{"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/310","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":310,"pages_in_order":375,"rows_per_page":100,"rows":[30901,31000],"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/309","next":"/method/softmax/papers/311","papers":[{"paper":"/paper/revisiting-language-encoding-in-learning","slug":"revisiting-language-encoding-in-learning","title":"Revisiting Language Encoding in Learning Multilingual Representations","date":"2021-02-16","arxiv_id":"2102.08357","n_code_links":1,"syntology":null},{"paper":"/paper/terapipe-token-level-pipeline-parallelism-for","slug":"terapipe-token-level-pipeline-parallelism-for","title":"TeraPipe: Token-Level Pipeline Parallelism for Training Large-Scale Language Models","date":"2021-02-16","arxiv_id":"2102.07988","n_code_links":1,"syntology":{"ran":7,"of":8,"n_ran_checked":3,"n_instrument":4,"unverified":1,"pointer_only":8,"phrase":"7 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified","official":{"repos":["zhuohan123/terapipe"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"training-larger-networks-for-deep","title":"Training Larger Networks for Deep Reinforcement Learning","date":"2021-02-16","arxiv_id":"2102.07920","n_code_links":0,"syntology":null},{"paper":"/paper/unsupervised-energy-based-out-of-distribution","slug":"unsupervised-energy-based-out-of-distribution","title":"Unsupervised Energy-based Out-of-distribution Detection using Stiefel-Restricted Kernel Machine","date":"2021-02-16","arxiv_id":"2102.08443","n_code_links":1,"syntology":null},{"paper":null,"slug":"colored-kimia-path24-dataset-configurations","title":"Colored Kimia Path24 Dataset: Configurations and Benchmarks with Deep Embeddings","date":"2021-02-15","arxiv_id":"2102.07611","n_code_links":0,"syntology":null},{"paper":null,"slug":"detection-and-severity-classification-of","title":"Detection and severity classification of COVID-19 in CT images using deep learning","date":"2021-02-15","arxiv_id":"2102.07726","n_code_links":0,"syntology":null},{"paper":"/paper/dobf-a-deobfuscation-pre-training-objective","slug":"dobf-a-deobfuscation-pre-training-objective","title":"DOBF: A Deobfuscation Pre-Training Objective for Programming Languages","date":"2021-02-15","arxiv_id":"2102.07492","n_code_links":2,"syntology":null},{"paper":null,"slug":"fast-end-to-end-speech-recognition-via-non","title":"Fast End-to-End Speech Recognition via Non-Autoregressive Models and Cross-Modal Knowledge Transferring from BERT","date":"2021-02-15","arxiv_id":"2102.07594","n_code_links":0,"syntology":null},{"paper":null,"slug":"improved-customer-transaction-classification","title":"Improved Customer Transaction Classification using Semi-Supervised Knowledge Distillation","date":"2021-02-15","arxiv_id":"2102.07635","n_code_links":0,"syntology":null},{"paper":null,"slug":"prompt-programming-for-large-language-models","title":"Prompt Programming for Large Language Models: Beyond the Few-Shot Paradigm","date":"2021-02-15","arxiv_id":"2102.07350","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-corruptive-force-of-ai-generated-advice","title":"The corruptive force of AI-generated advice","date":"2021-02-15","arxiv_id":"2102.07536","n_code_links":0,"syntology":null},{"paper":"/paper/translational-equivariance-in-kernelizable","slug":"translational-equivariance-in-kernelizable","title":"Translational Equivariance in Kernelizable Attention","date":"2021-02-15","arxiv_id":"2102.07680","n_code_links":1,"syntology":null},{"paper":null,"slug":"within-document-event-coreference-with-bert","title":"Within-Document Event Coreference with BERT-Based Contextualized Representations","date":"2021-02-15","arxiv_id":"2102.09600","n_code_links":0,"syntology":null},{"paper":null,"slug":"building-outline-delineation-from-aerial","title":"Building outline delineation: From aerial images to polygons with an improved end-to-end learning