{"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/softmax/papers/240","list_of":"/method/softmax","method":"Softmax","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":240,"pages_in_order":375,"rows_per_page":100,"rows":[23901,24000],"of":37443,"counts":{"archive_papers_tagged":37443,"with_a_code_link":15869,"where_syntology_ran_a_sample":4578,"not_listed_spam_title":0,"listed":37443,"listed_where_code_ran":4578,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":3835,"every_run_a_failure_of_syntologys_instrument":743,"listed_with_a_run_with_no_instrument_failure":3835,"listed_every_run_a_failure_of_syntologys_instrument":743,"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/softmax","prev":"/method/softmax/papers/239","next":"/method/softmax/papers/241","papers":[{"paper":"/paper/active-example-selection-for-in-context","slug":"active-example-selection-for-in-context","title":"Active Example Selection for In-Context Learning","date":"2022-11-08","arxiv_id":"2211.04486","n_code_links":1,"syntology":{"ran":10,"of":16,"n_ran_checked":4,"n_instrument":6,"unverified":6,"pointer_only":0,"phrase":"10 ran (of which 3 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 6 where Syntology's instrument failed) · 6 unverified","official":{"repos":["chicagohai/active-example-selection"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":3,"n_ran_no_instrument_failure":4,"n_unverified":6,"ran_from_kinds":["official"]}}},{"paper":"/paper/conciseness-an-overlooked-language-task","slug":"conciseness-an-overlooked-language-task","title":"Conciseness: An Overlooked Language Task","date":"2022-11-08","arxiv_id":"2211.04126","n_code_links":0,"syntology":null},{"paper":null,"slug":"discover-explanation-improvement-automatic","title":"Discover, Explanation, Improvement: An Automatic Slice Detection Framework for Natural Language Processing","date":"2022-11-08","arxiv_id":"2211.04476","n_code_links":0,"syntology":null},{"paper":"/paper/going-for-goal-a-resource-for-grounded","slug":"going-for-goal-a-resource-for-grounded","title":"Going for GOAL: A Resource for Grounded Football Commentaries","date":"2022-11-08","arxiv_id":"2211.04534","n_code_links":1,"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/pushing-the-limits-of-self-supervised-speaker","slug":"pushing-the-limits-of-self-supervised-speaker","title":"Pushing the limits of self-supervised speaker verification using regularized distillation framework","date":"2022-11-08","arxiv_id":"2211.04168","n_code_links":1,"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":null,"slug":"ad-bert-using-pre-trained-contextualized","title":"AD-BERT: Using Pre-trained contextualized embeddings to Predict the Progression from Mild Cognitive Impairment to Alzheimer's Disease","date":"2022-11-07","arxiv_id":"2212.06042","n_code_links":0,"syntology":null},{"paper":null,"slug":"automatic-number-plate-recognition-anpr-with","title":"Automatic Number Plate Recognition (ANPR) with YOLOv3-CNN","date":"2022-11-07","arxiv_id":"2211.05229","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":"interpreting-deep-learning-output-for-out-of","title":"Interpreting deep learning output for out-of-distribution detection","date":"2022-11-07","arxiv_id":"2211.03637","n_code_links":0,"syntology":null},{"paper":"/paper/hear-the-flow-optical-flow-based-self","slug":"hear-the-flow-optical-flow-based-self","title":"Hear The Flow: Optical Flow-Based Self-Supervised Visual Sound Source Localization","date":"2022-11-06","arxiv_id":"2211.03019","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":"/paper/suffix-retrieval-augmented-language-modeling","slug":"suffix-retrieval-augmented-language-modeling","title":"Suffix Retrieval-Augmented Language Modeling","date":"2022-11-06","arxiv_id":"2211.03053","n_code_links":1,"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":null,"slug":"a-robust-and-low-complexity-deep-learning","title":"A Robust and Low Complexity Deep Learning Model for Remote Sensing Image Classification","date":"2022-11-05","arxiv_id":"2211.02820","n_code_links":0,"syntology":null},{"paper":null,"slug":"accurate-and-reliable-methods-for-5g-uav","title":"Accurate and Reliable Methods for 5G UAV Jamming Identification With Calibrated Uncertainty","date":"2022-11-05","arxiv_id":"2211.02924","n_code_links":0,"syntology":null},{"paper":"/paper/esknet-an-enhanced-adaptive-selection-kernel","slug":"esknet-an-enhanced-adaptive-selection-kernel","title":"ESKNet-An enhanced adaptive selection kernel convolution for breast tumors segmentation","date":"2022-11-05","arxiv_id":"2211.02915","n_code_links":1,"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":"/paper/learning-to-infer-from-unlabeled-data-a-semi","slug":"learning-to-infer-from-unlabeled-data-a-semi","title":"Learning to Infer from Unlabeled Data: A Semi-supervised Learning Approach for