{"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/bpe/papers/127","list_of":"/method/bpe","method":"BPE","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":127,"pages_in_order":190,"rows_per_page":100,"rows":[12601,12700],"of":18975,"counts":{"archive_papers_tagged":18975,"with_a_code_link":8675,"where_syntology_ran_a_sample":2895,"not_listed_spam_title":0,"listed":18975,"listed_where_code_ran":2895,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":2443,"every_run_a_failure_of_syntologys_instrument":452,"listed_with_a_run_with_no_instrument_failure":2443,"listed_every_run_a_failure_of_syntologys_instrument":452,"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/bpe","prev":"/method/bpe/papers/126","next":"/method/bpe/papers/128","papers":[{"paper":null,"slug":"foundation-models-for-natural-language","title":"Foundation Models for Natural Language Processing -- Pre-trained Language Models Integrating Media","date":"2023-02-16","arxiv_id":"2302.08575","n_code_links":0,"syntology":null},{"paper":null,"slug":"hierarchical-cross-modal-transformer-for-rgb","title":"Hierarchical Cross-modal Transformer for RGB-D Salient Object Detection","date":"2023-02-16","arxiv_id":"2302.08052","n_code_links":0,"syntology":null},{"paper":"/paper/keep-it-neutral-using-natural-language","slug":"keep-it-neutral-using-natural-language","title":"For Generated Text, Is NLI-Neutral Text the Best Text?","date":"2023-02-16","arxiv_id":"2302.08577","n_code_links":1,"syntology":null},{"paper":"/paper/learning-non-local-spatial-angular","slug":"learning-non-local-spatial-angular","title":"Learning Non-Local Spatial-Angular Correlation for Light Field Image Super-Resolution","date":"2023-02-16","arxiv_id":"2302.08058","n_code_links":1,"syntology":null},{"paper":null,"slug":"prompt-tuning-of-deep-neural-networks-for","title":"Prompt Tuning of Deep Neural Networks for Speaker-adaptive Visual Speech Recognition","date":"2023-02-16","arxiv_id":"2302.08102","n_code_links":0,"syntology":null},{"paper":null,"slug":"robust-human-motion-forecasting-using","title":"Robust Human Motion Forecasting using Transformer-based Model","date":"2023-02-16","arxiv_id":"2302.08274","n_code_links":0,"syntology":null},{"paper":"/paper/search-engine-augmented-dialogue-response","slug":"search-engine-augmented-dialogue-response","title":"Search-Engine-augmented Dialogue Response Generation with Cheaply Supervised Query Production","date":"2023-02-16","arxiv_id":"2302.09300","n_code_links":1,"syntology":null},{"paper":null,"slug":"short-term-and-long-term-memory-self","title":"Short-term and long-term memory self-attention network for segmentation of tumours in 3D medical images","date":"2023-02-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"speaker-change-detection-for-transformer","title":"Speaker Change Detection for Transformer Transducer ASR","date":"2023-02-16","arxiv_id":"2302.08549","n_code_links":0,"syntology":null},{"paper":"/paper/urcdc-depth-uncertainty-rectified-cross","slug":"urcdc-depth-uncertainty-rectified-cross","title":"URCDC-Depth: Uncertainty Rectified Cross-Distillation with CutFlip for Monocular Depth Estimation","date":"2023-02-16","arxiv_id":"2302.08149","n_code_links":1,"syntology":{"ran":7,"of":11,"n_ran_checked":5,"n_instrument":2,"unverified":4,"pointer_only":5,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified","official":{"repos":["shuweishao/urcdc-depth"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"commonsense-reasoning-for-conversational-ai-a","title":"Commonsense Reasoning for Conversational AI: A Survey of the State of the Art","date":"2023-02-15","arxiv_id":"2302.07926","n_code_links":0,"syntology":null},{"paper":"/paper/confidence-score-based-speaker-adaptation-of","slug":"confidence-score-based-speaker-adaptation-of","title":"Confidence