{"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/adam/papers/124","list_of":"/method/adam","method":"Adam","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":124,"pages_in_order":244,"rows_per_page":100,"rows":[12301,12400],"of":24390,"counts":{"archive_papers_tagged":24390,"with_a_code_link":10944,"where_syntology_ran_a_sample":3424,"not_listed_spam_title":0,"listed":24390,"listed_where_code_ran":3424,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":2899,"every_run_a_failure_of_syntologys_instrument":525,"listed_with_a_run_with_no_instrument_failure":2899,"listed_every_run_a_failure_of_syntologys_instrument":525,"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/adam","prev":"/method/adam/papers/123","next":"/method/adam/papers/125","papers":[{"paper":null,"slug":"transformer-based-unet-with-multi-headed","title":"Transformer-Based UNet with Multi-Headed Cross-Attention Skip Connections to Eliminate Artifacts in Scanned Documents","date":"2023-06-05","arxiv_id":"2306.02815","n_code_links":0,"syntology":null},{"paper":"/paper/using-sequences-of-life-events-to-predict","slug":"using-sequences-of-life-events-to-predict","title":"Using Sequences of Life-events to Predict Human Lives","date":"2023-06-05","arxiv_id":"2306.03009","n_code_links":2,"syntology":null},{"paper":null,"slug":"a-mathematical-abstraction-for-balancing-the","title":"A Mathematical Abstraction for Balancing the Trade-off Between Creativity and Reality in Large Language Models","date":"2023-06-04","arxiv_id":"2306.02295","n_code_links":0,"syntology":null},{"paper":"/paper/auto-gpt-for-online-decision-making","slug":"auto-gpt-for-online-decision-making","title":"Auto-GPT for Online Decision Making: Benchmarks and Additional Opinions","date":"2023-06-04","arxiv_id":"2306.02224","n_code_links":1,"syntology":{"ran":6,"of":11,"n_ran_checked":5,"n_instrument":1,"unverified":5,"pointer_only":4,"phrase":"6 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; 1 where Syntology's instrument failed) · 5 unverified","official":{"repos":["younghuman/llmagent"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":"/paper/for-sale-state-action-representation-learning-1","slug":"for-sale-state-action-representation-learning-1","title":"For SALE: State-Action Representation Learning for Deep Reinforcement Learning","date":"2023-06-04","arxiv_id":"2306.02451","n_code_links":2,"syntology":{"ran":3,"of":3,"n_ran_checked":1,"n_instrument":2,"unverified":0,"pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["sfujim/td7"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["found_in_text","official"]}}},{"paper":"/paper/graph-transformer-for-recommendation","slug":"graph-transformer-for-recommendation","title":"Graph Transformer for Recommendation","date":"2023-06-04","arxiv_id":"2306.02330","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":3,"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) · 0 unverified","official":{"repos":["hkuds/gformer"],"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":null,"slug":"modular-transformers-compressing-transformers","title":"Modular Transformers: Compressing Transformers into Modularized Layers for Flexible Efficient Inference","date":"2023-06-04","arxiv_id":"2306.02379","n_code_links":0,"syntology":null},{"paper":"/paper/spellmapper-a-non-autoregressive-neural","slug":"spellmapper-a-non-autoregressive-neural","title":"SpellMapper: A non-autoregressive neural spellchecker for ASR customization with candidate retrieval based on n-gram mappings","date":"2023-06-04","arxiv_id":"2306.02317","n_code_links":1,"syntology":null},{"paper":null,"slug":"financial-sentiment-analysis-using-finbert","title":"Financial sentiment analysis using FinBERT with application in predicting stock movement","date":"2023-06-03","arxiv_id":"2306.02136","n_code_links":0,"syntology":null},{"paper":null,"slug":"gat-gan-a-graph-attention-based-time-series","title":"GAT-GAN : A Graph-Attention-based Time-Series Generative Adversarial Network","date":"2023-06-03","arxiv_id":"2306.01999","n_code_links":0,"syntology":null},{"paper":null,"slug":"lightweight-structure-aware-transformer","title":"Lightweight Structure-aware Transformer Network for VHR Remote Sensing