{"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/neat","slug":"neat","name":"NEAT","full_name":"Neural Attention Fields","full_name_withheld":false,"description_markdown":"**NEAT**, or **Neural Attention Fields**, is a feature representation for end-to-end imitation learning models. NEAT is a continuous function which maps locations in Bird's Eye View (BEV) scene coordinates to waypoints and semantics, using intermediate attention maps to iteratively compress high-dimensional 2D image features into a compact representation. This allows the model to selectively attend to relevant regions in the input while ignoring information irrelevant to the driving task, effectively associating the images with the BEV representation. Furthermore, visualizing the attention maps for models with NEAT intermediate representations provides improved interpretability.","description_state":"present","introduced_year":null,"introduced_by":{"title":null,"paper":null,"first_author":null,"n_authors":0,"url_abs":null,"archive_paper_url":null},"source":{"url":"https://arxiv.org/abs/2109.04456v1","title":"NEAT: Neural Attention Fields for End-to-End Autonomous Driving","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"Computer Vision","area_id":"computer-vision","collection":"Feature Extractors","url":"/methods/category/feature-extractors","pwc_aliases":[]}],"n_papers_tagged":25,"archive_num_papers":null,"papers_newest_first":[{"paper":null,"slug":"neuropal-punctuated-anytime-learning-with","title":"NeuroPAL: Punctuated Anytime Learning with Neuroevolution for Macromanagement in Starcraft: Brood War","date":"2025-06-12","arxiv_id":"2506.10384","n_code_links":0,"syntology":null},{"paper":null,"slug":"neat-and-hyperneat-based-design-for-soft","title":"NEAT and HyperNEAT based Design for Soft Actuator Controllers","date":"2025-06-05","arxiv_id":"2506.04698","n_code_links":0,"syntology":null},{"paper":null,"slug":"near-driven-autonomous-rover-navigation-in","title":"Near-Driven Autonomous Rover Navigation in Complex Environments: Extensions to Urban Search-and-Rescue and Industrial Inspection","date":"2025-04-11","arxiv_id":"2504.17794","n_code_links":0,"syntology":null},{"paper":"/paper/tensorneat-a-gpu-accelerated-library-for","slug":"tensorneat-a-gpu-accelerated-library-for","title":"TensorNEAT: A GPU-accelerated Library for NeuroEvolution of Augmenting Topologies","date":"2025-04-11","arxiv_id":"2504.08339","n_code_links":1,"syntology":null},{"paper":null,"slug":"state-estimation-using-particle-filtering-in","title":"State Estimation Using Particle Filtering in Adaptive Machine Learning Methods: Integrating Q-Learning and NEAT Algorithms with Noisy Radar Measurements","date":"2025-04-10","arxiv_id":"2504.07393","n_code_links":0,"syntology":null},{"paper":"/paper/the-odyssey-of-the-fittest-can-agents-survive","slug":"the-odyssey-of-the-fittest-can-agents-survive","title":"The Odyssey of the Fittest: Can Agents Survive and Still Be Good?","date":"2025-02-08","arxiv_id":"2502.05442","n_code_links":1,"syntology":null},{"paper":null,"slug":"neat-algorithm-based-stock-trading-strategy","title":"NEAT Algorithm-based Stock Trading Strategy with Multiple Technical Indicators Resonance","date":"2024-12-11","arxiv_id":"2501.14736","n_code_links":0,"syntology":null},{"paper":null,"slug":"propneat-efficient-gpu-compatible","title":"PropNEAT -- Efficient GPU-Compatible Backpropagation over NeuroEvolutionary Augmenting Topology Networks","date":"2024-11-06","arxiv_id":"2411.03726","n_code_links":0,"syntology":null},{"paper":null,"slug":"negative-prompt-driven-alignment-for","title":"Negative-Prompt-driven Alignment for Generative Language Model","date":"2024-10-16","arxiv_id":"2410.12194","n_code_links":0,"syntology":null},{"paper":null,"slug":"neat-nonlinear-parameter-efficient-adaptation","title":"NEAT: Nonlinear Parameter-efficient Adaptation of Pre-trained Models","date":"2024-10-02","arxiv_id":"2410.01870","n_code_links":0,"syntology":null},{"paper":"/paper/tensorized-neuroevolution-of-augmenting","slug":"tensorized-neuroevolution-of-augmenting","title":"Tensorized NeuroEvolution of Augmenting Topologies for GPU