Score Based Speaker Adaptation of Conformer Speech Recognition Systems","date":"2023-02-15","arxiv_id":"2302.07521","n_code_links":1,"syntology":null},{"paper":"/paper/learning-performance-improving-code-edits","slug":"learning-performance-improving-code-edits","title":"Learning Performance-Improving Code Edits","date":"2023-02-15","arxiv_id":"2302.07867","n_code_links":2,"syntology":{"ran":8,"of":19,"n_ran_checked":3,"n_instrument":5,"unverified":11,"pointer_only":19,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 0 violated, 1 with no contract checked; 5 where Syntology's instrument failed) · 11 unverified","official":{"repos":["madaan/pie-perf"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":11,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"pose-oriented-transformer-with-uncertainty","title":"Pose-Oriented Transformer with Uncertainty-Guided Refinement for 2D-to-3D Human Pose Estimation","date":"2023-02-15","arxiv_id":"2302.07408","n_code_links":0,"syntology":null},{"paper":null,"slug":"self-supervised-learning-for-modeling-gamma","title":"Self-Supervised Learning for Modeling Gamma-ray Variability in Blazars","date":"2023-02-15","arxiv_id":"2302.07700","n_code_links":0,"syntology":null},{"paper":"/paper/speculative-decoding-with-big-little-decoder-1","slug":"speculative-decoding-with-big-little-decoder-1","title":"Speculative Decoding with Big Little Decoder","date":"2023-02-15","arxiv_id":"2302.07863","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":0,"n_instrument":2,"unverified":1,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["kssteven418/biglittledecoder"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/tree-based-representation-and-generation-of","slug":"tree-based-representation-and-generation-of","title":"Tree-Based Representation and Generation of Natural and Mathematical Language","date":"2023-02-15","arxiv_id":"2302.07974","n_code_links":1,"syntology":null},{"paper":null,"slug":"deep-learning-based-modeling-of-5g-core","title":"Deep Learning-Based Modeling of 5G Core Control Plane for 5G Network Digital Twin","date":"2023-02-14","arxiv_id":"2302.06980","n_code_links":0,"syntology":null},{"paper":"/paper/difffashion-reference-based-fashion-design","slug":"difffashion-reference-based-fashion-design","title":"DiffFashion: Reference-based Fashion Design with Structure-aware Transfer by Diffusion Models","date":"2023-02-14","arxiv_id":"2302.06826","n_code_links":1,"syntology":null},{"paper":"/paper/energy-transformer","slug":"energy-transformer","title":"Energy Transformer","date":"2023-02-14","arxiv_id":"2302.07253","n_code_links":4,"syntology":{"ran":13,"of":13,"n_ran_checked":7,"n_instrument":6,"unverified":0,"pointer_only":3,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 2 honoured, 0 violated, 5 with no contract checked; 6 where Syntology's instrument failed) · 0 unverified","official":{"repos":["bhoov/energy-transformer-jax","zhuergou/energy-transformer-for-graph-anomaly-detection","Lemon-cmd/energy-transformer-graph","Lemon-cmd/energy-transformer-torch"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"paper":null,"slug":"few-shot-learning-approaches-for-classifying","title":"Few-shot learning approaches for classifying low resource domain specific software requirements","date":"2023-02-14","arxiv_id":"2302.06951","n_code_links":0,"syntology":null},{"paper":"/paper/polyformer-referring-image-segmentation-as","slug":"polyformer-referring-image-segmentation-as","title":"PolyFormer: Referring Image Segmentation as Sequential Polygon Generation","date":"2023-02-14","arxiv_id":"2302.07387","n_code_links":1,"syntology":{"ran":5,"of":6,"n_ran_checked":5,"n_instrument":0,"unverified":1,"pointer_only":6,"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) · 