{"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/multi-head-attention/papers/158","list_of":"/method/multi-head-attention","method":"Multi-Head Attention","archive":{"snapshot":"2025-07-28"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"date (newest first), then slug","page":158,"pages_in_order":249,"rows_per_page":100,"rows":[15701,15800],"of":24855,"counts":{"archive_papers_tagged":24855,"with_a_code_link":11214,"where_syntology_ran_a_sample":3454,"not_listed_spam_title":0,"listed":24855,"listed_where_code_ran":3454,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":2916,"every_run_a_failure_of_syntologys_instrument":538,"listed_with_a_run_with_no_instrument_failure":2916,"listed_every_run_a_failure_of_syntologys_instrument":538,"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"},"first_page":"/method/multi-head-attention","prev":"/method/multi-head-attention/papers/157","next":"/method/multi-head-attention/papers/159","papers":[{"paper":null,"slug":"speech-emotion-recognition-via-an-attentive","title":"Speech Emotion Recognition via an Attentive Time-Frequency Neural Network","date":"2022-10-22","arxiv_id":"2210.12430","n_code_links":0,"syntology":null},{"paper":"/paper/syngec-syntax-enhanced-grammatical-error","slug":"syngec-syntax-enhanced-grammatical-error","title":"SynGEC: Syntax-Enhanced Grammatical Error Correction with a Tailored GEC-Oriented Parser","date":"2022-10-22","arxiv_id":"2210.12484","n_code_links":1,"syntology":null},{"paper":null,"slug":"transformer-based-conditioned-variational","title":"Transformer-Based Conditioned Variational Autoencoder for Dialogue Generation","date":"2022-10-22","arxiv_id":"2210.12326","n_code_links":0,"syntology":null},{"paper":"/paper/a-causal-framework-to-quantify-the-robustness","slug":"a-causal-framework-to-quantify-the-robustness","title":"A Causal Framework to Quantify the Robustness of Mathematical Reasoning with Language Models","date":"2022-10-21","arxiv_id":"2210.12023","n_code_links":1,"syntology":{"ran":5,"of":7,"n_ran_checked":3,"n_instrument":2,"unverified":2,"pointer_only":7,"phrase":"5 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","official":{"repos":["alestolfo/causal-math"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":2,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/amos-an-adam-style-optimizer-with-adaptive","slug":"amos-an-adam-style-optimizer-with-adaptive","title":"Amos: An Adam-style Optimizer with Adaptive Weight Decay towards Model-Oriented Scale","date":"2022-10-21","arxiv_id":"2210.11693","n_code_links":1,"syntology":{"ran":14,"of":18,"n_ran_checked":14,"n_instrument":0,"unverified":4,"pointer_only":0,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","official":{"repos":["google-research/jestimator"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":14,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/context-enhanced-stereo-transformer","slug":"context-enhanced-stereo-transformer","title":"Context-Enhanced Stereo Transformer","date":"2022-10-21","arxiv_id":"2210.11719","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["guoweiyu/context-enhanced-stereo-transformer"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/decoding-a-neural-retriever-s-latent-space","slug":"decoding-a-neural-retriever-s-latent-space","title":"Decoding a Neural Retriever's Latent Space for Query Suggestion","date":"2022-10-21","arxiv_id":"2210.12084","n_code_links":1,"syntology":null},{"paper":"/paper/diffuser-efficient-transformers-with-multi","slug":"diffuser-efficient-transformers-with-multi","title":"Diffuser: Efficient Transformers with Multi-hop Attention Diffusion for Long Sequences","date":"2022-10-21","arxiv_id":"2210.11794","n_code_links":1,"syntology":null},{"paper":"/paper/discovering-differences-in-the-representation","slug":"discovering-differences-in-the-representation","title":"Discovering