{"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/transformer/papers/95","list_of":"/method/transformer","method":"Transformer","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":95,"pages_in_order":140,"rows_per_page":100,"rows":[9401,9500],"of":13999,"counts":{"archive_papers_tagged":13999,"with_a_code_link":6572,"where_syntology_ran_a_sample":2248,"not_listed_spam_title":0,"listed":13999,"listed_where_code_ran":2248,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1919,"every_run_a_failure_of_syntologys_instrument":329,"listed_with_a_run_with_no_instrument_failure":1919,"listed_every_run_a_failure_of_syntologys_instrument":329,"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/transformer","prev":"/method/transformer/papers/94","next":"/method/transformer/papers/96","papers":[{"paper":null,"slug":"adaptive-multi-neighborhood-attention-based","title":"Adaptive Multi-Neighborhood Attention based Transformer for Graph Representation Learning","date":"2022-11-15","arxiv_id":"2211.07970","n_code_links":0,"syntology":null},{"paper":null,"slug":"contextual-transformer-for-offline-meta","title":"Contextual Transformer for Offline Meta Reinforcement Learning","date":"2022-11-15","arxiv_id":"2211.08016","n_code_links":0,"syntology":null},{"paper":null,"slug":"convformer-combining-cnn-and-transformer-for","title":"ConvFormer: Combining CNN and Transformer for Medical Image Segmentation","date":"2022-11-15","arxiv_id":"2211.08564","n_code_links":0,"syntology":null},{"paper":null,"slug":"cross-modality-transformer-for-visible","title":"Cross-Modality Transformer for Visible-Infrared Person Re-Identification","date":"2022-11-15","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/dynamic-temporal-filtering-in-video-models","slug":"dynamic-temporal-filtering-in-video-models","title":"Dynamic Temporal Filtering in Video Models","date":"2022-11-15","arxiv_id":"2211.08252","n_code_links":1,"syntology":null},{"paper":null,"slug":"fedtune-a-deep-dive-into-efficient-federated","title":"FedTune: A Deep Dive into Efficient Federated Fine-Tuning with Pre-trained Transformers","date":"2022-11-15","arxiv_id":"2211.08025","n_code_links":0,"syntology":null},{"paper":"/paper/hybrid-transformers-for-music-source","slug":"hybrid-transformers-for-music-source","title":"Hybrid Transformers for Music Source Separation","date":"2022-11-15","arxiv_id":"2211.08553","n_code_links":2,"syntology":{"ran":9,"of":10,"n_ran_checked":9,"n_instrument":0,"unverified":1,"pointer_only":10,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["facebookresearch/demucs"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":"/paper/knowledge-distillation-for-detection","slug":"knowledge-distillation-for-detection","title":"Knowledge Distillation for Detection Transformer with Consistent Distillation Points Sampling","date":"2022-11-15","arxiv_id":"2211.08071","n_code_links":2,"syntology":null},{"paper":"/paper/latent-bottlenecked-attentive-neural","slug":"latent-bottlenecked-attentive-neural","title":"Latent Bottlenecked Attentive Neural Processes","date":"2022-11-15","arxiv_id":"2211.08458","n_code_links":1,"syntology":null},{"paper":"/paper/shadowdiffusion-diffusion-based-shadow","slug":"shadowdiffusion-diffusion-based-shadow","title":"DeS3: Adaptive Attention-driven Self and Soft Shadow Removal using ViT Similarity","date":"2022-11-15","arxiv_id":"2211.08089","n_code_links":1,"syntology":null},{"paper":"/paper/evade-the-trap-of-mediocrity-promoting","slug":"evade-the-trap-of-mediocrity-promoting","title":"Evade the Trap of Mediocrity: Promoting Diversity and Novelty in Text Generation via Concentrating Attention","date":"2022-11-14","arxiv_id":"2211.07164","n_code_links":1,"syntology":null},{"paper":"/paper/on-analyzing-the-role-of-image-for-visual","slug":"on-analyzing-the-role-of-image-for-visual","title":"On Analyzing the Role of Image for Visual-enhanced Relation Extraction","date":"2022-11-14","arxiv_id":"2211.07504","n_code_links":2,"syntology":null},{"paper":null,"slug":"queryform-a-simple-zero-shot-form-entity","title":"QueryForm: A Simple Zero-shot Form