{"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":"/task/benchmarking/papers/44","list_of":"/task/benchmarking","task":"Benchmarking","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":44,"pages_in_order":56,"rows_per_page":100,"rows":[4301,4400],"of":5548,"counts":{"archive_papers_tagged":5548,"with_a_code_link":2658,"where_syntology_ran_a_sample":749,"not_listed_spam_title":0,"listed":5548,"listed_where_code_ran":749,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":624,"every_run_a_failure_of_syntologys_instrument":125,"listed_with_a_run_with_no_instrument_failure":624,"listed_every_run_a_failure_of_syntologys_instrument":125,"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":"/task/benchmarking","prev":"/task/benchmarking/papers/43","next":"/task/benchmarking/papers/45","papers":[{"url":null,"slug":"enhancing-navigation-benchmarking-and","title":"Enhancing Navigation Benchmarking and Perception Data Generation for Row-based Crops in Simulation","date":"2023-06-27","arxiv_id":"2306.15517","repositories_listed":0,"syntology":null},{"url":null,"slug":"paradigm-shift-in-sustainability-disclosure","title":"Paradigm Shift in Sustainability Disclosure Analysis: Empowering Stakeholders with CHATREPORT, a Language Model-Based Tool","date":"2023-06-27","arxiv_id":"2306.15518","repositories_listed":0,"syntology":null},{"url":null,"slug":"pulse-shape-aided-multipath-delay-estimation","title":"Pulse Shape-Aided Multipath Delay Estimation for Fine-Grained WiFi Sensing","date":"2023-06-27","arxiv_id":"2306.15320","repositories_listed":0,"syntology":null},{"url":null,"slug":"hybrid-precoder-and-combiner-designs-for","title":"Hybrid Precoder and Combiner Designs for Decentralized Parameter Estimation in mmWave MIMO Wireless Sensor Networks","date":"2023-06-25","arxiv_id":"2306.14301","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-reference-based-distinctive-image","title":"Improving Reference-based Distinctive Image Captioning with Contrastive Rewards","date":"2023-06-25","arxiv_id":"2306.14259","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-comprehensive-study-on-the-robustness-of","title":"A Comprehensive Study on the Robustness of Image Classification and Object Detection in Remote Sensing: Surveying and Benchmarking","date":"2023-06-21","arxiv_id":"2306.12111","repositories_listed":0,"syntology":null},{"url":null,"slug":"evaluation-of-popular-xai-applied-to-clinical","title":"Evaluation of Popular XAI Applied to Clinical Prediction Models: Can They be Trusted?","date":"2023-06-21","arxiv_id":"2306.11985","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-evaluation-of-document-classification","title":"On Evaluation of Document Classification using RVL-CDIP","date":"2023-06-21","arxiv_id":"2306.12550","repositories_listed":0,"syntology":null},{"url":null,"slug":"diverse-community-data-for-benchmarking-data","title":"Diverse Community Data for Benchmarking Data Privacy Algorithms","date":"2023-06-20","arxiv_id":"2306.13216","repositories_listed":0,"syntology":null},{"url":null,"slug":"benchmarking-robustness-of-deep-reinforcement","title":"Benchmarking Robustness of Deep Reinforcement Learning approaches to Online Portfolio Management","date":"2023-06-19","arxiv_id":"2306.10950","repositories_listed":0,"syntology":null},{"url":null,"slug":"fairness-index-measures-to-evaluate-bias-in","title":"Fairness Index Measures to Evaluate Bias in Biometric Recognition","date":"2023-06-19","arxiv_id":"2306.10919","repositories_listed":0,"syntology":null},{"url":null,"slug":"formal-covariate-benchmarking-to-bound","title":"Formal Covariate Benchmarking to Bound Omitted Variable Bias","date":"2023-06-18","arxiv_id":"2306.10562","repositories_listed":0,"syntology":null},{"url":null,"slug":"ma-bbob-many-affine-combinations-of-bbob","title":"MA-BBOB: Many-Affine Combinations of BBOB Functions for Evaluating AutoML Approaches in Noiseless Numerical Black-Box Optimization Contexts","date":"2023-06-18","arxiv_id":"2306.10627","repositories_listed":0,"syntology":null},{"url":null,"slug":"benchmarking-deep-learning-architectures-for","title":"Benchmarking Deep Learning Architectures for Urban Vegetation Point Cloud Semantic