{"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/217","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":217,"pages_in_order":375,"rows_per_page":100,"rows":[21601,21700],"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/216","next":"/method/softmax/papers/218","papers":[{"paper":"/paper/summarizing-simplifying-and-synthesizing","slug":"summarizing-simplifying-and-synthesizing","title":"Summarizing, Simplifying, and Synthesizing Medical Evidence Using GPT-3 (with Varying Success)","date":"2023-05-10","arxiv_id":"2305.06299","n_code_links":1,"syntology":null},{"paper":null,"slug":"vtpnet-for-3d-deep-learning-on-point-cloud","title":"VTPNet for 3D deep learning on point cloud","date":"2023-05-10","arxiv_id":"2305.06115","n_code_links":0,"syntology":null},{"paper":"/paper/a-mountain-shaped-single-stage-network-for","slug":"a-mountain-shaped-single-stage-network-for","title":"A Mountain-Shaped Single-Stage Network for Accurate Image Restoration","date":"2023-05-09","arxiv_id":"2305.05146","n_code_links":1,"syntology":null},{"paper":"/paper/a-review-of-vision-language-models-and-their","slug":"a-review-of-vision-language-models-and-their","title":"A Review of Vision-Language Models and their Performance on the Hateful Memes Challenge","date":"2023-05-09","arxiv_id":"2305.06159","n_code_links":1,"syntology":null},{"paper":"/paper/alleviating-over-smoothing-for-unsupervised","slug":"alleviating-over-smoothing-for-unsupervised","title":"Alleviating Over-smoothing for Unsupervised Sentence Representation","date":"2023-05-09","arxiv_id":"2305.06154","n_code_links":1,"syntology":{"ran":0,"of":4,"n_ran_checked":0,"n_instrument":0,"unverified":4,"pointer_only":0,"phrase":"0 ran · 4 unverified","official":{"repos":["nuochenpku/sscl"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":4,"ran_from_kinds":[]}}},{"paper":"/paper/an-exploration-of-encoder-decoder-approaches","slug":"an-exploration-of-encoder-decoder-approaches","title":"An Exploration of Encoder-Decoder Approaches to Multi-Label Classification for Legal and Biomedical Text","date":"2023-05-09","arxiv_id":"2305.05627","n_code_links":1,"syntology":null},{"paper":null,"slug":"attack-named-entity-recognition-by-entity","title":"Attack Named Entity Recognition by Entity Boundary Interference","date":"2023-05-09","arxiv_id":"2305.05253","n_code_links":0,"syntology":null},{"paper":null,"slug":"attention-based-transformer-networks-for","title":"Tomography of Quantum States from Structured Measurements via quantum-aware transformer","date":"2023-05-09","arxiv_id":"2305.05433","n_code_links":0,"syntology":null},{"paper":null,"slug":"audioslots-a-slot-centric-generative-model","title":"AudioSlots: A slot-centric generative model for audio separation","date":"2023-05-09","arxiv_id":"2305.05591","n_code_links":0,"syntology":null},{"paper":"/paper/codeie-large-code-generation-models-are","slug":"codeie-large-code-generation-models-are","title":"CodeIE: Large Code Generation Models are Better Few-Shot Information Extractors","date":"2023-05-09","arxiv_id":"2305.05711","n_code_links":1,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":1,"phrase":"0 ran · 1 unverified","official":{"repos":["dasepli/codeie"],"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/detection-of-depression-on-social-networks","slug":"detection-of-depression-on-social-networks","title":"Detection of depression on social networks using transformers and ensembles","date":"2023-05-09","arxiv_id":"2305.05325","n_code_links":1,"syntology":null},{"paper":"/paper/frugalgpt-how-to-use-large-language-models","slug":"frugalgpt-how-to-use-large-language-models","title":"FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance","date":"2023-05-09","arxiv_id":"2305.05176","n_code_links":1,"syntology":{"ran":9,"of":11,"n_ran_checked":9,"n_instrument":0,"unverified":2,"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) · 2 unverified","official":null}},{"paper":null,"slug":"gpt-agents-in-game-theory-experiments","title":"GPT