framework","date":"2021-02-14","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/healing-products-of-gaussian-processes","slug":"healing-products-of-gaussian-processes","title":"Healing Products of Gaussian Processes","date":"2021-02-14","arxiv_id":"2102.07106","n_code_links":1,"syntology":null},{"paper":"/paper/indicnlp-kgp-at-dravidianlangtech-eacl2021","slug":"indicnlp-kgp-at-dravidianlangtech-eacl2021","title":"indicnlp@kgp at DravidianLangTech-EACL2021: Offensive Language Identification in Dravidian Languages","date":"2021-02-14","arxiv_id":"2102.07150","n_code_links":1,"syntology":null},{"paper":"/paper/indicnlp-kgp-at-dravidianlangtech-eacl2021-1","slug":"indicnlp-kgp-at-dravidianlangtech-eacl2021-1","title":"indicnlp@ kgp at DravidianLangTech-EACL2021: Offensive Language Identification in Dravidian Languages","date":"2021-02-14","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"query-by-example-keyword-spotting-system","title":"Query-by-Example Keyword Spotting system using Multi-head Attention and Softtriple Loss","date":"2021-02-14","arxiv_id":"2102.07061","n_code_links":0,"syntology":null},{"paper":"/paper/fast-accurate-barcode-detection-in-ultra-high","slug":"fast-accurate-barcode-detection-in-ultra-high","title":"Fast, Accurate Barcode Detection in Ultra High-Resolution Images","date":"2021-02-13","arxiv_id":"2102.06868","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-novel-method-for-object-detection-using","title":"A novel method for object detection using deep learning and CAD models","date":"2021-02-12","arxiv_id":"2102.06729","n_code_links":0,"syntology":null},{"paper":"/paper/characterizing-english-variation-across","slug":"characterizing-english-variation-across","title":"Characterizing English Variation across Social Media Communities with BERT","date":"2021-02-12","arxiv_id":"2102.06820","n_code_links":1,"syntology":null},{"paper":null,"slug":"dancing-along-battery-enabling-transformer","title":"Dancing along Battery: Enabling Transformer with Run-time Reconfigurability on Mobile Devices","date":"2021-02-12","arxiv_id":"2102.06336","n_code_links":0,"syntology":null},{"paper":"/paper/dynamic-precision-analog-computing-for-neural","slug":"dynamic-precision-analog-computing-for-neural","title":"Dynamic Precision Analog Computing for Neural Networks","date":"2021-02-12","arxiv_id":"2102.06365","n_code_links":1,"syntology":null},{"paper":null,"slug":"enhancing-into-the-codec-noise-robust-speech","title":"Enhancing into the codec: Noise Robust Speech Coding with Vector-Quantized Autoencoders","date":"2021-02-12","arxiv_id":"2102.06610","n_code_links":0,"syntology":null},{"paper":"/paper/exploring-classic-and-neural-lexical","slug":"exploring-classic-and-neural-lexical","title":"Exploring Classic and Neural Lexical Translation Models for Information Retrieval: Interpretability, Effectiveness, and Efficiency Benefits","date":"2021-02-12","arxiv_id":"2102.06815","n_code_links":2,"syntology":null},{"paper":"/paper/improving-object-detection-in-art-images","slug":"improving-object-detection-in-art-images","title":"Improving Object Detection in Art Images Using Only Style Transfer","date":"2021-02-12","arxiv_id":"2102.06529","n_code_links":1,"syntology":null},{"paper":null,"slug":"improving-zero-shot-neural-machine","title":"Improving Zero-shot Neural Machine Translation on Language-specific Encoders-Decoders","date":"2021-02-12","arxiv_id":"2102.06578","n_code_links":0,"syntology":null},{"paper":null,"slug":"multiversal-views-on-language-models","title":"Multiversal views on language models","date":"2021-02-12","arxiv_id":"2102.06391","n_code_links":0,"syntology":null},{"paper":null,"slug":"optimizing-inference-performance-of","title":"Optimizing Inference Performance of Transformers on CPUs","date":"2021-02-12","arxiv_id":"2102.06621","n_code_links":0,"syntology":null},{"paper":"/paper/robust-and-efficient-planning-using-adaptive","slug":"robust-and-efficient-planning-using-adaptive","title":"Planning and Learning Using Adaptive Entropy Tree