{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/method/softmax/papers/219","list_of":"/method/softmax","method":"Softmax","archive":{"snapshot":"2025-07-28"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"date (newest first), then slug","page":219,"pages_in_order":375,"rows_per_page":100,"rows":[21801,21900],"of":37443,"counts":{"archive_papers_tagged":37443,"with_a_code_link":15869,"where_syntology_ran_a_sample":4578,"not_listed_spam_title":0,"listed":37443,"listed_where_code_ran":4578,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":3835,"every_run_a_failure_of_syntologys_instrument":743,"listed_with_a_run_with_no_instrument_failure":3835,"listed_every_run_a_failure_of_syntologys_instrument":743,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/method/softmax","prev":"/method/softmax/papers/218","next":"/method/softmax/papers/220","papers":[{"paper":"/paper/swectrl-mini-a-data-transparent-transformer","slug":"swectrl-mini-a-data-transparent-transformer","title":"SweCTRL-Mini: a data-transparent Transformer-based large language model for controllable text generation in Swedish","date":"2023-04-27","arxiv_id":"2304.13994","n_code_links":1,"syntology":null},{"paper":null,"slug":"tempee-temporal-spatial-parallel-transformer","title":"TempEE: Temporal-Spatial Parallel Transformer for Radar Echo Extrapolation Beyond Auto-Regression","date":"2023-04-27","arxiv_id":"2304.14131","n_code_links":0,"syntology":null},{"paper":"/paper/we-re-afraid-language-models-aren-t-modeling","slug":"we-re-afraid-language-models-aren-t-modeling","title":"We're Afraid Language Models Aren't Modeling Ambiguity","date":"2023-04-27","arxiv_id":"2304.14399","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-case-based-reasoning-framework-for-adaptive","title":"Prompting GPT-3.5 for Text-to-SQL with De-semanticization and Skeleton Retrieval","date":"2023-04-26","arxiv_id":"2304.13301","n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluation-of-gpt-3-5-and-gpt-4-for","title":"Evaluation of GPT-3.5 and GPT-4 for supporting real-world information needs in healthcare delivery","date":"2023-04-26","arxiv_id":"2304.13714","n_code_links":0,"syntology":null},{"paper":"/paper/exploring-the-curious-case-of-code-prompts","slug":"exploring-the-curious-case-of-code-prompts","title":"Exploring the Curious Case of Code Prompts","date":"2023-04-26","arxiv_id":"2304.13250","n_code_links":1,"syntology":{"ran":2,"of":6,"n_ran_checked":2,"n_instrument":0,"unverified":4,"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) · 4 unverified","official":{"repos":["zharry29/codex_vs_gpt3"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"extracting-structured-seed-mediated-gold","title":"Extracting Structured Seed-Mediated Gold Nanorod Growth Procedures from Literature with GPT-3","date":"2023-04-26","arxiv_id":"2304.13846","n_code_links":0,"syntology":null},{"paper":null,"slug":"fine-tuning-with-abnormal-examples","title":"Fine Tuning with Abnormal Examples","date":"2023-04-26","arxiv_id":"2304.13783","n_code_links":0,"syntology":null},{"paper":"/paper/hausanlp-at-semeval-2023-task-12-leveraging","slug":"hausanlp-at-semeval-2023-task-12-leveraging","title":"HausaNLP at SemEval-2023 Task 12: Leveraging African Low Resource TweetData for Sentiment Analysis","date":"2023-04-26","arxiv_id":"2304.13634","n_code_links":1,"syntology":null},{"paper":"/paper/impact-of-position-bias-on-language-models-in","slug":"impact-of-position-bias-on-language-models-in","title":"Technical Report: Impact of Position Bias on Language Models in Token Classification","date":"2023-04-26","arxiv_id":"2304.13567","n_code_links":2,"syntology":null},{"paper":"/paper/is-a-prompt-and-a-few-samples-all-you-need","slug":"is-a-prompt-and-a-few-samples-all-you-need","title":"The Parrot Dilemma: Human-Labeled vs. LLM-augmented Data in Classification Tasks","date":"2023-04-26","arxiv_id":"2304.13861","n_code_links":2,"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":["andersgiovanni/worker_vs_gpt","AGMoller/worker_vs_gpt"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/scatterformer-locally-invariant-scattering","slug":"scatterformer-locally-invariant-scattering","title":"ScatterFormer: Locally-Invariant Scattering Transformer for Patient-Independent Multispectral Detection of Epileptiform Discharges","date":"2023-04-26","arxiv_id":"2304.14919","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"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) · 0 unverified","official":{"repos":["albertcheng19/scatterformer"],"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/simara-a-database-for-key-value-information","slug":"simara-a-database-for-key-value-information","title":"SIMARA: a database for key-value information extraction from full pages","date":"2023-04-26","arxiv_id":"2304.13606","n_code_links":0,"syntology":null},{"paper":"/paper/textdeformer-geometry-manipulation-using-text","slug":"textdeformer-geometry-manipulation-using-text","title":"TextDeformer: Geometry Manipulation using Text Guidance","date":"2023-04-26","arxiv_id":"2304.13348","n_code_links":1,"syntology":{"ran":11,"of":16,"n_ran_checked":10,"n_instrument":1,"unverified":5,"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) · 5 unverified","official":{"repos":["threedle/TextDeformer"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"the-closeness-of-in-context-learning-and","title":"The Closeness of In-Context Learning and Weight Shifting for Softmax Regression","date":"2023-04-26","arxiv_id":"2304.13276","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-multi-modal-dbmss-for-seamless","title":"Towards Multi-Modal DBMSs for Seamless Querying of Texts and Tables","date":"2023-04-26","arxiv_id":"2304.13559","n_code_links":0,"syntology":null},{"paper":"/paper/ai-assisted-coding-experiments-with-gpt-4","slug":"ai-assisted-coding-experiments-with-gpt-4","title":"AI-assisted coding: Experiments with GPT-4","date":"2023-04-25","arxiv_id":"2304.13187","n_code_links":1,"syntology":null},{"paper":null,"slug":"application-of-transformers-for-nonlinear","title":"Application of Transformers for Nonlinear Channel Compensation in Optical Systems","date":"2023-04-25","arxiv_id":"2304.13119","n_code_links":0,"syntology":null},{"paper":"/paper/completionformer-depth-completion-with","slug":"completionformer-depth-completion-with","title":"CompletionFormer: Depth Completion with Convolutions and Vision Transformers","date":"2023-04-25","arxiv_id":"2304.13030","n_code_links":1,"syntology":null},{"paper":null,"slug":"depth-relative-self-attention-for-monocular","title":"Depth-Relative Self Attention for Monocular Depth Estimation","date":"2023-04-25","arxiv_id":"2304.12849","n_code_links":0,"syntology":null},{"paper":"/paper/detecting-out-of-distribution-data-through-in","slug":"detecting-out-of-distribution-data-through-in","title":"Detecting Out-of-distribution Data through In-distribution Class Prior","date":"2023-04-25","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/duett-dual-event-time-transformer-for","slug":"duett-dual-event-time-transformer-for","title":"DuETT: Dual Event Time Transformer for Electronic Health Records","date":"2023-04-25","arxiv_id":"2304.13017","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":["layer6ai-labs/duett"],"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/escaping-the-sentence-level-paradigm-in","slug":"escaping-the-sentence-level-paradigm-in","title":"Escaping the sentence-level paradigm in machine translation","date":"2023-04-25","arxiv_id":"2304.12959","n_code_links":1,"syntology":null},{"paper":"/paper/introducing-mbib-the-first-media-bias","slug":"introducing-mbib-the-first-media-bias","title":"Introducing MBIB -- the first Media Bias Identification Benchmark Task and Dataset Collection","date":"2023-04-25","arxiv_id":"2304.13148","n_code_links":1,"syntology":null},{"paper":null,"slug":"lemart-label-efficient-masked-region","title":"LEMaRT: Label-Efficient Masked Region Transform for Image Harmonization","date":"2023-04-25","arxiv_id":"2304.13166","n_code_links":0,"syntology":null},{"paper":"/paper/measuring-massive-multitask-chinese","slug":"measuring-massive-multitask-chinese","title":"Measuring Massive