{"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/dropout/papers/131","list_of":"/method/dropout","method":"Dropout","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":131,"pages_in_order":275,"rows_per_page":100,"rows":[13001,13100],"of":27472,"counts":{"archive_papers_tagged":27472,"with_a_code_link":12129,"where_syntology_ran_a_sample":3620,"not_listed_spam_title":0,"listed":27472,"listed_where_code_ran":3620,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":3044,"every_run_a_failure_of_syntologys_instrument":576,"listed_with_a_run_with_no_instrument_failure":3044,"listed_every_run_a_failure_of_syntologys_instrument":576,"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/dropout","prev":"/method/dropout/papers/130","next":"/method/dropout/papers/132","papers":[{"paper":null,"slug":"deep-fusion-efficient-network-training-via","title":"Deep Fusion: Efficient Network Training via Pre-trained Initializations","date":"2023-06-20","arxiv_id":"2306.11903","n_code_links":0,"syntology":null},{"paper":null,"slug":"democratizing-llms-for-low-resource-languages","title":"Democratizing LLMs for Low-Resource Languages by Leveraging their English Dominant Abilities with Linguistically-Diverse Prompts","date":"2023-06-20","arxiv_id":"2306.11372","n_code_links":0,"syntology":null},{"paper":"/paper/event-stream-gpt-a-data-pre-processing-and-1","slug":"event-stream-gpt-a-data-pre-processing-and-1","title":"Event Stream GPT: A Data Pre-processing and Modeling Library for Generative, Pre-trained Transformers over Continuous-time Sequences of Complex Events","date":"2023-06-20","arxiv_id":"2306.11547","n_code_links":1,"syntology":{"ran":5,"of":10,"n_ran_checked":5,"n_instrument":0,"unverified":5,"pointer_only":0,"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) · 5 unverified","official":{"repos":["mmcdermott/eventstreamgpt"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":"/paper/gpt-4-reticular-chemist-for-mof-discovery","slug":"gpt-4-reticular-chemist-for-mof-discovery","title":"A GPT-4 Reticular Chemist for Guiding MOF Discovery","date":"2023-06-20","arxiv_id":"2306.14915","n_code_links":1,"syntology":null},{"paper":null,"slug":"harnessing-the-power-of-adversarial-prompting","title":"Harnessing the Power of Adversarial Prompting and Large Language Models for Robust Hypothesis Generation in Astronomy","date":"2023-06-20","arxiv_id":"2306.11648","n_code_links":0,"syntology":null},{"paper":"/paper/inrank-incremental-low-rank-learning","slug":"inrank-incremental-low-rank-learning","title":"InRank: Incremental Low-Rank Learning","date":"2023-06-20","arxiv_id":"2306.11250","n_code_links":1,"syntology":null},{"paper":"/paper/learning-to-generate-better-than-your-llm","slug":"learning-to-generate-better-than-your-llm","title":"Learning to Generate Better Than Your LLM","date":"2023-06-20","arxiv_id":"2306.11816","n_code_links":1,"syntology":null},{"paper":null,"slug":"multiverse-transformer-1st-place-solution-for","title":"Multiverse Transformer: 1st Place Solution for Waymo Open Sim Agents Challenge 2023","date":"2023-06-20","arxiv_id":"2306.11868","n_code_links":0,"syntology":null},{"paper":null,"slug":"rm-prt-realistic-robotic-manipulation","title":"Surfer: Progressive Reasoning with World Models for Robotic Manipulation","date":"2023-06-20","arxiv_id":"2306.11335","n_code_links":0,"syntology":null},{"paper":null,"slug":"textbooks-are-all-you-need","title":"Textbooks Are All You Need","date":"2023-06-20","arxiv_id":"2306.11644","n_code_links":0,"syntology":null},{"paper":null,"slug":"transforming-graphs-for-enhanced-attribute","title":"Transforming Graphs for Enhanced Attribute Clustering: An Innovative Graph Transformer-Based