{"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/attention/papers/177","list_of":"/method/attention","method":"Attention","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":177,"pages_in_order":316,"rows_per_page":100,"rows":[17601,17700],"of":31583,"counts":{"archive_papers_tagged":31583,"with_a_code_link":13473,"where_syntology_ran_a_sample":3998,"not_listed_spam_title":0,"listed":31583,"listed_where_code_ran":3998,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":3366,"every_run_a_failure_of_syntologys_instrument":632,"listed_with_a_run_with_no_instrument_failure":3366,"listed_every_run_a_failure_of_syntologys_instrument":632,"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/attention","prev":"/method/attention/papers/176","next":"/method/attention/papers/178","papers":[{"paper":null,"slug":"fixpix-fixing-bad-pixels-using-deep-learning","title":"FixPix: Fixing Bad Pixels using Deep Learning","date":"2023-10-18","arxiv_id":"2310.11637","n_code_links":0,"syntology":null},{"paper":"/paper/harnessing-dataset-cartography-for-improved","slug":"harnessing-dataset-cartography-for-improved","title":"Harnessing Dataset Cartography for Improved Compositional Generalization in Transformers","date":"2023-10-18","arxiv_id":"2310.12118","n_code_links":1,"syntology":null},{"paper":"/paper/improving-long-document-topic-segmentation","slug":"improving-long-document-topic-segmentation","title":"Improving Long Document Topic Segmentation Models With Enhanced Coherence Modeling","date":"2023-10-18","arxiv_id":"2310.11772","n_code_links":1,"syntology":null},{"paper":"/paper/lacma-language-aligning-contrastive-learning","slug":"lacma-language-aligning-contrastive-learning","title":"LACMA: Language-Aligning Contrastive Learning with Meta-Actions for Embodied Instruction Following","date":"2023-10-18","arxiv_id":"2310.12344","n_code_links":1,"syntology":{"ran":1,"of":5,"n_ran_checked":1,"n_instrument":0,"unverified":4,"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) · 4 unverified","official":{"repos":["joeyy5588/lacma"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/monarch-mixer-a-simple-sub-quadratic-gemm-1","slug":"monarch-mixer-a-simple-sub-quadratic-gemm-1","title":"Monarch Mixer: A Simple Sub-Quadratic GEMM-Based Architecture","date":"2023-10-18","arxiv_id":"2310.12109","n_code_links":1,"syntology":{"ran":4,"of":7,"n_ran_checked":4,"n_instrument":0,"unverified":3,"pointer_only":0,"phrase":"4 ran (of which 4 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) · 3 unverified; every one of the 4 samples that ran constructed an object rather than computing a result","official":null}},{"paper":"/paper/quantify-health-related-atomic-knowledge-in","slug":"quantify-health-related-atomic-knowledge-in","title":"Quantifying Self-diagnostic Atomic Knowledge in Chinese Medical Foundation Model: A Computational Analysis","date":"2023-10-18","arxiv_id":"2310.11722","n_code_links":1,"syntology":null},{"paper":null,"slug":"solving-the-multiplication-problem-of-a-large","title":"Solving the multiplication problem of a large language model system using a graph-based method","date":"2023-10-18","arxiv_id":"2310.13016","n_code_links":0,"syntology":null},{"paper":"/paper/sotopia-interactive-evaluation-for-social","slug":"sotopia-interactive-evaluation-for-social","title":"SOTOPIA: Interactive Evaluation for Social Intelligence in Language Agents","date":"2023-10-18","arxiv_id":"2310.11667","n_code_links":2,"syntology":null},{"paper":null,"slug":"speed-speculative-pipelined-execution-for","title":"SPEED: Speculative Pipelined Execution for Efficient Decoding","date":"2023-10-18","arxiv_id":"2310.12072","n_code_links":0,"syntology":null},{"paper":null,"slug":"tailoring-adversarial-attacks-on-deep-neural","title":"Tailoring