{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/method/early-exiting","slug":"early-exiting","name":"Early exiting","full_name":"Early exiting using confidence measures","full_name_withheld":false,"description_markdown":"Exit whenever the model is confident enough allowing early exiting from hidden layers","description_state":"present","introduced_year":null,"introduced_by":{"title":"BranchyNet: Fast Inference via Early Exiting from Deep Neural Networks","paper":"/paper/branchynet-fast-inference-via-early-exiting","first_author":"Surat Teerapittayanon","n_authors":3,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/branchynet-fast-inference-via-early-exiting"},"source":{"url":"http://arxiv.org/abs/1709.01686v1","title":"BranchyNet: Fast Inference via Early Exiting from Deep Neural Networks","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"General","area_id":"general","collection":"Loss Functions","url":"/methods/category/loss-functions","pwc_aliases":[]}],"n_papers_tagged":66,"archive_num_papers":66,"papers_newest_first":[{"paper":null,"slug":"early-stopping-tabular-in-context-learning","title":"Early Stopping Tabular In-Context Learning","date":"2025-06-26","arxiv_id":"2506.21387","n_code_links":0,"syntology":null},{"paper":null,"slug":"languages-in-multilingual-speech-foundation","title":"Languages in Multilingual Speech Foundation Models Align Both Phonetically and Semantically","date":"2025-05-26","arxiv_id":"2505.19606","n_code_links":0,"syntology":null},{"paper":null,"slug":"system-1-5-reasoning-traversal-in-language","title":"System-1.5 Reasoning: Traversal in Language and Latent Spaces with Dynamic Shortcuts","date":"2025-05-25","arxiv_id":"2505.18962","n_code_links":0,"syntology":null},{"paper":null,"slug":"performance-control-in-early-exiting-to","title":"Performance Control in Early Exiting to Deploy Large Models at the Same Cost of Smaller Ones","date":"2024-12-26","arxiv_id":"2412.19325","n_code_links":0,"syntology":null},{"paper":"/paper/cosee-consistency-oriented-signal-based-early","slug":"cosee-consistency-oriented-signal-based-early","title":"COSEE: Consistency-Oriented Signal-Based Early Exiting via Calibrated Sample Weighting Mechanism","date":"2024-12-17","arxiv_id":"2412.13236","n_code_links":1,"syntology":null},{"paper":"/paper/a-stitch-in-time-saves-nine-small-vlm-is-a","slug":"a-stitch-in-time-saves-nine-small-vlm-is-a","title":"A Stitch in Time Saves Nine: Small VLM is a Precise Guidance for Accelerating Large VLMs","date":"2024-12-04","arxiv_id":"2412.03324","n_code_links":1,"syntology":{"ran":4,"of":5,"n_ran_checked":4,"n_instrument":0,"unverified":1,"pointer_only":5,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 2 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["NUS-HPC-AI-Lab/SGL"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["unlocated"]}}},{"paper":null,"slug":"energy-aware-dynamic-neural-inference","title":"Energy-Aware Dynamic Neural Inference","date":"2024-11-04","arxiv_id":"2411.02471","n_code_links":0,"syntology":null},{"paper":null,"slug":"berter-the-efficient-one","title":"BERTer: The Efficient One","date":"2024-07-19","arxiv_id":"2407.14039","n_code_links":0,"syntology":null},{"paper":null,"slug":"on-layer-wise-representation-similarity","title":"Tracing Representation Progression: Analyzing and Enhancing Layer-Wise Similarity","date":"2024-06-20","arxiv_id":"2406.14479","n_code_links":0,"syntology":null},{"paper":null,"slug":"predicting-probabilities-of-error-to-combine","title":"Predicting Probabilities of Error to Combine Quantization and Early Exiting: QuEE","date":"2024-06-20","arxiv_id":"2406.14404","n_code_links":0,"syntology":null},{"paper":null,"slug":"raee-a-training-free-retrieval-augmented","title":"RAEE: A Robust Retrieval-Augmented Early Exiting Framework for Efficient Inference","date":"2024-05-24","arxiv_id":"2405.15198","n_code_links":0,"syntology":null},{"paper":"/paper/a-comprehensive-survey-of-accelerated","slug":"a-comprehensive-survey-of-accelerated","title":"A