{"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/23","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":23,"pages_in_order":244,"rows_per_page":100,"rows":[2201,2300],"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/22","next":"/method/adam/papers/24","papers":[{"paper":null,"slug":"autoloop-fast-visual-slam-fine-tuning-through","title":"AutoLoop: Fast Visual SLAM Fine-tuning through Agentic Curriculum Learning","date":"2025-01-15","arxiv_id":"2501.09160","n_code_links":0,"syntology":null},{"paper":"/paper/bright-vo-brightness-guided-hybrid","slug":"bright-vo-brightness-guided-hybrid","title":"BRIGHT-VO: Brightness-Guided Hybrid Transformer for Visual Odometry with Multi-modality Refinement Module","date":"2025-01-15","arxiv_id":"2501.08659","n_code_links":1,"syntology":null},{"paper":null,"slug":"ct-patchtst-channel-time-patch-time-series","title":"CT-PatchTST: Channel-Time Patch Time-Series Transformer for Long-Term Renewable Energy Forecasting","date":"2025-01-15","arxiv_id":"2501.08620","n_code_links":0,"syntology":null},{"paper":null,"slug":"dynamic-portfolio-optimization-via-augmented","title":"Dynamic Portfolio Optimization via Augmented DDPG with Quantum Price Levels-Based Trading Strategy","date":"2025-01-15","arxiv_id":"2501.08528","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhanced-large-language-models-for-effective","title":"Enhanced Large Language Models for Effective Screening of Depression and Anxiety","date":"2025-01-15","arxiv_id":"2501.08769","n_code_links":0,"syntology":null},{"paper":null,"slug":"expanding-vietnamese-sentiwordnet-to-improve","title":"Expanding Vietnamese SentiWordNet to Improve Performance of Vietnamese Sentiment Analysis Models","date":"2025-01-15","arxiv_id":"2501.08758","n_code_links":0,"syntology":null},{"paper":null,"slug":"generative-ai-takes-a-statistics-exam-a","title":"Generative AI Takes a Statistics Exam: A Comparison of Performance between ChatGPT3.5, ChatGPT4, and ChatGPT4o-mini","date":"2025-01-15","arxiv_id":"2501.09171","n_code_links":0,"syntology":null},{"paper":null,"slug":"miafex-an-attention-based-feature-extraction","title":"MIAFEx: An Attention-based Feature Extraction Method for Medical Image Classification","date":"2025-01-15","arxiv_id":"2501.08562","n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-view-transformers-for-airway-to-lung","title":"Multi-View Transformers for Airway-To-Lung Ratio Inference on Cardiac CT Scans: The C4R Study","date":"2025-01-15","arxiv_id":"2501.08902","n_code_links":0,"syntology":null},{"paper":null,"slug":"multimodal-fake-news-video-explanation","title":"Multimodal Fake News Video Explanation: Dataset, Analysis and Evaluation","date":"2025-01-15","arxiv_id":"2501.08514","n_code_links":0,"syntology":null},{"paper":"/paper/supersam-crafting-a-sam-supernetwork-via","slug":"supersam-crafting-a-sam-supernetwork-via","title":"SuperSAM: Crafting a SAM Supernetwork via Structured Pruning and Unstructured Parameter Prioritization","date":"2025-01-15","arxiv_id":"2501.08504","n_code_links":1,"syntology":null},{"paper":"/paper/swintexco-exemplar-based-video-colorization","slug":"swintexco-exemplar-based-video-colorization","title":"SwinTExCo: Exemplar-based video colorization using Swin Transformer","date":"2025-01-15","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"the-impact-of-big-five-personality-traits-on","title":"The Impact of Big Five Personality Traits on AI Agent Decision-Making in Public Spaces: A Social Simulation Study","date":"2025-01-15","arxiv_id":"2503.15497","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-driver-advisory-system-based-on-large","title":"A