Multitask Chinese Understanding","date":"2023-04-25","arxiv_id":"2304.12986","n_code_links":2,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"pointer_only":3,"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":["Felixgithub2017/MMCU"],"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":["official","unlocated"]}}},{"paper":null,"slug":"nlp-ltu-at-semeval-2023-task-10-the-impact-of","title":"NLP-LTU at SemEval-2023 Task 10: The Impact of Data Augmentation and Semi-Supervised Learning Techniques on Text Classification Performance on an Imbalanced Dataset","date":"2023-04-25","arxiv_id":"2304.12847","n_code_links":0,"syntology":null},{"paper":"/paper/sdsc-unet-dual-skip-connection-vit-based-u","slug":"sdsc-unet-dual-skip-connection-vit-based-u","title":"SDSC-UNet: Dual Skip Connection ViT-based U-shaped Model for Building Extraction","date":"2023-04-25","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"semantic-compression-with-large-language","title":"Semantic Compression With Large Language Models","date":"2023-04-25","arxiv_id":"2304.12512","n_code_links":0,"syntology":null},{"paper":null,"slug":"state-spaces-aren-t-enough-machine","title":"State Spaces Aren't Enough: Machine Translation Needs Attention","date":"2023-04-25","arxiv_id":"2304.12776","n_code_links":0,"syntology":null},{"paper":null,"slug":"stm-unet-an-efficient-u-shaped-architecture","title":"STM-UNet: An Efficient U-shaped Architecture Based on Swin Transformer and Multi-scale MLP for Medical Image Segmentation","date":"2023-04-25","arxiv_id":"2304.12615","n_code_links":0,"syntology":null},{"paper":null,"slug":"swinfsr-stereo-image-super-resolution-using","title":"SwinFSR: Stereo Image Super-Resolution using SwinIR and Frequency Domain Knowledge","date":"2023-04-25","arxiv_id":"2304.12556","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-potential-of-visual-chatgpt-for-remote","title":"The Potential of Visual ChatGPT For Remote Sensing","date":"2023-04-25","arxiv_id":"2304.13009","n_code_links":0,"syntology":null},{"paper":null,"slug":"theory-of-posterior-concentration-for","title":"Theory of Posterior Concentration for Generalized Bayesian Additive Regression Trees","date":"2023-04-25","arxiv_id":"2304.12505","n_code_links":0,"syntology":null},{"paper":null,"slug":"what-does-bert-learn-about-prosody","title":"What does BERT learn about prosody?","date":"2023-04-25","arxiv_id":"2304.12706","n_code_links":0,"syntology":null},{"paper":null,"slug":"artificial-general-intelligence-agi-for","title":"AGI: Artificial General Intelligence for Education","date":"2023-04-24","arxiv_id":"2304.12479","n_code_links":0,"syntology":null},{"paper":null,"slug":"augmentation-based-domain-generalization-for","title":"Augmentation-based Domain Generalization for Semantic Segmentation","date":"2023-04-24","arxiv_id":"2304.12122","n_code_links":0,"syntology":null},{"paper":"/paper/better-question-answering-models-on-a-budget","slug":"better-question-answering-models-on-a-budget","title":"Better Question-Answering Models on a Budget","date":"2023-04-24","arxiv_id":"2304.12370","n_code_links":1,"syntology":null},{"paper":"/paper/directed-acyclic-transformer-pre-training-for","slug":"directed-acyclic-transformer-pre-training-for","title":"Directed Acyclic Transformer Pre-training for High-quality Non-autoregressive Text Generation","date":"2023-04-24","arxiv_id":"2304.11791","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":2,"n_instrument":2,"unverified":0,"pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["thu-coai/da-transformer"],"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","unlocated"]}}},{"paper":"/paper/explicit-correspondence-matching-for","slug":"explicit-correspondence-matching-for","title":"Explicit Correspondence Matching for Generalizable Neural Radiance Fields","date":"2023-04-24","arxiv_id":"2304.12294","n_code_links":1,"syntology":{"ran":8,"of":9,"n_ran_checked":8,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["donydchen/matchnerf"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"extreme-classification-for-answer-type","title":"Extreme