{"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/residual-connection/papers/164","list_of":"/method/residual-connection","method":"Residual Connection","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":164,"pages_in_order":285,"rows_per_page":100,"rows":[16301,16400],"of":28401,"counts":{"archive_papers_tagged":28401,"with_a_code_link":12847,"where_syntology_ran_a_sample":3897,"not_listed_spam_title":0,"listed":28401,"listed_where_code_ran":3897,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":3291,"every_run_a_failure_of_syntologys_instrument":606,"listed_with_a_run_with_no_instrument_failure":3291,"listed_every_run_a_failure_of_syntologys_instrument":606,"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/residual-connection","prev":"/method/residual-connection/papers/163","next":"/method/residual-connection/papers/165","papers":[{"paper":"/paper/crosslingual-generalization-through-multitask","slug":"crosslingual-generalization-through-multitask","title":"Crosslingual Generalization through Multitask Finetuning","date":"2022-11-03","arxiv_id":"2211.01786","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":4,"n_instrument":0,"unverified":0,"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) · 0 unverified","official":{"repos":["bigscience-workshop/xmtf"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"evaluating-a-synthetic-image-dataset","title":"Evaluating a Synthetic Image Dataset Generated with Stable Diffusion","date":"2022-11-03","arxiv_id":"2211.01777","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/fine-tuning-language-models-via-epistemic","slug":"fine-tuning-language-models-via-epistemic","title":"Fine-Tuning Language Models via Epistemic Neural Networks","date":"2022-11-03","arxiv_id":"2211.01568","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 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":["deepmind/neural_testbed"],"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":null,"slug":"graph-based-multi-camera-soccer-player","title":"Graph-Based Multi-Camera Soccer Player Tracker","date":"2022-11-03","arxiv_id":"2211.02125","n_code_links":0,"syntology":null},{"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":null,"slug":"rethinking-hierarchicies-in-pre-trained-plain","title":"Rethinking Hierarchies in Pre-trained Plain Vision Transformer","date":"2022-11-03","arxiv_id":"2211.01785","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":"scaling-multimodal-pre-training-via-cross","title":"Scaling Multimodal Pre-Training via Cross-Modality Gradient Harmonization","date":"2022-11-03","arxiv_id":"2211.02077","n_code_links":0,"syntology":null},{"paper":null,"slug":"self-similarity-matrix-based-cnn-filter","title":"Self Similarity Matrix based CNN Filter Pruning","date":"2022-11-03","arxiv_id":"2211.01814","n_code_links":0,"syntology":null},{"paper":null,"slug":"using-large-pre-trained-language-model-to","title":"Using Large Pre-Trained Language Model to Assist FDA in Premarket Medical Device","date":"2022-11-03","arxiv_id":"2212.01217","n_code_links":0,"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":null,"slug":"bectra-transducer-based-end-to-end-asr-with","title":"BECTRA: Transducer-based End-to-End ASR with BERT-Enhanced Encoder","date":"2022-11-02","arxiv_id":"2211.00792","n_code_links":0,"syntology":null},{"paper":"/paper/dc-cyclegan-bidirectional-ct-to-mr-synthesis","slug":"dc-cyclegan-bidirectional-ct-to-mr-synthesis","title":"DC-cycleGAN: Bidirectional CT-to-MR Synthesis from Unpaired Data","date":"2022-11-02","arxiv_id":"2211.01293","n_code_links":1,"syntology":null},{"paper":"/paper/ediffi-text-to-image-diffusion-models-with-an","slug":"ediffi-text-to-image-diffusion-models-with-an","title":"eDiff-I: Text-to-Image Diffusion Models with an Ensemble of Expert