in Game Theory Experiments","date":"2023-05-09","arxiv_id":"2305.05516","n_code_links":0,"syntology":null},{"paper":null,"slug":"gpt-nas-neural-architecture-search-with-the","title":"GPT-NAS: Evolutionary Neural Architecture Search with the Generative Pre-Trained Model","date":"2023-05-09","arxiv_id":"2305.05351","n_code_links":0,"syntology":null},{"paper":null,"slug":"hybrid-transformer-and-cnn-attention-network","title":"Hybrid Transformer and CNN Attention Network for Stereo Image Super-resolution","date":"2023-05-09","arxiv_id":"2305.05177","n_code_links":0,"syntology":null},{"paper":"/paper/internchat-solving-vision-centric-tasks-by","slug":"internchat-solving-vision-centric-tasks-by","title":"InternGPT: Solving Vision-Centric Tasks by Interacting with ChatGPT Beyond Language","date":"2023-05-09","arxiv_id":"2305.05662","n_code_links":2,"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":["opengvlab/internchat","opengvlab/interngpt"],"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":"investigating-the-effect-of-sub-word","title":"Effects of sub-word segmentation on performance of transformer language models","date":"2023-05-09","arxiv_id":"2305.05480","n_code_links":0,"syntology":null},{"paper":"/paper/simplicial-hopfield-networks","slug":"simplicial-hopfield-networks","title":"Simplicial Hopfield networks","date":"2023-05-09","arxiv_id":"2305.05179","n_code_links":1,"syntology":null},{"paper":null,"slug":"strae-autoencoding-for-pre-trained-embeddings","title":"StrAE: Autoencoding for Pre-Trained Embeddings using Explicit Structure","date":"2023-05-09","arxiv_id":"2305.05588","n_code_links":0,"syntology":null},{"paper":null,"slug":"structured-sentiment-analysis-as-transition","title":"Structured Sentiment Analysis as Transition-based Dependency Parsing","date":"2023-05-09","arxiv_id":"2305.05311","n_code_links":0,"syntology":null},{"paper":"/paper/swinia-self-supervised-blind-spot-image","slug":"swinia-self-supervised-blind-spot-image","title":"SwinIA: Self-Supervised Blind-Spot Image Denoising without Convolutions","date":"2023-05-09","arxiv_id":"2305.05651","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-an-automatic-optimisation-model","title":"Towards an Automatic Optimisation Model Generator Assisted with Generative Pre-trained Transformer","date":"2023-05-09","arxiv_id":"2305.05811","n_code_links":0,"syntology":null},{"paper":"/paper/towards-building-the-federated-gpt-federated","slug":"towards-building-the-federated-gpt-federated","title":"Towards Building the Federated GPT: Federated Instruction Tuning","date":"2023-05-09","arxiv_id":"2305.05644","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":1,"n_instrument":0,"unverified":1,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["jayzhang42/federatedgpt-shepherd"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/vision-language-models-in-remote-sensing","slug":"vision-language-models-in-remote-sensing","title":"Vision-Language Models in Remote Sensing: Current Progress and Future Trends","date":"2023-05-09","arxiv_id":"2305.05726","n_code_links":3,"syntology":null},{"paper":"/paper/birt-bio-inspired-replay-in-vision","slug":"birt-bio-inspired-replay-in-vision","title":"BiRT: Bio-inspired Replay in Vision Transformers for Continual Learning","date":"2023-05-08","arxiv_id":"2305.04769","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 2 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["neurai-lab/birt"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":2,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/code-execution-with-pre-trained-language","slug":"code-execution-with-pre-trained-language","title":"Code Execution with Pre-trained Language Models","date":"2023-05-08","arxiv_id":"2305.05383","n_code_links":1,"syntology":null},{"paper":null,"slug":"coherent-wave-dynamics-and-language","title":"Coherent Wave Dynamics and Language Generation of a Generative Pre-trained