Driver Advisory System Based on Large Language Model for High-speed Train","date":"2025-01-14","arxiv_id":"2501.07837","n_code_links":0,"syntology":null},{"paper":null,"slug":"active-sampling-for-node-attribute-completion","title":"Active Sampling for Node Attribute Completion on Graphs","date":"2025-01-14","arxiv_id":"2501.08450","n_code_links":0,"syntology":null},{"paper":null,"slug":"astrid-an-automated-and-scalable-triad-for","title":"ASTRID -- An Automated and Scalable TRIaD for the Evaluation of RAG-based Clinical Question Answering Systems","date":"2025-01-14","arxiv_id":"2501.08208","n_code_links":0,"syntology":null},{"paper":null,"slug":"comparative-analysis-of-efficient-adapter","title":"Comparative Analysis of Efficient Adapter-Based Fine-Tuning of State-of-the-Art Transformer Models","date":"2025-01-14","arxiv_id":"2501.08271","n_code_links":0,"syntology":null},{"paper":null,"slug":"decision-transformers-for-ris-assisted","title":"Decision Transformers for RIS-Assisted Systems with Diffusion Model-Based Channel Acquisition","date":"2025-01-14","arxiv_id":"2501.08007","n_code_links":0,"syntology":null},{"paper":null,"slug":"decoding-interpretable-logic-rules-from","title":"Decoding Interpretable Logic Rules from Neural Networks","date":"2025-01-14","arxiv_id":"2501.08281","n_code_links":0,"syntology":null},{"paper":"/paper/efficient-deep-learning-based-forward-solvers","slug":"efficient-deep-learning-based-forward-solvers","title":"Efficient Deep Learning-based Forward Solvers for Brain Tumor Growth Models","date":"2025-01-14","arxiv_id":"2501.08226","n_code_links":1,"syntology":null},{"paper":null,"slug":"eliciting-in-context-retrieval-and-reasoning","title":"Eliciting In-context Retrieval and Reasoning for Long-context Large Language Models","date":"2025-01-14","arxiv_id":"2501.08248","n_code_links":0,"syntology":null},{"paper":"/paper/emonext-an-adapted-convnext-for-facial-1","slug":"emonext-an-adapted-convnext-for-facial-1","title":"EmoNeXt: an Adapted ConvNeXt for Facial Emotion Recognition","date":"2025-01-14","arxiv_id":"2501.08199","n_code_links":1,"syntology":null},{"paper":null,"slug":"exploring-narrative-clustering-in-large","title":"Exploring Narrative Clustering in Large Language Models: A Layerwise Analysis of BERT","date":"2025-01-14","arxiv_id":"2501.08053","n_code_links":0,"syntology":null},{"paper":null,"slug":"investigating-energy-efficiency-and","title":"Investigating Energy Efficiency and Performance Trade-offs in LLM Inference Across Tasks and DVFS Settings","date":"2025-01-14","arxiv_id":"2501.08219","n_code_links":0,"syntology":null},{"paper":null,"slug":"large-language-models-for-text-classification","title":"Large Language Models For Text Classification: Case Study And Comprehensive Review","date":"2025-01-14","arxiv_id":"2501.08457","n_code_links":0,"syntology":null},{"paper":null,"slug":"optimizing-language-models-for-grammatical","title":"Optimizing Language Models for Grammatical Acceptability: A Comparative Study of Fine-Tuning Techniques","date":"2025-01-14","arxiv_id":"2501.07853","n_code_links":0,"syntology":null},{"paper":"/paper/pokerbench-training-large-language-models-to","slug":"pokerbench-training-large-language-models-to","title":"PokerBench: Training Large Language Models to become Professional Poker Players","date":"2025-01-14","arxiv_id":"2501.08328","n_code_links":1,"syntology":null},{"paper":null,"slug":"psreg-prior-guided-sparse-mixture-of-experts","title":"PSReg: Prior-guided Sparse Mixture of Experts for Point Cloud Registration","date":"2025-01-14","arxiv_id":"2501.07762","n_code_links":0,"syntology":null},{"paper":null,"slug":"read-reinforcement-based-adversarial-learning","title":"READ: Reinforcement-based Adversarial Learning for Text Classification with Limited Labeled Data","date":"2025-01-14","arxiv_id":"2501.08035","n_code_links":0,"syntology":null},{"paper":"/paper/rearter-retrieval-augmented-reasoning-with","slug":"rearter-retrieval-augmented-reasoning-with","title":"ReARTeR: Retrieval-Augmented Reasoning with Trustworthy Process Rewarding","date":"2025-01-14","arxiv_id":"2501.07861","n_code_links":1,"syntology":null},{"paper":null,"slug":"towards-lightweight-time-series-forecasting-a","title":"Towards Lightweight Time Series Forecasting: a Patch-wise Transformer with Weak Data Enriching","date":"2025-01-14","arxiv_id":"2501.10448","n_code_links":0,"syntology":null},{"paper":null,"slug":"transforming-indoor-localization-advanced","title":"Transforming Indoor Localization: Advanced Transformer Architecture for NLOS Dominated Wireless Environments with Distributed Sensors","date":"2025-01-14","arxiv_id":"2501.07774","n_code_links":0,"syntology":null},{"paper":"/paper/ufgraphfr-an-attempt-at-a-federated","slug":"ufgraphfr-an-attempt-at-a-federated","title":"UFGraphFR: An attempt at a federated recommendation system based on user text characteristics","date":"2025-01-14","arxiv_id":"2501.08044","n_code_links":1,"syntology":null},{"paper":"/paper/breaking-memory-limits-gradient-wavelet","slug":"breaking-memory-limits-gradient-wavelet","title":"Breaking Memory Limits: Gradient Wavelet Transform Enhances LLMs Training","date":"2025-01-13","arxiv_id":"2501.07237","n_code_links":1,"syntology":null},{"paper":"/paper/d3mes-diffusion-transformer-with-multihead","slug":"d3mes-diffusion-transformer-with-multihead","title":"D3MES: Diffusion Transformer with multihead equivariant self-attention for 3D molecule generation","date":"2025-01-13","arxiv_id":"2501.07077","n_code_links":1,"syntology":null},{"paper":"/paper/edgetam-on-device-track-anything-model","slug":"edgetam-on-device-track-anything-model","title":"EdgeTAM: On-Device Track Anything Model","date":"2025-01-13","arxiv_id":"2501.07256","n_code_links":1,"syntology":{"ran":7,"of":8,"n_ran_checked":4,"n_instrument":3,"unverified":1,"pointer_only":0,"phrase":"7 ran (of which 2 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 1 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","official":{"repos":["facebookresearch/edgetam"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["found_in_text"]}}},{"paper":"/paper/enhancing-retrieval-augmented-generation-a","slug":"enhancing-retrieval-augmented-generation-a","title":"Enhancing Retrieval-Augmented Generation: A Study of Best Practices","date":"2025-01-13","arxiv_id":"2501.07391","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":["ali-bahrainian/rag_best_practices"],"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":"enhancing-talent-employment-insights-through","title":"Enhancing Talent Employment Insights Through Feature Extraction with LLM Finetuning","date":"2025-01-13","arxiv_id":"2501.07663","n_code_links":0,"syntology":null},{"paper":"/paper/estimating-musical-surprisal-in-audio","slug":"estimating-musical-surprisal-in-audio","title":"Estimating Musical Surprisal in Audio","date":"2025-01-13","arxiv_id":"2501.07474","n_code_links":1,"syntology":null},{"paper":"/paper/finerweb-10bt-refining-web-data-with-llm","slug":"finerweb-10bt-refining-web-data-with-llm","title":"FinerWeb-10BT: Refining Web Data with LLM-Based Line-Level Filtering","date":"2025-01-13","arxiv_id":"2501.07314","n_code_links":1,"syntology":null},{"paper":null,"slug":"future-conditioned-recommendations-with-multi","title":"Future-Conditioned Recommendations