Segmentation from MLS","date":"2023-06-17","arxiv_id":"2306.10274","repositories_listed":0,"syntology":null},{"url":null,"slug":"alp-action-aware-embodied-learning-for","title":"ALP: Action-Aware Embodied Learning for Perception","date":"2023-06-16","arxiv_id":"2306.10190","repositories_listed":0,"syntology":null},{"url":null,"slug":"diplomat-a-dialogue-dataset-for-situated","title":"DiPlomat: A Dialogue Dataset for Situated Pragmatic Reasoning","date":"2023-06-15","arxiv_id":"2306.09030","repositories_listed":0,"syntology":null},{"url":null,"slug":"disc-a-dataset-for-integrated-sensing-and","title":"DISC: a Dataset for Integrated Sensing and Communication in mmWave Systems","date":"2023-06-15","arxiv_id":"2306.09469","repositories_listed":0,"syntology":null},{"url":null,"slug":"large-scale-quantum-separability-through-a","title":"Large-Scale Quantum Separability Through a Reproducible Machine Learning Lens","date":"2023-06-15","arxiv_id":"2306.09444","repositories_listed":0,"syntology":null},{"url":null,"slug":"revealing-the-illusion-of-joint-multimodal","title":"Dissecting Multimodality in VideoQA Transformer Models by Impairing Modality Fusion","date":"2023-06-15","arxiv_id":"2306.08889","repositories_listed":0,"syntology":null},{"url":null,"slug":"rrsis-referring-remote-sensing-image","title":"RRSIS: Referring Remote Sensing Image Segmentation","date":"2023-06-14","arxiv_id":"2306.08625","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-cloud-based-machine-learning-pipeline-for","title":"A Cloud-based Machine Learning Pipeline for the Efficient Extraction of Insights from Customer Reviews","date":"2023-06-13","arxiv_id":"2306.07786","repositories_listed":0,"syntology":null},{"url":null,"slug":"contribution-a-l-optimisation-d-un","title":"Contribution à l'Optimisation d'un Comportement Collectif pour un Groupe de Robots Autonomes","date":"2023-06-10","arxiv_id":"2306.06527","repositories_listed":0,"syntology":null},{"url":"/paper/benchmarking-self-supervised-video","slug":"benchmarking-self-supervised-video","title":"A Large-Scale Analysis on Self-Supervised Video Representation Learning","date":"2023-06-09","arxiv_id":"2306.06010","repositories_listed":0,"syntology":null},{"url":null,"slug":"public-transit-demand-prediction-during","title":"Share, Collaborate, Benchmark: Advancing Travel Demand Research through rigorous open-source collaboration","date":"2023-06-09","arxiv_id":"2306.06194","repositories_listed":0,"syntology":null},{"url":null,"slug":"fledge-benchmarking-federated-machine","title":"FLEdge: Benchmarking Federated Machine Learning Applications in Edge Computing Systems","date":"2023-06-08","arxiv_id":"2306.05172","repositories_listed":0,"syntology":null},{"url":null,"slug":"benchmarking-foundation-models-with-language","title":"Benchmarking Foundation Models with Language-Model-as-an-Examiner","date":"2023-06-07","arxiv_id":"2306.04181","repositories_listed":0,"syntology":null},{"url":null,"slug":"icon-2-reliably-benchmarking-predictive","title":"ICON$^2$: Reliably Benchmarking Predictive Inequity in Object Detection","date":"2023-06-07","arxiv_id":"2306.04482","repositories_listed":0,"syntology":null},{"url":null,"slug":"improved-statistical-benchmarking-of-digital","title":"Improved statistical benchmarking of digital pathology models using pairwise frames evaluation","date":"2023-06-07","arxiv_id":"2306.04709","repositories_listed":0,"syntology":null},{"url":null,"slug":"rd-suite-a-benchmark-for-ranking-distillation","title":"RD-Suite: A Benchmark for Ranking Distillation","date":"2023-06-07","arxiv_id":"2306.04455","repositories_listed":0,"syntology":null},{"url":null,"slug":"applying-standards-to-advance-upstream","title":"Applying Standards to Advance Upstream & Downstream Ethics in Large Language Models","date":"2023-06-06","arxiv_id":"2306.03503","repositories_listed":0,"syntology":null},{"url":null,"slug":"benchmarking-robustness-of-ai-enabled-multi","title":"Benchmarking Robustness of AI-Enabled Multi-sensor Fusion Systems: Challenges and Opportunities","date":"2023-06-06","arxiv_id":"2306.03454","repositories_listed":0,"syntology":null},{"url":null,"slug":"explainable-ai-using-expressive-boolean","title":"Explainable