Denoisers","date":"2022-11-02","arxiv_id":"2211.01324","n_code_links":2,"syntology":{"ran":11,"of":13,"n_ran_checked":10,"n_instrument":1,"unverified":2,"pointer_only":0,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 0 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","official":null}},{"paper":"/paper/equimod-an-equivariance-module-to-improve","slug":"equimod-an-equivariance-module-to-improve","title":"EquiMod: An Equivariance Module to Improve Self-Supervised Learning","date":"2022-11-02","arxiv_id":"2211.01244","n_code_links":1,"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":null,"slug":"multi-level-distillation-of-semantic","title":"Multi-level Distillation of Semantic Knowledge for Pre-training Multilingual Language Model","date":"2022-11-02","arxiv_id":"2211.01200","n_code_links":0,"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":"processing-long-legal-documents-with-pre","title":"Processing Long Legal Documents with Pre-trained Transformers: Modding LegalBERT and Longformer","date":"2022-11-02","arxiv_id":"2211.00974","n_code_links":0,"syntology":null},{"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":null,"slug":"tsaa-a-two-stage-anchor-assignment-method","title":"TSAA: A Two-Stage Anchor Assignment Method towards Anchor Drift in Crowded Object Detection","date":"2022-11-02","arxiv_id":"2211.00826","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":"/paper/classactionprediction-a-challenging-benchmark","slug":"classactionprediction-a-challenging-benchmark","title":"ClassActionPrediction: A Challenging Benchmark for Legal Judgment Prediction of Class Action Cases in the US","date":"2022-11-01","arxiv_id":"2211.00582","n_code_links":1,"syntology":null},{"paper":null,"slug":"frsum-towards-faithful-abstractive-1","title":"FRSUM: Towards Faithful Abstractive Summarization via Enhancing Factual Robustness","date":"2022-11-01","arxiv_id":"2211.00294","n_code_links":0,"syntology":null},{"paper":"/paper/how-well-do-unsupervised-learning-algorithms","slug":"how-well-do-unsupervised-learning-algorithms","title":"How Well Do Unsupervised Learning Algorithms Model Human Real-time and Life-long Learning?","date":"2022-11-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/interpretability-in-the-wild-a-circuit-for","slug":"interpretability-in-the-wild-a-circuit-for","title":"Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small","date":"2022-11-01","arxiv_id":"2211.00593","n_code_links":7,"syntology":{"ran":9,"of":13,"n_ran_checked":9,"n_instrument":0,"unverified":4,"pointer_only":0,"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) · 4 unverified","official":{"repos":["redwoodresearch/easy-transformer"],"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":"investigating-content-aware-neural-text-to","title":"Investigating Content-Aware Neural Text-To-Speech MOS Prediction Using Prosodic and Linguistic Features","date":"2022-11-01","arxiv_id":"2211.00342","n_code_links":0,"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":"preserving-in-context-learning-ability-in","title":"Two-stage LLM Fine-tuning with Less Specialization and More Generalization","date":"2022-11-01","arxiv_id":"2211.00635","n_code_links":0,"syntology":null},{"paper":null,"slug":"recognition-of-defective-mineral-wool-using","title":"Recognition of Defective Mineral Wool Using Pruned ResNet Models","date":"2022-11-01","arxiv_id":"2211.00466","n_code_links":0,"syntology":null},{"paper":null,"slug":"reduce-reuse-recycle-improving-training","title":"Reduce, Reuse, Recycle: Improving Training Efficiency with Distillation","date":"2022-11-01","arxiv_id":"2211.00683","n_code_links":0,"syntology":null},{"paper":"/paper/t5lephone-bridging-speech-and-text-self","slug":"t5lephone-bridging-speech-and-text-self","title":"T5lephone: Bridging Speech and Text Self-supervised Models for Spoken Language Understanding via Phoneme level