1 unverified","official":{"repos":["amazon-science/polygon-transformer"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/scattershot-interactive-in-context-example","slug":"scattershot-interactive-in-context-example","title":"ScatterShot: Interactive In-context Example Curation for Text Transformation","date":"2023-02-14","arxiv_id":"2302.07346","n_code_links":1,"syntology":null},{"paper":"/paper/team-detr-guide-queries-as-a-professional","slug":"team-detr-guide-queries-as-a-professional","title":"Team DETR: Guide Queries as a Professional Team in Detection Transformers","date":"2023-02-14","arxiv_id":"2302.07116","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-comprehensive-study-of-modern-architectures","title":"A Comprehensive Study of Modern Architectures and Regularization Approaches on CheXpert5000","date":"2023-02-13","arxiv_id":"2302.06684","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-study-on-relu-and-softmax-in-transformer","title":"A Study on ReLU and Softmax in Transformer","date":"2023-02-13","arxiv_id":"2302.06461","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-unified-view-of-long-sequence-models","title":"A Unified View of Long-Sequence Models towards Modeling Million-Scale Dependencies","date":"2023-02-13","arxiv_id":"2302.06218","n_code_links":0,"syntology":null},{"paper":null,"slug":"artificial-intelligence-in-psychology","title":"Diminished Diversity-of-Thought in a Standard Large Language Model","date":"2023-02-13","arxiv_id":"2302.07267","n_code_links":0,"syntology":null},{"paper":"/paper/can-gpt-3-perform-statutory-reasoning","slug":"can-gpt-3-perform-statutory-reasoning","title":"Can GPT-3 Perform Statutory Reasoning?","date":"2023-02-13","arxiv_id":"2302.06100","n_code_links":1,"syntology":null},{"paper":"/paper/cholectriplet2022-show-me-a-tool-and-tell-me","slug":"cholectriplet2022-show-me-a-tool-and-tell-me","title":"CholecTriplet2022: Show me a tool and tell me the triplet -- an endoscopic vision challenge for surgical action triplet detection","date":"2023-02-13","arxiv_id":"2302.06294","n_code_links":2,"syntology":null},{"paper":null,"slug":"clip-rr-improved-clip-network-for-relation","title":"VITR: Augmenting Vision Transformers with Relation-Focused Learning for Cross-Modal Information Retrieval","date":"2023-02-13","arxiv_id":"2302.06350","n_code_links":0,"syntology":null},{"paper":"/paper/encoding-sentence-position-in-context-aware","slug":"encoding-sentence-position-in-context-aware","title":"Encoding Sentence Position in Context-Aware Neural Machine Translation with Concatenation","date":"2023-02-13","arxiv_id":"2302.06459","n_code_links":1,"syntology":null},{"paper":null,"slug":"linguistic-ambiguity-analysis-in-chatgpt","title":"Linguistic ambiguity analysis in ChatGPT","date":"2023-02-13","arxiv_id":"2302.06426","n_code_links":0,"syntology":null},{"paper":"/paper/one-transformer-for-all-time-series","slug":"one-transformer-for-all-time-series","title":"One Transformer for All Time Series: Representing and Training with Time-Dependent Heterogeneous Tabular Data","date":"2023-02-13","arxiv_id":"2302.06375","n_code_links":1,"syntology":{"ran":3,"of":4,"n_ran_checked":3,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":null}},{"paper":"/paper/simple-hardware-efficient-long-convolutions","slug":"simple-hardware-efficient-long-convolutions","title":"Simple Hardware-Efficient Long Convolutions for Sequence Modeling","date":"2023-02-13","arxiv_id":"2302.06646","n_code_links":1,"syntology":null},{"paper":null,"slug":"street-a-multi-task-structured-reasoning-and","title":"STREET: A Multi-Task Structured Reasoning and Explanation Benchmark","date":"2023-02-13","arxiv_id":"2302.06729","n_code_links":0,"syntology":null},{"paper":"/paper/towards-local-visual-modeling-for-image","slug":"towards-local-visual-modeling-for-image","title":"Towards