Comprehensive Survey of Accelerated Generation Techniques in Large Language Models","date":"2024-05-15","arxiv_id":"2405.13019","n_code_links":1,"syntology":null},{"paper":null,"slug":"computational-efficient-width-wise-early","title":"Computational Efficient Width-Wise Early Exiting in Wireless Communication Systems","date":"2024-05-06","arxiv_id":"2405.03222","n_code_links":0,"syntology":null},{"paper":"/paper/kangaroo-lossless-self-speculative-decoding","slug":"kangaroo-lossless-self-speculative-decoding","title":"Kangaroo: Lossless Self-Speculative Decoding via Double Early Exiting","date":"2024-04-29","arxiv_id":"2404.18911","n_code_links":1,"syntology":{"ran":4,"of":6,"n_ran_checked":1,"n_instrument":3,"unverified":2,"pointer_only":6,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","official":{"repos":["Equationliu/Kangaroo"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/layer-skip-enabling-early-exit-inference-and","slug":"layer-skip-enabling-early-exit-inference-and","title":"LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding","date":"2024-04-25","arxiv_id":"2404.16710","n_code_links":1,"syntology":{"ran":4,"of":5,"n_ran_checked":1,"n_instrument":3,"unverified":1,"pointer_only":5,"phrase":"4 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; 3 where Syntology's instrument failed) · 1 unverified","official":{"repos":["facebookresearch/layerskip"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/efficient-transformer-encoders-for","slug":"efficient-transformer-encoders-for","title":"Efficient Transformer Encoders for Mask2Former-style models","date":"2024-04-23","arxiv_id":"2404.15244","n_code_links":1,"syntology":null},{"paper":"/paper/tiny-models-are-the-computational-saver-for","slug":"tiny-models-are-the-computational-saver-for","title":"Tiny Models are the Computational Saver for Large Models","date":"2024-03-26","arxiv_id":"2403.17726","n_code_links":1,"syntology":null},{"paper":null,"slug":"understanding-the-training-speedup-from","title":"Understanding the Training Speedup from Sampling with Approximate Losses","date":"2024-02-10","arxiv_id":"2402.07052","n_code_links":0,"syntology":null},{"paper":null,"slug":"eero-early-exit-with-reject-option-for","title":"EERO: Early Exit with Reject Option for Efficient Classification with limited budget","date":"2024-02-06","arxiv_id":"2402.03779","n_code_links":0,"syntology":null},{"paper":null,"slug":"de-3-bert-distance-enhanced-early-exiting-for","title":"DE$^3$-BERT: Distance-Enhanced Early Exiting for BERT based on Prototypical Networks","date":"2024-02-03","arxiv_id":"2402.05948","n_code_links":0,"syntology":null},{"paper":"/paper/consistentee-a-consistent-and-hardness-guided","slug":"consistentee-a-consistent-and-hardness-guided","title":"ConsistentEE: A Consistent and Hardness-Guided Early Exiting Method for Accelerating Language Models Inference","date":"2023-12-19","arxiv_id":"2312.11882","n_code_links":1,"syntology":null},{"paper":"/paper/ee-llm-large-scale-training-and-inference-of","slug":"ee-llm-large-scale-training-and-inference-of","title":"EE-LLM: Large-Scale Training and Inference of Early-Exit Large Language Models with 3D Parallelism","date":"2023-12-08","arxiv_id":"2312.04916","n_code_links":1,"syntology":{"ran":3,"of":5,"n_ran_checked":0,"n_instrument":3,"unverified":2,"pointer_only":5,"phrase":"3 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; 3 where Syntology's instrument failed) · 2 unverified","official":{"repos":["pan-x-c/ee-llm"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"adaptive-early-exiting-for-collaborative","title":"Adaptive Early Exiting for Collaborative Inference over Noisy Wireless Channels","date":"2023-11-29","arxiv_id":"2311.18098","n_code_links":0,"syntology":null},{"paper":null,"slug":"accelerating-llm-inference-by-enabling","title":"Accelerating LLaMA Inference by