AI using expressive Boolean formulas","date":"2023-06-06","arxiv_id":"2306.03976","repositories_listed":0,"syntology":null},{"url":null,"slug":"financial-numeric-extreme-labelling-a-dataset","title":"Financial Numeric Extreme Labelling: A Dataset and Benchmarking for XBRL Tagging","date":"2023-06-06","arxiv_id":"2306.03723","repositories_listed":0,"syntology":null},{"url":null,"slug":"n-shot-benchmarking-of-whisper-on-diverse","title":"N-Shot Benchmarking of Whisper on Diverse Arabic Speech Recognition","date":"2023-06-05","arxiv_id":"2306.02902","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficientsrface-an-efficient-network-with","title":"EfficientSRFace: An Efficient Network with Super-Resolution Enhancement for Accurate Face Detection","date":"2023-06-04","arxiv_id":"2306.02277","repositories_listed":0,"syntology":null},{"url":null,"slug":"moviepuzzle-visual-narrative-reasoning","title":"MoviePuzzle: Visual Narrative Reasoning through Multimodal Order Learning","date":"2023-06-04","arxiv_id":"2306.02252","repositories_listed":0,"syntology":null},{"url":"/paper/aci-bench-a-novel-ambient-clinical","slug":"aci-bench-a-novel-ambient-clinical","title":"ACI-BENCH: a Novel Ambient Clinical Intelligence Dataset for Benchmarking Automatic Visit Note Generation","date":"2023-06-03","arxiv_id":"2306.02022","repositories_listed":0,"syntology":null},{"url":null,"slug":"benchmarking-robustness-of-adaptation-methods","title":"Benchmarking Robustness of Adaptation Methods on Pre-trained Vision-Language Models","date":"2023-06-03","arxiv_id":"2306.02080","repositories_listed":0,"syntology":null},{"url":null,"slug":"leveraging-the-triple-exponential-moving","title":"Break a Lag: Triple Exponential Moving Average for Enhanced Optimization","date":"2023-06-02","arxiv_id":"2306.01423","repositories_listed":0,"syntology":null},{"url":null,"slug":"hybrid-long-document-summarization-using-c2f","title":"Hybrid Long Document Summarization using C2F-FAR and ChatGPT: A Practical Study","date":"2023-06-01","arxiv_id":"2306.01169","repositories_listed":0,"syntology":null},{"url":null,"slug":"hyspecnet-11k-a-large-scale-hyperspectral","title":"HySpecNet-11k: A Large-Scale Hyperspectral Dataset for Benchmarking Learning-Based Hyperspectral Image Compression Methods","date":"2023-06-01","arxiv_id":"2306.00385","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-brain-tumor-segmentation-brats-mets","title":"The Brain Tumor Segmentation (BraTS-METS) Challenge 2023: Brain Metastasis Segmentation on Pre-treatment MRI","date":"2023-06-01","arxiv_id":"2306.00838","repositories_listed":0,"syntology":null},{"url":"/paper/the-objectfolder-benchmark-multisensory-1","slug":"the-objectfolder-benchmark-multisensory-1","title":"The ObjectFolder Benchmark: Multisensory Learning with Neural and Real Objects","date":"2023-06-01","arxiv_id":"2306.00956","repositories_listed":0,"syntology":null},{"url":null,"slug":"human-body-shape-classification-based-on-a","title":"Human Body Shape Classification Based on a Single Image","date":"2023-05-29","arxiv_id":"2305.18480","repositories_listed":0,"syntology":null},{"url":null,"slug":"benchmarking-diverse-modal-entity-linking","title":"Benchmarking Diverse-Modal Entity Linking with Generative Models","date":"2023-05-27","arxiv_id":"2305.17337","repositories_listed":0,"syntology":null},{"url":null,"slug":"continually-updating-generative-retrieval-on","title":"Exploring the Practicality of Generative Retrieval on Dynamic Corpora","date":"2023-05-27","arxiv_id":"2305.18952","repositories_listed":0,"syntology":null},{"url":null,"slug":"benchmarking-state-of-the-art-gradient","title":"Benchmarking state-of-the-art gradient boosting algorithms for classification","date":"2023-05-26","arxiv_id":"2305.17094","repositories_listed":0,"syntology":null},{"url":null,"slug":"analysis-of-modular-cma-es-on-strict-box","title":"Analysis of modular CMA-ES on strict box-constrained problems in the SBOX-COST benchmarking suite","date":"2023-05-24","arxiv_id":"2305.15102","repositories_listed":0,"syntology":null},{"url":null,"slug":"barkour-benchmarking-animal-level-agility","title":"Barkour: Benchmarking Animal-level Agility