Image Change Detection","date":"2023-06-03","arxiv_id":"2306.01988","n_code_links":0,"syntology":null},{"paper":"/paper/memorization-capacity-of-multi-head-attention","slug":"memorization-capacity-of-multi-head-attention","title":"Memorization Capacity of Multi-Head Attention in Transformers","date":"2023-06-03","arxiv_id":"2306.02010","n_code_links":1,"syntology":null},{"paper":null,"slug":"multilegalpile-a-689gb-multilingual-legal","title":"MultiLegalPile: A 689GB Multilingual Legal Corpus","date":"2023-06-03","arxiv_id":"2306.02069","n_code_links":0,"syntology":null},{"paper":null,"slug":"question-context-alignment-and-answer-context","title":"Question-Context Alignment and Answer-Context Dependencies for Effective Answer Sentence Selection","date":"2023-06-03","arxiv_id":"2306.02196","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-coding-social-science-datasets-with-1","title":"Towards Coding Social Science Datasets with Language Models","date":"2023-06-03","arxiv_id":"2306.02177","n_code_links":0,"syntology":null},{"paper":"/paper/transrupnet-for-improved-out-of-distribution","slug":"transrupnet-for-improved-out-of-distribution","title":"TransRUPNet for Improved Polyp Segmentation","date":"2023-06-03","arxiv_id":"2306.02176","n_code_links":1,"syntology":null},{"paper":null,"slug":"unsupervised-low-light-image-enhancement","title":"Unsupervised Low Light Image Enhancement Using SNR-Aware Swin Transformer","date":"2023-06-03","arxiv_id":"2306.02082","n_code_links":0,"syntology":null},{"paper":"/paper/an-empirical-study-on-challenging-math","slug":"an-empirical-study-on-challenging-math","title":"MathChat: Converse to Tackle Challenging Math Problems with LLM Agents","date":"2023-06-02","arxiv_id":"2306.01337","n_code_links":2,"syntology":null},{"paper":"/paper/binary-and-ternary-natural-language","slug":"binary-and-ternary-natural-language","title":"Binary and Ternary Natural Language Generation","date":"2023-06-02","arxiv_id":"2306.01841","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":["facebookresearch/ternary_binary_transformer"],"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/can-contextual-biasing-remain-effective-with","slug":"can-contextual-biasing-remain-effective-with","title":"Can Contextual Biasing Remain Effective with Whisper and GPT-2?","date":"2023-06-02","arxiv_id":"2306.01942","n_code_links":1,"syntology":null},{"paper":null,"slug":"can-llms-like-gpt-4-outperform-traditional-ai","title":"Can LLMs like GPT-4 outperform traditional AI tools in dementia diagnosis? Maybe, but not today","date":"2023-06-02","arxiv_id":"2306.01499","n_code_links":0,"syntology":null},{"paper":null,"slug":"concurrent-classifier-error-detection-cced-in","title":"Concurrent Classifier Error Detection (CCED) in Large Scale Machine Learning Systems","date":"2023-06-02","arxiv_id":"2306.01820","n_code_links":0,"syntology":null},{"paper":null,"slug":"establishment-of-nlp-based-greenwashing","title":"Establishment of NLP-Based Greenwashing Pattern Detection Service","date":"2023-06-02","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/evaluating-language-models-for-mathematics","slug":"evaluating-language-models-for-mathematics","title":"Evaluating Language Models for Mathematics through Interactions","date":"2023-06-02","arxiv_id":"2306.01694","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":["collinskatie/checkmate"],"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/explainability-of-speech-recognition","slug":"explainability-of-speech-recognition","title":"Explainability of Speech Recognition Transformers via Gradient-based Attention Visualization","date":"2023-06-02","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/gateon-an-unsupervised-method-for-large-scale","slug":"gateon-an-unsupervised-method-for-large-scale","title":"Context selectivity with dynamic availability enables lifelong continual learning","date":"2023-06-02","arxiv_id":"2306.01690","n_code_links":1,"syntology":null},{"paper":"/paper/generalist-equivariant-transformer-towards-3d","slug":"generalist-equivariant-transformer-towards-3d","title":"Generalist Equivariant Transformer Towards 3D Molecular Interaction