Enabling Intermediate Layer Decoding via Instruction Tuning with LITE","date":"2023-10-28","arxiv_id":"2310.18581","n_code_links":0,"syntology":null},{"paper":null,"slug":"deediff-dynamic-uncertainty-aware-early","title":"AdaDiff: Accelerating Diffusion Models through Step-Wise Adaptive Computation","date":"2023-09-29","arxiv_id":"2309.17074","n_code_links":0,"syntology":null},{"paper":null,"slug":"dynamic-early-exiting-predictive-coding","title":"Dynamic Early Exiting Predictive Coding Neural Networks","date":"2023-09-05","arxiv_id":"2309.02022","n_code_links":0,"syntology":null},{"paper":null,"slug":"using-early-exits-for-fast-inference-in","title":"Using Early Exits for Fast Inference in Automatic Modulation Classification","date":"2023-08-22","arxiv_id":"2308.11100","n_code_links":0,"syntology":null},{"paper":"/paper/lgvit-dynamic-early-exiting-for-accelerating","slug":"lgvit-dynamic-early-exiting-for-accelerating","title":"LGViT: Dynamic Early Exiting for Accelerating Vision Transformer","date":"2023-08-01","arxiv_id":"2308.00255","n_code_links":1,"syntology":null},{"paper":null,"slug":"skipdecode-autoregressive-skip-decoding-with","title":"SkipDecode: Autoregressive Skip Decoding with Batching and Caching for Efficient LLM Inference","date":"2023-07-05","arxiv_id":"2307.02628","n_code_links":0,"syntology":null},{"paper":null,"slug":"csi-based-efficient-self-quarantine","title":"CSI-Based Efficient Self-Quarantine Monitoring System Using Branchy Convolution Neural Network","date":"2023-05-24","arxiv_id":"2306.01756","n_code_links":0,"syntology":null},{"paper":null,"slug":"sustainable-edge-intelligence-through-energy","title":"Sustainable Edge Intelligence Through Energy-Aware Early Exiting","date":"2023-05-23","arxiv_id":"2305.14094","n_code_links":0,"syntology":null},{"paper":null,"slug":"f-pabee-flexible-patience-based-early-exiting","title":"F-PABEE: Flexible-patience-based Early Exiting for Single-label and Multi-label text Classification Tasks","date":"2023-05-21","arxiv_id":"2305.11916","n_code_links":0,"syntology":null},{"paper":"/paper/smartbert-a-promotion-of-dynamic-early","slug":"smartbert-a-promotion-of-dynamic-early","title":"SmartBERT: A Promotion of Dynamic Early Exiting Mechanism for Accelerating BERT Inference","date":"2023-03-16","arxiv_id":"2303.09266","n_code_links":0,"syntology":{"ran":3,"of":4,"n_ran_checked":3,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"3 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; every one of the 3 samples that ran constructed an object rather than computing a result","official":null}},{"paper":"/paper/eenet-learning-to-early-exit-for-adaptive","slug":"eenet-learning-to-early-exit-for-adaptive","title":"Adaptive Deep Neural Network Inference Optimization with EENet","date":"2023-01-15","arxiv_id":"2301.07099","n_code_links":1,"syntology":null},{"paper":null,"slug":"adaensemble-learning-adaptively-sparse","title":"AdaEnsemble: Learning Adaptively Sparse Structured Ensemble Network for Click-Through Rate Prediction","date":"2023-01-06","arxiv_id":"2301.08353","n_code_links":0,"syntology":null},{"paper":"/paper/hadas-hardware-aware-dynamic-neural","slug":"hadas-hardware-aware-dynamic-neural","title":"HADAS: Hardware-Aware Dynamic Neural Architecture Search for Edge Performance Scaling","date":"2022-12-06","arxiv_id":"2212.03354","n_code_links":1,"syntology":null},{"paper":"/paper/you-need-multiple-exiting-dynamic-early","slug":"you-need-multiple-exiting-dynamic-early","title":"You Need Multiple Exiting: Dynamic Early Exiting for Accelerating Unified Vision Language Model","date":"2022-11-21","arxiv_id":"2211.11152","n_code_links":1,"syntology":null},{"paper":"/paper/cost-eff-collaborative-optimization-of","slug":"cost-eff-collaborative-optimization-of","title":"COST-EFF: Collaborative Optimization of Spatial and Temporal Efficiency with Slenderized Multi-exit Language