with Quadruped Robots","date":"2023-05-24","arxiv_id":"2305.14654","repositories_listed":0,"syntology":null},{"url":null,"slug":"benchmarking-arabic-ai-with-large-language","title":"LAraBench: Benchmarking Arabic AI with Large Language Models","date":"2023-05-24","arxiv_id":"2305.14982","repositories_listed":0,"syntology":null},{"url":null,"slug":"buffet-benchmarking-large-language-models-for","title":"BUFFET: Benchmarking Large Language Models for Few-shot Cross-lingual Transfer","date":"2023-05-24","arxiv_id":"2305.14857","repositories_listed":0,"syntology":null},{"url":null,"slug":"domain-expanded-aste-rethinking","title":"Domain-Expanded ASTE: Rethinking Generalization in Aspect Sentiment Triplet Extraction","date":"2023-05-23","arxiv_id":"2305.14434","repositories_listed":0,"syntology":null},{"url":null,"slug":"multilingual-large-language-models-are-not","title":"Multilingual Large Language Models Are Not (Yet) Code-Switchers","date":"2023-05-23","arxiv_id":"2305.14235","repositories_listed":0,"syntology":null},{"url":null,"slug":"r2h-building-multimodal-navigation-helpers","title":"R2H: Building Multimodal Navigation Helpers that Respond to Help Requests","date":"2023-05-23","arxiv_id":"2305.14260","repositories_listed":0,"syntology":null},{"url":null,"slug":"can-chatgpt-defend-the-truth-automatic","title":"Can ChatGPT Defend its Belief in Truth? Evaluating LLM Reasoning via Debate","date":"2023-05-22","arxiv_id":"2305.13160","repositories_listed":0,"syntology":null},{"url":null,"slug":"value-at-risk-based-portfolio-insurance","title":"Value-at-Risk-Based Portfolio Insurance: Performance Evaluation and Benchmarking Against CPPI in a Markov-Modulated Regime-Switching Market","date":"2023-05-21","arxiv_id":"2305.12539","repositories_listed":0,"syntology":null},{"url":null,"slug":"patterns-of-convergence-and-bound-constraint","title":"Patterns of Convergence and Bound Constraint Violation in Differential Evolution on SBOX-COST Benchmarking Suite","date":"2023-05-20","arxiv_id":"2305.12221","repositories_listed":0,"syntology":null},{"url":null,"slug":"teler-a-general-taxonomy-of-llm-prompts-for","title":"TELeR: A General Taxonomy of LLM Prompts for Benchmarking Complex Tasks","date":"2023-05-19","arxiv_id":"2305.11430","repositories_listed":0,"syntology":null},{"url":null,"slug":"ahead-of-time-p-tuning","title":"Ahead-of-Time P-Tuning","date":"2023-05-18","arxiv_id":"2305.10835","repositories_listed":0,"syntology":null},{"url":null,"slug":"benchmarking-deep-learning-frameworks-for","title":"Benchmarking Deep Learning Frameworks for Automated Diagnosis of Ocular Toxoplasmosis: A Comprehensive Approach to Classification and Segmentation","date":"2023-05-18","arxiv_id":"2305.10975","repositories_listed":0,"syntology":null},{"url":null,"slug":"boost-vision-transformer-with-gpu-friendly-1","title":"Boost Vision Transformer with GPU-Friendly Sparsity and Quantization","date":"2023-05-18","arxiv_id":"2305.10727","repositories_listed":0,"syntology":null},{"url":null,"slug":"numeric-magnitude-comparison-effects-in-large","title":"Human Behavioral Benchmarking: Numeric Magnitude Comparison Effects in Large Language Models","date":"2023-05-18","arxiv_id":"2305.10782","repositories_listed":0,"syntology":null},{"url":"/paper/restoring-images-captured-in-arbitrary-hybrid","slug":"restoring-images-captured-in-arbitrary-hybrid","title":"Restoring Images Captured in Arbitrary Hybrid Adverse Weather Conditions in One Go","date":"2023-05-17","arxiv_id":"2305.09996","repositories_listed":0,"syntology":null},{"url":null,"slug":"smiling-women-pitching-down-auditing","title":"Smiling Women Pitching Down: Auditing Representational and Presentational Gender Biases in Image Generative AI","date":"2023-05-17","arxiv_id":"2305.10566","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-more-robust-nlp-system-evaluation","title":"Towards More Robust NLP System Evaluation: Handling Missing Scores in Benchmarks","date":"2023-05-17","arxiv_id":"2305.10284","repositories_listed":0,"syntology":null},{"url":null,"slug":"dlue-benchmarking-document-language","title":"DLUE: Benchmarking Document Language