Differences in the Representation of People using Contextualized Semantic Axes","date":"2022-10-21","arxiv_id":"2210.12170","n_code_links":1,"syntology":null},{"paper":"/paper/do-vision-and-language-transformers-learn","slug":"do-vision-and-language-transformers-learn","title":"Do Vision-and-Language Transformers Learn Grounded Predicate-Noun Dependencies?","date":"2022-10-21","arxiv_id":"2210.12079","n_code_links":1,"syntology":null},{"paper":"/paper/face-pyramid-vision-transformer","slug":"face-pyramid-vision-transformer","title":"Face Pyramid Vision Transformer","date":"2022-10-21","arxiv_id":"2210.11974","n_code_links":1,"syntology":null},{"paper":null,"slug":"is-encoder-decoder-redundant-for-neural","title":"Is Encoder-Decoder Redundant for Neural Machine Translation?","date":"2022-10-21","arxiv_id":"2210.11807","n_code_links":0,"syntology":null},{"paper":null,"slug":"littlebird-efficient-faster-longer","title":"LittleBird: Efficient Faster & Longer Transformer for Question Answering","date":"2022-10-21","arxiv_id":"2210.11870","n_code_links":0,"syntology":null},{"paper":"/paper/probing-with-noise-unpicking-the-warp-and","slug":"probing-with-noise-unpicking-the-warp-and","title":"Probing with Noise: Unpicking the Warp and Weft of Embeddings","date":"2022-10-21","arxiv_id":"2210.12206","n_code_links":1,"syntology":null},{"paper":"/paper/shift-reduce-task-oriented-semantic-parsing","slug":"shift-reduce-task-oriented-semantic-parsing","title":"Shift-Reduce Task-Oriented Semantic Parsing with Stack-Transformers","date":"2022-10-21","arxiv_id":"2210.11984","n_code_links":1,"syntology":null},{"paper":"/paper/sling-sino-linguistic-evaluation-of-large","slug":"sling-sino-linguistic-evaluation-of-large","title":"SLING: Sino Linguistic Evaluation of Large Language Models","date":"2022-10-21","arxiv_id":"2210.11689","n_code_links":1,"syntology":{"ran":6,"of":9,"n_ran_checked":6,"n_instrument":0,"unverified":3,"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) · 3 unverified","official":{"repos":["yixiao-song/sling_data_code"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"spabert-a-pretrained-language-model-from","title":"SpaBERT: A Pretrained Language Model from Geographic Data for Geo-Entity Representation","date":"2022-10-21","arxiv_id":"2210.12213","n_code_links":0,"syntology":null},{"paper":"/paper/syntax-guided-localized-self-attention-by","slug":"syntax-guided-localized-self-attention-by","title":"Syntax-guided Localized Self-attention by Constituency Syntactic Distance","date":"2022-10-21","arxiv_id":"2210.11759","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":1,"phrase":"2 ran (of which 2 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; every one of the 2 samples that ran constructed an object rather than computing a result","official":{"repos":["lumia-group/distance_transformer"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"paper":"/paper/translist-a-transformer-based-linguistically","slug":"translist-a-transformer-based-linguistically","title":"TransLIST: A Transformer-Based Linguistically Informed Sanskrit Tokenizer","date":"2022-10-21","arxiv_id":"2210.11753","n_code_links":1,"syntology":null},{"paper":null,"slug":"wikiwhy-answering-and-explaining-cause-and","title":"WikiWhy: Answering and Explaining Cause-and-Effect Questions","date":"2022-10-21","arxiv_id":"2210.12152","n_code_links":0,"syntology":null},{"paper":null,"slug":"3dall-e-integrating-text-to-image-ai-in-3d","title":"3DALL-E: Integrating Text-to-Image AI in 3D Design Workflows","date":"2022-10-20","arxiv_id":"2210.11603","n_code_links":0,"syntology":null},{"paper":"/paper/composing-ensembles-of-pre-trained-models-via","slug":"composing-ensembles-of-pre-trained-models-via","title":"Composing Ensembles of Pre-trained