with Multi-Objective Controllable Decision Transformer","date":"2025-01-13","arxiv_id":"2501.07212","n_code_links":0,"syntology":null},{"paper":null,"slug":"gpt-as-a-monte-carlo-language-tree-a","title":"GPT as a Monte Carlo Language Tree: A Probabilistic Perspective","date":"2025-01-13","arxiv_id":"2501.07641","n_code_links":0,"syntology":null},{"paper":"/paper/how-gpt-learns-layer-by-layer","slug":"how-gpt-learns-layer-by-layer","title":"How GPT learns layer by layer","date":"2025-01-13","arxiv_id":"2501.07108","n_code_links":1,"syntology":null},{"paper":null,"slug":"parallel-key-value-cache-fusion-for-position","title":"Parallel Key-Value Cache Fusion for Position Invariant RAG","date":"2025-01-13","arxiv_id":"2501.07523","n_code_links":0,"syntology":null},{"paper":null,"slug":"scaling-up-esm2-architectures-for-long","title":"Scaling Up ESM2 Architectures for Long Protein Sequences Analysis: Long and Quantized Approaches","date":"2025-01-13","arxiv_id":"2501.07747","n_code_links":0,"syntology":null},{"paper":"/paper/sst-em-advanced-metrics-for-evaluating","slug":"sst-em-advanced-metrics-for-evaluating","title":"SST-EM: Advanced Metrics for Evaluating Semantic, Spatial and Temporal Aspects in Video Editing","date":"2025-01-13","arxiv_id":"2501.07554","n_code_links":1,"syntology":null},{"paper":"/paper/webwalker-benchmarking-llms-in-web-traversal","slug":"webwalker-benchmarking-llms-in-web-traversal","title":"WebWalker: Benchmarking LLMs in Web Traversal","date":"2025-01-13","arxiv_id":"2501.07572","n_code_links":2,"syntology":null},{"paper":null,"slug":"average-reward-reinforcement-learning-for","title":"Average Reward Reinforcement Learning for Wireless Radio Resource Management","date":"2025-01-12","arxiv_id":"2501.06700","n_code_links":0,"syntology":null},{"paper":null,"slug":"benchmarking-yolov8-for-optimal-crack","title":"Benchmarking YOLOv8 for Optimal Crack Detection in Civil Infrastructure","date":"2025-01-12","arxiv_id":"2501.06922","n_code_links":0,"syntology":null},{"paper":null,"slug":"better-prompt-compression-without-multi-layer","title":"Better Prompt Compression Without Multi-Layer Perceptrons","date":"2025-01-12","arxiv_id":"2501.06730","n_code_links":0,"syntology":null},{"paper":null,"slug":"drdt3-diffusion-refined-decision-test-time","title":"DRDT3: Diffusion-Refined Decision Test-Time Training Model","date":"2025-01-12","arxiv_id":"2501.06718","n_code_links":0,"syntology":null},{"paper":"/paper/eliza-a-web3-friendly-ai-agent-operating","slug":"eliza-a-web3-friendly-ai-agent-operating","title":"Eliza: A Web3 friendly AI Agent Operating System","date":"2025-01-12","arxiv_id":"2501.06781","n_code_links":2,"syntology":null},{"paper":null,"slug":"generative-artificial-intelligence-supported","title":"Generative Artificial Intelligence-Supported Pentesting: A Comparison between Claude Opus, GPT-4, and Copilot","date":"2025-01-12","arxiv_id":"2501.06963","n_code_links":0,"syntology":null},{"paper":null,"slug":"mfconvtr-multi-frequency-convolutional","title":"MFConvTr: Multi-Frequency Convolutional Transformer for Fetal Arrhythmia Detection in Non-Invasive fECG","date":"2025-01-12","arxiv_id":"2501.16649","n_code_links":0,"syntology":null},{"paper":"/paper/minirag-towards-extremely-simple-retrieval","slug":"minirag-towards-extremely-simple-retrieval","title":"MiniRAG: Towards Extremely Simple Retrieval-Augmented Generation","date":"2025-01-12","arxiv_id":"2501.06713","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":0,"phrase":"2 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; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["hkuds/minirag"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/spam-spike-aware-adam-with-momentum-reset-for","slug":"spam-spike-aware-adam-with-momentum-reset-for","title":"SPAM: Spike-Aware Adam with Momentum Reset for Stable LLM Training","date":"2025-01-12","arxiv_id":"2501.06842","n_code_links":1,"syntology":null},{"paper":"/paper/transforming-vision-transformer-towards","slug":"transforming-vision-transformer-towards","title":"Transforming Vision Transformer: Towards Efficient Multi-Task Asynchronous Learning","date":"2025-01-12","arxiv_id":"2501.06884","n_code_links":1,"syntology":{"ran":3,"of":7,"n_ran_checked":1,"n_instrument":2,"unverified":4,"pointer_only":7,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified","official":{"repos":["yewen1486/emtal"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/zno-eval-benchmarking-reasoning-capabilities","slug":"zno-eval-benchmarking-reasoning-capabilities","title":"ZNO-Eval: Benchmarking reasoning capabilities of large language models in Ukrainian","date":"2025-01-12","arxiv_id":"2501.06715","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-comparative-performance-analysis-of-1","title":"A Comparative Performance Analysis of Classification and Segmentation Models on Bangladeshi Pothole Dataset","date":"2025-01-11","arxiv_id":"2501.06602","n_code_links":0,"syntology":null},{"paper":"/paper/assessing-instructor-ai-cooperation-for","slug":"assessing-instructor-ai-cooperation-for","title":"Assessing instructor-AI cooperation for grading essay-type questions in an introductory sociology course","date":"2025-01-11","arxiv_id":"2501.06461","n_code_links":1,"syntology":null},{"paper":"/paper/cevit-copula-enhanced-vision-transformer-in","slug":"cevit-copula-enhanced-vision-transformer-in","title":"CeViT: Copula-Enhanced Vision Transformer in multi-task learning and bi-group image covariates with an application to myopia screening","date":"2025-01-11","arxiv_id":"2501.06540","n_code_links":1,"syntology":null},{"paper":null,"slug":"first-token-probability-guided-rag-for","title":"First Token Probability Guided RAG for Telecom Question Answering","date":"2025-01-11","arxiv_id":"2501.06468","n_code_links":0,"syntology":null},{"paper":"/paper/flash-window-attention-speedup-the-attention","slug":"flash-window-attention-speedup-the-attention","title":"Flash Window Attention: speedup the attention computation for Swin Transformer","date":"2025-01-11","arxiv_id":"2501.06480","n_code_links":2,"syntology":null},{"paper":null,"slug":"focusdd-real-world-scene-infusion-for-robust","title":"FocusDD: Real-World Scene Infusion for Robust Dataset Distillation","date":"2025-01-11","arxiv_id":"2501.06405","n_code_links":0,"syntology":null},{"paper":"/paper/ladder-residual-parallelism-aware","slug":"ladder-residual-parallelism-aware","title":"Ladder-residual: parallelism-aware architecture for accelerating large model inference with communication overlapping","date":"2025-01-11","arxiv_id":"2501.06589","n_code_links":1,"syntology":{"ran":9,"of":10,"n_ran_checked":4,"n_instrument":5,"unverified":1,"pointer_only":1,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified","official":{"repos":["mayank31398/ladder-residual-inference"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/tensor-product-attention-is-all-you-need","slug":"tensor-product-attention-is-all-you-need","title":"Tensor Product Attention Is All You Need","date":"2025-01-11","arxiv_id":"2501.06425","n_code_links":1,"syntology":{"ran":8,"of":9,"n_ran_checked":3,"n_instrument":5,"unverified":1,"pointer_only":2,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified","official":{"repos":["tensorgi/t6"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["community","official"]}}},{"paper":null,"slug":"ultra-memory-efficient-on-fpga-training-of","title":"Ultra