Classification for Answer Type Prediction in Question Answering","date":"2023-04-24","arxiv_id":"2304.12395","n_code_links":0,"syntology":null},{"paper":"/paper/generation-driven-contrastive-self-training","slug":"generation-driven-contrastive-self-training","title":"Generation-driven Contrastive Self-training for Zero-shot Text Classification with Instruction-following LLM","date":"2023-04-24","arxiv_id":"2304.11872","n_code_links":1,"syntology":null},{"paper":"/paper/irnext-rethinking-convolutional-network","slug":"irnext-rethinking-convolutional-network","title":"IRNeXt: Rethinking Convolutional Network Design for Image Restoration","date":"2023-04-24","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"master-meta-style-transformer-for","title":"Master: Meta Style Transformer for Controllable Zero-Shot and Few-Shot Artistic Style Transfer","date":"2023-04-24","arxiv_id":"2304.11818","n_code_links":0,"syntology":null},{"paper":"/paper/mixpro-data-augmentation-with-maskmix-and","slug":"mixpro-data-augmentation-with-maskmix-and","title":"MixPro: Data Augmentation with MaskMix and Progressive Attention Labeling for Vision Transformer","date":"2023-04-24","arxiv_id":"2304.12043","n_code_links":1,"syntology":{"ran":16,"of":18,"n_ran_checked":9,"n_instrument":7,"unverified":2,"pointer_only":8,"phrase":"16 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; 7 where Syntology's instrument failed) · 2 unverified","official":{"repos":["fistyee/mixpro"],"state":"official (archive's flag): 16 ran","n_ran":16,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"multi-crop-contrastive-learning-for","title":"Multi-cropping Contrastive Learning and Domain Consistency for Unsupervised Image-to-Image Translation","date":"2023-04-24","arxiv_id":"2304.12235","n_code_links":0,"syntology":null},{"paper":null,"slug":"noisetrans-point-cloud-denoising-with","title":"NoiseTrans: Point Cloud Denoising with Transformers","date":"2023-04-24","arxiv_id":"2304.11812","n_code_links":0,"syntology":null},{"paper":null,"slug":"now-you-see-me-robust-approach-to-partial","title":"Now You See Me: Robust approach to Partial Occlusions","date":"2023-04-24","arxiv_id":"2304.11779","n_code_links":0,"syntology":null},{"paper":"/paper/once-detected-never-lost-surpassing-human","slug":"once-detected-never-lost-surpassing-human","title":"Once Detected, Never Lost: Surpassing Human Performance in Offline LiDAR based 3D Object Detection","date":"2023-04-24","arxiv_id":"2304.12315","n_code_links":2,"syntology":{"ran":3,"of":5,"n_ran_checked":0,"n_instrument":3,"unverified":2,"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) · 2 unverified","official":{"repos":["tusen-ai/sst"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/paragraph2graph-a-gnn-based-framework-for","slug":"paragraph2graph-a-gnn-based-framework-for","title":"PARAGRAPH2GRAPH: A GNN-based framework for layout paragraph analysis","date":"2023-04-24","arxiv_id":"2304.11810","n_code_links":1,"syntology":null},{"paper":"/paper/pre-trained-embeddings-for-entity-resolution","slug":"pre-trained-embeddings-for-entity-resolution","title":"Pre-trained Embeddings for Entity Resolution: An Experimental Analysis [Experiment, Analysis & Benchmark]","date":"2023-04-24","arxiv_id":"2304.12329","n_code_links":1,"syntology":null},{"paper":"/paper/rank-flow-embedding-for-unsupervised-and-semi-1","slug":"rank-flow-embedding-for-unsupervised-and-semi-1","title":"Rank Flow Embedding for Unsupervised and Semi-Supervised Manifold Learning","date":"2023-04-24","arxiv_id":"2304.12448","n_code_links":1,"syntology":null},{"paper":"/paper/recurrent-transformer-encoders-for-vision","slug":"recurrent-transformer-encoders-for-vision","title":"Vision-based Estimation of Fatigue and Engagement in Cognitive Training Sessions","date":"2023-04-24","arxiv_id":"2304.12470","n_code_links":1,"syntology":null},{"paper":null,"slug":"self-regularised-minimum-latency-training-for","title":"Self-regularised Minimum Latency Training for Streaming Transformer-based Speech