Entity Query Framework","date":"2022-11-14","arxiv_id":"2211.07730","n_code_links":0,"syntology":null},{"paper":"/paper/technological-taxonomies-for-hypernym-and","slug":"technological-taxonomies-for-hypernym-and","title":"Technological taxonomies for hypernym and hyponym retrieval in patent texts","date":"2022-11-14","arxiv_id":"2212.06039","n_code_links":1,"syntology":null},{"paper":null,"slug":"wsc-trans-a-3d-network-model-for-automatic","title":"WSC-Trans: A 3D network model for automatic multi-structural segmentation of temporal bone CT","date":"2022-11-14","arxiv_id":"2211.07143","n_code_links":0,"syntology":null},{"paper":"/paper/enhancing-few-shot-image-classification-with","slug":"enhancing-few-shot-image-classification-with","title":"Enhancing Few-shot Image Classification with Cosine Transformer","date":"2022-11-13","arxiv_id":"2211.06828","n_code_links":1,"syntology":null},{"paper":"/paper/learning-from-partially-labeled-data-for","slug":"learning-from-partially-labeled-data-for","title":"Learning from partially labeled data for multi-organ and tumor segmentation","date":"2022-11-13","arxiv_id":"2211.06894","n_code_links":1,"syntology":null},{"paper":"/paper/residual-degradation-learning-unfolding","slug":"residual-degradation-learning-unfolding","title":"Residual Degradation Learning Unfolding Framework with Mixing Priors across Spectral and Spatial for Compressive Spectral Imaging","date":"2022-11-13","arxiv_id":"2211.06891","n_code_links":1,"syntology":null},{"paper":null,"slug":"au-aware-vision-transformers-for-biased","title":"AU-Aware Vision Transformers for Biased Facial Expression Recognition","date":"2022-11-12","arxiv_id":"2211.06609","n_code_links":0,"syntology":null},{"paper":null,"slug":"deyo-detr-with-yolo-for-step-by-step-object","title":"DEYO: DETR with YOLO for Step-by-Step Object Detection","date":"2022-11-12","arxiv_id":"2211.06588","n_code_links":0,"syntology":null},{"paper":null,"slug":"kinematics-transformer-solving-the-inverse","title":"Kinematics Transformer: Solving The Inverse Modeling Problem of Soft Robots using Transformers","date":"2022-11-12","arxiv_id":"2211.06643","n_code_links":0,"syntology":null},{"paper":null,"slug":"multicrossvit-multimodal-vision-transformer","title":"MultiCrossViT: Multimodal Vision Transformer for Schizophrenia Prediction using Structural MRI and Functional Network Connectivity Data","date":"2022-11-12","arxiv_id":"2211.06726","n_code_links":0,"syntology":null},{"paper":"/paper/neighbortrack-improving-single-object","slug":"neighbortrack-improving-single-object","title":"NeighborTrack: Improving Single Object Tracking by Bipartite Matching with Neighbor Tracklets","date":"2022-11-12","arxiv_id":"2211.06663","n_code_links":1,"syntology":null},{"paper":null,"slug":"an-adapter-based-multi-label-pre-training-for","title":"An Adapter based Multi-label Pre-training for Speech Separation and Enhancement","date":"2022-11-11","arxiv_id":"2211.06041","n_code_links":0,"syntology":null},{"paper":null,"slug":"control-transformer-robot-navigation-in","title":"Control Transformer: Robot Navigation in Unknown Environments through PRM-Guided Return-Conditioned Sequence Modeling","date":"2022-11-11","arxiv_id":"2211.06407","n_code_links":0,"syntology":null},{"paper":"/paper/efficient-hla-imputation-from-sequential-snps","slug":"efficient-hla-imputation-from-sequential-snps","title":"Efficient HLA imputation from sequential SNPs data by Transformer","date":"2022-11-11","arxiv_id":"2211.06430","n_code_links":1,"syntology":null},{"paper":null,"slug":"patchblender-a-motion-prior-for-video","title":"PatchBlender: A Motion Prior for Video Transformers","date":"2022-11-11","arxiv_id":"2211.14449","n_code_links":0,"syntology":null},{"paper":null,"slug":"ssgvs-semantic-scene-graph-to-video-synthesis","title":"SSGVS: Semantic Scene Graph-to-Video Synthesis","date":"2022-11-11","arxiv_id":"2211.06119","n_code_links":0,"syntology":null},{"paper":null,"slug":"token-transformer-can-class-token-help-window","title":"Token Transformer: Can class token help window-based transformer build better long-range