Transformer","date":"2023-05-08","arxiv_id":"2305.05061","n_code_links":0,"syntology":null},{"paper":null,"slug":"do-large-language-models-show-decision","title":"Do Large Language Models Show Decision Heuristics Similar to Humans? A Case Study Using GPT-3.5","date":"2023-05-08","arxiv_id":"2305.04400","n_code_links":0,"syntology":null},{"paper":"/paper/explanation-based-finetuning-makes-models","slug":"explanation-based-finetuning-makes-models","title":"Explanation-based Finetuning Makes Models More Robust to Spurious Cues","date":"2023-05-08","arxiv_id":"2305.04990","n_code_links":1,"syntology":null},{"paper":"/paper/fast-conformer-with-linearly-scalable","slug":"fast-conformer-with-linearly-scalable","title":"Fast Conformer with Linearly Scalable Attention for Efficient Speech Recognition","date":"2023-05-08","arxiv_id":"2305.05084","n_code_links":0,"syntology":null},{"paper":null,"slug":"gersteinlab-at-mediqa-chat-2023-clinical-note","title":"GersteinLab at MEDIQA-Chat 2023: Clinical Note Summarization from Doctor-Patient Conversations through Fine-tuning and In-context Learning","date":"2023-05-08","arxiv_id":"2305.05001","n_code_links":0,"syntology":null},{"paper":"/paper/graph-masked-autoencoder-for-sequential","slug":"graph-masked-autoencoder-for-sequential","title":"Graph Masked Autoencoder for Sequential Recommendation","date":"2023-05-08","arxiv_id":"2305.04619","n_code_links":2,"syntology":null},{"paper":null,"slug":"multi-task-end-to-end-training-improves-1","title":"Multi-Task End-to-End Training Improves Conversational Recommendation","date":"2023-05-08","arxiv_id":"2305.06218","n_code_links":0,"syntology":null},{"paper":"/paper/neurocomparatives-neuro-symbolic-distillation","slug":"neurocomparatives-neuro-symbolic-distillation","title":"NeuroComparatives: Neuro-Symbolic Distillation of Comparative Knowledge","date":"2023-05-08","arxiv_id":"2305.04978","n_code_links":1,"syntology":null},{"paper":null,"slug":"precog-exploring-the-relation-between","title":"PreCog: Exploring the Relation between Memorization and Performance in Pre-trained Language Models","date":"2023-05-08","arxiv_id":"2305.04673","n_code_links":0,"syntology":null},{"paper":null,"slug":"real-world-denoising-via-diffusion-model","title":"Real-World Denoising via Diffusion Model","date":"2023-05-08","arxiv_id":"2305.04457","n_code_links":0,"syntology":null},{"paper":null,"slug":"revisiting-relation-extraction-in-the-era-of","title":"Revisiting Relation Extraction in the era of Large Language Models","date":"2023-05-08","arxiv_id":"2305.05003","n_code_links":0,"syntology":null},{"paper":null,"slug":"robust-traffic-light-detection-using-salience","title":"Robust Traffic Light Detection Using Salience-Sensitive Loss: Computational Framework and Evaluations","date":"2023-05-08","arxiv_id":"2305.04516","n_code_links":0,"syntology":null},{"paper":null,"slug":"smart-home-device-detection-algorithm-based","title":"Smart Home Device Detection Algorithm Based on FSA-YOLOv5","date":"2023-05-08","arxiv_id":"2305.04534","n_code_links":0,"syntology":null},{"paper":"/paper/understanding-gaussian-attention-bias-of","slug":"understanding-gaussian-attention-bias-of","title":"Understanding Gaussian Attention Bias of Vision Transformers Using Effective Receptive Fields","date":"2023-05-08","arxiv_id":"2305.04722","n_code_links":1,"syntology":null},{"paper":null,"slug":"unlocking-practical-applications-in-legal","title":"Unlocking Practical Applications in Legal Domain: Evaluation of GPT for Zero-Shot Semantic Annotation of Legal Texts","date":"2023-05-08","arxiv_id":"2305.04417","n_code_links":0,"syntology":null},{"paper":"/paper/vision-transformer-off-the-shelf-a-surprising","slug":"vision-transformer-off-the-shelf-a-surprising","title":"Vision Transformer Off-the-Shelf: A Surprising Baseline for Few-Shot Class-Agnostic Counting","date":"2023-05-08","arxiv_id":"2305.04440","n_code_links":1,"syntology":null},{"paper":null,"slug":"vulnerability-detection-using-two-stage-deep","title":"Vulnerability