Learning","date":"2023-06-02","arxiv_id":"2306.01474","n_code_links":1,"syntology":{"ran":6,"of":6,"n_ran_checked":6,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["thunlp-mt/get"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"improved-training-for-end-to-end-streaming","title":"Improved Training for End-to-End Streaming Automatic Speech Recognition Model with Punctuation","date":"2023-06-02","arxiv_id":"2306.01296","n_code_links":0,"syntology":null},{"paper":"/paper/mkor-momentum-enabled-kronecker-factor-based","slug":"mkor-momentum-enabled-kronecker-factor-based","title":"MKOR: Momentum-Enabled Kronecker-Factor-Based Optimizer Using Rank-1 Updates","date":"2023-06-02","arxiv_id":"2306.01685","n_code_links":1,"syntology":{"ran":9,"of":10,"n_ran_checked":6,"n_instrument":3,"unverified":1,"pointer_only":10,"phrase":"9 ran (of which 2 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","official":{"repos":["mohammad-mozaffari/mkor"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":2,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/nnmobile-net-rethinking-cnn-design-for-deep","slug":"nnmobile-net-rethinking-cnn-design-for-deep","title":"nnMobileNet: Rethinking CNN for Retinopathy Research","date":"2023-06-02","arxiv_id":"2306.01289","n_code_links":2,"syntology":null},{"paper":"/paper/relu-to-the-rescue-improve-your-on-policy","slug":"relu-to-the-rescue-improve-your-on-policy","title":"ReLU to the Rescue: Improve Your On-Policy Actor-Critic with Positive Advantages","date":"2023-06-02","arxiv_id":"2306.01460","n_code_links":1,"syntology":null},{"paper":null,"slug":"rita-group-attention-is-all-you-need-for","title":"RITA: Group Attention is All You Need for Timeseries Analytics","date":"2023-06-02","arxiv_id":"2306.01926","n_code_links":0,"syntology":null},{"paper":"/paper/transformer-based-annotation-bias-aware","slug":"transformer-based-annotation-bias-aware","title":"Transformer-based Annotation Bias-aware Medical Image Segmentation","date":"2023-06-02","arxiv_id":"2306.01340","n_code_links":1,"syntology":null},{"paper":null,"slug":"word-embeddings-for-banking-industry","title":"Word Embeddings for Banking Industry","date":"2023-06-02","arxiv_id":"2306.01807","n_code_links":0,"syntology":null},{"paper":"/paper/a-novel-driver-distraction-behavior-detection","slug":"a-novel-driver-distraction-behavior-detection","title":"A Novel Driver Distraction Behavior Detection Method Based on Self-supervised Learning with Masked Image Modeling","date":"2023-06-01","arxiv_id":"2306.00543","n_code_links":1,"syntology":null},{"paper":null,"slug":"accelerated-fingerprint-enhancement-a-gpu","title":"Accelerated Fingerprint Enhancement: A GPU-Optimized Mixed Architecture Approach","date":"2023-06-01","arxiv_id":"2306.00272","n_code_links":0,"syntology":null},{"paper":"/paper/aclm-a-selective-denoising-based-generative","slug":"aclm-a-selective-denoising-based-generative","title":"ACLM: A Selective-Denoising based Generative Data Augmentation Approach for Low-Resource Complex NER","date":"2023-06-01","arxiv_id":"2306.00928","n_code_links":1,"syntology":null},{"paper":"/paper/adapting-pre-trained-language-models-to","slug":"adapting-pre-trained-language-models-to","title":"Adapting Pre-trained Language Models to Vision-Language Tasks via Dynamic Visual Prompting","date":"2023-06-01","arxiv_id":"2306.00409","n_code_links":1,"syntology":null},{"paper":null,"slug":"adaptive-contextual-biasing-for-transducer","title":"Adaptive Contextual Biasing for Transducer Based Streaming Speech Recognition","date":"2023-06-01","arxiv_id":"2306.00804","n_code_links":0,"syntology":null},{"paper":"/paper/an-abstractive-text-summarization-technique","slug":"an-abstractive-text-summarization-technique","title":"An abstractive text summarization technique using transformer model with self-attention mechanism","date":"2023-06-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"auto-spikformer-spikformer-architecture","title":"Auto-Spikformer: Spikformer Architecture Search","date":"2023-06-01","arxiv_id":"2306.00807","n_code_links":0,"syntology":null},{"paper":null,"slug":"automatic-glossary-of-clinical-terminology-a","title":"Automatic Glossary of Clinical Terminology: a Large-Scale Dictionary of Biomedical