Adversarial Attacks on Deep Neural Networks for Targeted Class Manipulation Using DeepFool Algorithm","date":"2023-10-18","arxiv_id":"2310.13019","n_code_links":0,"syntology":null},{"paper":null,"slug":"vst-efficient-and-stronger-visual-saliency","title":"VST++: Efficient and Stronger Visual Saliency Transformer","date":"2023-10-18","arxiv_id":"2310.11725","n_code_links":0,"syntology":null},{"paper":"/paper/bitnet-scaling-1-bit-transformers-for-large","slug":"bitnet-scaling-1-bit-transformers-for-large","title":"BitNet: Scaling 1-bit Transformers for Large Language Models","date":"2023-10-17","arxiv_id":"2310.11453","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":null}},{"paper":"/paper/compatible-transformer-for-irregularly","slug":"compatible-transformer-for-irregularly","title":"Compatible Transformer for Irregularly Sampled Multivariate Time Series","date":"2023-10-17","arxiv_id":"2310.11022","n_code_links":1,"syntology":null},{"paper":"/paper/compost-characterizing-and-evaluating","slug":"compost-characterizing-and-evaluating","title":"CoMPosT: Characterizing and Evaluating Caricature in LLM Simulations","date":"2023-10-17","arxiv_id":"2310.11501","n_code_links":1,"syntology":{"ran":3,"of":4,"n_ran_checked":3,"n_instrument":0,"unverified":1,"pointer_only":4,"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":["myracheng/lm_caricature"],"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":null,"slug":"diar-deep-image-alignment-and-reconstruction","title":"DIAR: Deep Image Alignment and Reconstruction using Swin Transformers","date":"2023-10-17","arxiv_id":"2310.11605","n_code_links":0,"syntology":null},{"paper":null,"slug":"disentangling-the-linguistic-competence-of","title":"Disentangling the Linguistic Competence of Privacy-Preserving BERT","date":"2023-10-17","arxiv_id":"2310.11363","n_code_links":0,"syntology":null},{"paper":null,"slug":"emergent-ai-assisted-discourse-case-study-of","title":"Emergent AI-Assisted Discourse: Case Study of a Second Language Writer Authoring with ChatGPT","date":"2023-10-17","arxiv_id":"2310.10903","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhanced-transformer-architecture-for-natural","title":"Enhanced Transformer Architecture for Natural Language Processing","date":"2023-10-17","arxiv_id":"2310.10930","n_code_links":0,"syntology":null},{"paper":"/paper/evaluating-llms-for-privilege-escalation","slug":"evaluating-llms-for-privilege-escalation","title":"LLMs as Hackers: Autonomous Linux Privilege Escalation Attacks","date":"2023-10-17","arxiv_id":"2310.11409","n_code_links":1,"syntology":null},{"paper":null,"slug":"experimenting-ai-technologies-for","title":"Experimenting AI Technologies for Disinformation Combat: the IDMO Project","date":"2023-10-17","arxiv_id":"2310.11097","n_code_links":0,"syntology":null},{"paper":null,"slug":"focdepthformer-transformer-with-lstm-for","title":"FocDepthFormer: Transformer with latent LSTM for Depth Estimation from Focal Stack","date":"2023-10-17","arxiv_id":"2310.11178","n_code_links":0,"syntology":null},{"paper":"/paper/intent-detection-and-slot-filling-for-home","slug":"intent-detection-and-slot-filling-for-home","title":"Intent Detection and Slot Filling for Home Assistants: Dataset and Analysis for Bangla and Sylheti","date":"2023-10-17","arxiv_id":"2310.10935","n_code_links":1,"syntology":null},{"paper":null,"slug":"large-language-model-prediction-capabilities","title":"Large Language Model Prediction Capabilities: Evidence from a Real-World Forecasting Tournament","date":"2023-10-17","arxiv_id":"2310.13014","n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-from-red-teaming-gender-bias","title":"Learning from Red Teaming: Gender Bias Provocation and Mitigation in