Models via Iterative Consensus","date":"2022-10-20","arxiv_id":"2210.11522","n_code_links":0,"syntology":null},{"paper":"/paper/general-image-descriptors-for-open-world","slug":"general-image-descriptors-for-open-world","title":"General Image Descriptors for Open World Image Retrieval using ViT CLIP","date":"2022-10-20","arxiv_id":"2210.11141","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":0,"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":{"repos":["ivanaer/g-universal-clip"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"gpr-net-multi-view-layout-estimation-via-a","title":"GPR-Net: Multi-view Layout Estimation via a Geometry-aware Panorama Registration Network","date":"2022-10-20","arxiv_id":"2210.11419","n_code_links":0,"syntology":null},{"paper":null,"slug":"identifying-human-strategies-for-generating","title":"Identifying Human Strategies for Generating Word-Level Adversarial Examples","date":"2022-10-20","arxiv_id":"2210.11598","n_code_links":0,"syntology":null},{"paper":"/paper/scaling-instruction-finetuned-language-models","slug":"scaling-instruction-finetuned-language-models","title":"Scaling Instruction-Finetuned Language Models","date":"2022-10-20","arxiv_id":"2210.11416","n_code_links":9,"syntology":{"ran":8,"of":17,"n_ran_checked":1,"n_instrument":7,"unverified":9,"pointer_only":2,"phrase":"8 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; 7 where Syntology's instrument failed) · 9 unverified","official":null}},{"paper":"/paper/self-supervised-learning-with-masked-image","slug":"self-supervised-learning-with-masked-image","title":"Self-Supervised Learning with Masked Image Modeling for Teeth Numbering, Detection of Dental Restorations, and Instance Segmentation in Dental Panoramic Radiographs","date":"2022-10-20","arxiv_id":"2210.11404","n_code_links":1,"syntology":null},{"paper":"/paper/simpleclick-interactive-image-segmentation","slug":"simpleclick-interactive-image-segmentation","title":"SimpleClick: Interactive Image Segmentation with Simple Vision Transformers","date":"2022-10-20","arxiv_id":"2210.11006","n_code_links":2,"syntology":{"ran":2,"of":3,"n_ran_checked":1,"n_instrument":1,"unverified":1,"pointer_only":1,"phrase":"2 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; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["uncbiag/simpleclick"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official","unlocated"]}}},{"paper":null,"slug":"single-image-super-resolution-using-2","title":"Single Image Super-Resolution Using Lightweight Networks Based on Swin Transformer","date":"2022-10-20","arxiv_id":"2210.11019","n_code_links":0,"syntology":null},{"paper":null,"slug":"solving-reasoning-tasks-with-a-slot","title":"Solving Reasoning Tasks with a Slot Transformer","date":"2022-10-20","arxiv_id":"2210.11394","n_code_links":0,"syntology":null},{"paper":"/paper/ssit-saliency-guided-self-supervised-image","slug":"ssit-saliency-guided-self-supervised-image","title":"SSiT: Saliency-guided Self-supervised Image Transformer for Diabetic Retinopathy Grading","date":"2022-10-20","arxiv_id":"2210.10969","n_code_links":1,"syntology":null},{"paper":"/paper/a-unified-neural-network-model-for-1","slug":"a-unified-neural-network-model-for-1","title":"A Unified Neural Network Model for Readability Assessment with Feature Projection and Length-Balanced Loss","date":"2022-10-19","arxiv_id":"2210.10305","n_code_links":1,"syntology":null},{"paper":"/paper/a-unified-view-of-masked-image-modeling","slug":"a-unified-view-of-masked-image-modeling","title":"A Unified View of Masked Image Modeling","date":"2022-10-19","arxiv_id":"2210.10615","n_code_links":1,"syntology":null},{"paper":"/paper/biogpt-generative-pre-trained-transformer-for","slug":"biogpt-generative-pre-trained-transformer-for","title":"BioGPT: Generative Pre-trained Transformer