{"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/dropout/papers/47","list_of":"/method/dropout","method":"Dropout","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":47,"pages_in_order":275,"rows_per_page":100,"rows":[4601,4700],"of":27472,"counts":{"archive_papers_tagged":27472,"with_a_code_link":12129,"where_syntology_ran_a_sample":3620,"not_listed_spam_title":0,"listed":27472,"listed_where_code_ran":3620,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":3044,"every_run_a_failure_of_syntologys_instrument":576,"listed_with_a_run_with_no_instrument_failure":3044,"listed_every_run_a_failure_of_syntologys_instrument":576,"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/dropout","prev":"/method/dropout/papers/46","next":"/method/dropout/papers/48","papers":[{"paper":null,"slug":"financial-sentiment-analysis-on-news-and","title":"Financial Sentiment Analysis on News and Reports Using Large Language Models and FinBERT","date":"2024-10-02","arxiv_id":"2410.01987","n_code_links":0,"syntology":null},{"paper":"/paper/flashmask-efficient-and-rich-mask-extension","slug":"flashmask-efficient-and-rich-mask-extension","title":"FlashMask: Efficient and Rich Mask Extension of FlashAttention","date":"2024-10-02","arxiv_id":"2410.01359","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"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) · 0 unverified","official":{"repos":["PaddlePaddle/Paddle"],"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":"getting-free-bits-back-from-rotational","title":"Getting Free Bits Back from Rotational Symmetries in LLMs","date":"2024-10-02","arxiv_id":"2410.01309","n_code_links":0,"syntology":null},{"paper":null,"slug":"house-of-cards-massive-weights-in-llms","title":"House of Cards: Massive Weights in LLMs","date":"2024-10-02","arxiv_id":"2410.01866","n_code_links":0,"syntology":null},{"paper":"/paper/marple-a-benchmark-for-long-horizon-inference","slug":"marple-a-benchmark-for-long-horizon-inference","title":"MARPLE: A Benchmark for Long-Horizon Inference","date":"2024-10-02","arxiv_id":"2410.01926","n_code_links":1,"syntology":{"ran":6,"of":6,"n_ran_checked":6,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["marple-benchmark/marple"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/mind-scramble-unveiling-large-language-model","slug":"mind-scramble-unveiling-large-language-model","title":"Mind Scramble: Unveiling Large Language Model Psychology Via Typoglycemia","date":"2024-10-02","arxiv_id":"2410.01677","n_code_links":1,"syntology":null},{"paper":"/paper/normalizing-flow-based-metric-for-image","slug":"normalizing-flow-based-metric-for-image","title":"Normalizing Flow-Based Metric for Image Generation","date":"2024-10-02","arxiv_id":"2410.02004","n_code_links":1,"syntology":null},{"paper":null,"slug":"on-the-adaptation-of-unlimiformer-for-decoder","title":"On The Adaptation of Unlimiformer for Decoder-Only Transformers","date":"2024-10-02","arxiv_id":"2410.01637","n_code_links":0,"syntology":null},{"paper":"/paper/open-rag-enhanced-retrieval-augmented","slug":"open-rag-enhanced-retrieval-augmented","title":"Open-RAG: Enhanced Retrieval-Augmented Reasoning with Open-Source Large Language Models","date":"2024-10-02","arxiv_id":"2410.01782","n_code_links":1,"syntology":null},{"paper":"/paper/quantifying-generalization-complexity-for","slug":"quantifying-generalization-complexity-for","title":"Quantifying Generalization Complexity for Large Language Models","date":"2024-10-02","arxiv_id":"2410.01769","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":4,"n_instrument":0,"unverified":0,"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) · 0 unverified","official":{"repos":["zhentingqi/scylla"],"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":"radar-robust-two-stage-modality-incomplete","title":"RADAR: Robust Two-stage Modality-incomplete Industrial Anomaly Detection","date":"2024-10-02","arxiv_id":"2410.01737","n_code_links":0,"syntology":null},{"paper":null,"slug":"rs-fme-swint-a-novel-feature-map-enhancement","title":"RS-FME-SwinT: A Novel Feature Map Enhancement Framework Integrating Customized SwinT with Residual and Spatial CNN for Monkeypox Diagnosis","date":"2024-10-02","arxiv_id":"2410.01216","n_code_links":0,"syntology":null},{"paper":"/paper/saliency-guided-detr-for-moment-retrieval-and","slug":"saliency-guided-detr-for-moment-retrieval-and","title":"Saliency-Guided DETR for Moment Retrieval and Highlight Detection","date":"2024-10-02","arxiv_id":"2410.01615","n_code_links":1,"syntology":null},{"paper":"/paper/seeing-eye-to-ai-human-alignment-via-gaze","slug":"seeing-eye-to-ai-human-alignment-via-gaze","title":"Seeing Eye to AI: Human Alignment via Gaze-Based Response Rewards for Large Language Models","date":"2024-10-02","arxiv_id":"2410.01532","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":["telefonica-scientific-research/gaze_reward"],"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":"towards-a-deeper-understanding-of-transformer","title":"Towards a Deeper Understanding of Transformer for Residential Non-intrusive Load Monitoring","date":"2024-10-02","arxiv_id":"2410.03758","n_code_links":0,"syntology":null},{"paper":null,"slug":"ulcergpt-a-multimodal-approach-leveraging","title":"UlcerGPT: A Multimodal Approach Leveraging Large Language and Vision Models for Diabetic Foot Ulcer Image Transcription","date":"2024-10-02","arxiv_id":"2410.01989","n_code_links":0,"syntology":null},{"paper":null,"slug":"advanced-arabic-alphabet-sign-language","title":"Advanced Arabic Alphabet Sign Language Recognition Using Transfer Learning and Transformer Models","date":"2024-10-01","arxiv_id":"2410.00681","n_code_links":0,"syntology":null},{"paper":"/paper/adversarial-suffixes-may-be-features-too","slug":"adversarial-suffixes-may-be-features-too","title":"Unleashing the Unseen: Harnessing Benign Datasets for Jailbreaking Large Language Models","date":"2024-10-01","arxiv_id":"2410.00451","n_code_links":1,"syntology":null},{"paper":"/paper/alignsum-data-pyramid-hierarchical-fine","slug":"alignsum-data-pyramid-hierarchical-fine","title":"AlignSum: Data Pyramid Hierarchical Fine-tuning for Aligning with Human Summarization Preference","date":"2024-10-01","arxiv_id":"2410.00409","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"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) · 0 unverified","official":{"repos":["csyanghan/alignsum"],"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":"/paper/creative-and-context-aware-translation-of","slug":"creative-and-context-aware-translation-of","title":"Creative and Context-Aware Translation of East Asian Idioms with GPT-4","date":"2024-10-01","arxiv_id":"2410.00988","n_code_links":1,"syntology":null},{"paper":null,"slug":"decoding-hate-exploring-language-models","title":"Decoding Hate: Exploring Language Models' Reactions to Hate Speech","date":"2024-10-01","arxiv_id":"2410.00775","n_code_links":0,"syntology":null},{"paper":"/paper/deep-multimodal-fusion-for-semantic","slug":"deep-multimodal-fusion-for-semantic","title":"Deep Multimodal Fusion for Semantic Segmentation of Remote Sensing Earth Observation Data","date":"2024-10-01","arxiv_id":"2410.00469","n_code_links":0,"syntology":null},{"paper":"/paper/domain-aware-multi-task-pretraining-of-3d","slug":"domain-aware-multi-task-pretraining-of-3d","title":"Domain Aware Multi-Task Pretraining of 3D Swin Transformer for T1-weighted Brain MRI","date":"2024-10-01","arxiv_id":"2410.00410","n_code_links":1,"syntology":null},{"paper":"/paper/end-to-end-speech-recognition-with-pre","slug":"end-to-end-speech-recognition-with-pre","title":"End-to-End Speech Recognition with Pre-trained Masked Language Model","date":"2024-10-01","arxiv_id":"2410.00528","n_code_links":1,"syntology":null},{"paper":null,"slug":"exploring-the-learning-capabilities-of","title":"Exploring the Learning Capabilities of Language Models using LEVERWORLDS","date":"2024-10-01","arxiv_id":"2410.00519","n_code_links":0,"syntology":null},{"paper":"/paper/fce-yolov8-yolov8-with-feature-context","slug":"fce-yolov8-yolov8-with-feature-context","title":"Pediatric