Large Language Models","date":"2023-10-17","arxiv_id":"2310.11079","n_code_links":0,"syntology":null},{"paper":null,"slug":"mason-nlp-at-erisk-2023-deep-learning-based","title":"MASON-NLP at eRisk 2023: Deep Learning-Based Detection of Depression Symptoms from Social Media Texts","date":"2023-10-17","arxiv_id":"2310.10941","n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-omics-sampling-based-graph-transformer","title":"Multi-omics Sampling-based Graph Transformer for Synthetic Lethality Prediction","date":"2023-10-17","arxiv_id":"2310.11082","n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-self-supervised-pre-fine-tuned","title":"Multi Self-supervised Pre-fine-tuned Transformer Fusion for Better Intelligent Transportation Detection","date":"2023-10-17","arxiv_id":"2310.11307","n_code_links":0,"syntology":null},{"paper":"/paper/neural-attention-enhancing-qkv-calculation-in","slug":"neural-attention-enhancing-qkv-calculation-in","title":"Neural Attention: Enhancing QKV Calculation in Self-Attention Mechanism with Neural Networks","date":"2023-10-17","arxiv_id":"2310.11398","n_code_links":1,"syntology":null},{"paper":"/paper/probing-the-creativity-of-large-language","slug":"probing-the-creativity-of-large-language","title":"Probing the Creativity of Large Language Models: Can models produce divergent semantic association?","date":"2023-10-17","arxiv_id":"2310.11158","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":0,"n_instrument":1,"unverified":1,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["dingnlab/probing_creativity"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/signgt-signed-attention-based-graph","slug":"signgt-signed-attention-based-graph","title":"SignGT: Signed Attention-based Graph Transformer for Graph Representation Learning","date":"2023-10-17","arxiv_id":"2310.11025","n_code_links":0,"syntology":null},{"paper":"/paper/understanding-writing-style-in-social-media","slug":"understanding-writing-style-in-social-media","title":"Understanding writing style in social media with a supervised contrastively pre-trained transformer","date":"2023-10-17","arxiv_id":"2310.11081","n_code_links":1,"syntology":null},{"paper":null,"slug":"usdc-unified-static-and-dynamic-compression","title":"USDC: Unified Static and Dynamic Compression for Visual Transformer","date":"2023-10-17","arxiv_id":"2310.11117","n_code_links":0,"syntology":null},{"paper":null,"slug":"utilising-a-large-language-model-to-annotate","title":"Utilising a Large Language Model to Annotate Subject Metadata: A Case Study in an Australian National Research Data Catalogue","date":"2023-10-17","arxiv_id":"2310.11318","n_code_links":0,"syntology":null},{"paper":"/paper/vct-visual-change-transformer-for-remote","slug":"vct-visual-change-transformer-for-remote","title":"VcT: Visual change Transformer for Remote Sensing Image Change Detection","date":"2023-10-17","arxiv_id":"2310.11417","n_code_links":1,"syntology":null},{"paper":null,"slug":"what-is-a-good-question-task-oriented-asking","title":"Alexpaca: Learning Factual Clarification Question Generation Without Examples","date":"2023-10-17","arxiv_id":"2310.11571","n_code_links":0,"syntology":null},{"paper":"/paper/a-cross-transformer-for-image-denoising","slug":"a-cross-transformer-for-image-denoising","title":"A cross Transformer for image denoising","date":"2023-10-16","arxiv_id":"2310.10408","n_code_links":1,"syntology":null},{"paper":"/paper/approximating-two-layer-feedforward-networks","slug":"approximating-two-layer-feedforward-networks","title":"Approximating Two-Layer Feedforward Networks for Efficient Transformers","date":"2023-10-16","arxiv_id":"2310.10837","n_code_links":2,"syntology":{"ran":3,"of":4,"n_ran_checked":1,"n_instrument":2,"unverified":1,"pointer_only":0,"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) · 