Local Visual Modeling for Image Captioning","date":"2023-02-13","arxiv_id":"2302.06098","n_code_links":1,"syntology":null},{"paper":null,"slug":"using-shap-values-and-machine-learning-to","title":"Using SHAP Values and Machine Learning to Understand Trends in the Transient Stability Limit","date":"2023-02-13","arxiv_id":"2302.06274","n_code_links":0,"syntology":null},{"paper":null,"slug":"academic-writing-with-gpt-3-5-reflections-on","title":"Academic Writing with GPT-3.5: Reflections on Practices, Efficacy and Transparency","date":"2023-02-12","arxiv_id":"2304.11079","n_code_links":0,"syntology":null},{"paper":"/paper/generalized-few-shot-continual-learning-with","slug":"generalized-few-shot-continual-learning-with","title":"Generalized Few-Shot Continual Learning with Contrastive Mixture of Adapters","date":"2023-02-12","arxiv_id":"2302.05936","n_code_links":1,"syntology":null},{"paper":null,"slug":"transformer-models-an-introduction-and","title":"Transformer models: an introduction and catalog","date":"2023-02-12","arxiv_id":"2302.07730","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-brief-report-on-lawgpt-1-0-a-virtual-legal","title":"A Brief Report on LawGPT 1.0: A Virtual Legal Assistant Based on GPT-3","date":"2023-02-11","arxiv_id":"2302.05729","n_code_links":0,"syntology":null},{"paper":"/paper/differentiable-outlier-detection-enable","slug":"differentiable-outlier-detection-enable","title":"Differentiable Outlier Detection Enable Robust Deep Multimodal Analysis","date":"2023-02-11","arxiv_id":"2302.05608","n_code_links":1,"syntology":null},{"paper":"/paper/docile-benchmark-for-document-information","slug":"docile-benchmark-for-document-information","title":"DocILE Benchmark for Document Information Localization and Extraction","date":"2023-02-11","arxiv_id":"2302.05658","n_code_links":1,"syntology":null},{"paper":null,"slug":"best-bert-pre-training-for-sign-language","title":"BEST: BERT Pre-Training for Sign Language Recognition with Coupling Tokenization","date":"2023-02-10","arxiv_id":"2302.05075","n_code_links":0,"syntology":null},{"paper":"/paper/combat-ai-with-ai-counteract-machine","slug":"combat-ai-with-ai-counteract-machine","title":"Combat AI With AI: Counteract Machine-Generated Fake Restaurant Reviews on Social Media","date":"2023-02-10","arxiv_id":"2302.07731","n_code_links":1,"syntology":null},{"paper":"/paper/dual-memory-units-with-uncertainty-regulation","slug":"dual-memory-units-with-uncertainty-regulation","title":"Dual Memory Units with Uncertainty Regulation for Weakly Supervised Video Anomaly Detection","date":"2023-02-10","arxiv_id":"2302.05160","n_code_links":1,"syntology":{"ran":7,"of":7,"n_ran_checked":7,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"7 ran (of which 6 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["henrryzh1/UR-DMU"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":6,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/effective-document-image-enhancement-using","slug":"effective-document-image-enhancement-using","title":"Effective Document Image Enhancement Using tokens-to-token Transformer Network","date":"2023-02-10","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/fairpy-a-toolkit-for-evaluation-of-social","slug":"fairpy-a-toolkit-for-evaluation-of-social","title":"FairPy: A Toolkit for Evaluation of Prediction Biases and their Mitigation in Large Language Models","date":"2023-02-10","arxiv_id":"2302.05508","n_code_links":1,"syntology":null},{"paper":null,"slug":"patcorrect-non-autoregressive-phoneme","title":"PATCorrect: Non-autoregressive Phoneme-augmented Transformer for ASR Error