T5","date":"2022-11-01","arxiv_id":"2211.00586","n_code_links":1,"syntology":null},{"paper":"/paper/text-only-training-for-image-captioning-using","slug":"text-only-training-for-image-captioning-using","title":"Text-Only Training for Image Captioning using Noise-Injected CLIP","date":"2022-11-01","arxiv_id":"2211.00575","n_code_links":4,"syntology":{"ran":4,"of":5,"n_ran_checked":2,"n_instrument":2,"unverified":1,"pointer_only":1,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["davidhuji/capdec"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/titan-bringing-the-deep-image-prior-to","slug":"titan-bringing-the-deep-image-prior-to","title":"TITAN: Bringing The Deep Image Prior to Implicit Representations","date":"2022-11-01","arxiv_id":"2211.00219","n_code_links":1,"syntology":null},{"paper":"/paper/vid-trans-reid-enhanced-video-transformers","slug":"vid-trans-reid-enhanced-video-transformers","title":"VID-Trans-ReID: Enhanced Video Transformers for Person Re-identification","date":"2022-11-01","arxiv_id":null,"n_code_links":1,"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/a-law-of-data-separation-in-deep-learning","slug":"a-law-of-data-separation-in-deep-learning","title":"A Law of Data Separation in Deep Learning","date":"2022-10-31","arxiv_id":"2210.17020","n_code_links":2,"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/controllable-factuality-in-document-grounded","slug":"controllable-factuality-in-document-grounded","title":"Controllable Factuality in Document-Grounded Dialog Systems Using a Noisy Channel Model","date":"2022-10-31","arxiv_id":"2210.17418","n_code_links":1,"syntology":null},{"paper":null,"slug":"convolution-based-channel-frequency-attention","title":"Convolution-Based Channel-Frequency Attention for Text-Independent Speaker Verification","date":"2022-10-31","arxiv_id":"2210.17310","n_code_links":0,"syntology":null},{"paper":null,"slug":"cross-lingual-text-to-speech-with-flow-based","title":"Cross-lingual Text-To-Speech with Flow-based Voice Conversion for Improved Pronunciation","date":"2022-10-31","arxiv_id":"2210.17264","n_code_links":0,"syntology":null},{"paper":"/paper/efficient-document-retrieval-by-end-to-end","slug":"efficient-document-retrieval-by-end-to-end","title":"Efficient Document Retrieval by End-to-End Refining and Quantizing BERT Embedding with Contrastive Product Quantization","date":"2022-10-31","arxiv_id":"2210.17170","n_code_links":1,"syntology":null},{"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":"model-compression-for-dnn-based-text","title":"Model Compression for DNN-based Speaker Verification Using Weight Quantization","date":"2022-10-31","arxiv_id":"2210.17326","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":null,"slug":"sdcl-self-distillation-contrastive-learning","title":"SDCL: Self-Distillation Contrastive Learning for Chinese Spell Checking","date":"2022-10-31","arxiv_id":"2210.17168","n_code_links":0,"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":"/paper/ssd-lm-semi-autoregressive-simplex-based","slug":"ssd-lm-semi-autoregressive-simplex-based","title":"SSD-LM: Semi-autoregressive Simplex-based Diffusion Language Model for Text Generation and Modular Control","date":"2022-10-31","arxiv_id":"2210.17432","n_code_links":2,"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":"teacher-student-curriculum-learning-for","title":"Teacher-student curriculum learning for reinforcement learning","date":"2022-10-31","arxiv_id":"2210.17368","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-importance-of-accurate-alignments-in-end","title":"Towards Developing State-of-the-Art TTS Synthesisers for 13 Indian Languages with Signal Processing aided Alignments","date":"2022-10-31","arxiv_id":"2210.17153","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-zero-shot-and-few-shot-table-question","title":"Towards Zero-Shot and Few-Shot Table Question Answering using