Recognition","date":"2023-04-24","arxiv_id":"2304.11985","n_code_links":0,"syntology":null},{"paper":"/paper/socialdial-a-benchmark-for-socially-aware","slug":"socialdial-a-benchmark-for-socially-aware","title":"SocialDial: A Benchmark for Socially-Aware Dialogue Systems","date":"2023-04-24","arxiv_id":"2304.12026","n_code_links":1,"syntology":null},{"paper":"/paper/text-to-audio-generation-using-instruction","slug":"text-to-audio-generation-using-instruction","title":"Text-to-Audio Generation using Instruction-Tuned LLM and Latent Diffusion Model","date":"2023-04-24","arxiv_id":"2304.13731","n_code_links":1,"syntology":null},{"paper":null,"slug":"transformer-based-stereo-aware-3d-object","title":"Transformer-based stereo-aware 3D object detection from binocular images","date":"2023-04-24","arxiv_id":"2304.11906","n_code_links":0,"syntology":null},{"paper":"/paper/universal-domain-adaptation-via-compressive","slug":"universal-domain-adaptation-via-compressive","title":"Universal Domain Adaptation via Compressive Attention Matching","date":"2023-04-24","arxiv_id":"2304.11862","n_code_links":0,"syntology":null},{"paper":"/paper/wizardlm-empowering-large-language-models-to","slug":"wizardlm-empowering-large-language-models-to","title":"WizardLM: Empowering Large Language Models to Follow Complex Instructions","date":"2023-04-24","arxiv_id":"2304.12244","n_code_links":4,"syntology":{"ran":2,"of":3,"n_ran_checked":1,"n_instrument":1,"unverified":1,"pointer_only":3,"phrase":"2 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["nlpxucan/wizardlm"],"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":["listed","official"]}}},{"paper":"/paper/exploring-challenges-of-deploying-bert-based","slug":"exploring-challenges-of-deploying-bert-based","title":"Processing Natural Language on Embedded Devices: How Well Do Transformer Models Perform?","date":"2023-04-23","arxiv_id":"2304.11520","n_code_links":2,"syntology":null},{"paper":null,"slug":"vision-transformer-for-efficient-chest-x-ray","title":"Vision Transformer for Efficient Chest X-ray and Gastrointestinal Image Classification","date":"2023-04-23","arxiv_id":"2304.11529","n_code_links":0,"syntology":null},{"paper":"/paper/boosting-theory-of-mind-performance-in-large","slug":"boosting-theory-of-mind-performance-in-large","title":"Boosting Theory-of-Mind Performance in Large Language Models via Prompting","date":"2023-04-22","arxiv_id":"2304.11490","n_code_links":1,"syntology":null},{"paper":"/paper/dilated-unet-a-fast-and-accurate-medical","slug":"dilated-unet-a-fast-and-accurate-medical","title":"Dilated-UNet: A Fast and Accurate Medical Image Segmentation Approach using a Dilated Transformer and U-Net Architecture","date":"2023-04-22","arxiv_id":"2304.11450","n_code_links":1,"syntology":null},{"paper":null,"slug":"incomplete-multimodal-learning-for-remote","title":"Incomplete Multimodal Learning for Remote Sensing Data Fusion","date":"2023-04-22","arxiv_id":"2304.11381","n_code_links":0,"syntology":null},{"paper":null,"slug":"l3cube-indicsbert-a-simple-approach-for","title":"L3Cube-IndicSBERT: A simple approach for learning cross-lingual sentence representations using multilingual BERT","date":"2023-04-22","arxiv_id":"2304.11434","n_code_links":0,"syntology":null},{"paper":null,"slug":"vision-transformers-a-new-approach-for-high","title":"Vision Transformers, a new approach for high-resolution and large-scale mapping of canopy heights","date":"2023-04-22","arxiv_id":"2304.11487","n_code_links":0,"syntology":null},{"paper":"/paper/a-group-specific-approach-to-nlp-for-hate","slug":"a-group-specific-approach-to-nlp-for-hate","title":"A Group-Specific Approach to NLP for Hate Speech Detection","date":"2023-04-21","arxiv_id":"2304.11223","n_code_links":1,"syntology":null},{"paper":"/paper/a-preliminary-study-of-deep-learning-sensor","slug":"a-preliminary-study-of-deep-learning-sensor","title":"A Preliminary Study of Deep Learning Sensor Fusion for Pedestrian Detection","date":"2023-04-21","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"bert-based-clinical-knowledge-extraction-for","title":"BERT Based Clinical Knowledge Extraction for Biomedical Knowledge Graph Construction and