Method","date":"2023-06-20","arxiv_id":"2306.11307","n_code_links":0,"syntology":null},{"paper":"/paper/uncertainty-estimation-for-molecules","slug":"uncertainty-estimation-for-molecules","title":"Uncertainty Estimation for Molecules: Desiderata and Methods","date":"2023-06-20","arxiv_id":"2306.14916","n_code_links":1,"syntology":null},{"paper":null,"slug":"unfolding-framework-with-prior-of-convolution","title":"Unfolding Framework with Prior of Convolution-Transformer Mixture and Uncertainty Estimation for Video Snapshot Compressive Imaging","date":"2023-06-20","arxiv_id":"2306.11316","n_code_links":0,"syntology":null},{"paper":"/paper/a-preliminary-study-of-chatgpt-on-news","slug":"a-preliminary-study-of-chatgpt-on-news","title":"A Preliminary Study of ChatGPT on News Recommendation: Personalization, Provider Fairness, Fake News","date":"2023-06-19","arxiv_id":"2306.10702","n_code_links":1,"syntology":null},{"paper":"/paper/amrs-assemble-learning-to-ensemble-with","slug":"amrs-assemble-learning-to-ensemble-with","title":"AMRs Assemble! Learning to Ensemble with Autoregressive Models for AMR Parsing","date":"2023-06-19","arxiv_id":"2306.10786","n_code_links":1,"syntology":null},{"paper":"/paper/bayling-bridging-cross-lingual-alignment-and","slug":"bayling-bridging-cross-lingual-alignment-and","title":"BayLing: Bridging Cross-lingual Alignment and Instruction Following through Interactive Translation for Large Language Models","date":"2023-06-19","arxiv_id":"2306.10968","n_code_links":1,"syntology":null},{"paper":"/paper/fine-tuning-language-models-for-scientific","slug":"fine-tuning-language-models-for-scientific","title":"Fine-Tuning Language Models for Scientific Writing Support","date":"2023-06-19","arxiv_id":"2306.10974","n_code_links":1,"syntology":null},{"paper":null,"slug":"generative-sequential-recommendation-with","title":"Generative Sequential Recommendation with GPTRec","date":"2023-06-19","arxiv_id":"2306.11114","n_code_links":0,"syntology":null},{"paper":"/paper/multi-task-learning-for-radar-signal","slug":"multi-task-learning-for-radar-signal","title":"Multi-task Learning for Radar Signal Characterisation","date":"2023-06-19","arxiv_id":"2306.13105","n_code_links":1,"syntology":null},{"paper":null,"slug":"multitrack-music-transcription-with-a-time","title":"Multitrack Music Transcription with a Time-Frequency Perceiver","date":"2023-06-19","arxiv_id":"2306.10785","n_code_links":0,"syntology":null},{"paper":"/paper/nar-former-v2-rethinking-transformer-for-1","slug":"nar-former-v2-rethinking-transformer-for-1","title":"NAR-Former V2: Rethinking Transformer for Universal Neural Network Representation Learning","date":"2023-06-19","arxiv_id":"2306.10792","n_code_links":1,"syntology":{"ran":9,"of":15,"n_ran_checked":9,"n_instrument":0,"unverified":6,"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) · 6 unverified","official":{"repos":["yuny220/NAR-Former-V2"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":6,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"ravitt-random-vision-transformer-tokens","title":"RaViTT: Random Vision Transformer Tokens","date":"2023-06-19","arxiv_id":"2306.10959","n_code_links":0,"syntology":null},{"paper":"/paper/renderers-are-good-zero-shot-representation","slug":"renderers-are-good-zero-shot-representation","title":"Renderers are Good Zero-Shot Representation Learners: Exploring Diffusion Latents for Metric Learning","date":"2023-06-19","arxiv_id":"2306.10721","n_code_links":1,"syntology":null},{"paper":null,"slug":"synergpt-in-context-learning-for-personalized","title":"SynerGPT: In-Context Learning for Personalized Drug Synergy Prediction and Drug