Search","date":"2021-02-12","arxiv_id":"2102.06808","n_code_links":1,"syntology":null},{"paper":"/paper/transformer-language-models-with-lstm-based","slug":"transformer-language-models-with-lstm-based","title":"Transformer Language Models with LSTM-based Cross-utterance Information Representation","date":"2021-02-12","arxiv_id":"2102.06474","n_code_links":1,"syntology":null},{"paper":null,"slug":"aboships-an-inshore-and-offshore-maritime","title":"ABOShips -- An Inshore and Offshore Maritime Vessel Detection Dataset with Precise Annotations","date":"2021-02-11","arxiv_id":"2102.05869","n_code_links":0,"syntology":null},{"paper":null,"slug":"deep-reinforcement-learning-for-combinatorial","title":"Deep Reinforcement Learning for Combinatorial Optimization: Covering Salesman Problems","date":"2021-02-11","arxiv_id":"2102.05875","n_code_links":0,"syntology":null},{"paper":null,"slug":"optimization-issues-in-kl-constrained","title":"Optimization Issues in KL-Constrained Approximate Policy Iteration","date":"2021-02-11","arxiv_id":"2102.06234","n_code_links":0,"syntology":null},{"paper":"/paper/proof-artifact-co-training-for-theorem","slug":"proof-artifact-co-training-for-theorem","title":"Proof Artifact Co-training for Theorem Proving with Language Models","date":"2021-02-11","arxiv_id":"2102.06203","n_code_links":4,"syntology":{"ran":3,"of":4,"n_ran_checked":0,"n_instrument":3,"unverified":1,"pointer_only":0,"phrase":"3 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; 3 where Syntology's instrument failed) · 1 unverified","official":{"repos":["jasonrute/lean-proof-recording-public","jasonrute/lean_proof_recording","jesse-michael-han/lean-step-public"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"text-compression-aided-transformer-encoding","title":"Text Compression-aided Transformer Encoding","date":"2021-02-11","arxiv_id":"2102.05951","n_code_links":0,"syntology":null},{"paper":null,"slug":"adafuse-adaptive-temporal-fusion-network-for-1","title":"AdaFuse: Adaptive Temporal Fusion Network for Efficient Action Recognition","date":"2021-02-10","arxiv_id":"2102.05775","n_code_links":0,"syntology":null},{"paper":"/paper/enhancing-real-world-adversarial-patches-with","slug":"enhancing-real-world-adversarial-patches-with","title":"Enhancing Real-World Adversarial Patches through 3D Modeling of Complex Target Scenes","date":"2021-02-10","arxiv_id":"2102.05334","n_code_links":1,"syntology":null},{"paper":null,"slug":"main-multihead-attention-imputation-networks","title":"MAIN: Multihead-Attention Imputation Networks","date":"2021-02-10","arxiv_id":"2102.05428","n_code_links":0,"syntology":null},{"paper":"/paper/nast-non-autoregressive-spatial-temporal","slug":"nast-non-autoregressive-spatial-temporal","title":"NAST: Non-Autoregressive Spatial-Temporal Transformer for Time Series Forecasting","date":"2021-02-10","arxiv_id":"2102.05624","n_code_links":1,"syntology":null},{"paper":"/paper/pruning-of-convolutional-neural-networks","slug":"pruning-of-convolutional-neural-networks","title":"Pruning of Convolutional Neural Networks Using Ising Energy Model","date":"2021-02-10","arxiv_id":"2102.05437","n_code_links":1,"syntology":null},{"paper":null,"slug":"searching-for-fast-model-families-on","title":"Searching for Fast Model Families on Datacenter Accelerators","date":"2021-02-10","arxiv_id":"2102.05610","n_code_links":0,"syntology":null},{"paper":"/paper/augpt-dialogue-with-pre-trained-language","slug":"augpt-dialogue-with-pre-trained-language","title":"AuGPT: Auxiliary Tasks and Data Augmentation for End-To-End Dialogue with Pre-Trained Language Models","date":"2021-02-09","arxiv_id":"2102.05126","n_code_links":1,"syntology":null},{"paper":null,"slug":"bayesian-transformer-language-models-for","title":"Bayesian Transformer Language Models for Speech Recognition","date":"2021-02-09","arxiv_id":"2102.04754","n_code_links":0,"syntology":null},{"paper":null,"slug":"conversational-query-rewriting-with-self","title":"Conversational Query Rewriting with Self-supervised