Models","date":"2022-10-27","arxiv_id":"2210.15523","n_code_links":1,"syntology":null},{"paper":"/paper/unsupervised-early-exit-in-dnns-with-multiple","slug":"unsupervised-early-exit-in-dnns-with-multiple","title":"Unsupervised Early Exit in DNNs with Multiple Exits","date":"2022-09-20","arxiv_id":"2209.09480","n_code_links":1,"syntology":null},{"paper":null,"slug":"improving-the-performance-of-dnn-based","title":"Improving the Performance of DNN-based Software Services using Automated Layer Caching","date":"2022-09-18","arxiv_id":"2209.08625","n_code_links":0,"syntology":null},{"paper":null,"slug":"confident-adaptive-language-modeling","title":"Confident Adaptive Language Modeling","date":"2022-07-14","arxiv_id":"2207.07061","n_code_links":0,"syntology":null},{"paper":"/paper/a-simple-hash-based-early-exiting-approach-1","slug":"a-simple-hash-based-early-exiting-approach-1","title":"A Simple Hash-Based Early Exiting Approach For Language Understanding and Generation","date":"2022-03-03","arxiv_id":"2203.01670","n_code_links":1,"syntology":{"ran":6,"of":7,"n_ran_checked":6,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["txsun1997/hashee"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"magic-pyramid-accelerating-inference-with-1","title":"Magic Pyramid: Accelerating Inference with Early Exiting and Token Pruning","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"pcee-bert-accelerating-bert-inference-via","title":"PCEE-BERT: Accelerating BERT Inference via Patient and Confident Early Exiting","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"vee-bert-accelerating-bert-inference-for","title":"VEE-BERT: Accelerating BERT Inference for Named Entity Recognition via Vote Early Exiting","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/deecap-dynamic-early-exiting-for-efficient","slug":"deecap-dynamic-early-exiting-for-efficient","title":"DeeCap: Dynamic Early Exiting for Efficient Image Captioning","date":"2022-01-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"a-simple-hash-based-early-exiting-approach","title":"A Simple Hash-Based Early Exiting Approach For Language Understanding and Generation","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"magic-pyramid-accelerating-inference-with","title":"Magic Pyramid: Accelerating Inference with Early Exiting and Token Pruning","date":"2021-10-30","arxiv_id":"2111.00230","n_code_links":0,"syntology":null},{"paper":null,"slug":"wacky-weights-in-learned-sparse","title":"Wacky Weights in Learned Sparse Representations and the Revenge of Score-at-a-Time Query Evaluation","date":"2021-10-22","arxiv_id":"2110.11540","n_code_links":0,"syntology":null},{"paper":"/paper/towards-efficient-nlp-a-standard-evaluation","slug":"towards-efficient-nlp-a-standard-evaluation","title":"Towards Efficient NLP: A Standard Evaluation and A Strong Baseline","date":"2021-10-13","arxiv_id":"2110.07038","n_code_links":1,"syntology":null},{"paper":"/paper/accelerating-bert-inference-for-sequence","slug":"accelerating-bert-inference-for-sequence","title":"Accelerating BERT Inference for Sequence Labeling via Early-Exit","date":"2021-05-28","arxiv_id":"2105.13878","n_code_links":1,"syntology":null},{"paper":null,"slug":"early-exiting-with-ensemble-internal","title":"Early Exiting with Ensemble Internal Classifiers","date":"2021-05-28","arxiv_id":"2105.13792","n_code_links":0,"syntology":null},{"paper":null,"slug":"single-layer-vision-transformers-for-more","title":"Single-Layer Vision Transformers for More Accurate Early Exits with Less Overhead","date":"2021-05-19","arxiv_id":"2105.09121","n_code_links":0,"syntology":null},{"paper":"/paper/frameexit-conditional-early-exiting-for","slug":"frameexit-conditional-early-exiting-for","title":"FrameExit: Conditional Early Exiting for Efficient Video Recognition","date":"2021-04-27","arxiv_id":"2104.13400","n_code_links":1,"syntology":{"ran":6,"of":9,"n_ran_checked":2,"n_instrument":4,"unverified":3,"pointer_only":9,"phrase":"6 