Design","date":"2023-06-19","arxiv_id":"2307.11694","n_code_links":0,"syntology":null},{"paper":null,"slug":"temporal-data-meets-llm-explainable-financial","title":"Temporal Data Meets LLM -- Explainable Financial Time Series Forecasting","date":"2023-06-19","arxiv_id":"2306.11025","n_code_links":0,"syntology":null},{"paper":"/paper/transformer-training-strategies-for","slug":"transformer-training-strategies-for","title":"Transformer Training Strategies for Forecasting Multiple Load Time Series","date":"2023-06-19","arxiv_id":"2306.10891","n_code_links":1,"syntology":null},{"paper":null,"slug":"dropout-regularization-versus-ell-2","title":"Dropout Regularization Versus $\\ell_2$-Penalization in the Linear Model","date":"2023-06-18","arxiv_id":"2306.10529","n_code_links":0,"syntology":null},{"paper":"/paper/enhanced-masked-image-modeling-for-analysis","slug":"enhanced-masked-image-modeling-for-analysis","title":"Enhanced Masked Image Modeling for Analysis of Dental Panoramic Radiographs","date":"2023-06-18","arxiv_id":"2306.10623","n_code_links":1,"syntology":null},{"paper":null,"slug":"gender-bias-in-transformer-models-a","title":"Gender Bias in Transformer Models: A comprehensive survey","date":"2023-06-18","arxiv_id":"2306.10530","n_code_links":0,"syntology":null},{"paper":"/paper/instant-soup-cheap-pruning-ensembles-in-a","slug":"instant-soup-cheap-pruning-ensembles-in-a","title":"Instant Soup: Cheap Pruning Ensembles in A Single Pass Can Draw Lottery Tickets from Large Models","date":"2023-06-18","arxiv_id":"2306.10460","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"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) · 0 unverified","official":{"repos":["vita-group/instant_soup"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"mixed-curvature-transformers-for-graph","title":"Mixed-Curvature Transformers for Graph Representation Learning papersreview","date":"2023-06-18","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"news-verifiers-showdown-a-comparative","title":"News Verifiers Showdown: A Comparative Performance Evaluation of ChatGPT 3.5, ChatGPT 4.0, Bing AI, and Bard in News Fact-Checking","date":"2023-06-18","arxiv_id":"2306.17176","n_code_links":0,"syntology":null},{"paper":null,"slug":"summarization-from-leaderboards-to-practice","title":"Summarization from Leaderboards to Practice: Choosing A Representation Backbone and Ensuring Robustness","date":"2023-06-18","arxiv_id":"2306.10555","n_code_links":0,"syntology":null},{"paper":"/paper/enhancing-social-network-hate-detection-using","slug":"enhancing-social-network-hate-detection-using","title":"Enhancing social network hate detection using back translation and GPT-3 augmentations during training and test-time","date":"2023-06-17","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/nbmod-find-it-and-grasp-it-in-noisy","slug":"nbmod-find-it-and-grasp-it-in-noisy","title":"NBMOD: Find It and Grasp It in Noisy Background","date":"2023-06-17","arxiv_id":"2306.10265","n_code_links":1,"syntology":null},{"paper":null,"slug":"snowman-a-million-scale-chinese-commonsense","title":"Snowman: A Million-scale Chinese Commonsense Knowledge Graph Distilled from Foundation Model","date":"2023-06-17","arxiv_id":"2306.10241","n_code_links":0,"syntology":null},{"paper":null,"slug":"ad-autogpt-an-autonomous-gpt-for-alzheimer-s","title":"AD-AutoGPT: An Autonomous GPT for Alzheimer's Disease Infodemiology","date":"2023-06-16","arxiv_id":"2306.10095","n_code_links":0,"syntology":null},{"paper":"/paper/demystifying-gpt-self-repair-for-code","slug":"demystifying-gpt-self-repair-for-code","title":"Is Self-Repair a Silver Bullet for Code