{"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/adam/papers/34","list_of":"/method/adam","method":"Adam","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":34,"pages_in_order":244,"rows_per_page":100,"rows":[3301,3400],"of":24390,"counts":{"archive_papers_tagged":24390,"with_a_code_link":10944,"where_syntology_ran_a_sample":3424,"not_listed_spam_title":0,"listed":24390,"listed_where_code_ran":3424,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":2899,"every_run_a_failure_of_syntologys_instrument":525,"listed_with_a_run_with_no_instrument_failure":2899,"listed_every_run_a_failure_of_syntologys_instrument":525,"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/adam","prev":"/method/adam/papers/33","next":"/method/adam/papers/35","papers":[{"paper":null,"slug":"selecting-between-bert-and-gpt-for-text","title":"Selecting Between BERT and GPT for Text Classification in Political Science Research","date":"2024-11-07","arxiv_id":"2411.05050","n_code_links":0,"syntology":null},{"paper":null,"slug":"stand-guard-a-small-task-adaptive-content","title":"STAND-Guard: A Small Task-Adaptive Content Moderation Model","date":"2024-11-07","arxiv_id":"2411.05214","n_code_links":0,"syntology":null},{"paper":null,"slug":"words-that-move-markets-quantifying-the","title":"Words that Move Markets- Quantifying the Impact of RBI's Monetary Policy Communications on Indian Financial Market","date":"2024-11-07","arxiv_id":"2411.04808","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-comparative-study-of-recent-large-language","title":"A Comparative Study of Recent Large Language Models on Generating Hospital Discharge Summaries for Lung Cancer Patients","date":"2024-11-06","arxiv_id":"2411.03805","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-contrastive-self-supervised-learning-scheme","title":"A Contrastive Self-Supervised Learning scheme for beat tracking amenable to few-shot learning","date":"2024-11-06","arxiv_id":"2411.04152","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-multilingual-sentiment-lexicon-for-low","title":"A Multilingual Sentiment Lexicon for Low-Resource Language Translation using Large Languages Models and Explainable AI","date":"2024-11-06","arxiv_id":"2411.04316","n_code_links":0,"syntology":null},{"paper":null,"slug":"advanced-rag-models-with-graph-structures","title":"Advanced RAG Models with Graph Structures: Optimizing Complex Knowledge Reasoning and Text Generation","date":"2024-11-06","arxiv_id":"2411.03572","n_code_links":0,"syntology":null},{"paper":"/paper/bio-xlstm-generative-modeling-representation","slug":"bio-xlstm-generative-modeling-representation","title":"Bio-xLSTM: Generative modeling, representation and in-context learning of biological and chemical sequences","date":"2024-11-06","arxiv_id":"2411.04165","n_code_links":3,"syntology":{"ran":27,"of":29,"n_ran_checked":25,"n_instrument":2,"unverified":2,"pointer_only":1,"phrase":"27 ran (of which 0 constructed an object rather than computing a result; 25 with no instrument failure: 0 honoured, 1 violated, 24 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","official":{"repos":["ml-jku/chem-xlstm","ml-jku/dna-xlstm","ml-jku/prot-xlstm"],"state":"official (archive's flag): 27 ran","n_ran":27,"n_constructed":0,"n_ran_no_instrument_failure":25,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/can-custom-models-learn-in-context-an","slug":"can-custom-models-learn-in-context-an","title":"Can Custom Models Learn In-Context? An Exploration of Hybrid Architecture Performance on In-Context Learning Tasks","date":"2024-11-06","arxiv_id":"2411.03945","n_code_links":1,"syntology":null},{"paper":"/paper/customized-multiple-clustering-via-multi","slug":"customized-multiple-clustering-via-multi","title":"Customized Multiple Clustering via Multi-Modal Subspace Proxy Learning","date":"2024-11-06","arxiv_id":"2411.03978","n_code_links":1,"syntology":{"ran":3,"of":5,"n_ran_checked":0,"n_instrument":3,"unverified":2,"pointer_only":5,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","official":{"repos":["alexander-yao/multi-sub"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"diversity-helps-jailbreak-large-language","title":"Diversity