for Biomedical Text Generation and Mining","date":"2022-10-19","arxiv_id":"2210.10341","n_code_links":4,"syntology":null},{"paper":null,"slug":"grounded-video-situation-recognition","title":"Grounded Video Situation Recognition","date":"2022-10-19","arxiv_id":"2210.10828","n_code_links":0,"syntology":null},{"paper":"/paper/language-detoxification-with-attribute","slug":"language-detoxification-with-attribute","title":"Language Detoxification with Attribute-Discriminative Latent Space","date":"2022-10-19","arxiv_id":"2210.10329","n_code_links":1,"syntology":null},{"paper":"/paper/language-model-decomposition-quantifying-the","slug":"language-model-decomposition-quantifying-the","title":"Language Model Decomposition: Quantifying the Dependency and Correlation of Language Models","date":"2022-10-19","arxiv_id":"2210.10289","n_code_links":1,"syntology":null},{"paper":null,"slug":"multi-view-gait-recognition-based-on-siamese","title":"Multi-view Gait Recognition based on Siamese Vision Transformer","date":"2022-10-19","arxiv_id":"2210.10421","n_code_links":0,"syntology":null},{"paper":"/paper/museformer-transformer-with-fine-and-coarse","slug":"museformer-transformer-with-fine-and-coarse","title":"Museformer: Transformer with Fine- and Coarse-Grained Attention for Music Generation","date":"2022-10-19","arxiv_id":"2210.10349","n_code_links":1,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"0 ran · 1 unverified","official":{"repos":["microsoft/muzic"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"paper":"/paper/posegpt-quantization-based-3d-human-motion","slug":"posegpt-quantization-based-3d-human-motion","title":"PoseGPT: Quantization-based 3D Human Motion Generation and Forecasting","date":"2022-10-19","arxiv_id":"2210.10542","n_code_links":1,"syntology":null},{"paper":"/paper/revision-transformers-getting-rit-of-no-nos","slug":"revision-transformers-getting-rit-of-no-nos","title":"Revision Transformers: Instructing Language Models to Change their Values","date":"2022-10-19","arxiv_id":"2210.10332","n_code_links":1,"syntology":null},{"paper":"/paper/self-supervised-graph-masking-pre-training","slug":"self-supervised-graph-masking-pre-training","title":"Self-supervised Graph Masking Pre-training for Graph-to-Text Generation","date":"2022-10-19","arxiv_id":"2210.10599","n_code_links":1,"syntology":null},{"paper":"/paper/tempo-accelerating-transformer-based-model","slug":"tempo-accelerating-transformer-based-model","title":"Tempo: Accelerating Transformer-Based Model Training through Memory Footprint Reduction","date":"2022-10-19","arxiv_id":"2210.10246","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":0,"n_instrument":1,"unverified":1,"pointer_only":2,"phrase":"1 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; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["uoft-ecosystem/tempo"],"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":"towards-a-neural-architecture-of-language","title":"Towards a neural architecture of language: Deep learning versus logistics of access in neural architectures for compositional processing","date":"2022-10-19","arxiv_id":"2210.10543","n_code_links":0,"syntology":null},{"paper":null,"slug":"transformers-learn-shortcuts-to-automata","title":"Transformers Learn Shortcuts to Automata","date":"2022-10-19","arxiv_id":"2210.10749","n_code_links":0,"syntology":null},{"paper":"/paper/a-hybrid-system-of-sound-event-detection","slug":"a-hybrid-system-of-sound-event-detection","title":"A Hybrid System of Sound Event Detection Transformer and Frame-wise Model for DCASE 2022 Task 4","date":"2022-10-18","arxiv_id":"2210.09529","n_code_links":1,"syntology":null},{"paper":"/paper/cross-domain-aspect-extraction-using","slug":"cross-domain-aspect-extraction-using","title":"Cross-Domain Aspect Extraction using Transformers