Acceleration","date":"2024-04-02","arxiv_id":"2404.01817","n_code_links":1,"syntology":null},{"paper":"/paper/inconsistency-based-data-centric-active-open","slug":"inconsistency-based-data-centric-active-open","title":"Inconsistency-Based Data-Centric Active Open-Set Annotation","date":"2024-01-10","arxiv_id":"2401.04923","n_code_links":1,"syntology":null},{"paper":null,"slug":"neural-modelling-of-dynamic-systems-with-time","title":"Neural Modelling of Dynamic Systems with Time Delays Based on an Adjusted NEAT Algorithm","date":"2023-09-21","arxiv_id":"2309.12148","n_code_links":0,"syntology":null},{"paper":"/paper/class-binarization-to-neuroevolution-for","slug":"class-binarization-to-neuroevolution-for","title":"Class Binarization to NeuroEvolution for Multiclass Classification","date":"2023-08-26","arxiv_id":"2308.13876","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-look-into-causal-effects-under-entangled","title":"A Look into Causal Effects under Entangled Treatment in Graphs: Investigating the Impact of Contact on MRSA Infection","date":"2023-07-17","arxiv_id":"2307.08237","n_code_links":0,"syntology":null},{"paper":"/paper/volumetric-wireframe-parsing-from-neural","slug":"volumetric-wireframe-parsing-from-neural","title":"NEAT: Distilling 3D Wireframes from Neural Attraction Fields","date":"2023-07-14","arxiv_id":"2307.10206","n_code_links":1,"syntology":null},{"paper":null,"slug":"eincasm-emergent-intelligence-in-neural","title":"EINCASM: Emergent Intelligence in Neural Cellular Automaton Slime Molds","date":"2023-05-22","arxiv_id":"2305.13425","n_code_links":0,"syntology":null},{"paper":null,"slug":"co-evolving-morphology-and-control-of-soft","title":"Co-evolving morphology and control of soft robots using a single genome","date":"2022-12-22","arxiv_id":"2212.11517","n_code_links":0,"syntology":null},{"paper":"/paper/prosky-neat-meets-noma-mmwave-in-the-sky-of","slug":"prosky-neat-meets-noma-mmwave-in-the-sky-of","title":"ProSky: NEAT Meets NOMA-mmWave in the Sky of 6G","date":"2022-10-13","arxiv_id":"2210.11406","n_code_links":1,"syntology":null},{"paper":"/paper/detecting-narrative-elements-in-informational-1","slug":"detecting-narrative-elements-in-informational-1","title":"Detecting Narrative Elements in Informational Text","date":"2022-10-06","arxiv_id":"2210.03028","n_code_links":1,"syntology":null},{"paper":null,"slug":"playing-a-2d-game-indefinitely-using-neat-and","title":"Playing a 2D Game Indefinitely using NEAT and Reinforcement Learning","date":"2022-07-28","arxiv_id":"2207.14140","n_code_links":0,"syntology":null},{"paper":"/paper/modularity-in-neat-reinforcement-learning","slug":"modularity-in-neat-reinforcement-learning","title":"Towards Understanding the Link Between Modularity and Performance in Neural Networks for Reinforcement Learning","date":"2022-05-13","arxiv_id":"2205.06451","n_code_links":1,"syntology":null},{"paper":"/paper/hybrid-self-attention-neat-a-novel","slug":"hybrid-self-attention-neat-a-novel","title":"Hybrid Self-Attention NEAT: A novel evolutionary approach to improve the NEAT algorithm","date":"2021-12-07","arxiv_id":"2112.03670","n_code_links":1,"syntology":null},{"paper":null,"slug":"adaptability-of-improved-neat-in-variable","title":"Adaptability of Improved NEAT in Variable Environments","date":"2021-10-22","arxiv_id":"2201.07977","n_code_links":0,"syntology":null},{"paper":"/paper/neat-neural-attention-fields-for-end-to-end","slug":"neat-neural-attention-fields-for-end-to-end","title":"NEAT: Neural Attention Fields for End-to-End Autonomous Driving","date":"2021-09-09","arxiv_id":"2109.04456","n_code_links":1,"syntology":{"ran":0,"of":2,"n_ran_checked":0,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"0 ran · 2 unverified","official":{"repos":["autonomousvision/neat"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":[]}}}],"papers_shown":25,"papers_order":"date (newest first), then slug","paper_counts":{"archive_papers_tagged":25,"with_a_code_link":11,"where_syntology_ran_a_sample":0,"not_listed_spam_title":0,"listed":25,"listed_where_code_ran":0,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":0,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":0,"listed_every_run_a_failure_of_syntologys_instrument":0,"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":0,"papers_where_code_ran_first_page":null,"papers_where_code_ran_caption":"We