Wrist Fracture Detection Using Feature Context Excitation Modules in X-ray Images","date":"2024-10-01","arxiv_id":"2410.01031","n_code_links":1,"syntology":null},{"paper":null,"slug":"glmha-a-guided-low-rank-multi-head-self","title":"GLMHA A Guided Low-rank Multi-Head Self-Attention for Efficient Image Restoration and Spectral Reconstruction","date":"2024-10-01","arxiv_id":"2410.00380","n_code_links":0,"syntology":null},{"paper":null,"slug":"insight-a-multi-modal-diagnostic-pipeline","title":"Insight: A Multi-Modal Diagnostic Pipeline using LLMs for Ocular Surface Disease Diagnosis","date":"2024-10-01","arxiv_id":"2410.00292","n_code_links":0,"syntology":null},{"paper":null,"slug":"investigating-the-synergistic-effects-of","title":"Investigating the Synergistic Effects of Dropout and Residual Connections on Language Model Training","date":"2024-10-01","arxiv_id":"2410.01019","n_code_links":0,"syntology":null},{"paper":null,"slug":"language-enhanced-model-for-eye-leme-an-open","title":"Language Enhanced Model for Eye (LEME): An Open-Source Ophthalmology-Specific Large Language Model","date":"2024-10-01","arxiv_id":"2410.03740","n_code_links":0,"syntology":null},{"paper":null,"slug":"map-unleashing-hybrid-mamba-transformer","title":"MAP: Unleashing Hybrid Mamba-Transformer Vision Backbone's Potential with Masked Autoregressive Pretraining","date":"2024-10-01","arxiv_id":"2410.00871","n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-scale-temporal-transformer-for-speech","title":"Multi-Scale Temporal Transformer For Speech Emotion Recognition","date":"2024-10-01","arxiv_id":"2410.00390","n_code_links":0,"syntology":null},{"paper":null,"slug":"ngpt-normalized-transformer-with","title":"nGPT: Normalized Transformer with Representation Learning on the Hypersphere","date":"2024-10-01","arxiv_id":"2410.01131","n_code_links":0,"syntology":null},{"paper":"/paper/optimizing-and-evaluating-enterprise","slug":"optimizing-and-evaluating-enterprise","title":"Optimizing and Evaluating Enterprise Retrieval-Augmented Generation (RAG): A Content Design Perspective","date":"2024-10-01","arxiv_id":"2410.12812","n_code_links":1,"syntology":null},{"paper":null,"slug":"quantifying-reliance-on-external-information","title":"Quantifying reliance on external information over parametric knowledge during Retrieval Augmented Generation (RAG) using mechanistic analysis","date":"2024-10-01","arxiv_id":"2410.00857","n_code_links":0,"syntology":null},{"paper":"/paper/rationalyst-pre-training-process-supervision","slug":"rationalyst-pre-training-process-supervision","title":"RATIONALYST: Pre-training Process-Supervision for Improving Reasoning","date":"2024-10-01","arxiv_id":"2410.01044","n_code_links":1,"syntology":null},{"paper":"/paper/robust-traffic-forecasting-against-spatial","slug":"robust-traffic-forecasting-against-spatial","title":"Robust Traffic Forecasting against Spatial Shift over Years","date":"2024-10-01","arxiv_id":"2410.00373","n_code_links":1,"syntology":{"ran":10,"of":13,"n_ran_checked":10,"n_instrument":0,"unverified":3,"pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["dreamzz5/st-expert"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/sparse-attention-decomposition-applied-to","slug":"sparse-attention-decomposition-applied-to","title":"Sparse Attention Decomposition Applied to Circuit Tracing","date":"2024-10-01","arxiv_id":"2410.00340","n_code_links":1,"syntology":null},{"paper":null,"slug":"squeeze-and-remember-block","title":"Squeeze-and-Remember Block","date":"2024-10-01","arxiv_id":"2410.00823","n_code_links":0,"syntology":null},{"paper":"/paper/stgformer-efficient-spatiotemporal-graph","slug":"stgformer-efficient-spatiotemporal-graph","title":"STGformer: Efficient Spatiotemporal Graph Transformer for Traffic Forecasting","date":"2024-10-01","arxiv_id":"2410.00385","n_code_links":1,"syntology":null},{"paper":"/paper/tfct-i2p-three-stream-fusion-network-with","slug":"tfct-i2p-three-stream-fusion-network-with","title":"TFCT-I2P: Three stream fusion network with color aware transformer for image-to-point cloud registration","date":"2024-10-01","arxiv_id":"2410.00360","n_code_links":1,"syntology":null},{"paper":"/paper/transresnet-integrating-the-strengths-of-vits","slug":"transresnet-integrating-the-strengths-of-vits","title":"TransResNet: Integrating the Strengths of ViTs and CNNs for High Resolution Medical Image Segmentation via Feature Grafting","date":"2024-10-01","arxiv_id":"2410.00986","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-looming-replication-crisis-in-evaluating","title":"A Looming Replication Crisis in Evaluating Behavior in Language Models? Evidence and Solutions","date":"2024-09-30","arxiv_id":"2409.20303","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-methodology-for-explainable-large-language","title":"A Methodology for Explainable Large Language Models with Integrated Gradients and Linguistic Analysis in Text Classification","date":"2024-09-30","arxiv_id":"2410.00250","n_code_links":0,"syntology":null},{"paper":null,"slug":"ace-all-round-creator-and-editor-following","title":"ACE: All-round Creator and Editor Following Instructions via Diffusion Transformer","date":"2024-09-30","arxiv_id":"2410.00086","n_code_links":0,"syntology":null},{"paper":null,"slug":"adapting-llms-for-the-medical-domain-in","title":"Adapting LLMs for the Medical Domain in Portuguese: A Study on Fine-Tuning and Model Evaluation","date":"2024-09-30","arxiv_id":"2410.00163","n_code_links":0,"syntology":null},{"paper":"/paper/asquery-a-query-based-model-for-action","slug":"asquery-a-query-based-model-for-action","title":"ASQuery: A Query-based Model for Action Segmentation","date":"2024-09-30","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"bsharedrag-backbone-shared-retrieval","title":"BSharedRAG: Backbone Shared Retrieval-Augmented Generation for the E-commerce Domain","date":"2024-09-30","arxiv_id":"2409.20075","n_code_links":0,"syntology":null},{"paper":null,"slug":"cbam-swint-bl-small-rail-surface-detect","title":"CBAM-SwinT-BL: Small Rail Surface Defect Detection Method Based on Swin Transformer with Block Level CBAM Enhancement","date":"2024-09-30","arxiv_id":"2409.20113","n_code_links":0,"syntology":null},{"paper":"/paper/climb-an-ai-enabled-partner-for-clinical","slug":"climb-an-ai-enabled-partner-for-clinical","title":"CliMB: An AI-enabled Partner for Clinical Predictive Modeling","date":"2024-09-30","arxiv_id":"2410.03736","n_code_links":1,"syntology":{"ran":7,"of":10,"n_ran_checked":7,"n_instrument":0,"unverified":3,"pointer_only":0,"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) · 3 unverified","official":{"repos":["vanderschaarlab/climb"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"depression-detection-in-social-media-posts-1","title":"Depression detection in social media posts using transformer-based models and auxiliary features","date":"2024-09-30","arxiv_id":"2409.20048","n_code_links":0,"syntology":null},{"paper":"/paper/evaluating-the-fairness-of-task-adaptive","slug":"evaluating-the-fairness-of-task-adaptive","title":"Evaluating the fairness of task-adaptive pretraining on unlabeled test data before few-shot text classification","date":"2024-09-30","arxiv_id":"2410.00179","n_code_links":1,"syntology":null},{"paper":null,"slug":"gtranspdm-a-graph-embedded-transformer-with","title":"GTransPDM: A Graph-embedded Transformer with Positional Decoupling for Pedestrian Crossing Intention Prediction","date":"2024-09-30","arxiv_id":"2409.20223","n_code_links":0,"syntology":null},{"paper":null,"slug":"illustrious-an-open-advanced-illustration","title":"Illustrious: an Open Advanced Illustration Model","date":"2024-09-30","arxiv_id":"2409.19946","n_code_links":0,"syntology":null},{"paper":null,"slug":"ingest-and-ground-dispelling-hallucinations","title":"Ingest-And-Ground: Dispelling Hallucinations from Continually-Pretrained LLMs with