Augmented with Knowledge Graphs","date":"2022-10-18","arxiv_id":"2210.10144","n_code_links":1,"syntology":null},{"paper":"/paper/ctgan-cloud-transformer-generative","slug":"ctgan-cloud-transformer-generative","title":"CTGAN : Cloud Transformer Generative Adversarial Network","date":"2022-10-18","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/elastic-numerical-reasoning-with-adaptive","slug":"elastic-numerical-reasoning-with-adaptive","title":"ELASTIC: Numerical Reasoning with Adaptive Symbolic Compiler","date":"2022-10-18","arxiv_id":"2210.10105","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"2 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; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["neurasearch/neurips-2022-submission-3358"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"from-play-to-policy-conditional-behavior","title":"From Play to Policy: Conditional Behavior Generation from Uncurated Robot Data","date":"2022-10-18","arxiv_id":"2210.10047","n_code_links":0,"syntology":null},{"paper":"/paper/multimodal-image-fusion-based-on-hybrid-cnn","slug":"multimodal-image-fusion-based-on-hybrid-cnn","title":"Multimodal Image Fusion based on Hybrid CNN-Transformer and Non-local Cross-modal Attention","date":"2022-10-18","arxiv_id":"2210.09847","n_code_links":1,"syntology":null},{"paper":null,"slug":"sequence-and-circle-exploring-the","title":"Sequence and Circle: Exploring the Relationship Between Patches","date":"2022-10-18","arxiv_id":"2210.09871","n_code_links":0,"syntology":null},{"paper":"/paper/swinv2-imagen-hierarchical-vision-transformer","slug":"swinv2-imagen-hierarchical-vision-transformer","title":"Swinv2-Imagen: Hierarchical Vision Transformer Diffusion Models for Text-to-Image Generation","date":"2022-10-18","arxiv_id":"2210.09549","n_code_links":0,"syntology":null},{"paper":null,"slug":"systematicity-in-gpt-3-s-interpretation-of","title":"Systematicity in GPT-3's Interpretation of Novel English Noun Compounds","date":"2022-10-18","arxiv_id":"2210.09492","n_code_links":0,"syntology":null},{"paper":null,"slug":"team-flow-at-drc2022-pipeline-system-for","title":"Team Flow at DRC2022: Pipeline System for Travel Destination Recommendation Task in Spoken Dialogue","date":"2022-10-18","arxiv_id":"2210.09518","n_code_links":0,"syntology":null},{"paper":null,"slug":"tiny-attention-adapter-contexts-are-more","title":"Tiny-Attention Adapter: Contexts Are More Important Than the Number of Parameters","date":"2022-10-18","arxiv_id":"2211.01979","n_code_links":0,"syntology":null},{"paper":null,"slug":"transfer-learning-for-video-classification","title":"Transfer-learning for video classification: Video Swin Transformer on multiple domains","date":"2022-10-18","arxiv_id":"2210.09969","n_code_links":0,"syntology":null},{"paper":"/paper/vitcod-vision-transformer-acceleration-via","slug":"vitcod-vision-transformer-acceleration-via","title":"ViTCoD: Vision Transformer Acceleration via Dedicated Algorithm and Accelerator Co-Design","date":"2022-10-18","arxiv_id":"2210.09573","n_code_links":1,"syntology":null},{"paper":"/paper/a-generative-user-simulator-with-gpt-based","slug":"a-generative-user-simulator-with-gpt-based","title":"A Generative User Simulator with GPT-based Architecture and Goal State Tracking for Reinforced Multi-Domain Dialog Systems","date":"2022-10-17","arxiv_id":"2210.08692","n_code_links":1,"syntology":{"ran":8,"of":9,"n_ran_checked":8,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["thu-spmi/gus"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"a-mixing-time-lower-bound-for-a-simplified","title":"A Mixing Time Lower Bound for a Simplified Version of BART","date":"2022-10-17","arxiv_id":"2210.09352","n_code_links":0,"syntology":null},{"paper":null,"slug":"can-bert-do-it-controller-area-network","title":"CAN-BERT do