1 unverified","official":{"repos":["robertcsordas/moe","robertcsordas/moe_layer"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"battle-of-the-large-language-models-dolly-vs","title":"Battle of the Large Language Models: Dolly vs LLaMA vs Vicuna vs Guanaco vs Bard vs ChatGPT -- A Text-to-SQL Parsing Comparison","date":"2023-10-16","arxiv_id":"2310.10190","n_code_links":0,"syntology":null},{"paper":null,"slug":"biomedjourney-counterfactual-biomedical-image","title":"BiomedJourney: Counterfactual Biomedical Image Generation by Instruction-Learning from Multimodal Patient Journeys","date":"2023-10-16","arxiv_id":"2310.10765","n_code_links":0,"syntology":null},{"paper":"/paper/bioplanner-automatic-evaluation-of-llms-on","slug":"bioplanner-automatic-evaluation-of-llms-on","title":"BioPlanner: Automatic Evaluation of LLMs on Protocol Planning in Biology","date":"2023-10-16","arxiv_id":"2310.10632","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":2,"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) · 0 unverified","official":{"repos":["bioplanner/bioplanner"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/data-contamination-through-the-lens-of-time","slug":"data-contamination-through-the-lens-of-time","title":"Data Contamination Through the Lens of Time","date":"2023-10-16","arxiv_id":"2310.10628","n_code_links":1,"syntology":{"ran":2,"of":4,"n_ran_checked":2,"n_instrument":0,"unverified":2,"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) · 2 unverified","official":{"repos":["abacusai/to-the-cutoff"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/factored-verification-detecting-and-reducing","slug":"factored-verification-detecting-and-reducing","title":"Factored Verification: Detecting and Reducing Hallucination in Summaries of Academic Papers","date":"2023-10-16","arxiv_id":"2310.10627","n_code_links":1,"syntology":null},{"paper":null,"slug":"few-shot-action-recognition-with-captioning","title":"Few-shot Action Recognition with Captioning Foundation Models","date":"2023-10-16","arxiv_id":"2310.10125","n_code_links":0,"syntology":null},{"paper":null,"slug":"fine-tuning-chatgpt-for-automatic-scoring","title":"Fine-tuning ChatGPT for Automatic Scoring","date":"2023-10-16","arxiv_id":"2310.10072","n_code_links":0,"syntology":null},{"paper":"/paper/investigating-bias-in-multilingual-language","slug":"investigating-bias-in-multilingual-language","title":"Investigating Bias in Multilingual Language Models: Cross-Lingual Transfer of Debiasing Techniques","date":"2023-10-16","arxiv_id":"2310.10310","n_code_links":1,"syntology":null},{"paper":"/paper/learning-to-rank-context-for-named-entity","slug":"learning-to-rank-context-for-named-entity","title":"Learning to Rank Context for Named Entity Recognition Using a Synthetic Dataset","date":"2023-10-16","arxiv_id":"2310.10118","n_code_links":1,"syntology":null},{"paper":null,"slug":"mask-wearing-object-detection-algorithm-based","title":"Mask wearing object detection algorithm based on improved YOLOv5","date":"2023-10-16","arxiv_id":"2310.10245","n_code_links":0,"syntology":null},{"paper":null,"slug":"moconvq-unified-physics-based-motion-control","title":"MoConVQ: Unified Physics-Based Motion Control via Scalable Discrete Representations","date":"2023-10-16","arxiv_id":"2310.10198","n_code_links":0,"syntology":null},{"paper":"/paper/pela-learning-parameter-efficient-models-with","slug":"pela-learning-parameter-efficient-models-with","title":"PELA: Learning Parameter-Efficient Models with Low-Rank Approximation","date":"2023-10-16","arxiv_id":"2310.10700","n_code_links":1,"syntology":null},{"paper":null,"slug":"prediction-of-arabic-legal-rulings-using","title":"Prediction