Understanding","date":"2023-05-16","arxiv_id":"2305.09520","repositories_listed":0,"syntology":null},{"url":null,"slug":"benchmarking-the-human-brain-against","title":"Benchmarking the human brain against computational architectures","date":"2023-05-15","arxiv_id":"2305.14363","repositories_listed":0,"syntology":null},{"url":null,"slug":"ood-speech-a-large-bengali-speech-recognition","title":"OOD-Speech: A Large Bengali Speech Recognition Dataset for Out-of-Distribution Benchmarking","date":"2023-05-15","arxiv_id":"2305.09688","repositories_listed":0,"syntology":null},{"url":null,"slug":"predictive-models-from-quantum-computer","title":"Predictive Models from Quantum Computer Benchmarks","date":"2023-05-15","arxiv_id":"2305.08796","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-strong-sustainability-paradigm-based","title":"A Strong Sustainability Paradigm Based Analytical Hierarchy Process (SSP-AHP) Method to Evaluate Sustainable Healthcare Systems","date":"2023-05-13","arxiv_id":"2306.00718","repositories_listed":0,"syntology":null},{"url":null,"slug":"medgpteval-a-dataset-and-benchmark-to","title":"MedGPTEval: A Dataset and Benchmark to Evaluate Responses of Large Language Models in Medicine","date":"2023-05-12","arxiv_id":"2305.07340","repositories_listed":0,"syntology":null},{"url":null,"slug":"search-for-the-ugle-truth-an-investigation","title":"Uncertainty in GNN Learning Evaluations: The Importance of a Consistent Benchmark for Community Detection","date":"2023-05-10","arxiv_id":"2305.06026","repositories_listed":0,"syntology":null},{"url":null,"slug":"comparing-foundation-models-using-data","title":"Comparing Foundation Models using Data Kernels","date":"2023-05-09","arxiv_id":"2305.05126","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-comprehensive-study-on-dataset-distillation","title":"A Comprehensive Study on Dataset Distillation: Performance, Privacy, Robustness and Fairness","date":"2023-05-05","arxiv_id":"2305.03355","repositories_listed":0,"syntology":null},{"url":null,"slug":"how-segment-anything-model-sam-boost-medical","title":"Towards Segment Anything Model (SAM) for Medical Image Segmentation: A Survey","date":"2023-05-05","arxiv_id":"2305.03678","repositories_listed":0,"syntology":null},{"url":null,"slug":"semantic-segmentation-using-vision","title":"Semantic Segmentation using Vision Transformers: A survey","date":"2023-05-05","arxiv_id":"2305.03273","repositories_listed":0,"syntology":null},{"url":null,"slug":"analyzing-hong-kong-s-legal-judgments-from-a","title":"Analyzing Hong Kong's Legal Judgments from a Computational Linguistics point-of-view","date":"2023-05-04","arxiv_id":"2305.02558","repositories_listed":0,"syntology":null},{"url":null,"slug":"language-time-preferences-and-consumer","title":"Can LLMs Capture Human Preferences?","date":"2023-05-04","arxiv_id":"2305.02531","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-simulation-augmented-benchmarking-framework","title":"A Simulation-Augmented Benchmarking Framework for Automatic RSO Streak Detection in Single-Frame Space Images","date":"2023-04-30","arxiv_id":"2305.00412","repositories_listed":0,"syntology":null},{"url":null,"slug":"benchmarking-automated-machine-learning","title":"Benchmarking Automated Machine Learning Methods for Price Forecasting Applications","date":"2023-04-28","arxiv_id":"2304.14735","repositories_listed":0,"syntology":null},{"url":null,"slug":"chatgpt-vs-state-of-the-art-models-a","title":"ChatGPT vs State-of-the-Art Models: A Benchmarking Study in Keyphrase Generation Task","date":"2023-04-27","arxiv_id":"2304.14177","repositories_listed":0,"syntology":null},{"url":null,"slug":"scalable-distributed-ai-frameworks-leveraging","title":"Scalable, Distributed AI Frameworks: Leveraging Cloud Computing for Enhanced Deep Learning Performance and Efficiency","date":"2023-04-26","arxiv_id":"2304.13738","repositories_listed":0,"syntology":null},{"url":null,"slug":"cimla-interpretable-ai-for-inference-of","title":"CIMLA: Interpretable AI for inference of differential causal networks","date":"2023-04-25","arxiv_id":"2304.12523","repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-synthetic-image-refinement-via","title":"Unsupervised Synthetic Image Refinement via Contrastive