Helps Jailbreak Large Language Models","date":"2024-11-06","arxiv_id":"2411.04223","n_code_links":0,"syntology":null},{"paper":null,"slug":"fine-grained-guidance-for-retrievers","title":"Fine-Grained Guidance for Retrievers: Leveraging LLMs' Feedback in Retrieval-Augmented Generation","date":"2024-11-06","arxiv_id":"2411.03957","n_code_links":0,"syntology":null},{"paper":null,"slug":"from-medprompt-to-o1-exploration-of-run-time","title":"From Medprompt to o1: Exploration of Run-Time Strategies for Medical Challenge Problems and Beyond","date":"2024-11-06","arxiv_id":"2411.03590","n_code_links":0,"syntology":null},{"paper":null,"slug":"from-word-vectors-to-multimodal-embeddings","title":"From Word Vectors to Multimodal Embeddings: Techniques, Applications, and Future Directions For Large Language Models","date":"2024-11-06","arxiv_id":"2411.05036","n_code_links":0,"syntology":null},{"paper":null,"slug":"on-device-emoji-classifier-trained-with-gpt","title":"On-Device Emoji Classifier Trained with GPT-based Data Augmentation for a Mobile Keyboard","date":"2024-11-06","arxiv_id":"2411.05031","n_code_links":0,"syntology":null},{"paper":null,"slug":"paragan-a-scalable-distributed-training","title":"ParaGAN: A Scalable Distributed Training Framework for Generative Adversarial Networks","date":"2024-11-06","arxiv_id":"2411.03999","n_code_links":0,"syntology":null},{"paper":null,"slug":"phdgpt-introducing-a-psychometric-and","title":"PhDGPT: Introducing a psychometric and linguistic dataset about how large language models perceive graduate students and professors in psychology","date":"2024-11-06","arxiv_id":"2411.10473","n_code_links":0,"syntology":null},{"paper":"/paper/prion-vit-prions-inspired-vision-transformers","slug":"prion-vit-prions-inspired-vision-transformers","title":"Prion-ViT: Prions-Inspired Vision Transformers for Temperature prediction with Specklegrams","date":"2024-11-06","arxiv_id":"2411.05836","n_code_links":0,"syntology":null},{"paper":null,"slug":"prompt-engineering-using-gpt-for-word-level","title":"Prompt Engineering Using GPT for Word-Level Code-Mixed Language Identification in Low-Resource Dravidian Languages","date":"2024-11-06","arxiv_id":"2411.04025","n_code_links":0,"syntology":null},{"paper":null,"slug":"ragulator-lightweight-out-of-context","title":"RAGulator: Lightweight Out-of-Context Detectors for Grounded Text Generation","date":"2024-11-06","arxiv_id":"2411.03920","n_code_links":0,"syntology":null},{"paper":"/paper/towards-interpreting-language-models-a-case","slug":"towards-interpreting-language-models-a-case","title":"Towards Interpreting Language Models: A Case Study in Multi-Hop Reasoning","date":"2024-11-06","arxiv_id":"2411.05037","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":2,"n_instrument":0,"unverified":1,"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) · 1 unverified","official":{"repos":["msakarvadia/attentionlens"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/understanding-the-effects-of-human-written","slug":"understanding-the-effects-of-human-written","title":"Understanding the Effects of Human-written Paraphrases in LLM-generated Text Detection","date":"2024-11-06","arxiv_id":"2411.03806","n_code_links":1,"syntology":null},{"paper":null,"slug":"youtube-comments-decoded-leveraging-llms-for","title":"YouTube Comments Decoded: Leveraging LLMs for Low Resource Language Classification","date":"2024-11-06","arxiv_id":"2411.05039","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-mamba-foundation-model-for-time-series","title":"A Mamba Foundation Model for Time Series Forecasting","date":"2024-11-05","arxiv_id":"2411.02941","n_code_links":0,"syntology":null},{"paper":"/paper/adopt-modified-adam-can-converge-with-any-b-2","slug":"adopt-modified-adam-can-converge-with-any-b-2","title":"ADOPT: Modified Adam Can Converge with Any $β_2$ with the Optimal Rate","date":"2024-11-05","arxiv_id":"2411.02853","n_code_links":2,"syntology":{"ran":14,"of":23,"n_ran_checked":11,"n_instrument":3,"unverified":9,"pointer_only":4,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 3 where Syntology's instrument failed) · 9 