Detection Using Two-Stage Deep Learning Models","date":"2023-05-08","arxiv_id":"2305.09673","n_code_links":0,"syntology":null},{"paper":"/paper/adaptiveclick-clicks-aware-transformer-with","slug":"adaptiveclick-clicks-aware-transformer-with","title":"AdaptiveClick: Clicks-aware Transformer with Adaptive Focal Loss for Interactive Image Segmentation","date":"2023-05-07","arxiv_id":"2305.04276","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":4,"n_instrument":0,"unverified":0,"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) · 0 unverified","official":{"repos":["lab206/adaptiveclick"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"cit-emotionnet-cnn-interactive-transformer","title":"CIT-EmotionNet: CNN Interactive Transformer Network for EEG Emotion Recognition","date":"2023-05-07","arxiv_id":"2305.05548","n_code_links":0,"syntology":null},{"paper":"/paper/language-models-don-t-always-say-what-they-1","slug":"language-models-don-t-always-say-what-they-1","title":"Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting","date":"2023-05-07","arxiv_id":"2305.04388","n_code_links":2,"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":["milesaturpin/cot-unfaithfulness"],"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":"/paper/learning-from-synthetic-data-generated-with","slug":"learning-from-synthetic-data-generated-with","title":"Learning from synthetic data generated with GRADE","date":"2023-05-07","arxiv_id":"2305.04282","n_code_links":1,"syntology":null},{"paper":null,"slug":"model-contrastive-federated-domain-adaptation","title":"Model-Contrastive Federated Domain Adaptation","date":"2023-05-07","arxiv_id":"2305.10432","n_code_links":0,"syntology":null},{"paper":null,"slug":"poses-as-queries-image-to-lidar-map","title":"Poses as Queries: Image-to-LiDAR Map Localization with Transformers","date":"2023-05-07","arxiv_id":"2305.04298","n_code_links":0,"syntology":null},{"paper":null,"slug":"professional-certification-benchmark-dataset","title":"Professional Certification Benchmark Dataset: The First 500 Jobs For Large Language Models","date":"2023-05-07","arxiv_id":"2305.05377","n_code_links":0,"syntology":null},{"paper":null,"slug":"rats-nas-redirection-of-adjacent-trails-on","title":"RATs-NAS: Redirection of Adjacent Trails on GCN for Neural Architecture Search","date":"2023-05-07","arxiv_id":"2305.04206","n_code_links":0,"syntology":null},{"paper":"/paper/rfr-wwanet-weighted-window-attention-based","slug":"rfr-wwanet-weighted-window-attention-based","title":"RFR-WWANet: Weighted Window Attention-Based Recovery Feature Resolution Network for Unsupervised Image Registration","date":"2023-05-07","arxiv_id":"2305.04236","n_code_links":1,"syntology":null},{"paper":null,"slug":"stanford-mlab-at-semeval-2023-task-10","title":"Stanford MLab at SemEval-2023 Task 10: Exploring GloVe- and Transformer-Based Methods for the Explainable Detection of Online Sexism","date":"2023-05-07","arxiv_id":"2305.04356","n_code_links":0,"syntology":null},{"paper":"/paper/x-llm-bootstrapping-advanced-large-language","slug":"x-llm-bootstrapping-advanced-large-language","title":"X-LLM: Bootstrapping Advanced Large Language Models by Treating Multi-Modalities as Foreign Languages","date":"2023-05-07","arxiv_id":"2305.04160","n_code_links":2,"syntology":{"ran":8,"of":11,"n_ran_checked":4,"n_instrument":4,"unverified":3,"pointer_only":2,"phrase":"8 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; 4 where Syntology's instrument failed) · 3 unverified","official":null}},{"paper":null,"slug":"an-adversarial-non-autoregressive-model-for","title":"Unlocking the Power of GANs in Non-Autoregressive Text Generation","date":"2023-05-06","arxiv_id":"2305.03977","n_code_links":0,"syntology":null},{"paper":null,"slug":"artificial-neuropsychology-are-large-language","title":"Artificial Neuropsychology: Are Large Language Models Developing Executive Functions?","date":"2023-05-06","arxiv_id":"2305.04134","n_code_links":0,"syntology":null},{"paper":null,"slug":"cognition-guided-human-object-relationship","title":"Cognition