it? Controller Area Network Intrusion Detection System based on BERT Language Model","date":"2022-10-17","arxiv_id":"2210.09439","n_code_links":0,"syntology":null},{"paper":"/paper/deep-bidirectional-language-knowledge-graph","slug":"deep-bidirectional-language-knowledge-graph","title":"Deep Bidirectional Language-Knowledge Graph Pretraining","date":"2022-10-17","arxiv_id":"2210.09338","n_code_links":2,"syntology":{"ran":9,"of":18,"n_ran_checked":8,"n_instrument":1,"unverified":9,"pointer_only":1,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 9 unverified","official":{"repos":["michiyasunaga/dragon"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":9,"ran_from_kinds":["official"]}}},{"paper":"/paper/histopathological-image-classification-based","slug":"histopathological-image-classification-based","title":"Histopathological Image Classification based on Self-Supervised Vision Transformer and Weak Labels","date":"2022-10-17","arxiv_id":"2210.09021","n_code_links":1,"syntology":null},{"paper":"/paper/idna-abf-multi-scale-deep-biological-language","slug":"idna-abf-multi-scale-deep-biological-language","title":"iDNA-ABF: multi-scale deep biological language learning model for the interpretable prediction of DNA methylations","date":"2022-10-17","arxiv_id":null,"n_code_links":2,"syntology":null},{"paper":"/paper/intelligent-resource-allocation-in-joint","slug":"intelligent-resource-allocation-in-joint","title":"Intelligent Resource Allocation in Joint Radar-Communication With Graph Neural Networks","date":"2022-10-17","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"multi-granularity-argument-mining-in-legal","title":"Multi-granularity Argument Mining in Legal Texts","date":"2022-10-17","arxiv_id":"2210.09472","n_code_links":0,"syntology":null},{"paper":"/paper/prompting-gpt-3-to-be-reliable","slug":"prompting-gpt-3-to-be-reliable","title":"Prompting GPT-3 To Be Reliable","date":"2022-10-17","arxiv_id":"2210.09150","n_code_links":1,"syntology":null},{"paper":null,"slug":"sgram-improving-scene-graph-parsing-via","title":"SGRAM: Improving Scene Graph Parsing via Abstract Meaning Representation","date":"2022-10-17","arxiv_id":"2210.08675","n_code_links":0,"syntology":null},{"paper":"/paper/using-bottleneck-adapters-to-identify-cancer","slug":"using-bottleneck-adapters-to-identify-cancer","title":"Using Bottleneck Adapters to Identify Cancer in Clinical Notes under Low-Resource Constraints","date":"2022-10-17","arxiv_id":"2210.09440","n_code_links":1,"syntology":null},{"paper":null,"slug":"zero-shot-ranking-socio-political-texts-with","title":"Zero-Shot Ranking Socio-Political Texts with Transformer Language Models to Reduce Close Reading Time","date":"2022-10-17","arxiv_id":"2210.09179","n_code_links":0,"syntology":null},{"paper":"/paper/accelerating-transfer-learning-with-near-data","slug":"accelerating-transfer-learning-with-near-data","title":"Accelerating Transfer Learning with Near-Data Computation on Cloud Object Stores","date":"2022-10-16","arxiv_id":"2210.08650","n_code_links":1,"syntology":null},{"paper":null,"slug":"acoustic-aware-non-autoregressive-spell","title":"Acoustic-aware Non-autoregressive Spell Correction with Mask Sample Decoding","date":"2022-10-16","arxiv_id":"2210.08665","n_code_links":0,"syntology":null},{"paper":"/paper/cofar-commonsense-and-factual-reasoning-in","slug":"cofar-commonsense-and-factual-reasoning-in","title":"COFAR: Commonsense and Factual Reasoning in Image Search","date":"2022-10-16","arxiv_id":"2210.08554","n_code_links":1,"syntology":null},{"paper":null,"slug":"ctcbert-advancing-hidden-unit-bert-with-ctc","title":"CTCBERT: Advancing Hidden-unit BERT with CTC Objectives","date":"2022-10-16","arxiv_id":"2210.08603","n_code_links":0,"syntology":null},{"paper":"/paper/efficient-cross-modal-video-retrieval-with","slug":"efficient-cross-modal-video-retrieval-with","title":"Efficient