Generation?","date":"2023-06-16","arxiv_id":"2306.09896","n_code_links":1,"syntology":null},{"paper":"/paper/end-to-end-vectorized-hd-map-construction-1","slug":"end-to-end-vectorized-hd-map-construction-1","title":"End-to-End Vectorized HD-map Construction with Piecewise Bezier Curve","date":"2023-06-16","arxiv_id":"2306.09700","n_code_links":1,"syntology":null},{"paper":"/paper/evaluating-superhuman-models-with-consistency","slug":"evaluating-superhuman-models-with-consistency","title":"Evaluating Superhuman Models with Consistency Checks","date":"2023-06-16","arxiv_id":"2306.09983","n_code_links":2,"syntology":null},{"paper":"/paper/gpt4-is-slightly-helpful-for-peer-review","slug":"gpt4-is-slightly-helpful-for-peer-review","title":"GPT4 is Slightly Helpful for Peer-Review Assistance: A Pilot Study","date":"2023-06-16","arxiv_id":"2307.05492","n_code_links":2,"syntology":null},{"paper":null,"slug":"investigating-masking-based-data-generation","title":"Investigating Masking-based Data Generation in Language Models","date":"2023-06-16","arxiv_id":"2307.00008","n_code_links":0,"syntology":null},{"paper":"/paper/multiwave-multiresolution-deep-architectures","slug":"multiwave-multiresolution-deep-architectures","title":"MultiWave: Multiresolution Deep Architectures through Wavelet Decomposition for Multivariate Time Series Prediction","date":"2023-06-16","arxiv_id":"2306.10164","n_code_links":1,"syntology":null},{"paper":null,"slug":"revealing-the-impact-of-social-circumstances","title":"Revealing the impact of social circumstances on the selection of cancer therapy through natural language processing of social work notes","date":"2023-06-16","arxiv_id":"2306.09877","n_code_links":0,"syntology":null},{"paper":null,"slug":"robot-learning-with-sensorimotor-pre-training","title":"Robot Learning with Sensorimotor Pre-training","date":"2023-06-16","arxiv_id":"2306.10007","n_code_links":0,"syntology":null},{"paper":null,"slug":"spatial-spindrop-spatial-dropout-based-binary","title":"Spatial-SpinDrop: Spatial Dropout-based Binary Bayesian Neural Network with Spintronics Implementation","date":"2023-06-16","arxiv_id":"2306.10185","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-better-orthogonality-regularization","title":"Towards Better Orthogonality Regularization with Disentangled Norm in Training Deep CNNs","date":"2023-06-16","arxiv_id":"2306.09939","n_code_links":0,"syntology":null},{"paper":null,"slug":"tsnet-sac-leveraging-transformers-for","title":"TSNet-SAC: Leveraging Transformers for Efficient Task Scheduling","date":"2023-06-16","arxiv_id":"2307.07445","n_code_links":0,"syntology":null},{"paper":"/paper/bed-bi-encoder-based-detectors-for-out-of","slug":"bed-bi-encoder-based-detectors-for-out-of","title":"BED: Bi-Encoder-Based Detectors for Out-of-Distribution Detection","date":"2023-06-15","arxiv_id":"2306.08852","n_code_links":1,"syntology":null},{"paper":null,"slug":"block-state-transformer","title":"Block-State Transformers","date":"2023-06-15","arxiv_id":"2306.09539","n_code_links":0,"syntology":null},{"paper":"/paper/chessgpt-bridging-policy-learning-and-1","slug":"chessgpt-bridging-policy-learning-and-1","title":"ChessGPT: Bridging Policy Learning and Language Modeling","date":"2023-06-15","arxiv_id":"2306.09200","n_code_links":1,"syntology":{"ran":14,"of":20,"n_ran_checked":10,"n_instrument":4,"unverified":6,"pointer_only":0,"phrase":"14 ran (of which 8 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 1 violated, 9 with no contract checked; 4 where Syntology's instrument failed) · 6 unverified","official":{"repos":["waterhorse1/chessgpt"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":8,"n_ran_no_instrument_failure":10,"n_unverified":6,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"distillation-strategies-for-discriminative","title":"Distillation