RAG","date":"2024-09-30","arxiv_id":"2410.02825","n_code_links":0,"syntology":null},{"paper":null,"slug":"maskmamba-a-hybrid-mamba-transformer-model","title":"MaskMamba: A Hybrid Mamba-Transformer Model for Masked Image Generation","date":"2024-09-30","arxiv_id":"2409.19937","n_code_links":0,"syntology":null},{"paper":null,"slug":"modelando-procesos-cognitivos-de-la-lectura","title":"Modelando procesos cognitivos de la lectura natural con GPT-2","date":"2024-09-30","arxiv_id":"2409.20174","n_code_links":0,"syntology":null},{"paper":null,"slug":"on-large-uni-and-multi-modal-models-for","title":"Exploring Social Media Image Categorization Using Large Models with Different Adaptation Methods: A Case Study on Cultural Nature's Contributions to People","date":"2024-09-30","arxiv_id":"2410.00275","n_code_links":0,"syntology":null},{"paper":"/paper/on-the-planning-abilities-of-openai-s-o1","slug":"on-the-planning-abilities-of-openai-s-o1","title":"On The Planning Abilities of OpenAI's o1 Models: Feasibility, Optimality, and Generalizability","date":"2024-09-30","arxiv_id":"2409.19924","n_code_links":2,"syntology":null},{"paper":null,"slug":"pomonag-pareto-optimal-many-objective-neural","title":"POMONAG: Pareto-Optimal Many-Objective Neural Architecture Generator","date":"2024-09-30","arxiv_id":"2409.20447","n_code_links":0,"syntology":null},{"paper":"/paper/qaencoder-towards-aligned-representation","slug":"qaencoder-towards-aligned-representation","title":"QAEncoder: Towards Aligned Representation Learning in Question Answering System","date":"2024-09-30","arxiv_id":"2409.20434","n_code_links":1,"syntology":null},{"paper":null,"slug":"training-a-computer-vision-model-for","title":"Training a Computer Vision Model for Commercial Bakeries with Primarily Synthetic Images","date":"2024-09-30","arxiv_id":"2409.20122","n_code_links":0,"syntology":null},{"paper":null,"slug":"abstractive-summarization-of-low-resourced","title":"Abstractive Summarization of Low resourced Nepali language using Multilingual Transformers","date":"2024-09-29","arxiv_id":"2409.19566","n_code_links":0,"syntology":null},{"paper":null,"slug":"adversarial-examples-for-dna-classification","title":"Adversarial Examples for DNA Classification","date":"2024-09-29","arxiv_id":"2409.19788","n_code_links":0,"syntology":null},{"paper":null,"slug":"automated-disease-diagnosis-in-pumpkin-plants","title":"Automated Disease Diagnosis in Pumpkin Plants Using Advanced CNN Models","date":"2024-09-29","arxiv_id":"2410.00062","n_code_links":0,"syntology":null},{"paper":null,"slug":"brain-tumor-classification-on-mri-in-light-of","title":"Brain Tumor Classification on MRI in Light of Molecular Markers","date":"2024-09-29","arxiv_id":"2409.19583","n_code_links":0,"syntology":null},{"paper":null,"slug":"can-models-learn-skill-composition-from","title":"Can Models Learn Skill Composition from Examples?","date":"2024-09-29","arxiv_id":"2409.19808","n_code_links":0,"syntology":null},{"paper":"/paper/does-rag-introduce-unfairness-in-llms","slug":"does-rag-introduce-unfairness-in-llms","title":"Does RAG Introduce Unfairness in LLMs? Evaluating Fairness in Retrieval-Augmented Generation Systems","date":"2024-09-29","arxiv_id":"2409.19804","n_code_links":1,"syntology":{"ran":8,"of":10,"n_ran_checked":6,"n_instrument":2,"unverified":2,"pointer_only":10,"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) · 2 unverified","official":{"repos":["elviswxy/rag_fairness"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"gentel-safe-a-unified-benchmark-and-shielding","title":"GenTel-Safe: A Unified Benchmark and Shielding Framework for Defending Against Prompt Injection Attacks","date":"2024-09-29","arxiv_id":"2409.19521","n_code_links":0,"syntology":null},{"paper":"/paper/gradient-is-all-you-need-gradient-based","slug":"gradient-is-all-you-need-gradient-based","title":"DATransNet: Dynamic Attention Transformer Network for Infrared Small Target Detection","date":"2024-09-29","arxiv_id":"2409.19599","n_code_links":1,"syntology":null},{"paper":"/paper/improved-user-identification-through","slug":"improved-user-identification-through","title":"Improved