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 3 unverified","official":{"repos":["Qualcomm-AI-research/FrameExit"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/berxit-early-exiting-for-bert-with-better","slug":"berxit-early-exiting-for-bert-with-better","title":"BERxiT: Early Exiting for BERT with Better Fine-Tuning and Extension to Regression","date":"2021-04-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/split-computing-and-early-exiting-for-deep","slug":"split-computing-and-early-exiting-for-deep","title":"Split Computing and Early Exiting for Deep Learning Applications: Survey and Research Challenges","date":"2021-03-08","arxiv_id":"2103.04505","n_code_links":19,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":2,"phrase":"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","official":null}},{"paper":"/paper/romebert-robust-training-of-multi-exit-bert","slug":"romebert-robust-training-of-multi-exit-bert","title":"RomeBERT: Robust Training of Multi-Exit BERT","date":"2021-01-24","arxiv_id":"2101.09755","n_code_links":1,"syntology":null},{"paper":"/paper/accelerating-pre-trained-language-models-via","slug":"accelerating-pre-trained-language-models-via","title":"CascadeBERT: Accelerating Inference of Pre-trained Language Models via Calibrated Complete Models Cascade","date":"2020-12-29","arxiv_id":"2012.14682","n_code_links":1,"syntology":null},{"paper":null,"slug":"hapi-hardware-aware-progressive-inference","title":"HAPI: Hardware-Aware Progressive Inference","date":"2020-08-10","arxiv_id":"2008.03997","n_code_links":0,"syntology":null},{"paper":"/paper/bert-loses-patience-fast-and-robust-inference","slug":"bert-loses-patience-fast-and-robust-inference","title":"BERT Loses Patience: Fast and Robust Inference with Early Exit","date":"2020-06-07","arxiv_id":"2006.04152","n_code_links":1,"syntology":null},{"paper":null,"slug":"query-level-early-exit-for-additive-learning","title":"Query-level Early Exit for Additive Learning-to-Rank Ensembles","date":"2020-04-30","arxiv_id":"2004.14641","n_code_links":0,"syntology":null},{"paper":"/paper/deebert-dynamic-early-exiting-for","slug":"deebert-dynamic-early-exiting-for","title":"DeeBERT: Dynamic Early Exiting for Accelerating BERT Inference","date":"2020-04-27","arxiv_id":"2004.12993","n_code_links":3,"syntology":{"ran":5,"of":6,"n_ran_checked":5,"n_instrument":0,"unverified":1,"pointer_only":5,"phrase":"5 ran (of which 3 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["castorini/deebert"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/fast-intent-classification-for-spoken","slug":"fast-intent-classification-for-spoken","title":"Fast Intent Classification for Spoken Language Understanding","date":"2019-12-03","arxiv_id":"1912.01728","n_code_links":1,"syntology":null},{"paper":null,"slug":"depth-adaptive-transformer","title":"Depth-Adaptive Transformer","date":"2019-10-22","arxiv_id":"1910.10073","n_code_links":0,"syntology":null},{"paper":null,"slug":"edge-ai-on-demand-accelerating-deep-neural","title":"Edge AI: On-Demand Accelerating Deep Neural Network Inference via Edge Computing","date":"2019-10-04","arxiv_id":"1910.05316","n_code_links":0,"syntology":null},{"paper":"/paper/branchynet-fast-inference-via-early-exiting","slug":"branchynet-fast-inference-via-early-exiting","title":"BranchyNet: Fast Inference via Early Exiting from Deep Neural Networks","date":"2017-09-06","arxiv_id":"1709.01686","n_code_links":3,"syntology":null}],"papers_shown":66,"papers_order":"date (newest first), then slug","paper_counts":{"archive_papers_tagged":66,"with_a_code_link":28,"where_syntology_ran_a_sample":9,"not_listed_spam_title":0,"listed":66,"listed_where_code_ran":9,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":7,"every_run_a_failure_of_syntologys_instrument":2,"listed_with_a_run_with_no_instrument_failure":7,"listed_every_run_a_failure_of_syntologys_instrument":2,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"papers_where_code_ran":9,"papers_where_code_ran_first_page":"/method/early-exiting/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not