Guided Human-Object Relationship Detection","date":"2023-05-06","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/dbat-dynamic-backward-attention-transformer","slug":"dbat-dynamic-backward-attention-transformer","title":"DBAT: Dynamic Backward Attention Transformer for Material Segmentation with Cross-Resolution Patches","date":"2023-05-06","arxiv_id":"2305.03919","n_code_links":1,"syntology":null},{"paper":null,"slug":"degradation-noise-aware-deep-unfolding","title":"Degradation-Noise-Aware Deep Unfolding Transformer for Hyperspectral Image Denoising","date":"2023-05-06","arxiv_id":"2305.04047","n_code_links":0,"syntology":null},{"paper":null,"slug":"diffusion-nat-self-prompting-discrete","title":"Diffusion-NAT: Self-Prompting Discrete Diffusion for Non-Autoregressive Text Generation","date":"2023-05-06","arxiv_id":"2305.04044","n_code_links":0,"syntology":null},{"paper":null,"slug":"feature-chirality-in-deep-learning-models","title":"Feature Chirality in Deep Learning Models","date":"2023-05-06","arxiv_id":"2305.03966","n_code_links":0,"syntology":null},{"paper":null,"slug":"on-the-usage-of-continual-learning-for-out-of","title":"On the Usage of Continual Learning for Out-of-Distribution Generalization in Pre-trained Language Models of Code","date":"2023-05-06","arxiv_id":"2305.04106","n_code_links":0,"syntology":null},{"paper":"/paper/plan-and-solve-prompting-improving-zero-shot","slug":"plan-and-solve-prompting-improving-zero-shot","title":"Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Models","date":"2023-05-06","arxiv_id":"2305.04091","n_code_links":3,"syntology":{"ran":0,"of":2,"n_ran_checked":0,"n_instrument":0,"unverified":2,"pointer_only":2,"phrase":"0 ran · 2 unverified","official":{"repos":["agi-edgerunners/plan-and-solve-prompting"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":[]}}},{"paper":null,"slug":"pre-training-language-model-as-a-multi","title":"Pre-training Language Model as a Multi-perspective Course Learner","date":"2023-05-06","arxiv_id":"2305.03981","n_code_links":0,"syntology":null},{"paper":"/paper/refining-the-responses-of-llms-by-themselves","slug":"refining-the-responses-of-llms-by-themselves","title":"Refining the Responses of LLMs by Themselves","date":"2023-05-06","arxiv_id":"2305.04039","n_code_links":1,"syntology":null},{"paper":null,"slug":"rhetorical-role-labeling-of-legal-documents","title":"Rhetorical Role Labeling of Legal Documents using Transformers and Graph Neural Networks","date":"2023-05-06","arxiv_id":"2305.04100","n_code_links":0,"syntology":null},{"paper":"/paper/a-transformer-based-method-for-zero-and-few","slug":"a-transformer-based-method-for-zero-and-few","title":"From Zero to Hero: Harnessing Transformers for Biomedical Named Entity Recognition in Zero- and Few-shot Contexts","date":"2023-05-05","arxiv_id":"2305.04928","n_code_links":1,"syntology":null},{"paper":null,"slug":"adapting-transformer-language-models-for","title":"Adapting Transformer Language Models for Predictive Typing in Brain-Computer Interfaces","date":"2023-05-05","arxiv_id":"2305.03819","n_code_links":0,"syntology":null},{"paper":null,"slug":"block-the-label-and-noise-an-n-gram-masked","title":"Block the Label and Noise: An N-Gram Masked Speller for Chinese Spell Checking","date":"2023-05-05","arxiv_id":"2305.03314","n_code_links":0,"syntology":null},{"paper":null,"slug":"clac-at-semeval-2023-task-2-comparing-span","title":"CLaC at SemEval-2023 Task 2: Comparing Span-Prediction and Sequence-Labeling approaches for NER","date":"2023-05-05","arxiv_id":"2305.03845","n_code_links":0,"syntology":null},{"paper":null,"slug":"demystifying-softmax-gating-in-gaussian","title":"Demystifying Softmax Gating Function in Gaussian Mixture of Experts","date":"2023-05-05","arxiv_id":"2305.03288","n_code_links":0,"syntology":null},{"paper":null,"slug":"fm-vit-flexible-modal-vision-transformers-for","title":"FM-ViT: Flexible