User Identification through Calibrated Monte-Carlo Dropout","date":"2024-09-29","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/investigating-the-effect-of-network-pruning","slug":"investigating-the-effect-of-network-pruning","title":"Investigating the Effect of Network Pruning on Performance and Interpretability","date":"2024-09-29","arxiv_id":"2409.19727","n_code_links":1,"syntology":null},{"paper":null,"slug":"medhalu-hallucinations-in-responses-to","title":"MedHalu: Hallucinations in Responses to Healthcare Queries by Large Language Models","date":"2024-09-29","arxiv_id":"2409.19492","n_code_links":0,"syntology":null},{"paper":null,"slug":"pear-position-embedding-agnostic-attention-re","title":"PEAR: Position-Embedding-Agnostic Attention Re-weighting Enhances Retrieval-Augmented Generation with Zero Inference Overhead","date":"2024-09-29","arxiv_id":"2409.19745","n_code_links":0,"syntology":null},{"paper":null,"slug":"see-then-tell-enhancing-key-information","title":"See then Tell: Enhancing Key Information Extraction with Vision Grounding","date":"2024-09-29","arxiv_id":"2409.19573","n_code_links":0,"syntology":null},{"paper":"/paper/spiking-transformer-with-spatial-temporal","slug":"spiking-transformer-with-spatial-temporal","title":"Spiking Transformer with Spatial-Temporal Attention","date":"2024-09-29","arxiv_id":"2409.19764","n_code_links":1,"syntology":null},{"paper":"/paper/analog-in-memory-computing-attention","slug":"analog-in-memory-computing-attention","title":"Analog In-Memory Computing Attention Mechanism for Fast and Energy-Efficient Large Language Models","date":"2024-09-28","arxiv_id":"2409.19315","n_code_links":1,"syntology":null},{"paper":null,"slug":"deneb-a-hallucination-robust-automatic","title":"DENEB: A Hallucination-Robust Automatic Evaluation Metric for Image Captioning","date":"2024-09-28","arxiv_id":"2409.19255","n_code_links":0,"syntology":null},{"paper":"/paper/efficient-federated-intrusion-detection-in-5g","slug":"efficient-federated-intrusion-detection-in-5g","title":"Efficient Federated Intrusion Detection in 5G ecosystem using optimized BERT-based model","date":"2024-09-28","arxiv_id":"2409.19390","n_code_links":1,"syntology":null},{"paper":"/paper/insightbuddy-ai-medication-extraction-and","slug":"insightbuddy-ai-medication-extraction-and","title":"INSIGHTBUDDY-AI: Medication Extraction and Entity Linking using Large Language Models and Ensemble Learning","date":"2024-09-28","arxiv_id":"2409.19467","n_code_links":2,"syntology":null},{"paper":null,"slug":"multi-atlas-brain-network-classification","title":"Multi-Atlas Brain Network Classification through Consistency Distillation and Complementary Information Fusion","date":"2024-09-28","arxiv_id":"2410.08228","n_code_links":0,"syntology":null},{"paper":null,"slug":"unveil-benign-overfitting-for-transformer-in","title":"Unveil Benign Overfitting for Transformer in Vision: Training Dynamics, Convergence, and Generalization","date":"2024-09-28","arxiv_id":"2409.19345","n_code_links":0,"syntology":null},{"paper":null,"slug":"aipatient-simulating-patients-with-ehrs-and","title":"AIPatient: Simulating Patients with EHRs and LLM Powered Agentic Workflow","date":"2024-09-27","arxiv_id":"2409.18924","n_code_links":0,"syntology":null},{"paper":null,"slug":"charting-the-future-using-chart-question","title":"Charting the Future: Using Chart Question-Answering for Scalable Evaluation of LLM-Driven Data Visualizations","date":"2024-09-27","arxiv_id":"2409.18764","n_code_links":0,"syntology":null},{"paper":"/paper/cottention-linear-transformers-with-cosine","slug":"cottention-linear-transformers-with-cosine","title":"Cottention: Linear Transformers With Cosine Attention","date":"2024-09-27","arxiv_id":"2409.18747","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":1,"n_instrument":0,"unverified":1,"pointer_only":2,"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":["gmongaras/Cottention_Transformer"],"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":null,"slug":"experimental-evaluation-of-machine-learning","title":"Experimental