Strategies for Discriminative Speech Recognition Rescoring","date":"2023-06-15","arxiv_id":"2306.09452","n_code_links":0,"syntology":null},{"paper":"/paper/efficient-token-guided-image-text-retrieval","slug":"efficient-token-guided-image-text-retrieval","title":"Efficient Token-Guided Image-Text Retrieval with Consistent Multimodal Contrastive Training","date":"2023-06-15","arxiv_id":"2306.08789","n_code_links":1,"syntology":{"ran":11,"of":15,"n_ran_checked":10,"n_instrument":1,"unverified":4,"pointer_only":2,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 1 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","official":null}},{"paper":null,"slug":"explaining-legal-concepts-with-augmented","title":"Explaining Legal Concepts with Augmented Large Language Models (GPT-4)","date":"2023-06-15","arxiv_id":"2306.09525","n_code_links":0,"syntology":null},{"paper":"/paper/explore-establish-exploit-red-teaming","slug":"explore-establish-exploit-red-teaming","title":"Explore, Establish, Exploit: Red Teaming Language Models from Scratch","date":"2023-06-15","arxiv_id":"2306.09442","n_code_links":3,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":1,"phrase":"0 ran · 1 unverified","official":{"repos":["algorithmic-alignment-lab/commonclaim","thestephencasper/common_claim","thestephencasper/explore_establish_exploit_llms"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"paper":null,"slug":"exploring-the-mit-mathematics-and-eecs","title":"Exploring the MIT Mathematics and EECS Curriculum Using Large Language Models","date":"2023-06-15","arxiv_id":"2306.08997","n_code_links":0,"syntology":null},{"paper":"/paper/fast-training-of-diffusion-models-with-masked","slug":"fast-training-of-diffusion-models-with-masked","title":"Fast Training of Diffusion Models with Masked Transformers","date":"2023-06-15","arxiv_id":"2306.09305","n_code_links":1,"syntology":{"ran":13,"of":17,"n_ran_checked":10,"n_instrument":3,"unverified":4,"pointer_only":2,"phrase":"13 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; 3 where Syntology's instrument failed) · 4 unverified","official":{"repos":["anima-lab/maskdit"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"language-guided-music-recommendation-for-1","title":"Language-Guided Music Recommendation for Video via Prompt Analogies","date":"2023-06-15","arxiv_id":"2306.09327","n_code_links":0,"syntology":null},{"paper":null,"slug":"mapping-researcher-activity-based-on","title":"Mapping Researcher Activity based on Publication Data by means of Transformers","date":"2023-06-15","arxiv_id":"2306.09049","n_code_links":0,"syntology":null},{"paper":null,"slug":"mpsa-densenet-a-novel-deep-learning-model-for","title":"MPSA-DenseNet: A novel deep learning model for English accent classification","date":"2023-06-15","arxiv_id":"2306.08798","n_code_links":0,"syntology":null},{"paper":"/paper/recurrent-memory-decision-transformer","slug":"recurrent-memory-decision-transformer","title":"Recurrent Action Transformer with Memory","date":"2023-06-15","arxiv_id":"2306.09459","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":2,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"3 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; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["airi-institute/rate"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"relational-temporal-graph-reasoning-for-dual","title":"Relational Temporal Graph Reasoning for Dual-task Dialogue Language Understanding","date":"2023-06-15","arxiv_id":"2306.09114","n_code_links":0,"syntology":null},{"paper":null,"slug":"revealing-the-illusion-of-joint-multimodal","title":"Dissecting