GPT-3","date":"2022-10-31","arxiv_id":"2210.17284","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/a-simple-efficient-and-scalable-contrastive","slug":"a-simple-efficient-and-scalable-contrastive","title":"A simple, efficient and scalable contrastive masked autoencoder for learning visual representations","date":"2022-10-30","arxiv_id":"2210.16870","n_code_links":1,"syntology":{"ran":5,"of":7,"n_ran_checked":5,"n_instrument":0,"unverified":2,"pointer_only":2,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":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/exemplar-guided-deep-neural-network-for","slug":"exemplar-guided-deep-neural-network-for","title":"Exemplar Guided Deep Neural Network for Spatial Transcriptomics Analysis of Gene Expression Prediction","date":"2022-10-30","arxiv_id":"2210.16721","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":null,"slug":"learning-to-decompose-hypothetical-question","title":"Learning to Decompose: Hypothetical Question Decomposition Based on Comparable Texts","date":"2022-10-30","arxiv_id":"2210.16865","n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-view-multi-label-anomaly-network","title":"Multi-view Multi-label Anomaly Network Traffic Classification based on MLP-Mixer Neural Network","date":"2022-10-30","arxiv_id":"2210.16719","n_code_links":0,"syntology":null},{"paper":"/paper/parameter-efficient-tuning-makes-a-good","slug":"parameter-efficient-tuning-makes-a-good","title":"Parameter-Efficient Tuning Makes a Good Classification Head","date":"2022-10-30","arxiv_id":"2210.16771","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/unsupervised-learning-of-structured","slug":"unsupervised-learning-of-structured","title":"Unsupervised Learning of Structured Representations via Closed-Loop Transcription","date":"2022-10-30","arxiv_id":"2210.16782","n_code_links":1,"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":"bert-meets-ctc-new-formulation-of-end-to-end","title":"BERT Meets CTC: New Formulation of End-to-End Speech Recognition with Pre-trained Masked Language Model","date":"2022-10-29","arxiv_id":"2210.16663","n_code_links":0,"syntology":null},{"paper":"/paper/clenshaw-graph-neural-networks","slug":"clenshaw-graph-neural-networks","title":"Clenshaw Graph Neural Networks","date":"2022-10-29","arxiv_id":"2210.16508","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},{"paper":"/paper/defix-detecting-and-fixing-failure-scenarios","slug":"defix-detecting-and-fixing-failure-scenarios","title":"DeFIX: Detecting and Fixing Failure Scenarios with Reinforcement Learning in Imitation Learning Based Autonomous Driving","date":"2022-10-29","arxiv_id":"2210.16567","n_code_links":2,"syntology":null},{"paper":null,"slug":"empirical-evaluation-of-post-training","title":"Empirical Evaluation of Post-Training Quantization Methods for Language Tasks","date":"2022-10-29","arxiv_id":"2210.16621","n_code_links":0,"syntology":null},{"paper":"/paper/exploiting-prompt-learning-with-pre-trained","slug":"exploiting-prompt-learning-with-pre-trained","title":"Exploiting prompt learning with pre-trained language models for Alzheimer's Disease detection","date":"2022-10-29","arxiv_id":"2210.16539","n_code_links":1,"syntology":null},{"paper":null,"slug":"pair-detr-contrastive-learning-speeds-up-detr","title":"Pair DETR: Contrastive Learning Speeds Up DETR Training","date":"2022-10-29","arxiv_id":"2210.16476","n_code_links":0,"syntology":null},{"paper":"/paper/recursive-reasoning-in-minimax-games-a-level","slug":"recursive-reasoning-in-minimax-games-a-level","title":"Recursive Reasoning in Minimax Games: A Level $k$ Gradient Play Method","date":"2022-10-29","arxiv_id":"2210.16482","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-long-term-dependent-and-trustworthy","title":"A Long-term Dependent and Trustworthy Approach to Reactor Accident Prognosis based on Temporal Fusion