unverified","official":{"repos":["ishohei220/adopt"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["found_in_text","official"]}}},{"paper":null,"slug":"automatic-generation-of-question-hints-for","title":"Automatic Generation of Question Hints for Mathematics Problems using Large Language Models in Educational Technology","date":"2024-11-05","arxiv_id":"2411.03495","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhanced-real-time-threat-detection-in-5g","title":"Enhanced Real-Time Threat Detection in 5G Networks: A Self-Attention RNN Autoencoder Approach for Spectral Intrusion Analysis","date":"2024-11-05","arxiv_id":"2411.03365","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancing-transformer-training-efficiency","title":"Enhancing Transformer Training Efficiency with Dynamic Dropout","date":"2024-11-05","arxiv_id":"2411.03236","n_code_links":0,"syntology":null},{"paper":null,"slug":"exploring-the-benefits-of-domain-pretraining","title":"Exploring the Benefits of Domain-Pretraining of Generative Large Language Models for Chemistry","date":"2024-11-05","arxiv_id":"2411.03542","n_code_links":0,"syntology":null},{"paper":null,"slug":"foundation-ai-model-for-medical-image","title":"Foundation AI Model for Medical Image Segmentation","date":"2024-11-05","arxiv_id":"2411.02745","n_code_links":0,"syntology":null},{"paper":null,"slug":"from-pixels-to-prose-advancing-multi-modal","title":"From Pixels to Prose: Advancing Multi-Modal Language Models for Remote Sensing","date":"2024-11-05","arxiv_id":"2411.05826","n_code_links":0,"syntology":null},{"paper":"/paper/htmlrag-html-is-better-than-plain-text-for","slug":"htmlrag-html-is-better-than-plain-text-for","title":"HtmlRAG: HTML is Better Than Plain Text for Modeling Retrieved Knowledge in RAG Systems","date":"2024-11-05","arxiv_id":"2411.02959","n_code_links":1,"syntology":null},{"paper":"/paper/kernel-approximation-using-analog-in-memory","slug":"kernel-approximation-using-analog-in-memory","title":"Kernel Approximation using Analog In-Memory Computing","date":"2024-11-05","arxiv_id":"2411.03375","n_code_links":1,"syntology":null},{"paper":null,"slug":"laser-attention-with-exponential","title":"LASER: Attention with Exponential Transformation","date":"2024-11-05","arxiv_id":"2411.03493","n_code_links":0,"syntology":null},{"paper":null,"slug":"long-context-rag-performance-of-large","title":"Long Context RAG Performance of Large Language Models","date":"2024-11-05","arxiv_id":"2411.03538","n_code_links":0,"syntology":null},{"paper":null,"slug":"mixtures-of-in-context-learners","title":"Mixtures of In-Context Learners","date":"2024-11-05","arxiv_id":"2411.02830","n_code_links":0,"syntology":null},{"paper":null,"slug":"neurons-for-neutrons-a-transformer-model-for","title":"Neurons for Neutrons: A Transformer Model for Computation Load Estimation on Domain-Decomposed Neutron Transport Problems","date":"2024-11-05","arxiv_id":"2411.03389","n_code_links":0,"syntology":null},{"paper":null,"slug":"p-moss-learned-scheduling-for-indexes-over","title":"P-MOSS: Learned Scheduling For Indexes Over NUMA Servers Using Low-Level Hardware Statistics","date":"2024-11-05","arxiv_id":"2411.02933","n_code_links":0,"syntology":null},{"paper":null,"slug":"persianrag-a-retrieval-augmented-generation","title":"PersianRAG: A Retrieval-Augmented Generation System for Persian Language","date":"2024-11-05","arxiv_id":"2411.02832","n_code_links":0,"syntology":null},{"paper":null,"slug":"predictor-corrector-enhanced-transformers","title":"Predictor-Corrector Enhanced Transformers with Exponential Moving Average Coefficient Learning","date":"2024-11-05","arxiv_id":"2411.03042","n_code_links":0,"syntology":null},{"paper":"/paper/rethinking-decoders-for-transformer-based","slug":"rethinking-decoders-for-transformer-based","title":"Rethinking Decoders for Transformer-based Semantic Segmentation: A Compression Perspective","date":"2024-11-05","arxiv_id":"2411.03033","n_code_links":1,"syntology":null},{"paper":null,"slug":"transunext-towards-a-more-advanced-u-shaped","title":"TransUNext: towards a more advanced U-shaped framework for automatic vessel segmentation in the fundus