Learning","date":"2021-02-09","arxiv_id":"2102.04708","n_code_links":0,"syntology":null},{"paper":null,"slug":"distribution-adaptive-int8-quantization-for","title":"Distribution Adaptive INT8 Quantization for Training CNNs","date":"2021-02-09","arxiv_id":"2102.04782","n_code_links":0,"syntology":null},{"paper":null,"slug":"joint-intent-detection-and-slot-filling-with","title":"Joint Intent Detection and Slot Filling with Wheel-Graph Attention Networks","date":"2021-02-09","arxiv_id":"2102.04610","n_code_links":0,"syntology":null},{"paper":null,"slug":"large-scale-training-system-for-100-million","title":"Large-Scale Training System for 100-Million Classification at Alibaba","date":"2021-02-09","arxiv_id":"2102.06025","n_code_links":0,"syntology":null},{"paper":null,"slug":"newsbert-distilling-pre-trained-language","title":"NewsBERT: Distilling Pre-trained Language Model for Intelligent News Application","date":"2021-02-09","arxiv_id":"2102.04887","n_code_links":0,"syntology":null},{"paper":"/paper/point-cloud-transformers-applied-to-collider","slug":"point-cloud-transformers-applied-to-collider","title":"Point Cloud Transformers applied to Collider Physics","date":"2021-02-09","arxiv_id":"2102.05073","n_code_links":1,"syntology":null},{"paper":null,"slug":"rmopp-robust-multi-objective-post-processing","title":"RMOPP: Robust Multi-Objective Post-Processing for Effective Object Detection","date":"2021-02-09","arxiv_id":"2102.04582","n_code_links":0,"syntology":null},{"paper":null,"slug":"sparse-antenna-array-design-for-mimo-radar","title":"Sparse Antenna Array Design for MIMO Radar Using Softmax Selection","date":"2021-02-09","arxiv_id":"2102.05092","n_code_links":0,"syntology":null},{"paper":null,"slug":"train-a-one-million-way-instance-classifier","title":"Train a One-Million-Way Instance Classifier for Unsupervised Visual Representation Learning","date":"2021-02-09","arxiv_id":"2102.04848","n_code_links":0,"syntology":null},{"paper":null,"slug":"transfer-learning-approach-for-arabic","title":"Transfer Learning Approach for Arabic Offensive Language Detection System -- BERT-Based Model","date":"2021-02-09","arxiv_id":"2102.05708","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-histogram-thresholding-improvement-to-mask","title":"A Histogram Thresholding Improvement to Mask R-CNN for Scalable Segmentation of New and Old Rural Buildings","date":"2021-02-08","arxiv_id":"2102.04838","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-hybrid-task-oriented-dialog-system-with","title":"A Hybrid Task-Oriented Dialog System with Domain and Task Adaptive Pretraining","date":"2021-02-08","arxiv_id":"2102.04506","n_code_links":0,"syntology":null},{"paper":"/paper/colorization-transformer-1","slug":"colorization-transformer-1","title":"Colorization Transformer","date":"2021-02-08","arxiv_id":"2102.04432","n_code_links":2,"syntology":null},{"paper":null,"slug":"curse-of-dimensionality-for-tsk-fuzzy-neural","title":"Curse of Dimensionality for TSK Fuzzy Neural Networks: Explanation and Solutions","date":"2021-02-08","arxiv_id":"2102.04271","n_code_links":0,"syntology":null},{"paper":null,"slug":"generating-fake-cyber-threat-intelligence","title":"Generating Fake Cyber Threat Intelligence Using Transformer-Based Models","date":"2021-02-08","arxiv_id":"2102.04351","n_code_links":0,"syntology":null},{"paper":"/paper/how-true-is-gpt-2-an-empirical-analysis-of","slug":"how-true-is-gpt-2-an-empirical-analysis-of","title":"Bias Out-of-the-Box: An Empirical Analysis of Intersectional Occupational Biases in Popular Generative Language Models","date":"2021-02-08","arxiv_id":"2102.04130","n_code_links":1,"syntology":{"ran":5,"of":5,"n_ran_checked":0,"n_instrument":5,"unverified":0,"pointer_only":0,"phrase":"5 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; 5 where Syntology's instrument failed) · 0 unverified","official":{"repos":["oxai/intersectional_gpt2"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/transreid-transformer-based-object-re","slug":"transreid-transformer-based-object-re","title":"TransReID: Transformer-based Object Re-Identification","date":"2021-02-08","arxiv_id":"2102.04378","n_code_links":4,"syntology":null},{"paper":"/paper/transunet-transformers-make-strong-encoders","slug":"transunet-transformers-make-strong-encoders","title":"TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation","date":"2021-02-08","arxiv_id":"2102.04306","n_code_links":22,"syntology":{"ran":6,"of":7,"n_ran_checked":2,"n_instrument":4,"unverified":1,"pointer_only":7,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified","official":{"repos":["Beckschen/TransUNet"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]}}},{"paper":null,"slug":"unlocking-pixels-for-reinforcement-learning","title":"Unlocking Pixels for Reinforcement Learning via Implicit Attention","date":"2021-02-08","arxiv_id":"2102.04353","n_code_links":0,"syntology":null},{"paper":null,"slug":"wake-word-detection-with-streaming","title":"Wake Word Detection with Streaming Transformers","date":"2021-02-08","arxiv_id":"2102.04488","n_code_links":0,"syntology":null},{"paper":"/paper/nystromformer-a-nystrom-based-algorithm-for","slug":"nystromformer-a-nystrom-based-algorithm-for","title":"Nyströmformer: A Nyström-Based Algorithm for Approximating Self-Attention","date":"2021-02-07","arxiv_id":"2102.03902","n_code_links":10,"syntology":{"ran":1,"of":2,"n_ran_checked":1,"n_instrument":0,"unverified":1,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["mlpen/Nystromformer"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["unlocated"]}}},{"paper":"/paper/spoiler-alert-using-natural-language","slug":"spoiler-alert-using-natural-language","title":"Spoiler Alert: Using Natural Language Processing to Detect Spoilers in Book Reviews","date":"2021-02-07","arxiv_id":"2102.03882","n_code_links":1,"syntology":null},{"paper":null,"slug":"jointly-improving-language-understanding-and","title":"Jointly Improving Language Understanding and Generation with Quality-Weighted Weak Supervision of Automatic Labeling","date":"2021-02-06","arxiv_id":"2102.03551","n_code_links":0,"syntology":null},{"paper":null,"slug":"neural-data-to-text-generation-with-lm-based","title":"Neural Data-to-Text Generation with LM-based Text Augmentation","date":"2021-02-06","arxiv_id":"2102.03556","n_code_links":0,"syntology":null},{"paper":null,"slug":"adversarial-training-makes-weight-loss","title":"Adversarial Training Makes Weight Loss Landscape Sharper in Logistic Regression","date":"2021-02-05","arxiv_id":"2102.02950","n_code_links":0,"syntology":null},{"paper":"/paper/baller2vec-a-multi-entity-transformer-for","slug":"baller2vec-a-multi-entity-transformer-for","title":"baller2vec: A Multi-Entity Transformer For Multi-Agent Spatiotemporal Modeling","date":"2021-02-05","arxiv_id":"2102.03291","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":["airalcorn2/baller2vec"],"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/gnn-rl-compression-topology-aware-network","slug":"gnn-rl-compression-topology-aware-network","title":"Topology-Aware Network Pruning using Multi-stage Graph Embedding and Reinforcement Learning","date":"2021-02-05","arxiv_id":"2102.03214","n_code_links":1,"syntology":{"ran":3,"of":4,"n_ran_checked":1,"n_instrument":2,"unverified":1,"pointer_only":4,"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) · 1 unverified","official":{"repos":["yusx-swapp/gnn-rl-model-compression"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"hyperspherical-embedding-for-novel-class","title":"Hyperspherical embedding for novel class classification","date":"2021-02-05","arxiv_id":"2102.03243","n_code_links":0,"syntology":null},{"paper":null,"slug":"instance-and-panoptic-segmentation-using","title":"Instance and Panoptic Segmentation Using Conditional Convolutions","date":"2021-02-05","arxiv_id":"2102.03026","n_code_links":0,"syntology":null},{"paper":"/paper/pipetransformer-automated-elastic-pipelining","slug":"pipetransformer-automated-elastic-pipelining","title":"PipeTransformer: Automated Elastic Pipelining for Distributed Training of Transformers","date":"2021-02-05","arxiv_id":"2102.03161","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["Distributed-AI/PipeTransformer"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/rpbert-a-text-image-relation-propagation","slug":"rpbert-a-text-image-relation-propagation","title":"RpBERT: A Text-image Relation Propagation-based BERT Model for Multimodal NER","date":"2021-02-05","arxiv_id":"2102.02967","n_code_links":1,"syntology":null},{"paper":null,"slug":"understanding-emails-and-drafting-responses","title":"Understanding Emails and Drafting Responses -- An Approach Using GPT-3","date":"2021-02-05","arxiv_id":"2102.03062","n_code_links":0,"syntology":null},{"paper":"/paper/vilt-vision-and-language-transformer-without","slug":"vilt-vision-and-language-transformer-without","title":"ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision","date":"2021-02-05","arxiv_id":"2102.03334","n_code_links":6,"syntology":{"ran":1,"of":4,"n_ran_checked":1,"n_instrument":0,"unverified":3,"pointer_only":1,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified; the one sample that ran constructed an object rather than computing a result","official":{"repos":["dandelin/vilt"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed"]}}},{"paper":"/paper/1-bit-adam-communication-efficient-large","slug":"1-bit-adam-communication-efficient-large","title":"1-bit Adam: Communication Efficient Large-Scale Training with Adam's Convergence Speed","date":"2021-02-04","arxiv_id":"2102.02888","n_code_links":2,"syntology":null},{"paper":null,"slug":"a-survey-of-motion-planning-algorithms-for","title":"A review of motion planning algorithms for intelligent robotics","date":"2021-02-04","arxiv_id":"2102.02376","n_code_links":0,"syntology":null},{"paper":null,"slug":"adaptive-semiparametric-language-models","title":"Adaptive Semiparametric Language Models","date":"2021-02-04","arxiv_id":"2102.02557","n_code_links":0,"syntology":null},{"paper":"/paper/hierarchical-multi-head-attentive-network-for","slug":"hierarchical-multi-head-attentive-network-for","title":"Hierarchical Multi-head Attentive Network for Evidence-aware Fake News Detection","date":"2021-02-04","arxiv_id":"2102.02680","n_code_links":1,"syntology":null},{"paper":"/paper/ml-doctor-holistic-risk-assessment-of","slug":"ml-doctor-holistic-risk-assessment-of","title":"ML-Doctor: Holistic Risk Assessment of Inference Attacks Against Machine Learning Models","date":"2021-02-04","arxiv_id":"2102.02551","n_code_links":1,"syntology":{"ran":1,"of":3,"n_ran_checked":0,"n_instrument":1,"unverified":2,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","official":{"repos":["liuyugeng/ml-doctor"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"understanding-the-capabilities-limitations","title":"Understanding the Capabilities, Limitations, and Societal Impact of Large Language Models","date":"2021-02-04","arxiv_id":"2102.02503","n_code_links":0,"syntology":null},{"paper":null,"slug":"bootstrapping-multilingual-amr-with","title":"Bootstrapping Multilingual AMR with Contextual Word Alignments","date":"2021-02-03","arxiv_id":"2102.02189","n_code_links":0,"syntology":null},{"paper":null,"slug":"hebert-hebemo-a-hebrew-bert-model-and-a-tool","title":"HeBERT & HebEMO: a Hebrew BERT Model and a Tool for Polarity Analysis and Emotion Recognition","date":"2021-02-03","arxiv_id":"2102.01909","n_code_links":0,"syntology":null},{"paper":null,"slug":"mufasa-multimodal-fusion-architecture-search","title":"MUFASA: Multimodal Fusion Architecture Search for Electronic Health Records","date":"2021-02-03","arxiv_id":"2102.02340","n_code_links":0,"syntology":null},{"paper":null,"slug":"neural-transfer-learning-with-transformers","title":"Introduction to Neural Transfer Learning with Transformers for Social Science Text