of Arabic Legal Rulings using Large Language Models","date":"2023-10-16","arxiv_id":"2310.10260","n_code_links":0,"syntology":null},{"paper":null,"slug":"prompt-packer-deceiving-llms-through","title":"Prompt Packer: Deceiving LLMs through Compositional Instruction with Hidden Attacks","date":"2023-10-16","arxiv_id":"2310.10077","n_code_links":0,"syntology":null},{"paper":null,"slug":"seunet-trans-a-simple-yet-effective-unet","title":"SeUNet-Trans: A Simple yet Effective UNet-Transformer Model for Medical Image Segmentation","date":"2023-10-16","arxiv_id":"2310.09998","n_code_links":0,"syntology":null},{"paper":"/paper/transom-an-efficient-fault-tolerant-system","slug":"transom-an-efficient-fault-tolerant-system","title":"TRANSOM: An Efficient Fault-Tolerant System for Training LLMs","date":"2023-10-16","arxiv_id":"2310.10046","n_code_links":1,"syntology":{"ran":0,"of":3,"n_ran_checked":0,"n_instrument":0,"unverified":3,"pointer_only":0,"phrase":"0 ran · 3 unverified","official":{"repos":["SenseCore/transom-checkpoint-engine"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":[]}}},{"paper":"/paper/trigo-benchmarking-formal-mathematical-proof","slug":"trigo-benchmarking-formal-mathematical-proof","title":"TRIGO: Benchmarking Formal Mathematical Proof Reduction for Generative Language Models","date":"2023-10-16","arxiv_id":"2310.10180","n_code_links":1,"syntology":{"ran":7,"of":11,"n_ran_checked":7,"n_instrument":0,"unverified":4,"pointer_only":11,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","official":{"repos":["menik1126/TRIGO"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"verbosity-bias-in-preference-labeling-by","title":"Verbosity Bias in Preference Labeling by Large Language Models","date":"2023-10-16","arxiv_id":"2310.10076","n_code_links":0,"syntology":null},{"paper":"/paper/cocoformer-a-controllable-feature-rich","slug":"cocoformer-a-controllable-feature-rich","title":"CoCoFormer: A controllable feature-rich polyphonic music generation method","date":"2023-10-15","arxiv_id":"2310.09843","n_code_links":1,"syntology":null},{"paper":null,"slug":"configuration-validation-with-large-language","title":"Configuration Validation with Large Language Models","date":"2023-10-15","arxiv_id":"2310.09690","n_code_links":0,"syntology":null},{"paper":null,"slug":"diversifying-the-mixture-of-experts","title":"Diversifying the Mixture-of-Experts Representation for Language Models with Orthogonal Optimizer","date":"2023-10-15","arxiv_id":"2310.09762","n_code_links":0,"syntology":null},{"paper":"/paper/domain-specific-language-model-post-training","slug":"domain-specific-language-model-post-training","title":"Domain-Specific Language Model Post-Training for Indonesian Financial NLP","date":"2023-10-15","arxiv_id":"2310.09736","n_code_links":1,"syntology":null},{"paper":null,"slug":"empirical-study-of-pretrained-multilingual","title":"Empirical study of pretrained multilingual language models for zero-shot cross-lingual knowledge transfer in generation","date":"2023-10-15","arxiv_id":"2310.09917","n_code_links":0,"syntology":null},{"paper":null,"slug":"image-augmentation-with-controlled-diffusion","title":"Image Augmentation with Controlled Diffusion for Weakly-Supervised Semantic Segmentation","date":"2023-10-15","arxiv_id":"2310.09760","n_code_links":0,"syntology":null},{"paper":null,"slug":"large-language-model-aware-in-context","title":"Large Language Model-Aware In-Context Learning for Code Generation","date":"2023-10-15","arxiv_id":"2310.09748","n_code_links":0,"syntology":null},{"paper":"/paper/large-language-models-for-in-context-student","slug":"large-language-models-for-in-context-student","title":"Large Language Models for In-Context Student Modeling: Synthesizing