Correction","date":"2023-02-10","arxiv_id":"2302.05040","n_code_links":0,"syntology":null},{"paper":"/paper/the-wisdom-of-hindsight-makes-language-models","slug":"the-wisdom-of-hindsight-makes-language-models","title":"The Wisdom of Hindsight Makes Language Models Better Instruction Followers","date":"2023-02-10","arxiv_id":"2302.05206","n_code_links":1,"syntology":null},{"paper":"/paper/translating-natural-language-to-planning","slug":"translating-natural-language-to-planning","title":"Translating Natural Language to Planning Goals with Large-Language Models","date":"2023-02-10","arxiv_id":"2302.05128","n_code_links":1,"syntology":null},{"paper":null,"slug":"better-by-you-better-than-me-chatgpt3-as","title":"Better by you, better than me, chatgpt3 as writing assistance in students essays","date":"2023-02-09","arxiv_id":"2302.04536","n_code_links":0,"syntology":null},{"paper":"/paper/binarized-neural-machine-translation-1","slug":"binarized-neural-machine-translation-1","title":"Binarized Neural Machine Translation","date":"2023-02-09","arxiv_id":"2302.04907","n_code_links":1,"syntology":{"ran":4,"of":6,"n_ran_checked":4,"n_instrument":0,"unverified":2,"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) · 2 unverified","official":{"repos":["google/aqt"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"flexible-model-agnostic-method-for-materials","title":"Flexible, Model-Agnostic Method for Materials Data Extraction from Text Using General Purpose Language Models","date":"2023-02-09","arxiv_id":"2302.04914","n_code_links":0,"syntology":null},{"paper":"/paper/hybrik-transformer","slug":"hybrik-transformer","title":"3D Human Pose and Shape Estimation via HybrIK-Transformer","date":"2023-02-09","arxiv_id":"2302.04774","n_code_links":1,"syntology":null},{"paper":"/paper/reversible-vision-transformers-1","slug":"reversible-vision-transformers-1","title":"Reversible Vision Transformers","date":"2023-02-09","arxiv_id":"2302.04869","n_code_links":4,"syntology":{"ran":24,"of":29,"n_ran_checked":23,"n_instrument":1,"unverified":5,"pointer_only":26,"phrase":"24 ran (of which 5 constructed an object rather than computing a result; 23 with no instrument failure: 0 honoured, 0 violated, 23 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified","official":{"repos":["karttikeya/minrev","facebookresearch/SlowFast","facebookresearch/mvit"],"state":"official (archive's flag): 22 ran","n_ran":22,"n_constructed":5,"n_ran_no_instrument_failure":21,"n_unverified":4,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/adapting-pre-trained-vision-transformers-from","slug":"adapting-pre-trained-vision-transformers-from","title":"Adapting Pre-trained Vision Transformers from 2D to 3D through Weight Inflation Improves Medical Image Segmentation","date":"2023-02-08","arxiv_id":"2302.04303","n_code_links":1,"syntology":null},{"paper":null,"slug":"an-empirical-study-of-uniform-architecture","title":"An Empirical Study of Uniform-Architecture Knowledge Distillation in Document Ranking","date":"2023-02-08","arxiv_id":"2302.04112","n_code_links":0,"syntology":null},{"paper":"/paper/attending-to-graph-transformers","slug":"attending-to-graph-transformers","title":"Attending to Graph Transformers","date":"2023-02-08","arxiv_id":"2302.04181","n_code_links":1,"syntology":{"ran":5,"of":8,"n_ran_checked":5,"n_instrument":0,"unverified":3,"pointer_only":4,"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) · 3 unverified","official":{"repos":["luis-mueller/probing-graph-transformers"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"auto-learning-an-adversarial-process-of-two","title":"EvoText: Enhancing Natural Language Generation Models via Self-Escalation Learning for Up-to-Date Knowledge and Improved Performance","date":"2023-02-08","arxiv_id":"2302.03896","n_code_links":0,"syntology":null},{"paper":"/paper/dual-interest-factorization-heads-attention","slug":"dual-interest-factorization-heads-attention","title":"Dual-interest