Cross-Modal Video Retrieval with Meta-Optimized Frames","date":"2022-10-16","arxiv_id":"2210.08452","n_code_links":1,"syntology":null},{"paper":null,"slug":"improving-semantic-matching-through","title":"Improving Semantic Matching through Dependency-Enhanced Pre-trained Model with Adaptive Fusion","date":"2022-10-16","arxiv_id":"2210.08471","n_code_links":0,"syntology":null},{"paper":"/paper/normsage-multi-lingual-multi-cultural-norm","slug":"normsage-multi-lingual-multi-cultural-norm","title":"NormSAGE: Multi-Lingual Multi-Cultural Norm Discovery from Conversations On-the-Fly","date":"2022-10-16","arxiv_id":"2210.08604","n_code_links":1,"syntology":null},{"paper":null,"slug":"ost-efficient-one-stream-network-for-3d","title":"OST: Efficient One-stream Network for 3D Single Object Tracking in Point Clouds","date":"2022-10-16","arxiv_id":"2210.08518","n_code_links":0,"syntology":null},{"paper":null,"slug":"aralegal-bert-a-pretrained-language-model-for","title":"AraLegal-BERT: A pretrained language model for Arabic Legal text","date":"2022-10-15","arxiv_id":"2210.08284","n_code_links":0,"syntology":null},{"paper":null,"slug":"distributionally-robust-multiclass-1","title":"Distributionally Robust Multiclass Classification and Applications in Deep Image Classifiers","date":"2022-10-15","arxiv_id":"2210.08198","n_code_links":0,"syntology":null},{"paper":null,"slug":"machine-learning-love-classifying-the","title":"Machine-Learning Love: classifying the equation of state of neutron stars with Transformers","date":"2022-10-15","arxiv_id":"2210.08382","n_code_links":0,"syntology":null},{"paper":null,"slug":"transformer-based-dimensionality-reduction","title":"Transformer-based dimensionality reduction","date":"2022-10-15","arxiv_id":"2210.08288","n_code_links":0,"syntology":null},{"paper":"/paper/automoe-neural-architecture-search-for","slug":"automoe-neural-architecture-search-for","title":"AutoMoE: Heterogeneous Mixture-of-Experts with Adaptive Computation for Efficient Neural Machine Translation","date":"2022-10-14","arxiv_id":"2210.07535","n_code_links":1,"syntology":{"ran":5,"of":6,"n_ran_checked":3,"n_instrument":2,"unverified":1,"pointer_only":4,"phrase":"5 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["microsoft/automoe"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official","unlocated"]}}},{"paper":"/paper/dylora-parameter-efficient-tuning-of-pre","slug":"dylora-parameter-efficient-tuning-of-pre","title":"DyLoRA: Parameter Efficient Tuning of Pre-trained Models using Dynamic Search-Free Low-Rank Adaptation","date":"2022-10-14","arxiv_id":"2210.07558","n_code_links":2,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"0 ran · 1 unverified","official":{"repos":["huawei-noah/kd-nlp"],"state":"official: not harvested","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":[]}}},{"paper":null,"slug":"efficiently-controlling-multiple-risks-with","title":"Efficiently Controlling Multiple Risks with Pareto Testing","date":"2022-10-14","arxiv_id":"2210.07913","n_code_links":0,"syntology":null},{"paper":"/paper/extracting-cultural-commonsense-knowledge-at","slug":"extracting-cultural-commonsense-knowledge-at","title":"Extracting Cultural Commonsense Knowledge at Scale","date":"2022-10-14","arxiv_id":"2210.07763","n_code_links":2,"syntology":null},{"paper":"/paper/john-is-50-years-old-can-his-son-be-65","slug":"john-is-50-years-old-can-his-son-be-65","title":"\"John is 50 years old, can his son be 65?