Multimodality in VideoQA Transformer Models by Impairing Modality Fusion","date":"2023-06-15","arxiv_id":"2306.08889","n_code_links":0,"syntology":null},{"paper":"/paper/seeing-the-pose-in-the-pixels-learning-pose","slug":"seeing-the-pose-in-the-pixels-learning-pose","title":"Seeing the Pose in the Pixels: Learning Pose-Aware Representations in Vision Transformers","date":"2023-06-15","arxiv_id":"2306.09331","n_code_links":1,"syntology":null},{"paper":"/paper/slamb-accelerated-large-batch-training-with","slug":"slamb-accelerated-large-batch-training-with","title":"SLAMB: Accelerated Large Batch Training with Sparse Communication","date":"2023-06-15","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"stochastic-re-weighted-gradient-descent-via","title":"Stochastic Re-weighted Gradient Descent via Distributionally Robust Optimization","date":"2023-06-15","arxiv_id":"2306.09222","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-pop-song-generator-designing-an-online","title":"The pop song generator: designing an online course to teach collaborative, creative AI","date":"2023-06-15","arxiv_id":"2306.10069","n_code_links":0,"syntology":null},{"paper":null,"slug":"thrilled-by-your-progress-large-language","title":"Thrilled by Your Progress! Large Language Models (GPT-4) No Longer Struggle to Pass Assessments in Higher Education Programming Courses","date":"2023-06-15","arxiv_id":"2306.10073","n_code_links":0,"syntology":null},{"paper":null,"slug":"tighter-prediction-intervals-for-causal","title":"Ensembled Prediction Intervals for Causal Outcomes Under Hidden Confounding","date":"2023-06-15","arxiv_id":"2306.09520","n_code_links":0,"syntology":null},{"paper":null,"slug":"training-diffusion-classifiers-with-denoising","title":"DiffAug: A Diffuse-and-Denoise Augmentation for Training Robust Classifiers","date":"2023-06-15","arxiv_id":"2306.09192","n_code_links":0,"syntology":null},{"paper":"/paper/a-semantically-enhanced-dual-encoder-for","slug":"a-semantically-enhanced-dual-encoder-for","title":"A semantically enhanced dual encoder for aspect sentiment triplet extraction","date":"2023-06-14","arxiv_id":"2306.08373","n_code_links":1,"syntology":null},{"paper":"/paper/assessing-the-effectiveness-of-gpt-3-in","slug":"assessing-the-effectiveness-of-gpt-3-in","title":"Assessing the Effectiveness of GPT-3 in Detecting False Political Statements: A Case Study on the LIAR Dataset","date":"2023-06-14","arxiv_id":"2306.08190","n_code_links":1,"syntology":null},{"paper":null,"slug":"building-a-corpus-for-biomedical-relation","title":"Building a Corpus for Biomedical Relation Extraction of Species Mentions","date":"2023-06-14","arxiv_id":"2306.08403","n_code_links":0,"syntology":null},{"paper":"/paper/language-models-are-not-naysayers-an-analysis","slug":"language-models-are-not-naysayers-an-analysis","title":"Language models are not naysayers: An analysis of language models on negation benchmarks","date":"2023-06-14","arxiv_id":"2306.08189","n_code_links":1,"syntology":null},{"paper":null,"slug":"m-2unet-metaformer-multi-scale-upsampling","title":"M^2UNet: MetaFormer Multi-scale Upsampling Network for Polyp Segmentation","date":"2023-06-14","arxiv_id":"2306.08600","n_code_links":0,"syntology":null},{"paper":null,"slug":"mcr-data2vec-2-0-improving-self-supervised","title":"MCR-Data2vec 2.0: Improving Self-supervised Speech Pre-training via Model-level Consistency Regularization","date":"2023-06-14","arxiv_id":"2306.08463","n_code_links":0,"syntology":null},{"paper":"/paper/muben-benchmarking-the-uncertainty-of-pre","slug":"muben-benchmarking-the-uncertainty-of-pre","title":"MUBen: Benchmarking the Uncertainty of Molecular Representation