Student's Behavior in Visual Programming","date":"2023-10-15","arxiv_id":"2310.10690","n_code_links":1,"syntology":null},{"paper":"/paper/moemo-vision-transformer-integrating-cross","slug":"moemo-vision-transformer-integrating-cross","title":"MoEmo Vision Transformer: Integrating Cross-Attention and Movement Vectors in 3D Pose Estimation for HRI Emotion Detection","date":"2023-10-15","arxiv_id":"2310.09757","n_code_links":1,"syntology":null},{"paper":"/paper/spatio-temporal-graph-mixformer-for-traffic","slug":"spatio-temporal-graph-mixformer-for-traffic","title":"Spatio-Temporal Graph Mixformer for Traffic Forecasting","date":"2023-10-15","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"top-k-pooling-with-patch-contrastive-learning","title":"Top-K Pooling with Patch Contrastive Learning for Weakly-Supervised Semantic Segmentation","date":"2023-10-15","arxiv_id":"2310.09828","n_code_links":0,"syntology":null},{"paper":"/paper/unitime-a-language-empowered-unified-model","slug":"unitime-a-language-empowered-unified-model","title":"UniTime: A Language-Empowered Unified Model for Cross-Domain Time Series Forecasting","date":"2023-10-15","arxiv_id":"2310.09751","n_code_links":1,"syntology":{"ran":4,"of":8,"n_ran_checked":4,"n_instrument":0,"unverified":4,"pointer_only":4,"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) · 4 unverified","official":{"repos":["liuxu77/unitime"],"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":"arm-refining-multivariate-forecasting-with","title":"ARM: Refining Multivariate Forecasting with Adaptive Temporal-Contextual Learning","date":"2023-10-14","arxiv_id":"2310.09488","n_code_links":0,"syntology":null},{"paper":"/paper/dpzero-dimension-independent-and","slug":"dpzero-dimension-independent-and","title":"DPZero: Private Fine-Tuning of Language Models without Backpropagation","date":"2023-10-14","arxiv_id":"2310.09639","n_code_links":1,"syntology":{"ran":8,"of":17,"n_ran_checked":6,"n_instrument":2,"unverified":9,"pointer_only":3,"phrase":"8 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; 2 where Syntology's instrument failed) · 9 unverified","official":{"repos":["liang137/dpzero"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":9,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"efficient-model-agnostic-multi-group","title":"Efficient Model-Agnostic Multi-Group Equivariant Networks","date":"2023-10-14","arxiv_id":"2310.09675","n_code_links":0,"syntology":null},{"paper":"/paper/instruction-tuning-with-human-curriculum","slug":"instruction-tuning-with-human-curriculum","title":"Instruction Tuning with Human Curriculum","date":"2023-10-14","arxiv_id":"2310.09518","n_code_links":1,"syntology":null},{"paper":null,"slug":"leveraging-generative-ai-improving-software","title":"Leveraging Generative AI: Improving Software Metadata Classification with Generated Code-Comment Pairs","date":"2023-10-14","arxiv_id":"2311.03365","n_code_links":0,"syntology":null},{"paper":null,"slug":"topology-guided-hypergraph-transformer","title":"Topology-guided Hypergraph Transformer Network: Unveiling Structural Insights for Improved Representation","date":"2023-10-14","arxiv_id":"2310.09657","n_code_links":0,"syntology":null},{"paper":"/paper/uniqa-a-unified-framework-for-both-full","slug":"uniqa-a-unified-framework-for-both-full","title":"You Only Train Once: A Unified Framework for Both Full-Reference and No-Reference Image Quality Assessment","date":"2023-10-14","arxiv_id":"2310.09560","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-comparative-analysis-of-task-agnostic","title":"A Comparative Analysis of Task-Agnostic Distillation Methods for Compressing Transformer Language