Definitions Generated from Ontological Knowledge","date":"2023-06-01","arxiv_id":"2306.00665","n_code_links":0,"syntology":null},{"paper":null,"slug":"boosting-the-performance-of-transformer","title":"Boosting the Performance of Transformer Architectures for Semantic Textual Similarity","date":"2023-06-01","arxiv_id":"2306.00708","n_code_links":0,"syntology":null},{"paper":"/paper/column-type-annotation-using-chatgpt","slug":"column-type-annotation-using-chatgpt","title":"Column Type Annotation using ChatGPT","date":"2023-06-01","arxiv_id":"2306.00745","n_code_links":1,"syntology":null},{"paper":"/paper/differentiable-tree-operations-promote","slug":"differentiable-tree-operations-promote","title":"Differentiable Tree Operations Promote Compositional Generalization","date":"2023-06-01","arxiv_id":"2306.00751","n_code_links":1,"syntology":{"ran":9,"of":12,"n_ran_checked":6,"n_instrument":3,"unverified":3,"pointer_only":12,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 0 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","official":{"repos":["psoulos/dtm"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/eel-efficiently-encoding-lattices-for","slug":"eel-efficiently-encoding-lattices-for","title":"EEL: Efficiently Encoding Lattices for Reranking","date":"2023-06-01","arxiv_id":"2306.00947","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":["prasanns/eel-reranking"],"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":null,"slug":"enhancing-programming-etextbooks-with-chatgpt","title":"Enhancing Programming eTextbooks with ChatGPT Generated Counterfactual-Thinking-Inspired Questions","date":"2023-06-01","arxiv_id":"2306.00551","n_code_links":0,"syntology":null},{"paper":null,"slug":"exposing-attention-glitches-with-flip-flop","title":"Exposing Attention Glitches with Flip-Flop Language Modeling","date":"2023-06-01","arxiv_id":"2306.00946","n_code_links":0,"syntology":null},{"paper":null,"slug":"feature-engineering-based-detection-of-buffer","title":"Feature Engineering-Based Detection of Buffer Overflow Vulnerability in Source Code Using Neural Networks","date":"2023-06-01","arxiv_id":"2306.07981","n_code_links":0,"syntology":null},{"paper":null,"slug":"hybrid-long-document-summarization-using-c2f","title":"Hybrid Long Document Summarization using C2F-FAR and ChatGPT: A Practical Study","date":"2023-06-01","arxiv_id":"2306.01169","n_code_links":0,"syntology":null},{"paper":"/paper/improving-energy-conserving-descent-for","slug":"improving-energy-conserving-descent-for","title":"Improving Energy Conserving Descent for Machine Learning: Theory and Practice","date":"2023-06-01","arxiv_id":"2306.00352","n_code_links":1,"syntology":null},{"paper":"/paper/learning-transformer-programs-1","slug":"learning-transformer-programs-1","title":"Learning Transformer Programs","date":"2023-06-01","arxiv_id":"2306.01128","n_code_links":1,"syntology":{"ran":16,"of":21,"n_ran_checked":13,"n_instrument":3,"unverified":5,"pointer_only":21,"phrase":"16 ran (of which 12 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified","official":{"repos":["princeton-nlp/transformerprograms"],"state":"official (archive's flag): 16 ran","n_ran":16,"n_constructed":12,"n_ran_no_instrument_failure":13,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":"/paper/lightweight-vision-transformer-with-1","slug":"lightweight-vision-transformer-with-1","title":"Lightweight Vision Transformer with Bidirectional Interaction","date":"2023-06-01","arxiv_id":"2306.00396","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":["qhfan/fat"],"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/llava-med-training-a-large-language-and","slug":"llava-med-training-a-large-language-and","title":"LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day","date":"2023-06-01","arxiv_id":"2306.00890","n_code_links":1,"syntology":null},{"paper":"/paper/make-pre-trained-model-reversible-from-1","slug":"make-pre-trained-model-reversible-from-1","title":"Make Pre-trained Model Reversible: From Parameter to Memory Efficient Fine-Tuning","date":"2023-06-01","arxiv_id":"2306.00477","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":["baohaoliao/mefts"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["community"]}}},{"paper":"/paper/multi-dimensional-evaluation-of-text","slug":"multi-dimensional-evaluation-of-text","title":"Multi-Dimensional