Models","date":"2023-06-14","arxiv_id":"2306.10060","n_code_links":2,"syntology":{"ran":1,"of":2,"n_ran_checked":0,"n_instrument":1,"unverified":1,"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) · 1 unverified","official":{"repos":["Yinghao-Li/UncertaintyBenchmark","yinghao-li/muben"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/multimodal-optimal-transport-based-co","slug":"multimodal-optimal-transport-based-co","title":"Multimodal Optimal Transport-based Co-Attention Transformer with Global Structure Consistency for Survival Prediction","date":"2023-06-14","arxiv_id":"2306.08330","n_code_links":3,"syntology":{"ran":10,"of":18,"n_ran_checked":7,"n_instrument":3,"unverified":8,"pointer_only":18,"phrase":"10 ran (of which 6 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 8 unverified","official":{"repos":["innse/motcat"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["listed"]}}},{"paper":null,"slug":"research-on-named-entity-recognition-in","title":"Research on Named Entity Recognition in Improved transformer with R-Drop structure","date":"2023-06-14","arxiv_id":"2306.08315","n_code_links":0,"syntology":null},{"paper":"/paper/the-elm-neuron-an-efficient-and-expressive","slug":"the-elm-neuron-an-efficient-and-expressive","title":"The Expressive Leaky Memory Neuron: an Efficient and Expressive Phenomenological Neuron Model Can Solve Long-Horizon Tasks","date":"2023-06-14","arxiv_id":"2306.16922","n_code_links":1,"syntology":{"ran":6,"of":7,"n_ran_checked":3,"n_instrument":3,"unverified":1,"pointer_only":0,"phrase":"6 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; 3 where Syntology's instrument failed) · 1 unverified","official":{"repos":["AaronSpieler/elmneuron"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"towards-agi-in-computer-vision-lessons","title":"Towards AGI in Computer Vision: Lessons Learned from GPT and Large Language Models","date":"2023-06-14","arxiv_id":"2306.08641","n_code_links":0,"syntology":null},{"paper":"/paper/tsmixer-lightweight-mlp-mixer-model-for","slug":"tsmixer-lightweight-mlp-mixer-model-for","title":"TSMixer: Lightweight MLP-Mixer Model for Multivariate Time Series Forecasting","date":"2023-06-14","arxiv_id":"2306.09364","n_code_links":1,"syntology":{"ran":7,"of":8,"n_ran_checked":7,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["ibm/tsfm"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"unraveling-the-arc-puzzle-mimicking-human","title":"Unraveling the ARC Puzzle: Mimicking Human Solutions with Object-Centric Decision Transformer","date":"2023-06-14","arxiv_id":"2306.08204","n_code_links":0,"syntology":null},{"paper":"/paper/when-to-use-efficient-self-attention","slug":"when-to-use-efficient-self-attention","title":"When to Use Efficient Self Attention? Profiling Text, Speech and Image Transformer Variants","date":"2023-06-14","arxiv_id":"2306.08667","n_code_links":1,"syntology":null},{"paper":"/paper/world-to-words-grounded-open-vocabulary","slug":"world-to-words-grounded-open-vocabulary","title":"World-to-Words: Grounded Open Vocabulary Acquisition through Fast Mapping in Vision-Language Models","date":"2023-06-14","arxiv_id":"2306.08685","n_code_links":1,"syntology":{"ran":0,"of":2,"n_ran_checked":0,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"0 ran · 2 unverified","official":{"repos":["sled-group/world-to-words"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":[]}}},{"paper":"/paper/arxiveri-automatic-table-verification-with","slug":"arxiveri-automatic-table-verification-with","title":"arXiVeri: Automatic table verification with GPT","date":"2023-06-13","arxiv_id":"2306.07968","n_code_links":1,"syntology":null},{"paper":"/paper/can-chatgpt-enable-its-the-case-of-mixed","slug":"can-chatgpt-enable-its-the-case-of-mixed","title":"Can