Analysis","date":"2021-02-03","arxiv_id":"2102.02111","n_code_links":0,"syntology":null},{"paper":"/paper/pitfalls-of-static-language-modelling","slug":"pitfalls-of-static-language-modelling","title":"Mind the Gap: Assessing Temporal Generalization in Neural Language Models","date":"2021-02-03","arxiv_id":"2102.01951","n_code_links":1,"syntology":null},{"paper":"/paper/relaxed-transformer-decoders-for-direct","slug":"relaxed-transformer-decoders-for-direct","title":"Relaxed Transformer Decoders for Direct Action Proposal Generation","date":"2021-02-03","arxiv_id":"2102.01894","n_code_links":2,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","official":{"repos":["MCG-NJU/RTD-Action"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"robust-pedestrian-detection-in-thermal","title":"Robust pedestrian detection in thermal imagery using synthesized images","date":"2021-02-03","arxiv_id":"2102.02005","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-natural-and-controllable-cross","title":"Towards Natural and Controllable Cross-Lingual Voice Conversion Based on Neural TTS Model and Phonetic Posteriorgram","date":"2021-02-03","arxiv_id":"2102.01991","n_code_links":0,"syntology":null},{"paper":"/paper/autofreeze-automatically-freezing-model","slug":"autofreeze-automatically-freezing-model","title":"AutoFreeze: Automatically Freezing Model Blocks to Accelerate Fine-tuning","date":"2021-02-02","arxiv_id":"2102.01386","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"1 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; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["uw-mad-dash/AutoFreeze"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["unlocated"]}}},{"paper":null,"slug":"clickbait-headline-detection-in-indonesian","title":"Clickbait Headline Detection in Indonesian News Sites using Multilingual Bidirectional Encoder Representations from Transformers (M-BERT)","date":"2021-02-02","arxiv_id":"2102.01497","n_code_links":0,"syntology":null},{"paper":"/paper/generating-images-from-caption-and-vice-versa","slug":"generating-images-from-caption-and-vice-versa","title":"Generating images from caption and vice versa via CLIP-Guided Generative Latent Space Search","date":"2021-02-02","arxiv_id":"2102.01645","n_code_links":3,"syntology":null},{"paper":null,"slug":"rank-consistency-deep-hashing-for-scalable","title":"Rank-Consistency Deep Hashing for Scalable Multi-Label Image Search","date":"2021-02-02","arxiv_id":"2102.01486","n_code_links":0,"syntology":null},{"paper":"/paper/automated-query-reformulation-for-efficient","slug":"automated-query-reformulation-for-efficient","title":"Automated Query Reformulation for Efficient Search based on Query Logs From Stack Overflow","date":"2021-02-01","arxiv_id":"2102.00826","n_code_links":1,"syntology":null},{"paper":"/paper/convnets-for-counting-object-detection-of","slug":"convnets-for-counting-object-detection-of","title":"ConvNets for Counting: Object Detection of Transient Phenomena in Steelpan Drums","date":"2021-02-01","arxiv_id":"2102.00632","n_code_links":1,"syntology":null},{"paper":null,"slug":"gtae-graph-transformer-based-auto-encoders","title":"GTAE: Graph-Transformer based Auto-Encoders for Linguistic-Constrained Text Style Transfer","date":"2021-02-01","arxiv_id":"2102.00769","n_code_links":0,"syntology":null},{"paper":"/paper/improving-distantly-supervised-relation-3","slug":"improving-distantly-supervised-relation-3","title":"Improving Distantly-Supervised Relation Extraction through BERT-based Label & Instance Embeddings","date":"2021-02-01","arxiv_id":"2102.01156","n_code_links":1,"syntology":null},{"paper":null,"slug":"is-depression-related-to-cannabis-a-knowledge","title":"\"Is depression related to cannabis?\": A knowledge-infused model for Entity and Relation Extraction with Limited Supervision","date":"2021-02-01","arxiv_id":"2102.01222","n_code_links":0,"syntology":null}],"record_sha256":"4eb08af64baddade84cc5352e61f988ce90a157c785c423a5b30b2201291c91a","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}