Evaluation of Text Summarization with In-Context Learning","date":"2023-06-01","arxiv_id":"2306.01200","n_code_links":1,"syntology":null},{"paper":null,"slug":"reviewergpt-an-exploratory-study-on-using","title":"ReviewerGPT? An Exploratory Study on Using Large Language Models for Paper Reviewing","date":"2023-06-01","arxiv_id":"2306.00622","n_code_links":0,"syntology":null},{"paper":null,"slug":"systematic-evaluation-of-gpt-3-for-zero-shot","title":"Systematic Evaluation of GPT-3 for Zero-Shot Personality Estimation","date":"2023-06-01","arxiv_id":"2306.01183","n_code_links":0,"syntology":null},{"paper":null,"slug":"topex-topic-based-explanations-for-model","title":"TopEx: Topic-based Explanations for Model Comparison","date":"2023-06-01","arxiv_id":"2306.00976","n_code_links":0,"syntology":null},{"paper":"/paper/training-free-neural-architecture-search-for","slug":"training-free-neural-architecture-search-for","title":"Training-free Neural Architecture Search for RNNs and Transformers","date":"2023-06-01","arxiv_id":"2306.00288","n_code_links":1,"syntology":{"ran":5,"of":5,"n_ran_checked":5,"n_instrument":0,"unverified":0,"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) · 0 unverified","official":{"repos":["aaronserianni/training-free-nas"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/ucas-iie-nlp-at-semeval-2023-task-12","slug":"ucas-iie-nlp-at-semeval-2023-task-12","title":"UCAS-IIE-NLP at SemEval-2023 Task 12: Enhancing Generalization of Multilingual BERT for Low-resource Sentiment Analysis","date":"2023-06-01","arxiv_id":"2306.01093","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-universal-latent-fingerprint-enhancer-using","title":"A Universal Latent Fingerprint Enhancer Using Transformers","date":"2023-05-31","arxiv_id":"2306.00231","n_code_links":0,"syntology":null},{"paper":null,"slug":"accurate-and-structured-pruning-for-efficient","title":"Accurate and Structured Pruning for Efficient Automatic Speech Recognition","date":"2023-05-31","arxiv_id":"2305.19549","n_code_links":0,"syntology":null},{"paper":null,"slug":"adam-accumulation-to-reduce-memory-footprints","title":"Adam Accumulation to Reduce Memory Footprints of both Activations and Gradients for Large-scale DNN Training","date":"2023-05-31","arxiv_id":"2305.19982","n_code_links":0,"syntology":null},{"paper":null,"slug":"automated-annotation-with-generative-ai","title":"Automated Annotation with Generative AI Requires Validation","date":"2023-05-31","arxiv_id":"2306.00176","n_code_links":0,"syntology":null},{"paper":null,"slug":"building-extractive-question-answering-system","title":"Building Extractive Question Answering System to Support Human-AI Health Coaching Model for Sleep Domain","date":"2023-05-31","arxiv_id":"2305.19707","n_code_links":0,"syntology":null},{"paper":null,"slug":"catalysis-distillation-neural-network-for-the","title":"Catalysis distillation neural network for the few shot open catalyst challenge","date":"2023-05-31","arxiv_id":"2305.19545","n_code_links":0,"syntology":null},{"paper":"/paper/deepmerge-deep-learning-based-region-merging","slug":"deepmerge-deep-learning-based-region-merging","title":"DeepMerge: Deep-Learning-Based Region-Merging for Image Segmentation","date":"2023-05-31","arxiv_id":"2305.19787","n_code_links":1,"syntology":null},{"paper":"/paper/deepsolo-let-transformer-decoder-with-1","slug":"deepsolo-let-transformer-decoder-with-1","title":"DeepSolo++: Let Transformer Decoder with Explicit Points Solo for Multilingual Text Spotting","date":"2023-05-31","arxiv_id":"2305.19957","n_code_links":1,"syntology":null},{"paper":null,"slug":"evaluating-gpt-s-programming-capability","title":"Evaluating GPT's Programming Capability through CodeWars' Katas","date":"2023-05-31","arxiv_id":"2306.01784","n_code_links":0,"syntology":null},{"paper":null,"slug":"examining-the-emergence-of-deductive","title":"Examining the Emergence of Deductive Reasoning in Generative Language