Models","date":"2023-10-13","arxiv_id":"2310.08797","n_code_links":0,"syntology":null},{"paper":"/paper/a-systematic-evaluation-of-large-language-1","slug":"a-systematic-evaluation-of-large-language-1","title":"Assessing and Enhancing the Robustness of Large Language Models with Task Structure Variations for Logical Reasoning","date":"2023-10-13","arxiv_id":"2310.09430","n_code_links":1,"syntology":{"ran":6,"of":8,"n_ran_checked":6,"n_instrument":0,"unverified":2,"pointer_only":1,"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) · 2 unverified","official":{"repos":["strong-ai-lab/logical-and-abstract-reasoning"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"automated-claim-matching-with-large-language","title":"Automated Claim Matching with Large Language Models: Empowering Fact-Checkers in the Fight Against Misinformation","date":"2023-10-13","arxiv_id":"2310.09223","n_code_links":0,"syntology":null},{"paper":null,"slug":"ddmt-denoising-diffusion-mask-transformer","title":"DDMT: Denoising Diffusion Mask Transformer Models for Multivariate Time Series Anomaly Detection","date":"2023-10-13","arxiv_id":"2310.08800","n_code_links":0,"syntology":null},{"paper":null,"slug":"distance-rank-aware-sequential-reward","title":"Distance-rank Aware Sequential Reward Learning for Inverse Reinforcement Learning with Sub-optimal Demonstrations","date":"2023-10-13","arxiv_id":"2310.08823","n_code_links":0,"syntology":null},{"paper":"/paper/dont-add-dont-miss-effective-content","slug":"dont-add-dont-miss-effective-content","title":"Dont Add, dont Miss: Effective Content Preserving Generation from Pre-Selected Text Spans","date":"2023-10-13","arxiv_id":"2310.09017","n_code_links":1,"syntology":{"ran":4,"of":5,"n_ran_checked":4,"n_instrument":0,"unverified":1,"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) · 1 unverified","official":{"repos":["lovodkin93/cdr_ctr"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"enhancing-bert-based-visual-question","title":"Enhancing BERT-Based Visual Question Answering through Keyword-Driven Sentence Selection","date":"2023-10-13","arxiv_id":"2310.09432","n_code_links":0,"syntology":null},{"paper":"/paper/faster-3d-cardiac-ct-segmentation-with-vision","slug":"faster-3d-cardiac-ct-segmentation-with-vision","title":"Vision Transformers increase efficiency of 3D cardiac CT multi-label segmentation","date":"2023-10-13","arxiv_id":"2310.09099","n_code_links":1,"syntology":null},{"paper":"/paper/from-clip-to-dino-visual-encoders-shout-in","slug":"from-clip-to-dino-visual-encoders-shout-in","title":"From CLIP to DINO: Visual Encoders Shout in Multi-modal Large Language Models","date":"2023-10-13","arxiv_id":"2310.08825","n_code_links":1,"syntology":null},{"paper":null,"slug":"from-words-and-exercises-to-wellness-farsi","title":"From Words and Exercises to Wellness: Farsi Chatbot for Self-Attachment Technique","date":"2023-10-13","arxiv_id":"2310.09362","n_code_links":0,"syntology":null},{"paper":"/paper/glore-evaluating-logical-reasoning-of-large","slug":"glore-evaluating-logical-reasoning-of-large","title":"GLoRE: Evaluating Logical Reasoning of Large Language Models","date":"2023-10-13","arxiv_id":"2310.09107","n_code_links":1,"syntology":null},{"paper":"/paper/human-in-the-loop-machine-translation-with","slug":"human-in-the-loop-machine-translation-with","title":"Human-in-the-loop Machine Translation with Large Language Model","date":"2023-10-13","arxiv_id":"2310.08908","n_code_links":1,"syntology":null},{"paper":"/paper/pali-3-vision-language-models-smaller-faster","slug":"pali-3-vision-language-models-smaller-faster","title":"PaLI-3 Vision Language Models: Smaller, Faster, Stronger","date":"2023-10-13","arxiv_id":"2310.09199","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 3 