Evaluation of Machine Learning Models for Goal-oriented Customer Service Chatbot with Pipeline Architecture","date":"2024-09-27","arxiv_id":"2409.18568","n_code_links":0,"syntology":null},{"paper":null,"slug":"how-effective-is-pre-training-of-large-masked","title":"How Effective is Pre-training of Large Masked Autoencoders for Downstream Earth Observation Tasks?","date":"2024-09-27","arxiv_id":"2409.18536","n_code_links":0,"syntology":null},{"paper":"/paper/lml-language-model-learning-a-dataset-for","slug":"lml-language-model-learning-a-dataset-for","title":"LML-DAP: Language Model Learning a Dataset for Data-Augmented Prediction","date":"2024-09-27","arxiv_id":"2409.18957","n_code_links":1,"syntology":null},{"paper":null,"slug":"meta-rtl-reinforcement-based-meta-transfer","title":"Meta-RTL: Reinforcement-Based Meta-Transfer Learning for Low-Resource Commonsense Reasoning","date":"2024-09-27","arxiv_id":"2409.19075","n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-source-hard-and-soft-information-fusion","title":"Multi-Source Hard and Soft Information Fusion Approach for Accurate Cryptocurrency Price Movement Prediction","date":"2024-09-27","arxiv_id":"2409.18895","n_code_links":0,"syntology":null},{"paper":null,"slug":"not-the-silver-bullet-llm-enhanced","title":"Not the Silver Bullet: LLM-enhanced Programming Error Messages are Ineffective in Practice","date":"2024-09-27","arxiv_id":"2409.18661","n_code_links":0,"syntology":null},{"paper":null,"slug":"on-the-power-of-decision-trees-in-auto","title":"On the Power of Decision Trees in Auto-Regressive Language Modeling","date":"2024-09-27","arxiv_id":"2409.19150","n_code_links":0,"syntology":null},{"paper":null,"slug":"open-nav-exploring-zero-shot-vision-and","title":"Open-Nav: Exploring Zero-Shot Vision-and-Language Navigation in Continuous Environment with Open-Source LLMs","date":"2024-09-27","arxiv_id":"2409.18794","n_code_links":0,"syntology":null},{"paper":"/paper/pruning-then-reweighting-towards-data","slug":"pruning-then-reweighting-towards-data","title":"Pruning then Reweighting: Towards Data-Efficient Training of Diffusion Models","date":"2024-09-27","arxiv_id":"2409.19128","n_code_links":1,"syntology":null},{"paper":null,"slug":"query-matching-for-spatio-temporal-action","title":"Query matching for spatio-temporal action detection with query-based object detector","date":"2024-09-27","arxiv_id":"2409.18408","n_code_links":0,"syntology":null},{"paper":"/paper/rnc-efficient-rram-aware-nas-and-compilation","slug":"rnc-efficient-rram-aware-nas-and-compilation","title":"RNC: Efficient RRAM-aware NAS and Compilation for DNNs on Resource-Constrained Edge Devices","date":"2024-09-27","arxiv_id":"2409.18841","n_code_links":1,"syntology":null},{"paper":null,"slug":"spectral-wavelet-dropout-regularization-in","title":"Spectral Wavelet Dropout: Regularization in the Wavelet Domain","date":"2024-09-27","arxiv_id":"2409.18951","n_code_links":0,"syntology":null},{"paper":null,"slug":"speech-mamba-long-context-speech-recognition","title":"Speech-Mamba: Long-Context Speech Recognition with Selective State Spaces Models","date":"2024-09-27","arxiv_id":"2409.18654","n_code_links":0,"syntology":null},{"paper":null,"slug":"suicide-phenotyping-from-clinical-notes-in","title":"Suicide Phenotyping from Clinical Notes in Safety-Net Psychiatric Hospital Using Multi-Label Classification with Pre-Trained Language Models","date":"2024-09-27","arxiv_id":"2409.18878","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-craft-of-selective-prediction-towards","title":"The Craft of Selective Prediction: Towards Reliable Case Outcome Classification -- An Empirical Study on European Court of Human Rights Cases","date":"2024-09-27","arxiv_id":"2409.18645","n_code_links":0,"syntology":null}],"record_sha256":"7617cfce09f70db00b48d6465797410f1d2c500095b53fcb8b0f265a0eed2c3b","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}