interactions?","date":"2022-11-11","arxiv_id":"2211.06083","n_code_links":0,"syntology":null},{"paper":null,"slug":"bert-based-combination-of-convolutional-and","title":"BERT-Based Combination of Convolutional and Recurrent Neural Network for Indonesian Sentiment Analysis","date":"2022-11-10","arxiv_id":"2211.05273","n_code_links":0,"syntology":null},{"paper":"/paper/demystify-transformers-convolutions-in-modern","slug":"demystify-transformers-convolutions-in-modern","title":"Demystify Transformers & Convolutions in Modern Image Deep Networks","date":"2022-11-10","arxiv_id":"2211.05781","n_code_links":1,"syntology":{"ran":5,"of":5,"n_ran_checked":5,"n_instrument":0,"unverified":0,"pointer_only":5,"phrase":"5 ran (of which 0 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) · 0 unverified","official":{"repos":["opengvlab/stm-evaluation"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/fine-grained-entity-segmentation","slug":"fine-grained-entity-segmentation","title":"High-Quality Entity Segmentation","date":"2022-11-10","arxiv_id":"2211.05776","n_code_links":1,"syntology":null},{"paper":null,"slug":"hyperbolic-cosine-transformer-for-lidar-3d","title":"Hyperbolic Cosine Transformer for LiDAR 3D Object Detection","date":"2022-11-10","arxiv_id":"2211.05580","n_code_links":0,"syntology":null},{"paper":"/paper/oneformer-one-transformer-to-rule-universal","slug":"oneformer-one-transformer-to-rule-universal","title":"OneFormer: One Transformer to Rule Universal Image Segmentation","date":"2022-11-10","arxiv_id":"2211.06220","n_code_links":4,"syntology":{"ran":4,"of":5,"n_ran_checked":4,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["SHI-Labs/OneFormer"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/unifying-flow-stereo-and-depth-estimation","slug":"unifying-flow-stereo-and-depth-estimation","title":"Unifying Flow, Stereo and Depth Estimation","date":"2022-11-10","arxiv_id":"2211.05783","n_code_links":1,"syntology":null},{"paper":null,"slug":"viecap4h-vlsp-2021-objectaoa-enhancing","title":"VieCap4H-VLSP 2021: ObjectAoA-Enhancing performance of Object Relation Transformer with Attention on Attention for Vietnamese image captioning","date":"2022-11-10","arxiv_id":"2211.05405","n_code_links":0,"syntology":null},{"paper":"/paper/bloom-a-176b-parameter-open-access","slug":"bloom-a-176b-parameter-open-access","title":"BLOOM: A 176B-Parameter Open-Access Multilingual Language Model","date":"2022-11-09","arxiv_id":"2211.05100","n_code_links":7,"syntology":{"ran":2,"of":11,"n_ran_checked":1,"n_instrument":1,"unverified":9,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 9 unverified","official":null}},{"paper":null,"slug":"distribution-aligned-fine-tuning-for","title":"Distribution-Aligned Fine-Tuning for Efficient Neural Retrieval","date":"2022-11-09","arxiv_id":"2211.04942","n_code_links":0,"syntology":null},{"paper":"/paper/efficient-large-scale-audio-tagging-via","slug":"efficient-large-scale-audio-tagging-via","title":"Efficient Large-scale Audio Tagging via Transformer-to-CNN Knowledge Distillation","date":"2022-11-09","arxiv_id":"2211.04772","n_code_links":2,"syntology":{"ran":2,"of":2,"n_ran_checked":1,"n_instrument":1,"unverified":0,"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) · 0 unverified","official":{"repos":["fschmid56/efficientat"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":null,"slug":"efficiently-scaling-transformer-inference","title":"Efficiently Scaling Transformer Inference","date":"2022-11-09","arxiv_id":"2211.05102","n_code_links":0,"syntology":null},{"paper":"/paper/masked-vision-language-transformers-for-scene","slug":"masked-vision-language-transformers-for-scene","title":"Masked Vision-Language Transformers for Scene Text Recognition","date":"2022-11-09","arxiv_id":"2211.04785","n_code_links":1,"syntology":null},{"paper":null,"slug":"pure-transformer-with-integrated-experts-for","title":"Pure Transformer with Integrated Experts for Scene Text Recognition","date":"2022-11-09","arxiv_id":"2211.04963","n_code_links":0,"syntology":null},{"paper":null,"slug":"sg-shuffle-multi-aspect-shuffle-transformer","title":"SG-Shuffle: Multi-aspect Shuffle Transformer for Scene Graph Generation","date":"2022-11-09","arxiv_id":"2211.04773","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-reasoning-aware-explainable-vqa","title":"Towards Reasoning-Aware Explainable VQA","date":"2022-11-09","arxiv_id":"2211.05190","n_code_links":0,"syntology":null},{"paper":"/paper/training-a-vision-transformer-from-scratch-in","slug":"training-a-vision-transformer-from-scratch-in","title":"Training a Vision Transformer from scratch in less than 24 hours with 1 GPU","date":"2022-11-09","arxiv_id":"2211.05187","n_code_links":1,"syntology":{"ran":4,"of":6,"n_ran_checked":4,"n_instrument":0,"unverified":2,"pointer_only":6,"phrase":"4 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified; every one of the 4 samples that ran constructed an object rather than computing a result","official":null}},{"paper":"/paper/vitality-unifying-low-rank-and-sparse","slug":"vitality-unifying-low-rank-and-sparse","title":"ViTALiTy: Unifying Low-rank and Sparse Approximation for Vision Transformer Acceleration with a Linear Taylor Attention","date":"2022-11-09","arxiv_id":"2211.05109","n_code_links":1,"syntology":{"ran":13,"of":14,"n_ran_checked":11,"n_instrument":2,"unverified":1,"pointer_only":14,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 0 violated, 10 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["GATECH-EIC/ViTaLiTy"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"a-multimodal-approach-for-dementia-detection","title":"A Multimodal Approach for Dementia Detection from Spontaneous Speech with Tensor Fusion Layer","date":"2022-11-08","arxiv_id":"2211.04368","n_code_links":0,"syntology":null},{"paper":null,"slug":"linear-self-attention-approximation-via","title":"Linear Self-Attention Approximation via Trainable Feedforward Kernel","date":"2022-11-08","arxiv_id":"2211.04076","n_code_links":0,"syntology":null},{"paper":"/paper/simon-a-simple-framework-for-online-temporal","slug":"simon-a-simple-framework-for-online-temporal","title":"SimOn: A Simple Framework for Online Temporal Action Localization","date":"2022-11-08","arxiv_id":"2211.04905","n_code_links":1,"syntology":null},{"paper":null,"slug":"splitting-expands-the-application-range-of","title":"Splitting expands the application range of Vision Transformer -- variable Vision Transformer (vViT)","date":"2022-11-08","arxiv_id":"2211.03992","n_code_links":0,"syntology":null},{"paper":"/paper/cells-a-parallel-corpus-for-biomedical-lay","slug":"cells-a-parallel-corpus-for-biomedical-lay","title":"Retrieval augmentation of large language models for lay language generation","date":"2022-11-07","arxiv_id":"2211.03818","n_code_links":1,"syntology":{"ran":4,"of":7,"n_ran_checked":4,"n_instrument":0,"unverified":3,"pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["linguisticanomalies/pls_retrieval"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/conmix-for-source-free-single-and-multi","slug":"conmix-for-source-free-single-and-multi","title":"CoNMix for Source-free Single and Multi-target Domain Adaptation","date":"2022-11-07","arxiv_id":"2211.03876","n_code_links":1,"syntology":{"ran":2,"of":4,"n_ran_checked":0,"n_instrument":2,"unverified":2,"pointer_only":4,"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) · 2 unverified","official":{"repos":["vcl-iisc/CoNMix"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["unlocated"]}}},{"paper":"/paper/group-detr-v2-strong-object-detector-with-1","slug":"group-detr-v2-strong-object-detector-with-1","title":"Group DETR v2: Strong Object Detector with Encoder-Decoder Pretraining","date":"2022-11-07","arxiv_id":"2211.03594","n_code_links":0,"syntology":null},{"paper":"/paper/how-much-does-attention-actually-attend","slug":"how-much-does-attention-actually-attend","title":"How Much Does Attention Actually Attend? Questioning the Importance of Attention in Pretrained Transformers","date":"2022-11-07","arxiv_id":"2211.03495","n_code_links":1,"syntology":null},{"paper":null,"slug":"sequential-transformer-for-end-to-end-person","title":"Sequential