Models","date":"2023-05-31","arxiv_id":"2306.01009","n_code_links":0,"syntology":null},{"paper":"/paper/explanations-as-features-llm-based-features","slug":"explanations-as-features-llm-based-features","title":"Harnessing Explanations: LLM-to-LM Interpreter for Enhanced Text-Attributed Graph Representation Learning","date":"2023-05-31","arxiv_id":"2305.19523","n_code_links":3,"syntology":{"ran":6,"of":7,"n_ran_checked":6,"n_instrument":0,"unverified":1,"pointer_only":1,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["XiaoxinHe/TAPE","xiaoxinhe/tape_arxiv_2023"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/knowledge-base-question-answering-for-space","slug":"knowledge-base-question-answering-for-space","title":"Knowledge Base Question Answering for Space Debris Queries","date":"2023-05-31","arxiv_id":"2305.19734","n_code_links":1,"syntology":null},{"paper":"/paper/microsegnet-a-deep-learning-approach-for","slug":"microsegnet-a-deep-learning-approach-for","title":"MicroSegNet: A Deep Learning Approach for Prostate Segmentation on Micro-Ultrasound Images","date":"2023-05-31","arxiv_id":"2305.19956","n_code_links":1,"syntology":null},{"paper":"/paper/neuron-to-graph-interpreting-language-model","slug":"neuron-to-graph-interpreting-language-model","title":"Neuron to Graph: Interpreting Language Model Neurons at Scale","date":"2023-05-31","arxiv_id":"2305.19911","n_code_links":1,"syntology":null},{"paper":"/paper/recasting-self-attention-with-holographic","slug":"recasting-self-attention-with-holographic","title":"Recasting Self-Attention with Holographic Reduced Representations","date":"2023-05-31","arxiv_id":"2305.19534","n_code_links":1,"syntology":{"ran":4,"of":11,"n_ran_checked":4,"n_instrument":0,"unverified":7,"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) · 7 unverified","official":{"repos":["neuromorphiccomputationresearchprogram/hrrformer"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"scaling-evidence-based-instructional-design","title":"Scaling Evidence-based Instructional Design Expertise through Large Language Models","date":"2023-05-31","arxiv_id":"2306.01006","n_code_links":0,"syntology":null},{"paper":null,"slug":"toward-understanding-why-adam-converges","title":"Toward Understanding Why Adam Converges Faster Than SGD for Transformers","date":"2023-05-31","arxiv_id":"2306.00204","n_code_links":0,"syntology":null},{"paper":"/paper/xphonebert-a-pre-trained-multilingual-model","slug":"xphonebert-a-pre-trained-multilingual-model","title":"XPhoneBERT: A Pre-trained Multilingual Model for Phoneme Representations for Text-to-Speech","date":"2023-05-31","arxiv_id":"2305.19709","n_code_links":2,"syntology":{"ran":14,"of":18,"n_ran_checked":14,"n_instrument":0,"unverified":4,"pointer_only":10,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 2 honoured, 0 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","official":{"repos":["vinairesearch/xphonebert"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":14,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"xtransct-ultra-fast-volumetric-ct","title":"XTransCT: Ultra-Fast Volumetric CT Reconstruction using Two Orthogonal X-Ray Projections for Image-guided Radiation Therapy via a Transformer Network","date":"2023-05-31","arxiv_id":"2305.19621","n_code_links":0,"syntology":null},{"paper":null,"slug":"zero-shot-automatic-pronunciation-assessment","title":"Zero-Shot Automatic Pronunciation Assessment","date":"2023-05-31","arxiv_id":"2305.19563","n_code_links":0,"syntology":null},{"paper":null,"slug":"alphablock-embodied-finetuning-for-vision","title":"AlphaBlock: Embodied Finetuning for Vision-Language Reasoning in Robot Manipulation","date":"2023-05-30","arxiv_id":"2305.18898","n_code_links":0,"syntology":null},{"paper":null,"slug":"amatformer-efficient-feature-matching-via","title":"AMatFormer: Efficient Feature Matching via Anchor Matching Transformer","date":"2023-05-30","arxiv_id":"2305.19205","n_code_links":0,"syntology":null},{"paper":null,"slug":"approximation-and-estimation-ability-of","title":"Approximation and Estimation Ability of Transformers for Sequence-to-Sequence Functions with Infinite Dimensional Input","date":"2023-05-30","arxiv_id":"2305.18699","n_code_links":0,"syntology":null},{"paper":null,"slug":"auto-tune-pac-bayes-optimization-over-prior","title":"Improving