Learning and Consistent Semantic-Structural Constraints","date":"2023-04-25","arxiv_id":"2304.12591","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-framework-for-benchmarking-real-time","title":"A Framework for Benchmarking Real-Time Embedded Object Detection","date":"2023-04-23","arxiv_id":"2304.11580","repositories_listed":0,"syntology":null},{"url":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","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-a-quantum-computer-s-capability","title":"Learning a quantum computer's capability","date":"2023-04-20","arxiv_id":"2304.10650","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-a-benchmark-for-scientific","title":"Towards a Benchmark for Scientific Understanding in Humans and Machines","date":"2023-04-20","arxiv_id":"2304.10327","repositories_listed":0,"syntology":null},{"url":null,"slug":"computational-and-exploratory-landscape","title":"Computational and Exploratory Landscape Analysis of the GKLS Generator","date":"2023-04-18","arxiv_id":"2304.08913","repositories_listed":0,"syntology":null},{"url":null,"slug":"udtiri-an-open-source-road-pothole-detection","title":"UDTIRI: An Online Open-Source Intelligent Road Inspection Benchmark Suite","date":"2023-04-18","arxiv_id":"2304.08842","repositories_listed":0,"syntology":null},{"url":null,"slug":"ood-cv-v2-an-extended-benchmark-for","title":"OOD-CV-v2: An extended Benchmark for Robustness to Out-of-Distribution Shifts of Individual Nuisances in Natural Images","date":"2023-04-17","arxiv_id":"2304.10266","repositories_listed":0,"syntology":null},{"url":null,"slug":"dialogue-games-for-benchmarking-language","title":"Dialogue Games for Benchmarking Language Understanding: Motivation, Taxonomy, Strategy","date":"2023-04-14","arxiv_id":"2304.07007","repositories_listed":0,"syntology":null},{"url":null,"slug":"benchmarking-the-physical-world-adversarial","title":"Benchmarking the Physical-world Adversarial Robustness of Vehicle Detection","date":"2023-04-11","arxiv_id":"2304.05098","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-items-and-contexts-understanding","title":"Improving Items and Contexts Understanding with Descriptive Graph for Conversational Recommendation","date":"2023-04-11","arxiv_id":"2304.09093","repositories_listed":0,"syntology":null},{"url":"/paper/on-evaluation-of-bangla-word-analogies","slug":"on-evaluation-of-bangla-word-analogies","title":"On Evaluation of Bangla Word Analogies","date":"2023-04-10","arxiv_id":"2304.04613","repositories_listed":0,"syntology":{"n":11,"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":11,"phrase":"7 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; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/on-evaluation-of-bangla-word-analogies#ran","syntology_url":"https://syntology.ai/paper/2304.04613","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.04613"}},"official":null}},{"url":null,"slug":"foramvit-gan-exploring-new-paradigms-in-deep","title":"ForamViT-GAN: Exploring New Paradigms in Deep Learning for Micropaleontological Image Analysis","date":"2023-04-09","arxiv_id":"2304.04291","repositories_listed":0,"syntology":null},{"url":null,"slug":"benchmarking-the-robustness-of-quantized","title":"Benchmarking the Robustness of Quantized Models","date":"2023-04-08","arxiv_id":"2304.03968","repositories_listed":0,"syntology":null},{"url":null,"slug":"drac-diabetic-retinopathy-analysis-challenge","title":"DRAC: Diabetic Retinopathy Analysis Challenge with Ultra-Wide Optical Coherence Tomography Angiography Images","date":"2023-04-05","arxiv_id":"2304.02389","repositories_listed":0,"syntology":null},{"url":null,"slug":"opencontrails-benchmarking-contrail-detection","title":"OpenContrails: Benchmarking Contrail Detection on GOES-16 ABI","date":"2023-04-04","arxiv_id":"2304.02122","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-latent-fingerprint-in-the-wild-database","title":"A Latent Fingerprint in the Wild Database","date":"2023-04-03","arxiv_id":"2304.00979","repositories_listed":0,"syntology":null}],"record_sha256":"bb3624b0feaf45f38419d9062af192bb2240b5102d5f811041c0fa6cd19362a6","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}