ran code from the paper's repository; we did not isolate this method inside it.","pages":[],"tasks":[{"task":"/task/computational-efficiency","name":"Computational Efficiency","papers":3},{"task":null,"name":"GPU","papers":3},{"task":"/task/reinforcement-learning","name":"Reinforcement Learning","papers":3},{"task":"/task/reinforcement-learning-2","name":"reinforcement-learning","papers":3},{"task":"/task/binary-classification","name":"Binary Classification","papers":2},{"task":"/task/deep-reinforcement-learning","name":"Deep Reinforcement Learning","papers":2},{"task":"/task/novel-view-synthesis","name":"Novel View Synthesis","papers":2},{"task":"/task/q-learning","name":"Q-Learning","papers":2},{"task":"/task/reinforcement-learning-1","name":"Reinforcement Learning (RL)","papers":2},{"task":"/task/3d-reconstruction","name":"3D Reconstruction","papers":1},{"task":"/task/3d-wireframe-reconstruction","name":"3D Wireframe Reconstruction","papers":1},{"task":"/task/active-learning","name":"Active Learning","papers":1},{"task":"/task/articles","name":"Articles","papers":1},{"task":"/task/atari-games","name":"Atari Games","papers":1},{"task":"/task/autonomous-driving","name":"Autonomous Driving","papers":1},{"task":"/task/autonomous-navigation","name":"Autonomous Navigation","papers":1},{"task":"/task/binarization","name":"Binarization","papers":1},{"task":"/task/carla-longest6","name":"CARLA longest6","papers":1},{"task":"/task/classification-1","name":"Classification","papers":1},{"task":"/task/decision-making","name":"Decision Making","papers":1}],"tasks_shown":20,"n_tasks":37,"usage_by_year":[{"year":"2021","papers":3},{"year":"2022","papers":5},{"year":"2023","papers":5},{"year":"2024","papers":6},{"year":"2025","papers":6}],"row_source":"embedded","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/neat"},"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=NEAT","read_at":"2026-10-05T00:59:33+00:00","query":"NEAT","kind":"method","have":"declared_code","tier":"repo_known","verified_implementation":false,"level":null,"level_meaning":"the served verification level, per answer; never summed across methods","resolved_to":{"method":"NEAT","origin_arxiv_id":"2109.04456"},"resolution":"exact","resolved_name_differs":false,"absence_asserted":false,"absence_unchecked":null,"no_code_is_about_this_method":false,"subject":"unknown","archive_paper_arxiv_id":null,"repositories":{"listed":2,"in_graph":2,"list_truncated":false,"strongest_link":"official"},"retrieve_with":null,"name_competition":{"verdict":"contested","may_be_wrong_sense":false,"bearers_found":8,"served":{"arxiv_id":"2109.04456","citations":300},"leading_other_bearer":{"arxiv_id":"2303.12012","title":"NeAT: Learning Neural Implicit Surfaces with Arbitrary Topologies from Multi-view Images","citations":49,"named_by":["method_name","title_prefix"],"bearer_name":"NeAT","ask_with":"have('2303.12012')"},"n_other_bearers_listed":5,"note":"7 other thing(s) here are also called 'NEAT', and none of them is cited more than the paper this answer is about. They are listed in `also_named` -- check `served.arxiv_id` is the paper you meant."},"name_competition_text":null,"near_matches":null,"code_nearby":[],"code_nearby_caption":null,"origin_paper":{"arxiv_id":"2109.04456","page":"/paper/neat-neural-attention-fields-for-end-to-end","syntology_url":"https://syntology.ai/paper/2109.04456","in_graph_layer":true,"samples":2,"ran":0,"n_ran_checked":0,"n_instrument":0,"unverified":2,"phrase":"0 ran · 2 unverified","instrument_means":"failures of Syntology's instrument, not of the code"},"line":"repository known, no verified implementation (declared_code; repositories: 2 listed of 2 in the graph, strongest link: official). The archive credits no paper with an arXiv id for this method, so whether this answer (about arXiv:2109.04456) is about this method is not checked.","level_legend":null},"syntology_have_state":"loaded","record_sha256":"d99f8406a73fbf9e3a24d1c8803a18e335ac0c17b0c93dbda448ddc23c802228","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}