Factorization-heads Attention for Sequential Recommendation","date":"2023-02-08","arxiv_id":"2302.03965","n_code_links":1,"syntology":null},{"paper":null,"slug":"leveraging-summary-guidance-on-medical-report","title":"Leveraging Summary Guidance on Medical Report Summarization","date":"2023-02-08","arxiv_id":"2302.04001","n_code_links":0,"syntology":null},{"paper":null,"slug":"swincross-cross-modal-swin-transformer-for","title":"SwinCross: Cross-modal Swin Transformer for Head-and-Neck Tumor Segmentation in PET/CT Images","date":"2023-02-08","arxiv_id":"2302.03861","n_code_links":0,"syntology":null},{"paper":"/paper/osrt-omnidirectional-image-super-resolution","slug":"osrt-omnidirectional-image-super-resolution","title":"OSRT: Omnidirectional Image Super-Resolution with Distortion-aware Transformer","date":"2023-02-07","arxiv_id":"2302.03453","n_code_links":1,"syntology":{"ran":11,"of":12,"n_ran_checked":10,"n_instrument":1,"unverified":1,"pointer_only":1,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["fanghua-yu/osrt"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"reliable-natural-language-understanding-with","title":"Reliable Natural Language Understanding with Large Language Models and Answer Set Programming","date":"2023-02-07","arxiv_id":"2302.03780","n_code_links":0,"syntology":null},{"paper":"/paper/what-matters-in-the-structured-pruning-of","slug":"what-matters-in-the-structured-pruning-of","title":"What Matters In The Structured Pruning of Generative Language Models?","date":"2023-02-07","arxiv_id":"2302.03773","n_code_links":1,"syntology":{"ran":2,"of":8,"n_ran_checked":2,"n_instrument":0,"unverified":6,"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) · 6 unverified","official":{"repos":["huggingface/nn_pruning"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":6,"ran_from_kinds":["official"]}}},{"paper":"/paper/controllable-lexical-simplification-for","slug":"controllable-lexical-simplification-for","title":"Controllable Lexical Simplification for English","date":"2023-02-06","arxiv_id":"2302.02900","n_code_links":1,"syntology":null},{"paper":"/paper/gps-reviving-the-art-of-message-passing-for","slug":"gps-reviving-the-art-of-message-passing-for","title":"GPS++: Reviving the Art of Message Passing for Molecular Property Prediction","date":"2023-02-06","arxiv_id":"2302.02947","n_code_links":1,"syntology":null},{"paper":"/paper/v1t-large-scale-mouse-v1-response-prediction","slug":"v1t-large-scale-mouse-v1-response-prediction","title":"V1T: large-scale mouse V1 response prediction using a Vision Transformer","date":"2023-02-06","arxiv_id":"2302.03023","n_code_links":1,"syntology":{"ran":16,"of":17,"n_ran_checked":16,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"16 ran (of which 0 constructed an object rather than computing a result; 16 with no instrument failure: 0 honoured, 0 violated, 16 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["bryanlimy/V1T"],"state":"official (archive's flag): 16 ran","n_ran":16,"n_constructed":0,"n_ran_no_instrument_failure":16,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"nationality-bias-in-text-generation","title":"Nationality Bias in Text Generation","date":"2023-02-05","arxiv_id":"2302.02463","n_code_links":0,"syntology":null},{"paper":null,"slug":"quantized-distributed-training-of-large","title":"Quantized Distributed Training of Large Models with Convergence Guarantees","date":"2023-02-05","arxiv_id":"2302.02390","n_code_links":0,"syntology":null},{"paper":null,"slug":"vulaste-long-sequence-model-with-abstract","title":"VuLASTE: Long Sequence Model with Abstract Syntax Tree Embedding for vulnerability