\" Evaluating NLP Models' Understanding of Feasibility","date":"2022-10-14","arxiv_id":"2210.07471","n_code_links":1,"syntology":null},{"paper":"/paper/kernel-whitening-overcome-dataset-bias-with","slug":"kernel-whitening-overcome-dataset-bias-with","title":"Kernel-Whitening: Overcome Dataset Bias with Isotropic Sentence Embedding","date":"2022-10-14","arxiv_id":"2210.07547","n_code_links":2,"syntology":null},{"paper":null,"slug":"learning-to-jointly-transcribe-and-subtitle","title":"Learning to Jointly Transcribe and Subtitle for End-to-End Spontaneous Speech Recognition","date":"2022-10-14","arxiv_id":"2210.07771","n_code_links":0,"syntology":null},{"paper":"/paper/move-unsupervised-movable-object-segmentation","slug":"move-unsupervised-movable-object-segmentation","title":"MOVE: Unsupervised Movable Object Segmentation and Detection","date":"2022-10-14","arxiv_id":"2210.07920","n_code_links":1,"syntology":{"ran":3,"of":6,"n_ran_checked":2,"n_instrument":1,"unverified":3,"pointer_only":6,"phrase":"3 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","official":{"repos":["adambielski/move-seg"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/optimizing-vision-transformers-for-medical","slug":"optimizing-vision-transformers-for-medical","title":"Optimizing Vision Transformers for Medical Image Segmentation","date":"2022-10-14","arxiv_id":"2210.08066","n_code_links":1,"syntology":null},{"paper":null,"slug":"ovit-an-accurate-second-order-pruning","title":"CAP: Correlation-Aware Pruning for Highly-Accurate Sparse Vision Models","date":"2022-10-14","arxiv_id":"2210.09223","n_code_links":0,"syntology":null},{"paper":null,"slug":"pedformer-pedestrian-behavior-prediction-via","title":"PedFormer: Pedestrian Behavior Prediction via Cross-Modal Attention Modulation and Gated Multitask Learning","date":"2022-10-14","arxiv_id":"2210.07886","n_code_links":0,"syntology":null},{"paper":null,"slug":"self-repetition-in-abstractive-neural","title":"Self-Repetition in Abstractive Neural Summarizers","date":"2022-10-14","arxiv_id":"2210.08145","n_code_links":0,"syntology":null},{"paper":"/paper/testaug-a-framework-for-augmenting-capability-1","slug":"testaug-a-framework-for-augmenting-capability-1","title":"TestAug: A Framework for Augmenting Capability-based NLP Tests","date":"2022-10-14","arxiv_id":"2210.08097","n_code_links":1,"syntology":null},{"paper":"/paper/trailers12k-evaluating-transfer-learning-for","slug":"trailers12k-evaluating-transfer-learning-for","title":"Improving Transfer Learning with a Dual Image and Video Transformer for Multi-label Movie Trailer Genre Classification","date":"2022-10-14","arxiv_id":"2210.07983","n_code_links":1,"syntology":null},{"paper":null,"slug":"automotive-multilingual-fault-diagnosis","title":"Automotive Multilingual Fault Diagnosis","date":"2022-10-13","arxiv_id":"2210.06918","n_code_links":0,"syntology":null},{"paper":"/paper/brain-network-transformer","slug":"brain-network-transformer","title":"Brain Network Transformer","date":"2022-10-13","arxiv_id":"2210.06681","n_code_links":2,"syntology":{"ran":3,"of":7,"n_ran_checked":3,"n_instrument":0,"unverified":4,"pointer_only":0,"phrase":"3 ran (of which 1 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) · 4 unverified","official":{"repos":["hennyjie/braingb","wayfear/brainnetworktransformer"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":1,"n_ran_no_instrument_failure":3,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"categorizing-semantic-representations-for-1","title":"Categorizing Semantic Representations for Neural Machine Translation","date":"2022-10-13","arxiv_id":"2210.06709","n_code_links":0,"syntology":null},{"paper":"/paper/constructing-natural-language-explanations","slug":"constructing-natural-language-explanations","title":"Saliency Map Verbalization: Comparing Feature Importance Representations from Model-free and Instruction-based Methods","date":"2022-10-13","arxiv_id":"2210.07222","n_code_links":1,"syntology":null}],"record_sha256":"e9a1ecc1e9f03a714fcead9c76730a6385afa25df4b2447ca9c7f2f12467f859","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}