Modal Vision Transformers for Face Anti-Spoofing","date":"2023-05-05","arxiv_id":"2305.03277","n_code_links":0,"syntology":null},{"paper":null,"slug":"harnessing-the-power-of-bert-in-the-turkish","title":"Harnessing the Power of BERT in the Turkish Clinical Domain: Pretraining Approaches for Limited Data Scenarios","date":"2023-05-05","arxiv_id":"2305.03788","n_code_links":0,"syntology":null},{"paper":null,"slug":"heteroedge-addressing-asymmetry-in","title":"HeteroEdge: Addressing Asymmetry in Heterogeneous Collaborative Autonomous Systems","date":"2023-05-05","arxiv_id":"2305.03252","n_code_links":0,"syntology":null},{"paper":"/paper/lmeye-an-interactive-perception-network-for","slug":"lmeye-an-interactive-perception-network-for","title":"LMEye: An Interactive Perception Network for Large Language Models","date":"2023-05-05","arxiv_id":"2305.03701","n_code_links":1,"syntology":null},{"paper":null,"slug":"logo-former-local-global-spatio-temporal","title":"LOGO-Former: Local-Global Spatio-Temporal Transformer for Dynamic Facial Expression Recognition","date":"2023-05-05","arxiv_id":"2305.03343","n_code_links":0,"syntology":null},{"paper":"/paper/mindgames-targeting-theory-of-mind-in-large","slug":"mindgames-targeting-theory-of-mind-in-large","title":"MindGames: Targeting Theory of Mind in Large Language Models with Dynamic Epistemic Modal Logic","date":"2023-05-05","arxiv_id":"2305.03353","n_code_links":2,"syntology":null},{"paper":"/paper/neuromodulation-gated-transformer","slug":"neuromodulation-gated-transformer","title":"Neuromodulation Gated Transformer","date":"2023-05-05","arxiv_id":"2305.03232","n_code_links":1,"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":["kobeknowles/neuromodulation-gated-transformer"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"online-gesture-recognition-using-transformer","title":"Online Gesture Recognition using Transformer and Natural Language Processing","date":"2023-05-05","arxiv_id":"2305.03407","n_code_links":0,"syntology":null},{"paper":"/paper/otter-a-multi-modal-model-with-in-context","slug":"otter-a-multi-modal-model-with-in-context","title":"Otter: A Multi-Modal Model with In-Context Instruction Tuning","date":"2023-05-05","arxiv_id":"2305.03726","n_code_links":1,"syntology":null},{"paper":null,"slug":"predicting-covid-19-and-pneumonia","title":"Predicting COVID-19 and pneumonia complications from admission texts","date":"2023-05-05","arxiv_id":"2305.03661","n_code_links":0,"syntology":null},{"paper":"/paper/reduction-of-class-activation-uncertainty","slug":"reduction-of-class-activation-uncertainty","title":"Reduction of Class Activation Uncertainty with Background Information","date":"2023-05-05","arxiv_id":"2305.03238","n_code_links":2,"syntology":null},{"paper":null,"slug":"retrieval-augmented-chest-x-ray-report","title":"Retrieval Augmented Chest X-Ray Report Generation using OpenAI GPT models","date":"2023-05-05","arxiv_id":"2305.03660","n_code_links":0,"syntology":null},{"paper":null,"slug":"segmentation-of-fundus-vascular-images-based","title":"MAF-Net: Multiple attention-guided fusion network for fundus vascular image segmentation","date":"2023-05-05","arxiv_id":"2305.03617","n_code_links":0,"syntology":null},{"paper":null,"slug":"simulating-h-p-lovecraft-horror-literature","title":"Simulating H.P. Lovecraft horror literature with the ChatGPT large language model","date":"2023-05-05","arxiv_id":"2305.03429","n_code_links":0,"syntology":null},{"paper":"/paper/the-muse-2023-multimodal-sentiment-analysis","slug":"the-muse-2023-multimodal-sentiment-analysis","title":"The MuSe 2023 Multimodal Sentiment Analysis Challenge: Mimicked Emotions, Cross-Cultural Humour, and Personalisation","date":"2023-05-05","arxiv_id":"2305.03369","n_code_links":1,"syntology":null},{"paper":null,"slug":"transformer-working-memory-enables-regular","title":"Transformer Working Memory Enables Regular Language Reasoning and Natural Language Length