Transformer for End-to-End Person Search","date":"2022-11-06","arxiv_id":"2211.04323","n_code_links":0,"syntology":null},{"paper":null,"slug":"wall-street-tree-search-risk-aware-planning","title":"Wall Street Tree Search: Risk-Aware Planning for Offline Reinforcement Learning","date":"2022-11-06","arxiv_id":"2211.04583","n_code_links":0,"syntology":null},{"paper":"/paper/inductive-graph-transformer-for-delivery-time","slug":"inductive-graph-transformer-for-delivery-time","title":"Inductive Graph Transformer for Delivery Time Estimation","date":"2022-11-05","arxiv_id":"2211.02863","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-transformer-architecture-for-online-gesture","title":"A Transformer Architecture for Online Gesture Recognition of Mathematical Expressions","date":"2022-11-04","arxiv_id":"2211.02643","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-weakly-supervised-streaming-multilingual","title":"A Weakly-Supervised Streaming Multilingual Speech Model with Truly Zero-Shot Capability","date":"2022-11-04","arxiv_id":"2211.02499","n_code_links":0,"syntology":null},{"paper":null,"slug":"ccatmos-convolutional-context-aware","title":"CCATMos: Convolutional Context-aware Transformer Network for Non-intrusive Speech Quality Assessment","date":"2022-11-04","arxiv_id":"2211.02577","n_code_links":0,"syntology":null},{"paper":null,"slug":"deep-learning-for-structural-health","title":"Deep learning for structural health monitoring: An application to heritage structures","date":"2022-11-04","arxiv_id":"2211.10351","n_code_links":0,"syntology":null},{"paper":null,"slug":"fradulent-user-detection-via-behavior","title":"Fraudulent User Detection Via Behavior Information Aggregation Network (BIAN) On Large-Scale Financial Social Network","date":"2022-11-04","arxiv_id":"2211.06315","n_code_links":0,"syntology":null},{"paper":null,"slug":"osic-a-new-one-stage-image-captioner-coined","title":"OSIC: A New One-Stage Image Captioner Coined","date":"2022-11-04","arxiv_id":"2211.02321","n_code_links":0,"syntology":null},{"paper":null,"slug":"patch-dct-vs-lenet","title":"Patch DCT vs LeNet","date":"2022-11-04","arxiv_id":"2211.02392","n_code_links":0,"syntology":null},{"paper":"/paper/real-time-target-sound-extraction","slug":"real-time-target-sound-extraction","title":"Real-Time Target Sound Extraction","date":"2022-11-04","arxiv_id":"2211.02250","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":["vb000/waveformer"],"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":"/paper/speaker-vgg-cct-cross-corpus-speech-emotion","slug":"speaker-vgg-cct-cross-corpus-speech-emotion","title":"SPEAKER VGG CCT: Cross-corpus Speech Emotion Recognition with Speaker Embedding and Vision Transformers","date":"2022-11-04","arxiv_id":"2211.02366","n_code_links":1,"syntology":null},{"paper":null,"slug":"channel-aware-pretraining-of-joint-encoder","title":"Channel-Aware Pretraining of Joint Encoder-Decoder Self-Supervised Model for Telephonic-Speech ASR","date":"2022-11-03","arxiv_id":"2211.01669","n_code_links":0,"syntology":null},{"paper":"/paper/exploring-the-state-of-the-art-language","slug":"exploring-the-state-of-the-art-language","title":"Transformers on Multilingual Clause-Level Morphology","date":"2022-11-03","arxiv_id":"2211.01736","n_code_links":1,"syntology":null},{"paper":"/paper/fedtp-federated-learning-by-transformer","slug":"fedtp-federated-learning-by-transformer","title":"FedTP: Federated Learning by Transformer Personalization","date":"2022-11-03","arxiv_id":"2211.01572","n_code_links":1,"syntology":{"ran":7,"of":10,"n_ran_checked":5,"n_instrument":2,"unverified":3,"pointer_only":1,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 2 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","official":{"repos":["zhyczy/fedtp"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/pangu-weather-a-3d-high-resolution-model-for","slug":"pangu-weather-a-3d-high-resolution-model-for","title":"Pangu-Weather: A 3D High-Resolution Model for Fast and Accurate Global Weather