Transformer","date":"2022-10-28","arxiv_id":"2210.17298","n_code_links":0,"syntology":null},{"paper":null,"slug":"an-approach-for-noisy-crowdsourced-datasets","title":"Incorporating Crowdsourced Annotator Distributions into Ensemble Modeling to Improve Classification Trustworthiness for Ancient Greek Papyri","date":"2022-10-28","arxiv_id":"2210.16380","n_code_links":0,"syntology":null},{"paper":"/paper/bebert-efficient-and-robust-binary-ensemble","slug":"bebert-efficient-and-robust-binary-ensemble","title":"BEBERT: Efficient and Robust Binary Ensemble BERT","date":"2022-10-28","arxiv_id":"2210.15976","n_code_links":1,"syntology":null},{"paper":"/paper/contextual-learning-in-fourier-complex-field","slug":"contextual-learning-in-fourier-complex-field","title":"Contextual Learning in Fourier Complex Field for VHR Remote Sensing Images","date":"2022-10-28","arxiv_id":"2210.15972","n_code_links":3,"syntology":null},{"paper":null,"slug":"differentially-private-cutmix-for-split","title":"Differentially Private CutMix for Split Learning with Vision Transformer","date":"2022-10-28","arxiv_id":"2210.15986","n_code_links":0,"syntology":null},{"paper":null,"slug":"digital-twins-of-physical-printing-imaging","title":"Digital twins of physical printing-imaging channel","date":"2022-10-28","arxiv_id":"2210.17420","n_code_links":0,"syntology":null},{"paper":null,"slug":"dimensionality-reduced-antenna-array-for","title":"Dimensionality Reduced Antenna Array for Beamforming/steering","date":"2022-10-28","arxiv_id":"2210.16197","n_code_links":0,"syntology":null},{"paper":"/paper/efficient-speech-translation-with-dynamic","slug":"efficient-speech-translation-with-dynamic","title":"Efficient Speech Translation with Dynamic Latent Perceivers","date":"2022-10-28","arxiv_id":"2210.16264","n_code_links":1,"syntology":null},{"paper":null,"slug":"elastic-weight-consolidation-improves-the","title":"Elastic Weight Consolidation Improves the Robustness of Self-Supervised Learning Methods under Transfer","date":"2022-10-28","arxiv_id":"2210.16365","n_code_links":0,"syntology":null},{"paper":"/paper/exploring-spatial-temporal-features-for","slug":"exploring-spatial-temporal-features-for","title":"Exploring Spatial-Temporal Features for Deepfake Detection and Localization","date":"2022-10-28","arxiv_id":"2210.15872","n_code_links":1,"syntology":null},{"paper":null,"slug":"feature-engineering-vs-bert-on-twitter-data","title":"Feature Engineering vs BERT on Twitter Data","date":"2022-10-28","arxiv_id":"2210.16168","n_code_links":0,"syntology":null},{"paper":null,"slug":"federated-learning-for-chronic-obstructive","title":"Federated Learning for Chronic Obstructive Pulmonary Disease Classification with Partial Personalized Attention Mechanism","date":"2022-10-28","arxiv_id":"2210.16142","n_code_links":0,"syntology":null},{"paper":null,"slug":"flatter-faster-scaling-momentum-for-optimal","title":"Flatter, faster: scaling momentum for optimal speedup of SGD","date":"2022-10-28","arxiv_id":"2210.16400","n_code_links":0,"syntology":null},{"paper":null,"slug":"grafting-vision-transformers","title":"Grafting Vision Transformers","date":"2022-10-28","arxiv_id":"2210.15943","n_code_links":0,"syntology":null},{"paper":null,"slug":"modeling-structure-building-in-the-brain-with","title":"Modeling structure-building in the brain with CCG parsing and large language models","date":"2022-10-28","arxiv_id":"2210.16147","n_code_links":0,"syntology":null},{"paper":"/paper/nonparallel-high-quality-audio-super","slug":"nonparallel-high-quality-audio-super","title":"Nonparallel High-Quality Audio Super Resolution with Domain Adaptation and Resampling CycleGANs","date":"2022-10-28","arxiv_id":"2210.15887","n_code_links":1,"syntology":null}],"record_sha256":"304eeddd26735ecb8d50cd17ff8df158c3d75ceca9643ff62c9a9cf5bf7b5c0c","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}