Extrapolation","date":"2023-05-05","arxiv_id":"2305.03796","n_code_links":0,"syntology":null},{"paper":"/paper/using-chatgpt-for-entity-matching","slug":"using-chatgpt-for-entity-matching","title":"Using ChatGPT for Entity Matching","date":"2023-05-05","arxiv_id":"2305.03423","n_code_links":1,"syntology":null},{"paper":"/paper/verify-and-edit-a-knowledge-enhanced-chain-of","slug":"verify-and-edit-a-knowledge-enhanced-chain-of","title":"Verify-and-Edit: A Knowledge-Enhanced Chain-of-Thought Framework","date":"2023-05-05","arxiv_id":"2305.03268","n_code_links":1,"syntology":null},{"paper":"/paper/2x-faster-language-model-pre-training-via","slug":"2x-faster-language-model-pre-training-via","title":"Masked Structural Growth for 2x Faster Language Model Pre-training","date":"2023-05-04","arxiv_id":"2305.02869","n_code_links":1,"syntology":{"ran":16,"of":34,"n_ran_checked":10,"n_instrument":6,"unverified":18,"pointer_only":0,"phrase":"16 ran (of which 6 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 6 where Syntology's instrument failed) · 18 unverified","official":{"repos":["cofe-ai/msg"],"state":"official (archive's flag): 16 ran","n_ran":16,"n_constructed":6,"n_ran_no_instrument_failure":10,"n_unverified":18,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"an-automatically-discovered-chain-of-thought","title":"An automatically discovered chain-of-thought prompt generalizes to novel models and datasets","date":"2023-05-04","arxiv_id":"2305.02897","n_code_links":0,"syntology":null},{"paper":null,"slug":"automl-gpt-automatic-machine-learning-with","title":"AutoML-GPT: Automatic Machine Learning with GPT","date":"2023-05-04","arxiv_id":"2305.02499","n_code_links":0,"syntology":null},{"paper":null,"slug":"branchnorm-robustly-scaling-extremely-deep","title":"BranchNorm: Robustly Scaling Extremely Deep Transformers","date":"2023-05-04","arxiv_id":"2305.02790","n_code_links":0,"syntology":null},{"paper":null,"slug":"breast-cancer-diagnosis-using-machine","title":"Breast Cancer Diagnosis Using Machine Learning Techniques","date":"2023-05-04","arxiv_id":"2305.02482","n_code_links":0,"syntology":null},{"paper":"/paper/catch-missing-details-image-reconstruction","slug":"catch-missing-details-image-reconstruction","title":"Catch Missing Details: Image Reconstruction with Frequency Augmented Variational Autoencoder","date":"2023-05-04","arxiv_id":"2305.02541","n_code_links":1,"syntology":{"ran":13,"of":15,"n_ran_checked":11,"n_instrument":2,"unverified":2,"pointer_only":3,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 3 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","official":{"repos":["oppo-us-research/FA-VAE"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/chain-of-skills-a-configurable-model-for-open","slug":"chain-of-skills-a-configurable-model-for-open","title":"Chain-of-Skills: A Configurable Model for Open-domain Question Answering","date":"2023-05-04","arxiv_id":"2305.03130","n_code_links":1,"syntology":null},{"paper":null,"slug":"enhancing-pashto-text-classification-using","title":"Enhancing Pashto Text Classification using Language Processing Techniques for Single And Multi-Label Analysis","date":"2023-05-04","arxiv_id":"2305.03201","n_code_links":0,"syntology":null},{"paper":null,"slug":"gpt-4-a-review-on-advancements-and","title":"Gpt-4: A Review on Advancements and Opportunities in Natural Language Processing","date":"2023-05-04","arxiv_id":"2305.03195","n_code_links":0,"syntology":null},{"paper":null,"slug":"haista-net-human-assisted-instance","title":"HAISTA-NET: Human Assisted Instance Segmentation Through Attention","date":"2023-05-04","arxiv_id":"2305.03105","n_code_links":0,"syntology":null},{"paper":null,"slug":"hierarchical-transformer-for-scalable-graph","title":"Hierarchical Transformer for Scalable Graph Learning","date":"2023-05-04","arxiv_id":"2305.02866","n_code_links":0,"syntology":null}],"record_sha256":"ff4bb95bc526b98ca880f2e373107982c3434fd911baa77fca946a375d1a5efe","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}