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":"/paper/retrieval-generation-alignment-for-end-to-end","slug":"retrieval-generation-alignment-for-end-to-end","title":"Retrieval-Generation Alignment for End-to-End Task-Oriented Dialogue System","date":"2023-10-13","arxiv_id":"2310.08877","n_code_links":1,"syntology":null},{"paper":null,"slug":"table-gpt-table-tuned-gpt-for-diverse-table","title":"Table-GPT: Table-tuned GPT for Diverse Table Tasks","date":"2023-10-13","arxiv_id":"2310.09263","n_code_links":0,"syntology":null},{"paper":"/paper/towards-end-to-end-4-bit-inference-on","slug":"towards-end-to-end-4-bit-inference-on","title":"QUIK: Towards End-to-End 4-Bit Inference on Generative Large Language Models","date":"2023-10-13","arxiv_id":"2310.09259","n_code_links":1,"syntology":{"ran":9,"of":13,"n_ran_checked":9,"n_instrument":0,"unverified":4,"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) · 4 unverified","official":{"repos":["ist-daslab/quik"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/towards-example-based-nmt-with-multi","slug":"towards-example-based-nmt-with-multi","title":"Towards Example-Based NMT with Multi-Levenshtein Transformers","date":"2023-10-13","arxiv_id":"2310.08967","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"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) · 0 unverified","official":{"repos":["maxwell1447/fairseq"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"age-estimation-based-on-graph-convolutional","title":"Age Estimation Based on Graph Convolutional Networks and Multi-head Attention Mechanisms","date":"2023-10-12","arxiv_id":"2310.08064","n_code_links":0,"syntology":null},{"paper":null,"slug":"analyzing-textual-data-for-fatality","title":"Analyzing Textual Data for Fatality Classification in Afghanistan's Armed Conflicts: A BERT Approach","date":"2023-10-12","arxiv_id":"2310.08653","n_code_links":0,"syntology":null},{"paper":null,"slug":"can-gpt-models-be-financial-analysts-an","title":"Can GPT models be Financial Analysts? An Evaluation of ChatGPT and GPT-4 on mock CFA Exams","date":"2023-10-12","arxiv_id":"2310.08678","n_code_links":0,"syntology":null},{"paper":null,"slug":"can-large-language-models-really-improve-by","title":"Can Large Language Models Really Improve by Self-critiquing Their Own Plans?","date":"2023-10-12","arxiv_id":"2310.08118","n_code_links":0,"syntology":null},{"paper":"/paper/covid-19-detection-using-swin-transformer","slug":"covid-19-detection-using-swin-transformer","title":"COVID-19 detection using ViT transformer-based approach from Computed Tomography Images","date":"2023-10-12","arxiv_id":"2310.08165","n_code_links":1,"syntology":null},{"paper":null,"slug":"cross-episodic-curriculum-for-transformer","title":"Cross-Episodic Curriculum for Transformer Agents","date":"2023-10-12","arxiv_id":"2310.08549","n_code_links":0,"syntology":null},{"paper":null,"slug":"detection-and-prediction-of-clopidogrel","title":"Detection and prediction of clopidogrel treatment failures using longitudinal structured electronic health records","date":"2023-10-12","arxiv_id":"2310.08757","n_code_links":0,"syntology":null},{"paper":null,"slug":"do-pretrained-transformers-really-learn-in","title":"Do pretrained Transformers Learn In-Context by Gradient Descent?","date":"2023-10-12","arxiv_id":"2310.08540","n_code_links":0,"syntology":null},{"paper":"/paper/evaluating-the-effectiveness-of-capsule","slug":"evaluating-the-effectiveness-of-capsule","title":"Evaluating The Effectiveness of Capsule Neural Network in Toxic Comment Classification using Pre-trained BERT Embeddings","date":"2023-10-12","arxiv_id":null,"n_code_links":1,"syntology":null}],"record_sha256":"b2c9b228fae3124d0fe1c3494347c958f139f16c3d403929a3077b699bf50caa","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}