image","date":"2024-11-05","arxiv_id":"2411.02724","n_code_links":0,"syntology":null},{"paper":null,"slug":"uncertainty-quantification-for-clinical","title":"Uncertainty Quantification for Clinical Outcome Predictions with (Large) Language Models","date":"2024-11-05","arxiv_id":"2411.03497","n_code_links":0,"syntology":null},{"paper":null,"slug":"user-centric-semantic-communications","title":"Receiver-Centric Generative Semantic Communications","date":"2024-11-05","arxiv_id":"2411.03127","n_code_links":0,"syntology":null},{"paper":null,"slug":"veritas-a-unified-approach-to-reliability","title":"VERITAS: A Unified Approach to Reliability Evaluation","date":"2024-11-05","arxiv_id":"2411.03300","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-comparative-analysis-of-counterfactual","title":"A Comparative Analysis of Counterfactual Explanation Methods for Text Classifiers","date":"2024-11-04","arxiv_id":"2411.02643","n_code_links":0,"syntology":null},{"paper":null,"slug":"advancements-and-limitations-of-llms-in","title":"Advancements and limitations of LLMs in replicating human color-word associations","date":"2024-11-04","arxiv_id":"2411.02116","n_code_links":0,"syntology":null},{"paper":"/paper/amortized-bayesian-experimental-design-for","slug":"amortized-bayesian-experimental-design-for","title":"Amortized Bayesian Experimental Design for Decision-Making","date":"2024-11-04","arxiv_id":"2411.02064","n_code_links":1,"syntology":null},{"paper":"/paper/ask-and-it-shall-be-given-turing-completeness","slug":"ask-and-it-shall-be-given-turing-completeness","title":"Ask, and it shall be given: On the Turing completeness of prompting","date":"2024-11-04","arxiv_id":"2411.01992","n_code_links":1,"syntology":null},{"paper":null,"slug":"can-language-models-enable-in-context","title":"Can Language Models Enable In-Context Database?","date":"2024-11-04","arxiv_id":"2411.01807","n_code_links":0,"syntology":null},{"paper":null,"slug":"disrupting-test-development-with-ai","title":"Disrupting Test Development with AI Assistants","date":"2024-11-04","arxiv_id":"2411.02328","n_code_links":0,"syntology":null},{"paper":"/paper/elastst-towards-robust-varied-horizon","slug":"elastst-towards-robust-varied-horizon","title":"ElasTST: Towards Robust Varied-Horizon Forecasting with Elastic Time-Series Transformer","date":"2024-11-04","arxiv_id":"2411.01842","n_code_links":1,"syntology":{"ran":14,"of":14,"n_ran_checked":12,"n_instrument":2,"unverified":0,"pointer_only":1,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["microsoft/probts"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"encoding-multi-level-dynamics-in-effect","title":"Optimizing Multi-Scale Representations to Detect Effect Heterogeneity Using Earth Observation and Computer Vision: Applications to Two Anti-Poverty RCTs","date":"2024-11-04","arxiv_id":"2411.02134","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancing-risk-assessment-in-transformers","title":"Enhancing Risk Assessment in Transformers with Loss-at-Risk Functions","date":"2024-11-04","arxiv_id":"2411.02558","n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluating-the-ability-of-large-language-1","title":"Evaluating the Ability of Large Language Models to Generate Verifiable Specifications in VeriFast","date":"2024-11-04","arxiv_id":"2411.02318","n_code_links":0,"syntology":null},{"paper":null,"slug":"grounding-emotional-descriptions-to","title":"Grounding Emotional Descriptions to Electrovibration Haptic Signals","date":"2024-11-04","arxiv_id":"2411.02118","n_code_links":0,"syntology":null},{"paper":null,"slug":"mdeval-massively-multilingual-code-debugging","title":"MdEval: Massively Multilingual Code Debugging","date":"2024-11-04","arxiv_id":"2411.02310","n_code_links":0,"syntology":null},{"paper":"/paper/ragviz-diagnose-and-visualize-retrieval","slug":"ragviz-diagnose-and-visualize-retrieval","title":"RAGViz: Diagnose and Visualize Retrieval-Augmented Generation","date":"2024-11-04","arxiv_id":"2411.01751","n_code_links":1,"syntology":null},{"paper":"/paper/scalable-efficient-training-of-large-language","slug":"scalable-efficient-training-of-large-language","title":"Scalable Efficient Training of Large Language Models