Detection","date":"2023-02-05","arxiv_id":"2302.02345","n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-to-agree-on-vision-attention-for","title":"Learning to Agree on Vision Attention for Visual Commonsense Reasoning","date":"2023-02-04","arxiv_id":"2302.02117","n_code_links":0,"syntology":null},{"paper":"/paper/realtabformer-generating-realistic-relational","slug":"realtabformer-generating-realistic-relational","title":"REaLTabFormer: Generating Realistic Relational and Tabular Data using Transformers","date":"2023-02-04","arxiv_id":"2302.02041","n_code_links":3,"syntology":{"ran":3,"of":4,"n_ran_checked":3,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["avsolatorio/realtabformer"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/revisiting-image-deblurring-with-an-efficient","slug":"revisiting-image-deblurring-with-an-efficient","title":"Revisiting Image Deblurring with an Efficient ConvNet","date":"2023-02-04","arxiv_id":"2302.02234","n_code_links":1,"syntology":null},{"paper":null,"slug":"theory-of-mind-may-have-spontaneously-emerged","title":"Evaluating Large Language Models in Theory of Mind Tasks","date":"2023-02-04","arxiv_id":"2302.02083","n_code_links":0,"syntology":null},{"paper":null,"slug":"weight-is-attention-all-we-need-aeiuorder","title":"Greedy Ordering of Layer Weight Matrices in Transformers Improves Translation","date":"2023-02-04","arxiv_id":"2302.02123","n_code_links":0,"syntology":null},{"paper":null,"slug":"cfft-gan-cross-domain-feature-fusion","title":"CFFT-GAN: Cross-domain Feature Fusion Transformer for Exemplar-based Image Translation","date":"2023-02-03","arxiv_id":"2302.01608","n_code_links":0,"syntology":null},{"paper":null,"slug":"coinductive-guide-to-inductive-transformer","title":"Coinductive guide to inductive transformer heads","date":"2023-02-03","arxiv_id":"2302.01834","n_code_links":0,"syntology":null},{"paper":null,"slug":"device-depth-and-visual-concepts-aware","title":"DEVICE: DEpth and VIsual ConcEpts Aware Transformer for TextCaps","date":"2023-02-03","arxiv_id":"2302.01540","n_code_links":0,"syntology":null},{"paper":"/paper/dilateformer-multi-scale-dilated-transformer","slug":"dilateformer-multi-scale-dilated-transformer","title":"DilateFormer: Multi-Scale Dilated Transformer for Visual Recognition","date":"2023-02-03","arxiv_id":"2302.01791","n_code_links":1,"syntology":null},{"paper":"/paper/hdformer-high-order-directed-transformer-for","slug":"hdformer-high-order-directed-transformer-for","title":"HDFormer: High-order Directed Transformer for 3D Human Pose Estimation","date":"2023-02-03","arxiv_id":"2302.01825","n_code_links":1,"syntology":{"ran":6,"of":12,"n_ran_checked":4,"n_instrument":2,"unverified":6,"pointer_only":12,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 1 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 6 unverified","official":{"repos":["hyer/hdformer"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":6,"ran_from_kinds":["official"]}}},{"paper":"/paper/revisiting-intermediate-layer-distillation","slug":"revisiting-intermediate-layer-distillation","title":"Revisiting Intermediate Layer Distillation for Compressing Language Models: An Overfitting Perspective","date":"2023-02-03","arxiv_id":"2302.01530","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-survey-on-efficient-training-of","title":"A Survey on Efficient Training of Transformers","date":"2023-02-02","arxiv_id":"2302.01107","n_code_links":0,"syntology":null},{"paper":null,"slug":"boosting-low-data-instance-segmentation-by","title":"Boosting Low-Data Instance Segmentation by Unsupervised Pre-training with Saliency Prompt","date":"2023-02-02","arxiv_id":"2302.01171","n_code_links":0,"syntology":null},{"paper":null,"slug":"creating-a-large-language-model-of-a","title":"Creating a Large Language Model of a