Analysis","date":"2023-04-21","arxiv_id":"2304.10996","n_code_links":0,"syntology":null},{"paper":"/paper/building-multimodal-ai-chatbots","slug":"building-multimodal-ai-chatbots","title":"Building Multimodal AI Chatbots","date":"2023-04-21","arxiv_id":"2305.03512","n_code_links":1,"syntology":null},{"paper":"/paper/can-gpt-4-perform-neural-architecture-search","slug":"can-gpt-4-perform-neural-architecture-search","title":"Can GPT-4 Perform Neural Architecture Search?","date":"2023-04-21","arxiv_id":"2304.10970","n_code_links":1,"syntology":null},{"paper":null,"slug":"deformableformer-classification-of-endoscopic","title":"DeformableFormer: Classification of Endoscopic Ultrasound Guided Fine Needle Biopsy in Pancreatic Diseases","date":"2023-04-21","arxiv_id":"2304.10791","n_code_links":0,"syntology":null},{"paper":"/paper/evaluating-transformer-language-models-on-1","slug":"evaluating-transformer-language-models-on-1","title":"Evaluating Transformer Language Models on Arithmetic Operations Using Number Decomposition","date":"2023-04-21","arxiv_id":"2304.10977","n_code_links":1,"syntology":null},{"paper":"/paper/exploiting-patch-sizes-and-resolutions-for","slug":"exploiting-patch-sizes-and-resolutions-for","title":"Exploiting Patch Sizes and Resolutions for Multi-Scale Deep Learning in Mammogram Image Classification","date":"2023-04-21","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"inducing-anxiety-in-large-language-models","title":"Inducing anxiety in large language models can induce bias","date":"2023-04-21","arxiv_id":"2304.11111","n_code_links":0,"syntology":null},{"paper":"/paper/multi-modal-deep-learning-for-credit-rating","slug":"multi-modal-deep-learning-for-credit-rating","title":"Multi-Modal Deep Learning for Credit Rating Prediction Using Text and Numerical Data Streams","date":"2023-04-21","arxiv_id":"2304.10740","n_code_links":1,"syntology":null},{"paper":"/paper/self-attention-in-colors-another-take-on","slug":"self-attention-in-colors-another-take-on","title":"Self-Attention in Colors: Another Take on Encoding Graph Structure in Transformers","date":"2023-04-21","arxiv_id":"2304.10933","n_code_links":1,"syntology":null},{"paper":null,"slug":"text2time-transformer-based-article-time","title":"Text2Time: Transformer-based Article Time Period Prediction","date":"2023-04-21","arxiv_id":"2304.10859","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-dark-side-of-chatgpt-legal-and-ethical","title":"The Dark Side of ChatGPT: Legal and Ethical Challenges from Stochastic Parrots and Hallucination","date":"2023-04-21","arxiv_id":"2304.14347","n_code_links":0,"syntology":null},{"paper":null,"slug":"transformer-based-models-and-hardware","title":"Transformer-based models and hardware acceleration analysis in autonomous driving: A survey","date":"2023-04-21","arxiv_id":"2304.10891","n_code_links":0,"syntology":null},{"paper":null,"slug":"who-s-the-best-detective-llms-vs-mls-in","title":"Who's the Best Detective? LLMs vs. MLs in Detecting Incoherent Fourth Grade Math Answers","date":"2023-04-21","arxiv_id":"2304.11257","n_code_links":0,"syntology":null},{"paper":null,"slug":"an-introduction-to-transformers","title":"An Introduction to Transformers","date":"2023-04-20","arxiv_id":"2304.10557","n_code_links":0,"syntology":null},{"paper":null,"slug":"analyzing-fomc-minutes-accuracy-and","title":"Analyzing FOMC Minutes: Accuracy and Constraints of Language Models","date":"2023-04-20","arxiv_id":"2304.10164","n_code_links":0,"syntology":null},{"paper":"/paper/angle-based-dynamic-learning-rate-for","slug":"angle-based-dynamic-learning-rate-for","title":"Angle based dynamic learning rate for gradient descent","date":"2023-04-20","arxiv_id":"2304.10457","n_code_links":1,"syntology":null},{"paper":null,"slug":"attention-scheme-inspired-softmax-regression","title":"Attention Scheme Inspired Softmax Regression","date":"2023-04-20","arxiv_id":"2304.10411","n_code_links":0,"syntology":null},{"paper":"/paper/contrastive-tuning-a-little-help-to-make","slug":"contrastive-tuning-a-little-help-to-make","title":"Contrastive Tuning: A Little Help to Make Masked