with Low-dimensional Projected Attention","date":"2024-11-04","arxiv_id":"2411.02063","n_code_links":1,"syntology":{"ran":5,"of":5,"n_ran_checked":3,"n_instrument":2,"unverified":0,"pointer_only":5,"phrase":"5 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["tsinghuac3i/lpa"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/seq-vcr-preventing-collapse-in-intermediate","slug":"seq-vcr-preventing-collapse-in-intermediate","title":"Seq-VCR: Preventing Collapse in Intermediate Transformer Representations for Enhanced Reasoning","date":"2024-11-04","arxiv_id":"2411.02344","n_code_links":1,"syntology":null},{"paper":"/paper/sira-scalable-inter-frame-relation-and-1","slug":"sira-scalable-inter-frame-relation-and-1","title":"SIRA: Scalable Inter-frame Relation and Association for Radar Perception","date":"2024-11-04","arxiv_id":"2411.02220","n_code_links":0,"syntology":null},{"paper":"/paper/teleoracle-fine-tuned-retrieval-augmented","slug":"teleoracle-fine-tuned-retrieval-augmented","title":"TeleOracle: Fine-Tuned Retrieval-Augmented Generation with Long-Context Support for Network","date":"2024-11-04","arxiv_id":"2411.02617","n_code_links":1,"syntology":null},{"paper":null,"slug":"towards-leveraging-news-media-to-support","title":"Towards Leveraging News Media to Support Impact Assessment of AI Technologies","date":"2024-11-04","arxiv_id":"2411.02536","n_code_links":0,"syntology":null},{"paper":"/paper/training-compute-optimal-protein-language","slug":"training-compute-optimal-protein-language","title":"Training Compute-Optimal Protein Language Models","date":"2024-11-04","arxiv_id":"2411.02142","n_code_links":1,"syntology":null},{"paper":"/paper/training-free-regional-prompting-for","slug":"training-free-regional-prompting-for","title":"Training-free Regional Prompting for Diffusion Transformers","date":"2024-11-04","arxiv_id":"2411.02395","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":1,"n_instrument":1,"unverified":0,"pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["instantX-research/Regional-Prompting-FLUX"],"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","unlocated"]}}},{"paper":null,"slug":"wave-network-an-ultra-small-language-model","title":"Wave Network: An Ultra-Small Language Model","date":"2024-11-04","arxiv_id":"2411.02674","n_code_links":0,"syntology":null},{"paper":"/paper/xdit-an-inference-engine-for-diffusion","slug":"xdit-an-inference-engine-for-diffusion","title":"xDiT: an Inference Engine for Diffusion Transformers (DiTs) with Massive Parallelism","date":"2024-11-04","arxiv_id":"2411.01738","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-deep-dive-into-large-language-model-code","title":"A Deep Dive Into Large Language Model Code Generation Mistakes: What and Why?","date":"2024-11-03","arxiv_id":"2411.01414","n_code_links":0,"syntology":null},{"paper":null,"slug":"data-extraction-attacks-in-retrieval","title":"Data Extraction Attacks in Retrieval-Augmented Generation via Backdoors","date":"2024-11-03","arxiv_id":"2411.01705","n_code_links":0,"syntology":null},{"paper":"/paper/enhancing-glucose-level-prediction-of-icu","slug":"enhancing-glucose-level-prediction-of-icu","title":"Enhancing Glucose Level Prediction of ICU Patients through Hierarchical Modeling of Irregular Time-Series","date":"2024-11-03","arxiv_id":"2411.01418","n_code_links":1,"syntology":null},{"paper":null,"slug":"enriching-tabular-data-with-contextual-llm","title":"Enriching Tabular Data with Contextual LLM Embeddings: A Comprehensive Ablation Study for Ensemble Classifiers","date":"2024-11-03","arxiv_id":"2411.01645","n_code_links":0,"syntology":null},{"paper":null,"slug":"gitsr-graph-interaction-transformer-based","title":"GITSR: Graph Interaction Transformer-based Scene Representation for Multi Vehicle Collaborative Decision-making","date":"2024-11-03","arxiv_id":"2411.01608","n_code_links":0,"syntology":null},{"paper":"/paper/graphxform-graph-transformer-for-computer","slug":"graphxform-graph-transformer-for-computer","title":"GraphXForm: Graph transformer for computer-aided molecular design","date":"2024-11-03","arxiv_id":"2411.01667","n_code_links":1,"syntology":null},{"paper":null,"slug":"high-performance-automated-abstract-screening","title":"High-performance