ChatGPT Enable ITS? The Case of Mixed Traffic Control via Reinforcement Learning","date":"2023-06-13","arxiv_id":"2306.08094","n_code_links":1,"syntology":null},{"paper":"/paper/enhancing-social-network-hate-detection-using-1","slug":"enhancing-social-network-hate-detection-using-1","title":"Enhancing Social Network Hate Detection Using Back Translation and GPT-3 Augmentations During Training and Test-Time","date":"2023-06-13","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"flame-few-shot-learning-from-natural-language","title":"FLamE: Few-shot Learning from Natural Language Explanations","date":"2023-06-13","arxiv_id":"2306.08042","n_code_links":0,"syntology":null},{"paper":null,"slug":"gemo-clap-gender-attribute-enhanced","title":"GEmo-CLAP: Gender-Attribute-Enhanced Contrastive Language-Audio Pretraining for Accurate Speech Emotion Recognition","date":"2023-06-13","arxiv_id":"2306.07848","n_code_links":0,"syntology":null},{"paper":"/paper/h2ogpt-democratizing-large-language-models","slug":"h2ogpt-democratizing-large-language-models","title":"h2oGPT: Democratizing Large Language Models","date":"2023-06-13","arxiv_id":"2306.08161","n_code_links":2,"syntology":null},{"paper":null,"slug":"human-like-intuitive-behavior-and-reasoning","title":"Human-Like Intuitive Behavior and Reasoning Biases Emerged in Language Models -- and Disappeared in GPT-4","date":"2023-06-13","arxiv_id":"2306.07622","n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-opinion-based-question-answering","title":"Improving Opinion-based Question Answering Systems Through Label Error Detection and Overwrite","date":"2023-06-13","arxiv_id":"2306.07499","n_code_links":0,"syntology":null},{"paper":"/paper/improving-zero-shot-detection-of-low","slug":"improving-zero-shot-detection-of-low","title":"Improving Zero-Shot Detection of Low Prevalence Chest Pathologies using Domain Pre-trained Language Models","date":"2023-06-13","arxiv_id":"2306.08000","n_code_links":1,"syntology":null},{"paper":null,"slug":"molcap-molecular-chemical-reactivity","title":"MolCAP: Molecular Chemical reActivity pretraining and prompted-finetuning enhanced molecular representation learning","date":"2023-06-13","arxiv_id":"2306.09187","n_code_links":0,"syntology":null},{"paper":null,"slug":"monolingual-and-cross-lingual-knowledge","title":"Monolingual and Cross-Lingual Knowledge Transfer for Topic Classification","date":"2023-06-13","arxiv_id":"2306.07797","n_code_links":0,"syntology":null},{"paper":null,"slug":"vector-quantized-graph-auto-encoder","title":"Discrete Graph Auto-Encoder","date":"2023-06-13","arxiv_id":"2306.07735","n_code_links":0,"syntology":null},{"paper":"/paper/xraygpt-chest-radiographs-summarization-using","slug":"xraygpt-chest-radiographs-summarization-using","title":"XrayGPT: Chest Radiographs Summarization using Medical Vision-Language Models","date":"2023-06-13","arxiv_id":"2306.07971","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-survey-of-vision-language-pre-training-from","title":"A Survey of Vision-Language Pre-training from the Lens of Multimodal Machine Translation","date":"2023-06-12","arxiv_id":"2306.07198","n_code_links":0,"syntology":null},{"paper":"/paper/aerialformer-multi-resolution-transformer-for","slug":"aerialformer-multi-resolution-transformer-for","title":"AerialFormer: Multi-resolution Transformer for Aerial Image Segmentation","date":"2023-06-12","arxiv_id":"2306.06842","n_code_links":1,"syntology":null}],"record_sha256":"83e8bef27257d1b92223cab0922c4b99ce12c86ca8b4ec3175b90c18c5324461","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}