Generalization of Complex Models under Unbounded Loss Using PAC-Bayes Bounds","date":"2023-05-30","arxiv_id":"2305.19243","n_code_links":0,"syntology":null},{"paper":null,"slug":"bisls-sps-auto-tune-step-sizes-for-stable-bi","title":"BiSLS/SPS: Auto-tune Step Sizes for Stable Bi-level Optimization","date":"2023-05-30","arxiv_id":"2305.18666","n_code_links":0,"syntology":null},{"paper":"/paper/blockwise-parallel-transformer-for-long","slug":"blockwise-parallel-transformer-for-long","title":"Blockwise Parallel Transformer for Large Context Models","date":"2023-05-30","arxiv_id":"2305.19370","n_code_links":3,"syntology":{"ran":1,"of":3,"n_ran_checked":1,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"1 ran (of which 0 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) · 2 unverified","official":{"repos":["lhao499/blockwise-parallel-transformer"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":"/paper/client-cross-variable-linear-integrated","slug":"client-cross-variable-linear-integrated","title":"Client: Cross-variable Linear Integrated Enhanced Transformer for Multivariate Long-Term Time Series Forecasting","date":"2023-05-30","arxiv_id":"2305.18838","n_code_links":1,"syntology":null},{"paper":null,"slug":"does-conceptual-representation-require","title":"Does Conceptual Representation Require Embodiment? Insights From Large Language Models","date":"2023-05-30","arxiv_id":"2305.19103","n_code_links":0,"syntology":null},{"paper":null,"slug":"dynamic-clustering-transformer-network-for","title":"Dynamic Clustering Transformer Network for Point Cloud Segmentation","date":"2023-05-30","arxiv_id":"2306.08073","n_code_links":0,"syntology":null},{"paper":null,"slug":"explaining-hate-speech-classification-with","title":"Explaining Hate Speech Classification with Model Agnostic Methods","date":"2023-05-30","arxiv_id":"2306.00021","n_code_links":0,"syntology":null},{"paper":null,"slug":"generate-then-select-open-ended-visual","title":"Generate then Select: Open-ended Visual Question Answering Guided by World Knowledge","date":"2023-05-30","arxiv_id":"2305.18842","n_code_links":0,"syntology":null},{"paper":null,"slug":"gpt-models-in-construction-industry","title":"GPT Models in Construction Industry: Opportunities, Limitations, and a Use Case Validation","date":"2023-05-30","arxiv_id":"2305.18997","n_code_links":0,"syntology":null},{"paper":null,"slug":"gpt4geo-how-a-language-model-sees-the-world-s","title":"GPT4GEO: How a Language Model Sees the World's Geography","date":"2023-05-30","arxiv_id":"2306.00020","n_code_links":0,"syntology":null},{"paper":"/paper/gpt4tools-teaching-large-language-model-to","slug":"gpt4tools-teaching-large-language-model-to","title":"GPT4Tools: Teaching Large Language Model to Use Tools via Self-instruction","date":"2023-05-30","arxiv_id":"2305.18752","n_code_links":1,"syntology":null},{"paper":null,"slug":"long-term-wind-power-forecasting-with","title":"Long-term Wind Power Forecasting with Hierarchical Spatial-Temporal Transformer","date":"2023-05-30","arxiv_id":"2305.18724","n_code_links":0,"syntology":null},{"paper":"/paper/ms-detr-natural-language-video-localization","slug":"ms-detr-natural-language-video-localization","title":"MS-DETR: Natural Language Video Localization with Sampling Moment-Moment Interaction","date":"2023-05-30","arxiv_id":"2305.18969","n_code_links":1,"syntology":null},{"paper":null,"slug":"multitask-learning-for-recognizing-stress-and","title":"Multitask learning for recognizing stress and depression in social media","date":"2023-05-30","arxiv_id":"2305.18907","n_code_links":0,"syntology":null},{"paper":null,"slug":"prequant-a-task-agnostic-quantization","title":"PreQuant: A Task-agnostic Quantization Approach for Pre-trained Language Models","date":"2023-05-30","arxiv_id":"2306.00014","n_code_links":0,"syntology":null},{"paper":null,"slug":"research-on-multilingual-news-clustering","title":"Research on Multilingual News Clustering Based on Cross-Language Word Embeddings","date":"2023-05-30","arxiv_id":"2305.18880","n_code_links":0,"syntology":null}],"record_sha256":"b8ec070e42077ebde4c381556917e5a13fb90e1f6ab634c19ebdffbba42f80f5","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}