automated abstract screening with large language model ensembles","date":"2024-11-03","arxiv_id":"2411.02451","n_code_links":0,"syntology":null},{"paper":null,"slug":"himemformer-hierarchical-memory-aware","title":"HiMemFormer: Hierarchical Memory-Aware Transformer for Multi-Agent Action Anticipation","date":"2024-11-03","arxiv_id":"2411.01455","n_code_links":0,"syntology":null},{"paper":null,"slug":"integration-of-large-vision-language-models","title":"Integration of Large Vision Language Models for Efficient Post-disaster Damage Assessment and Reporting","date":"2024-11-03","arxiv_id":"2411.01511","n_code_links":0,"syntology":null},{"paper":"/paper/linrec-linear-attention-mechanism-for-long","slug":"linrec-linear-attention-mechanism-for-long","title":"LinRec: Linear Attention Mechanism for Long-term Sequential Recommender Systems","date":"2024-11-03","arxiv_id":"2411.01537","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":["Applied-Machine-Learning-Lab/LinRec"],"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/rethinking-weight-decay-for-robust-fine","slug":"rethinking-weight-decay-for-robust-fine","title":"Rethinking Weight Decay for Robust Fine-Tuning of Foundation Models","date":"2024-11-03","arxiv_id":"2411.01713","n_code_links":2,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","official":{"repos":["gt-ripl/selective-projection-decay"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"uniguard-towards-universal-safety-guardrails","title":"UniGuard: Towards Universal Safety Guardrails for Jailbreak Attacks on Multimodal Large Language Models","date":"2024-11-03","arxiv_id":"2411.01703","n_code_links":0,"syntology":null},{"paper":null,"slug":"can-large-language-model-predict-employee","title":"Can Large Language Model Predict Employee Attrition?","date":"2024-11-02","arxiv_id":"2411.01353","n_code_links":0,"syntology":null},{"paper":"/paper/enhancing-neural-network-interpretability-1","slug":"enhancing-neural-network-interpretability-1","title":"Enhancing Neural Network Interpretability with Feature-Aligned Sparse Autoencoders","date":"2024-11-02","arxiv_id":"2411.01220","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["luke-marks0/mutual-feature-regularization"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/few-class-arena-a-benchmark-for-efficient","slug":"few-class-arena-a-benchmark-for-efficient","title":"Few-Class Arena: A Benchmark for Efficient Selection of Vision Models and Dataset Difficulty Measurement","date":"2024-11-02","arxiv_id":"2411.01099","n_code_links":1,"syntology":null},{"paper":null,"slug":"privacy-preserving-federated-learning-with-2","title":"Privacy-Preserving Federated Learning with Differentially Private Hyperdimensional Computing","date":"2024-11-02","arxiv_id":"2411.01140","n_code_links":0,"syntology":null},{"paper":null,"slug":"reasoning-limitations-of-multimodal-large","title":"Reasoning Limitations of Multimodal Large Language Models. A case study of Bongard Problems","date":"2024-11-02","arxiv_id":"2411.01173","n_code_links":0,"syntology":null},{"paper":"/paper/task-aware-harmony-multi-task-decision","slug":"task-aware-harmony-multi-task-decision","title":"Task-Aware Harmony Multi-Task Decision Transformer for Offline Reinforcement Learning","date":"2024-11-02","arxiv_id":"2411.01146","n_code_links":1,"syntology":{"ran":10,"of":11,"n_ran_checked":10,"n_instrument":0,"unverified":1,"pointer_only":2,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["charleshsc/HarmoDT"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/a-lorentz-equivariant-transformer-for-all-of","slug":"a-lorentz-equivariant-transformer-for-all-of","title":"A Lorentz-Equivariant Transformer for All of the LHC","date":"2024-11-01","arxiv_id":"2411.00446","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["heidelberg-hepml/lorentz-gatr"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"attackqa-development-and-adoption-of-a","title":"AttackQA: Development and Adoption of a Dataset for Assisting Cybersecurity Operations using Fine-tuned and Open-Source