Robust Natural Language Inference","date":"2022-11-05","arxiv_id":"2211.02971","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":"bert-deep-cnn-state-of-the-art-for-sentiment","title":"BERT-Deep CNN: State-of-the-Art for Sentiment Analysis of COVID-19 Tweets","date":"2022-11-04","arxiv_id":"2211.09733","n_code_links":0,"syntology":null},{"paper":null,"slug":"bert-for-long-documents-a-case-study-of","title":"BERT for Long Documents: A Case Study of Automated ICD Coding","date":"2022-11-04","arxiv_id":"2211.02519","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":"/paper/continuous-prompt-tuning-based-textual","slug":"continuous-prompt-tuning-based-textual","title":"Continuous Prompt Tuning Based Textual Entailment Model for E-commerce Entity Typing","date":"2022-11-04","arxiv_id":"2211.02483","n_code_links":1,"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":"generation-of-chinese-classical-poetry-based","title":"Generation of Chinese classical poetry based on pre-trained model","date":"2022-11-04","arxiv_id":"2211.02541","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/rcdpt-radar-camera-fusion-dense-prediction","slug":"rcdpt-radar-camera-fusion-dense-prediction","title":"RCDPT: Radar-Camera fusion Dense Prediction Transformer","date":"2022-11-04","arxiv_id":"2211.02432","n_code_links":1,"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":"/paper/ssda-yolo-semi-supervised-domain-adaptive","slug":"ssda-yolo-semi-supervised-domain-adaptive","title":"SSDA-YOLO: Semi-supervised Domain Adaptive YOLO for Cross-Domain Object Detection","date":"2022-11-04","arxiv_id":"2211.02213","n_code_links":1,"syntology":null},{"paper":"/paper/towards-asteroid-detection-in-microlensing","slug":"towards-asteroid-detection-in-microlensing","title":"Towards Asteroid Detection in Microlensing Surveys with Deep Learning","date":"2022-11-04","arxiv_id":"2211.02239","n_code_links":1,"syntology":null},{"paper":"/paper/wavenets-wavelet-channel-attention-networks","slug":"wavenets-wavelet-channel-attention-networks","title":"WaveNets: Wavelet Channel Attention Networks","date":"2022-11-04","arxiv_id":"2211.02695","n_code_links":1,"syntology":null},{"paper":null,"slug":"alternative-formulations-for-gilthead","title":"Alternative formulations for gilthead seabream diets: towards a more sustainable production","date":"2022-11-03","arxiv_id":"2211.02430","n_code_links":0,"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/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/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/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":"simd-size-aware-weight-regularization-for","title":"SIMD-size aware weight regularization for fast neural vocoding on CPU","date":"2022-11-02","arxiv_id":"2211.00898","n_code_links":0,"syntology":null},{"paper":"/paper/the-lottery-ticket-hypothesis-for-vision","slug":"the-lottery-ticket-hypothesis-for-vision","title":"Data Level Lottery Ticket Hypothesis for Vision Transformers","date":"2022-11-02","arxiv_id":"2211.01484","n_code_links":1,"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/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":"/paper/kamel-knowledge-analysis-with-multitoken","slug":"kamel-knowledge-analysis-with-multitoken","title":"KAMEL : Knowledge Analysis with Multitoken Entities in Language Models","date":"2022-11-01","arxiv_id":null,"n_code_links":1,"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":"/paper/pixel-wise-contrastive-distillation","slug":"pixel-wise-contrastive-distillation","title":"Pixel-Wise Contrastive Distillation","date":"2022-11-01","arxiv_id":"2211.00218","n_code_links":1,"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":"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/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/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":"/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":"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":"probability-dependent-gradient-decay-in-large","title":"Probability-Dependent Gradient Decay in Large Margin Softmax","date":"2022-10-31","arxiv_id":"2210.17145","n_code_links":0,"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":"revisiting-attention-weights-as-explanations","title":"Revisiting Attention Weights as Explanations from an Information Theoretic Perspective","date":"2022-10-31","arxiv_id":"2211.07714","n_code_links":0,"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":null,"slug":"sevggnet-lstm-a-fused-deep-learning-model-for","title":"SEVGGNet-LSTM: a fused deep learning model for ECG classification","date":"2022-10-31","arxiv_id":"2210.17111","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}],"record_sha256":"daeb2be1e4527aae90c86439b4ceed38aec096a5b4a9fde30f1215db46988f8c","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}