Forecast","date":"2022-11-03","arxiv_id":"2211.02556","n_code_links":6,"syntology":null},{"paper":null,"slug":"polybuilding-polygon-transformer-for-end-to","title":"PolyBuilding: Polygon Transformer for End-to-End Building Extraction","date":"2022-11-03","arxiv_id":"2211.01589","n_code_links":0,"syntology":null},{"paper":"/paper/sap-detr-bridging-the-gap-between-salient","slug":"sap-detr-bridging-the-gap-between-salient","title":"SAP-DETR: Bridging the Gap Between Salient Points and Queries-Based Transformer Detector for Fast Model Convergency","date":"2022-11-03","arxiv_id":"2211.02006","n_code_links":1,"syntology":null},{"paper":null,"slug":"attention-based-neural-cellular-automata","title":"Attention-based Neural Cellular Automata","date":"2022-11-02","arxiv_id":"2211.01233","n_code_links":0,"syntology":null},{"paper":"/paper/mast-multiscale-audio-spectrogram","slug":"mast-multiscale-audio-spectrogram","title":"MAST: Multiscale Audio Spectrogram Transformers","date":"2022-11-02","arxiv_id":"2211.01515","n_code_links":1,"syntology":null},{"paper":"/paper/mpcformer-fast-performant-and-private","slug":"mpcformer-fast-performant-and-private","title":"MPCFormer: fast, performant and private Transformer inference with MPC","date":"2022-11-02","arxiv_id":"2211.01452","n_code_links":1,"syntology":null},{"paper":"/paper/pop2piano-pop-audio-based-piano-cover","slug":"pop2piano-pop-audio-based-piano-cover","title":"Pop2Piano : Pop Audio-based Piano Cover Generation","date":"2022-11-02","arxiv_id":"2211.00895","n_code_links":4,"syntology":{"ran":3,"of":3,"n_ran_checked":1,"n_instrument":2,"unverified":0,"pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["sweetcocoa/pop2piano"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"regclr-a-self-supervised-framework-for","title":"RegCLR: A Self-Supervised Framework for Tabular Representation Learning in the Wild","date":"2022-11-02","arxiv_id":"2211.01165","n_code_links":0,"syntology":null},{"paper":null,"slug":"transformer-based-encoder-encoder","title":"Transformer-based encoder-encoder architecture for Spoken Term Detection","date":"2022-11-02","arxiv_id":"2211.01089","n_code_links":0,"syntology":null},{"paper":"/paper/witt-a-wireless-image-transmission","slug":"witt-a-wireless-image-transmission","title":"WITT: A Wireless Image Transmission Transformer for Semantic Communications","date":"2022-11-02","arxiv_id":"2211.00937","n_code_links":2,"syntology":null},{"paper":null,"slug":"linkformer-automatic-contextualised-link","title":"An Empirical Study on Data Leakage and Generalizability of Link Prediction Models for Issues and Commits","date":"2022-11-01","arxiv_id":"2211.00381","n_code_links":0,"syntology":null},{"paper":null,"slug":"vit-deit-an-ensemble-model-for-breast-cancer","title":"ViT-DeiT: An Ensemble Model for Breast Cancer Histopathological Images Classification","date":"2022-11-01","arxiv_id":"2211.00749","n_code_links":0,"syntology":null},{"paper":"/paper/adamix-mixture-of-adaptations-for-parameter","slug":"adamix-mixture-of-adaptations-for-parameter","title":"AdaMix: Mixture-of-Adaptations for Parameter-efficient Model Tuning","date":"2022-10-31","arxiv_id":"2210.17451","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/AdaMix"],"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/gptq-accurate-post-training-quantization-for","slug":"gptq-accurate-post-training-quantization-for","title":"GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers","date":"2022-10-31","arxiv_id":"2210.17323","n_code_links":17,"syntology":{"ran":5,"of":15,"n_ran_checked":2,"n_instrument":3,"unverified":10,"pointer_only":1,"phrase":"5 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 10 unverified","official":{"repos":["ist-daslab/gptq"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":["listed","official"]}}},{"paper":null,"slug":"joint-audio-text-training-for-transformer","title":"Joint Audio/Text Training for Transformer Rescorer of Streaming Speech Recognition","date":"2022-10-31","arxiv_id":"2211.00174","n_code_links":0,"syntology":null},{"paper":null,"slug":"leveraging-pre-trained-models-for-failure","title":"Leveraging Pre-trained Models for