Autoencoders Forget","date":"2023-04-20","arxiv_id":"2304.10520","n_code_links":1,"syntology":null},{"paper":null,"slug":"domain-specific-continued-pretraining-of","title":"Domain-specific Continued Pretraining of Language Models for Capturing Long Context in Mental Health","date":"2023-04-20","arxiv_id":"2304.10447","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancing-object-detection-robustness-a","title":"Enhancing object detection robustness: A synthetic and natural perturbation approach","date":"2023-04-20","arxiv_id":"2304.10622","n_code_links":0,"syntology":null},{"paper":null,"slug":"ensembling-instance-and-semantic-segmentation","title":"Ensembling Instance and Semantic Segmentation for Panoptic Segmentation","date":"2023-04-20","arxiv_id":"2304.10326","n_code_links":0,"syntology":null},{"paper":"/paper/hm-vit-hetero-modal-vehicle-to-vehicle","slug":"hm-vit-hetero-modal-vehicle-to-vehicle","title":"HM-ViT: Hetero-modal Vehicle-to-Vehicle Cooperative perception with vision transformer","date":"2023-04-20","arxiv_id":"2304.10628","n_code_links":1,"syntology":{"ran":17,"of":21,"n_ran_checked":9,"n_instrument":8,"unverified":4,"pointer_only":21,"phrase":"17 ran (of which 7 constructed an object rather than computing a result; 9 with no instrument failure: 2 honoured, 0 violated, 7 with no contract checked; 8 where Syntology's instrument failed) · 4 unverified","official":null}},{"paper":null,"slug":"is-cross-modal-information-retrieval-possible","title":"Is Cross-modal Information Retrieval Possible without Training?","date":"2023-04-20","arxiv_id":"2304.11095","n_code_links":0,"syntology":null},{"paper":"/paper/learning-clip-guided-visual-text-fusion","slug":"learning-clip-guided-visual-text-fusion","title":"Learning CLIP Guided Visual-Text Fusion Transformer for Video-based Pedestrian Attribute Recognition","date":"2023-04-20","arxiv_id":"2304.10091","n_code_links":1,"syntology":null},{"paper":null,"slug":"meta-semantics-towards-better-natural","title":"Meta Semantics: Towards better natural language understanding and reasoning","date":"2023-04-20","arxiv_id":"2304.10663","n_code_links":0,"syntology":null},{"paper":"/paper/minigpt-4-enhancing-vision-language","slug":"minigpt-4-enhancing-vision-language","title":"MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models","date":"2023-04-20","arxiv_id":"2304.10592","n_code_links":6,"syntology":null},{"paper":null,"slug":"movie-box-office-prediction-with-self","title":"Movie Box Office Prediction With Self-Supervised and Visually Grounded Pretraining","date":"2023-04-20","arxiv_id":"2304.10311","n_code_links":0,"syntology":null},{"paper":null,"slug":"optogpt-a-foundation-model-for-inverse-design","title":"OptoGPT: A Foundation Model for Inverse Design in Optical Multilayer Thin Film Structures","date":"2023-04-20","arxiv_id":"2304.10294","n_code_links":0,"syntology":null},{"paper":null,"slug":"performance-of-chatgpt-on-the-us-fundamentals","title":"Performance of ChatGPT on the US Fundamentals of Engineering Exam: Comprehensive Assessment of Proficiency and Potential Implications for Professional Environmental Engineering Practice","date":"2023-04-20","arxiv_id":"2304.12198","n_code_links":0,"syntology":null},{"paper":null,"slug":"recurrent-transformer-for-dynamic-graph","title":"Dynamic Graph Representation Learning via Edge Temporal States Modeling and Structure-reinforced Transformer","date":"2023-04-20","arxiv_id":"2304.10079","n_code_links":0,"syntology":null},{"paper":"/paper/safety-assessment-of-chinese-large-language","slug":"safety-assessment-of-chinese-large-language","title":"Safety Assessment of Chinese Large Language Models","date":"2023-04-20","arxiv_id":"2304.10436","n_code_links":2,"syntology":null},{"paper":null,"slug":"sinc-spatial-composition-of-3d-human-motions","title":"SINC: Spatial Composition of 3D Human Motions for Simultaneous Action Generation","date":"2023-04-20","arxiv_id":"2304.10417","n_code_links":0,"syntology":null}],"record_sha256":"4caa8a4b66ef0d823a8b080a13e475f523d1ccf6b0249d8d1b34e5cca7623361","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}