isolate this method inside it.","pages":[{"order":"ran","page":1,"of":1,"url":"/method/early-exiting/papers/ran/1","json":"/method/early-exiting/papers/ran/1.json","rows":9}],"tasks":[{"task":"/task/language-modelling","name":"Language Modelling","papers":5},{"task":"/task/image-classification","name":"Image Classification","papers":4},{"task":"/task/language-modeling","name":"Language Modeling","papers":4},{"task":"/task/text-generation","name":"Text Generation","papers":4},{"task":"/task/computational-efficiency","name":"Computational Efficiency","papers":3},{"task":"/task/decoder","name":"Decoder","papers":3},{"task":"/task/edge-computing","name":"Edge-computing","papers":3},{"task":"/task/model-compression","name":"Model Compression","papers":3},{"task":"/task/retrieval","name":"Retrieval","papers":3},{"task":"/task/text-classification","name":"Text Classification","papers":3},{"task":"/task/image-classification","name":"image-classification","papers":3},{"task":"/task/text-classification-1","name":"text-classification","papers":3},{"task":"/task/collaborative-inference","name":"Collaborative Inference","papers":2},{"task":"/task/gsm8k","name":"GSM8K","papers":2},{"task":"/task/model-selection","name":"Model Selection","papers":2},{"task":"/task/named-entity-recognition-1","name":"Named Entity Recognition","papers":2},{"task":"/task/named-entity-recognition-ner","name":"Named Entity Recognition (NER)","papers":2},{"task":"/task/natural-language-understanding","name":"Natural Language Understanding","papers":2},{"task":"/task/object-detection","name":"Object Detection","papers":2},{"task":"/task/semantic-segmentation","name":"Semantic Segmentation","papers":2}],"tasks_shown":20,"n_tasks":86,"usage_by_year":[{"year":"2017","papers":1},{"year":"2019","papers":3},{"year":"2020","papers":5},{"year":"2021","papers":11},{"year":"2022","papers":11},{"year":"2023","papers":15},{"year":"2024","papers":17},{"year":"2025","papers":3}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/early-exiting"},"syntology_read_at":"2026-10-05T00:36:11+00:00","syntology":{"source":"Syntology's have check for this name (the free coverage lookup), read from Syntology's graph","have_url":"https://syntology.ai/api/graph/have?x=Early%20exiting","read_at":"2026-10-05T00:55:26+00:00","query":"Early exiting","kind":"method","have":"unknown_name","tier":null,"verified_implementation":null,"level":null,"level_meaning":"the served verification level, per answer; never summed across methods","resolved_to":null,"resolution":null,"resolved_name_differs":false,"absence_asserted":false,"absence_unchecked":null,"no_code_is_about_this_method":false,"subject":null,"archive_paper_arxiv_id":"1709.01686","repositories":null,"retrieve_with":null,"name_competition":{"verdict":"none","may_be_wrong_sense":false,"bearers_found":0,"served":null,"leading_other_bearer":null,"n_other_bearers_listed":0,"note":"Nothing in this corpus is named 'Early exiting' -- no method node, no paper announcing it in its title, no expanded form declaring it as an acronym."},"name_competition_text":null,"near_matches":["A Simple Early Exiting Framework","Performance Control Early Exiting (PCEE)","Hash-based Early Exiting approach (HASHEE)","Fast and Robust Early-Exiting (FREE) framework","Learning to Weight Samples for Dynamic Early-exiting Networks","early dropout","Early Cutting","Early-Bird Decoding"],"code_nearby":[],"code_nearby_caption":null,"origin_paper":null,"line":"name not resolved (unknown_name). The lookup matched no method, paper or venue by this name; that asserts nothing about whether code exists.","level_legend":null},"syntology_have_state":"loaded","record_sha256":"86fc4f81564984f284e7b142f0c54db29b87643e4ab83ddf23b20ac89e969adf","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}