LLMs","date":"2024-11-01","arxiv_id":"2411.01073","n_code_links":0,"syntology":null},{"paper":null,"slug":"corag-a-cost-constrained-retrieval","title":"CORAG: A Cost-Constrained Retrieval Optimization System for Retrieval-Augmented Generation","date":"2024-11-01","arxiv_id":"2411.00744","n_code_links":0,"syntology":null},{"paper":null,"slug":"cross-fundus-transformer-for-multi-modal","title":"Cross-Fundus Transformer for Multi-modal Diabetic Retinopathy Grading with Cataract","date":"2024-11-01","arxiv_id":"2411.00726","n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluating-the-impact-of-lab-test-results-on","title":"Evaluating the Impact of Lab Test Results on Large Language Models Generated Differential Diagnoses from Clinical Case Vignettes","date":"2024-11-01","arxiv_id":"2411.02523","n_code_links":0,"syntology":null},{"paper":null,"slug":"llm-ref-enhancing-reference-handling-in","title":"LLM-Ref: Enhancing Reference Handling in Technical Writing with Large Language Models","date":"2024-11-01","arxiv_id":"2411.00294","n_code_links":0,"syntology":null},{"paper":null,"slug":"llms-a-game-changer-for-software-engineers","title":"LLMs: A Game-Changer for Software Engineers?","date":"2024-11-01","arxiv_id":"2411.00932","n_code_links":0,"syntology":null},{"paper":null,"slug":"provenance-a-light-weight-fact-checker-for","title":"Provenance: A Light-weight Fact-checker for Retrieval Augmented LLM Generation Output","date":"2024-11-01","arxiv_id":"2411.01022","n_code_links":0,"syntology":null},{"paper":"/paper/rationale-guided-retrieval-augmented","slug":"rationale-guided-retrieval-augmented","title":"Rationale-Guided Retrieval Augmented Generation for Medical Question Answering","date":"2024-11-01","arxiv_id":"2411.00300","n_code_links":1,"syntology":{"ran":6,"of":9,"n_ran_checked":6,"n_instrument":0,"unverified":3,"pointer_only":9,"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) · 3 unverified","official":{"repos":["dmis-lab/rag2"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/self-evolved-reward-learning-for-llms","slug":"self-evolved-reward-learning-for-llms","title":"Self-Evolved Reward Learning for LLMs","date":"2024-11-01","arxiv_id":"2411.00418","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 1 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; the one sample that ran constructed an object rather than computing a result","official":null}},{"paper":"/paper/staa-spatio-temporal-attention-attribution","slug":"staa-spatio-temporal-attention-attribution","title":"STAA: Spatio-Temporal Attention Attribution for Real-Time Interpreting Transformer-based Video Models","date":"2024-11-01","arxiv_id":"2411.00630","n_code_links":1,"syntology":null},{"paper":"/paper/target-guided-adversarial-point-cloud","slug":"target-guided-adversarial-point-cloud","title":"Target-Guided Adversarial Point Cloud Transformer Towards Recognition Against Real-world Corruptions","date":"2024-11-01","arxiv_id":"2411.00462","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["roywangj/apct"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"towards-high-fidelity-head-blending-with","title":"Towards High-fidelity Head Blending with Chroma Keying for Industrial Applications","date":"2024-11-01","arxiv_id":"2411.00652","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-multi-source-retrieval-augmented","title":"Towards Multi-Source Retrieval-Augmented Generation via Synergizing Reasoning and Preference-Driven Retrieval","date":"2024-11-01","arxiv_id":"2411.00689","n_code_links":0,"syntology":null},{"paper":"/paper/ada-mshyper-adaptive-multi-scale-hypergraph","slug":"ada-mshyper-adaptive-multi-scale-hypergraph","title":"Ada-MSHyper: Adaptive Multi-Scale Hypergraph Transformer for Time Series Forecasting","date":"2024-10-31","arxiv_id":"2410.23992","n_code_links":1,"syntology":{"ran":0,"of":4,"n_ran_checked":0,"n_instrument":0,"unverified":4,"pointer_only":4,"phrase":"0 ran · 4 unverified","official":{"repos":["shangzongjiang/Ada-MSHyper"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":4,"ran_from_kinds":[]}}}],"record_sha256":"5dcd8643d40cfce82d8c219d21aa0161204c6c0b00557993e80a3e60cb753444","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}