.com/usryokousha/mone-pytorch/blob/HEAD/mone_pytorch/layers/nested_experts_linear.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d038c3fd8fece745"}},{"code_sha256_prefix":"9233bff4190475e0","entry":"normalize","repo":"usryokousha/mone-pytorch","repo_kind":"listed","path":"mone_pytorch/layers/routing.py","file_url":"https://github.com/usryokousha/mone-pytorch/blob/HEAD/mone_pytorch/layers/routing.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9233bff4190475e0"}},{"code_sha256_prefix":"ae348fbef238474c","entry":"scatter_experts","repo":"usryokousha/mone-pytorch","repo_kind":"listed","path":"mone_pytorch/layers/experts_choose_linear.py","file_url":"https://github.com/usryokousha/mone-pytorch/blob/HEAD/mone_pytorch/layers/experts_choose_linear.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ae348fbef238474c"}},{"code_sha256_prefix":"a76eb25a07812d98","entry":"combine","repo":"usryokousha/mone-pytorch","repo_kind":"listed","path":"mone_pytorch/layers/expert_linear.py","file_url":"https://github.com/usryokousha/mone-pytorch/blob/HEAD/mone_pytorch/layers/expert_linear.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a76eb25a07812d98"}},{"code_sha256_prefix":"791ac5ddd6e8c4b3","entry":"compute_capacity_distribution","repo":"usryokousha/mone-pytorch","repo_kind":"listed","path":"mone_pytorch/layers/routing.py","file_url":"https://github.com/usryokousha/mone-pytorch/blob/HEAD/mone_pytorch/layers/routing.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"791ac5ddd6e8c4b3"}},{"code_sha256_prefix":"42df7ba0cf9e47df","entry":"dispatch","repo":"usryokousha/mone-pytorch","repo_kind":"listed","path":"mone_pytorch/layers/expert_linear.py","file_url":"https://github.com/usryokousha/mone-pytorch/blob/HEAD/mone_pytorch/layers/expert_linear.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"42df7ba0cf9e47df"}},{"code_sha256_prefix":"65bb5b2b0e53a855","entry":"gather_experts","repo":"usryokousha/mone-pytorch","repo_kind":"listed","path":"mone_pytorch/layers/experts_choose_linear.py","file_url":"https://github.com/usryokousha/mone-pytorch/blob/HEAD/mone_pytorch/layers/experts_choose_linear.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"65bb5b2b0e53a855"}},{"code_sha256_prefix":"65105560b1984ac3","entry":"nested_linear_contract","repo":"usryokousha/mone-pytorch","repo_kind":"listed","path":"mone_pytorch/layers/nested_experts_linear.py","file_url":"https://github.com/usryokousha/mone-pytorch/blob/HEAD/mone_pytorch/layers/nested_experts_linear.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"65105560b1984ac3"}},{"code_sha256_prefix":"665512f1103be8ea","entry":"nested_mlp","repo":"usryokousha/mone-pytorch","repo_kind":"listed","path":"mone_pytorch/layers/nested_experts_linear.py","file_url":"https://github.com/usryokousha/mone-pytorch/blob/HEAD/mone_pytorch/layers/nested_experts_linear.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"665512f1103be8ea"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}