Philosopher","date":"2023-02-02","arxiv_id":"2302.01339","n_code_links":0,"syntology":null},{"paper":null,"slug":"curriculum-guided-abstractive-summarization-1","title":"Curriculum-Guided Abstractive Summarization","date":"2023-02-02","arxiv_id":"2302.01342","n_code_links":0,"syntology":null},{"paper":"/paper/dual-patchnorm","slug":"dual-patchnorm","title":"Dual PatchNorm","date":"2023-02-02","arxiv_id":"2302.01327","n_code_links":7,"syntology":{"ran":7,"of":9,"n_ran_checked":6,"n_instrument":1,"unverified":2,"pointer_only":2,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 4 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","official":{"repos":["google-research/big_vision"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":"/paper/fcb-swinv2-transformer-for-polyp-segmentation","slug":"fcb-swinv2-transformer-for-polyp-segmentation","title":"FCB-SwinV2 Transformer for Polyp Segmentation","date":"2023-02-02","arxiv_id":"2302.01027","n_code_links":0,"syntology":null},{"paper":null,"slug":"history-aware-hierarchical-transformer-for","title":"History-Aware Hierarchical Transformer for Multi-session Open-domain Dialogue System","date":"2023-02-02","arxiv_id":"2302.00907","n_code_links":0,"syntology":null},{"paper":null,"slug":"idt5-indonesian-version-of-multilingual-t5","title":"idT5: Indonesian Version of Multilingual T5 Transformer","date":"2023-02-02","arxiv_id":"2302.00856","n_code_links":0,"syntology":null},{"paper":null,"slug":"molecular-geometry-aware-transformer-for","title":"Molecular Geometry-aware Transformer for accurate 3D Atomic System modeling","date":"2023-02-02","arxiv_id":"2302.00855","n_code_links":0,"syntology":null},{"paper":"/paper/semantic-coherence-markers-for-the-early","slug":"semantic-coherence-markers-for-the-early","title":"Semantic Coherence Markers for the Early Diagnosis of the Alzheimer Disease","date":"2023-02-02","arxiv_id":"2302.01025","n_code_links":1,"syntology":null},{"paper":null,"slug":"vision-transformer-based-feature-extraction","title":"Vision Transformer-based Feature Extraction for Generalized Zero-Shot Learning","date":"2023-02-02","arxiv_id":"2302.00875","n_code_links":0,"syntology":null},{"paper":null,"slug":"what-language-reveals-about-perception","title":"Large language models predict human sensory judgments across six modalities","date":"2023-02-02","arxiv_id":"2302.01308","n_code_links":0,"syntology":null},{"paper":"/paper/analyzing-leakage-of-personally-identifiable","slug":"analyzing-leakage-of-personally-identifiable","title":"Analyzing Leakage of Personally Identifiable Information in Language Models","date":"2023-02-01","arxiv_id":"2302.00539","n_code_links":1,"syntology":null},{"paper":null,"slug":"clinical-decision-transformer-intended","title":"Clinical Decision Transformer: Intended Treatment Recommendation through Goal Prompting","date":"2023-02-01","arxiv_id":"2302.00612","n_code_links":0,"syntology":null},{"paper":null,"slug":"co-writing-with-opinionated-language-models","title":"Co-Writing with Opinionated Language Models Affects Users' Views","date":"2023-02-01","arxiv_id":"2302.00560","n_code_links":0,"syntology":null},{"paper":"/paper/feed-forward-blocks-control-contextualization","slug":"feed-forward-blocks-control-contextualization","title":"Analyzing Feed-Forward Blocks in Transformers through the Lens of Attention Maps","date":"2023-02-01","arxiv_id":"2302.00456","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":1,"n_instrument":1,"unverified":0,"pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["gorokoba560/norm-analysis-of-transformer"],"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":["official"]}}}],"record_sha256":"c187c7edcc22d0f161cda6459c6361ab46c44ab665bbac9299d67df873065ea3","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}