Failure Analysis Triplets Generation","date":"2022-10-31","arxiv_id":"2210.17497","n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-camera-calibration-free-bev","title":"Multi-Camera Calibration Free BEV Representation for 3D Object Detection","date":"2022-10-31","arxiv_id":"2210.17252","n_code_links":0,"syntology":null},{"paper":"/paper/probabilistic-decomposition-transformer-for","slug":"probabilistic-decomposition-transformer-for","title":"Probabilistic Decomposition Transformer for Time Series Forecasting","date":"2022-10-31","arxiv_id":"2210.17393","n_code_links":1,"syntology":null},{"paper":null,"slug":"qnet-a-quantum-native-sequence-encoder","title":"QNet: A Quantum-native Sequence Encoder Architecture","date":"2022-10-31","arxiv_id":"2210.17262","n_code_links":0,"syntology":null},{"paper":"/paper/quala-minilm-a-quantized-length-adaptive","slug":"quala-minilm-a-quantized-length-adaptive","title":"QuaLA-MiniLM: a Quantized Length Adaptive MiniLM","date":"2022-10-31","arxiv_id":"2210.17114","n_code_links":2,"syntology":null},{"paper":"/paper/spatial-temporal-synchronous-graph-1","slug":"spatial-temporal-synchronous-graph-1","title":"Spatial-Temporal Synchronous Graph Transformer network (STSGT) for COVID-19 forecasting","date":"2022-10-31","arxiv_id":"2211.00082","n_code_links":1,"syntology":null},{"paper":null,"slug":"structured-state-space-decoder-for-speech","title":"Structured State Space Decoder for Speech Recognition and Synthesis","date":"2022-10-31","arxiv_id":"2210.17098","n_code_links":0,"syntology":null},{"paper":null,"slug":"vit-lsla-vision-transformer-with-light-self","title":"ViT-LSLA: Vision Transformer with Light Self-Limited-Attention","date":"2022-10-31","arxiv_id":"2210.17115","n_code_links":0,"syntology":null},{"paper":"/paper/an-efficient-memory-augmented-transformer-for","slug":"an-efficient-memory-augmented-transformer-for","title":"An Efficient Memory-Augmented Transformer for Knowledge-Intensive NLP Tasks","date":"2022-10-30","arxiv_id":"2210.16773","n_code_links":1,"syntology":null},{"paper":"/paper/attention-swin-u-net-cross-contextual","slug":"attention-swin-u-net-cross-contextual","title":"Attention Swin U-Net: Cross-Contextual Attention Mechanism for Skin Lesion Segmentation","date":"2022-10-30","arxiv_id":"2210.16898","n_code_links":1,"syntology":null},{"paper":"/paper/foreign-object-debris-detection-for-airport","slug":"foreign-object-debris-detection-for-airport","title":"Foreign Object Debris Detection for Airport Pavement Images based on Self-supervised Localization and Vision Transformer","date":"2022-10-30","arxiv_id":"2210.16901","n_code_links":1,"syntology":null},{"paper":"/paper/quest-graph-transformer-for-quantum-circuit","slug":"quest-graph-transformer-for-quantum-circuit","title":"QuEst: Graph Transformer for Quantum Circuit Reliability Estimation","date":"2022-10-30","arxiv_id":"2210.16724","n_code_links":1,"syntology":null},{"paper":null,"slug":"time-reversed-diffusion-tensor-transformer-a","title":"Time-rEversed diffusioN tEnsor Transformer: A new TENET of Few-Shot Object Detection","date":"2022-10-30","arxiv_id":"2210.16897","n_code_links":0,"syntology":null},{"paper":null,"slug":"token2vec-a-joint-self-supervised-pre","title":"token2vec: A Joint Self-Supervised Pre-training Framework Using Unpaired Speech and Text","date":"2022-10-30","arxiv_id":"2210.16755","n_code_links":0,"syntology":null},{"paper":"/paper/vitasd-robust-vision-transformer-baselines","slug":"vitasd-robust-vision-transformer-baselines","title":"ViTASD: Robust Vision Transformer Baselines for Autism Spectrum Disorder Facial Diagnosis","date":"2022-10-30","arxiv_id":"2210.16943","n_code_links":1,"syntology":null},{"paper":null,"slug":"cmt-interpretable-model-for-rapid-recognition","title":"Interpretable CNN-Multilevel Attention Transformer for Rapid Recognition of Pneumonia from Chest X-Ray Images","date":"2022-10-29","arxiv_id":"2210.16584","n_code_links":0,"syntology":null}],"record_sha256":"35415d2a23da58f65eb13dd93b48ec44ff9b156b9859e87e02407ade3017dc32","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}