Memory-Efficient On-FPGA Training of Transformers via Tensor-Compressed Optimization","date":"2025-01-11","arxiv_id":"2501.06663","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-holistically-point-guided-text-framework","title":"A Holistically Point-guided Text Framework for Weakly-Supervised Camouflaged Object Detection","date":"2025-01-10","arxiv_id":"2501.06038","n_code_links":0,"syntology":null},{"paper":"/paper/an-attention-guided-deep-learning-approach","slug":"an-attention-guided-deep-learning-approach","title":"An Attention-Guided Deep Learning Approach for Classifying 39 Skin Lesion Types","date":"2025-01-10","arxiv_id":"2501.05991","n_code_links":1,"syntology":null},{"paper":null,"slug":"analyzing-spatio-temporal-dynamics-of","title":"Analyzing Spatio-Temporal Dynamics of Dissolved Oxygen for the River Thames using Superstatistical Methods and Machine Learning","date":"2025-01-10","arxiv_id":"2501.07599","n_code_links":0,"syntology":null},{"paper":"/paper/averaged-adam-accelerates-stochastic","slug":"averaged-adam-accelerates-stochastic","title":"Averaged Adam accelerates stochastic optimization in the training of deep neural network approximations for partial differential equation and optimal control problems","date":"2025-01-10","arxiv_id":"2501.06081","n_code_links":1,"syntology":null},{"paper":null,"slug":"binary-event-driven-spiking-transformer","title":"Binary Event-Driven Spiking Transformer","date":"2025-01-10","arxiv_id":"2501.05904","n_code_links":0,"syntology":null},{"paper":null,"slug":"cognospeak-an-automatic-remote-assessment-of","title":"CognoSpeak: an automatic, remote assessment of early cognitive decline in real-world conversational speech","date":"2025-01-10","arxiv_id":"2501.05755","n_code_links":0,"syntology":null},{"paper":null,"slug":"iconicity-in-large-language-models","title":"Iconicity in Large Language Models","date":"2025-01-10","arxiv_id":"2501.05643","n_code_links":0,"syntology":null},{"paper":"/paper/merging-feed-forward-sublayers-for-compressed","slug":"merging-feed-forward-sublayers-for-compressed","title":"Merging Feed-Forward Sublayers for Compressed Transformers","date":"2025-01-10","arxiv_id":"2501.06126","n_code_links":1,"syntology":null},{"paper":null,"slug":"mix-qvit-mixed-precision-vision-transformer","title":"Mix-QViT: Mixed-Precision Vision Transformer Quantization Driven by Layer Importance and Quantization Sensitivity","date":"2025-01-10","arxiv_id":"2501.06357","n_code_links":0,"syntology":null},{"paper":null,"slug":"model-inversion-in-split-learning-for","title":"Model Inversion in Split Learning for Personalized LLMs: New Insights from Information Bottleneck Theory","date":"2025-01-10","arxiv_id":"2501.05965","n_code_links":0,"syntology":null},{"paper":null,"slug":"mscvit-a-small-size-vit-architecture-with","title":"MSCViT: A Small-size ViT architecture with Multi-Scale Self-Attention Mechanism for Tiny Datasets","date":"2025-01-10","arxiv_id":"2501.06040","n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-subject-open-set-personalization-in","title":"Multi-subject Open-set Personalization in Video Generation","date":"2025-01-10","arxiv_id":"2501.06187","n_code_links":0,"syntology":null},{"paper":"/paper/punctuation-s-semantic-role-between-brain-and","slug":"punctuation-s-semantic-role-between-brain-and","title":"Aligning Brain Activity with Advanced Transformer Models: Exploring the Role of Punctuation in Semantic Processing","date":"2025-01-10","arxiv_id":"2501.06278","n_code_links":1,"syntology":null},{"paper":null,"slug":"swin-x2s-reconstructing-3d-shape-from-2d","title":"Swin-X2S: Reconstructing 3D Shape from 2D Biplanar X-ray with Swin Transformers","date":"2025-01-10","arxiv_id":"2501.05961","n_code_links":0,"syntology":null},{"paper":null,"slug":"tts-transducer-end-to-end-speech-synthesis","title":"TTS-Transducer: End-to-End Speech Synthesis with Neural Transducer","date":"2025-01-10","arxiv_id":"2501.06320","n_code_links":0,"syntology":null},{"paper":"/paper/videorag-retrieval-augmented-generation-over","slug":"videorag-retrieval-augmented-generation-over","title":"VideoRAG: Retrieval-Augmented Generation over Video Corpus","date":"2025-01-10","arxiv_id":"2501.05874","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, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["starsuzi/videorag"],"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":"weakly-supervised-segmentation-of-hyper","title":"Weakly Supervised Segmentation of Hyper-Reflective Foci with Compact Convolutional Transformers and SAM2","date":"2025-01-10","arxiv_id":"2501.05933","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-general-retrieval-augmented-generation","title":"A General Retrieval-Augmented Generation Framework for Multimodal Case-Based Reasoning Applications","date":"2025-01-09","arxiv_id":"2501.05030","n_code_links":0,"syntology":null},{"paper":null,"slug":"biomedical-relation-extraction-via-adaptive","title":"Biomedical Relation Extraction via Adaptive Document-Relation Cross-Mapping and Concept Unique Identifier","date":"2025-01-09","arxiv_id":"2501.05155","n_code_links":0,"syntology":null},{"paper":null,"slug":"dissim-finbert-text-simplification-for-core","title":"DisSim-FinBERT: Text Simplification for Core Message Extraction in Complex Financial Texts","date":"2025-01-09","arxiv_id":"2501.04959","n_code_links":0,"syntology":null},{"paper":"/paper/enhancing-plagiarism-detection-in-marathi","slug":"enhancing-plagiarism-detection-in-marathi","title":"Enhancing Plagiarism Detection in Marathi with a Weighted Ensemble of TF-IDF and BERT Embeddings for Low-Resource Language Processing","date":"2025-01-09","arxiv_id":"2501.05260","n_code_links":1,"syntology":null},{"paper":null,"slug":"large-language-models-streamline-automated","title":"Large language models streamline automated systematic review: A preliminary study","date":"2025-01-09","arxiv_id":"2502.15702","n_code_links":0,"syntology":null},{"paper":"/paper/llmquoter-enhancing-rag-capabilities-through","slug":"llmquoter-enhancing-rag-capabilities-through","title":"LLMQuoter: Enhancing RAG Capabilities Through Efficient Quote Extraction From Large Contexts","date":"2025-01-09","arxiv_id":"2501.05554","n_code_links":1,"syntology":null},{"paper":null,"slug":"longvitu-instruction-tuning-for-long-form","title":"LongViTU: Instruction Tuning for Long-Form Video Understanding","date":"2025-01-09","arxiv_id":"2501.05037","n_code_links":0,"syntology":null},{"paper":null,"slug":"openai-chatgpt-interprets-radiological-images","title":"OpenAI ChatGPT interprets Radiological Images: GPT-4 as a Medical Doctor for a Fast Check-Up","date":"2025-01-09","arxiv_id":"2501.06269","n_code_links":0,"syntology":null},{"paper":null,"slug":"optimizing-multitask-industrial-processes","title":"Optimizing Multitask Industrial Processes with Predictive Action Guidance","date":"2025-01-09","arxiv_id":"2501.05108","n_code_links":0,"syntology":null},{"paper":null,"slug":"rag-wm-an-efficient-black-box-watermarking","title":"RAG-WM: An Efficient Black-Box Watermarking Approach for Retrieval-Augmented Generation of Large Language Models","date":"2025-01-09","arxiv_id":"2501.05249","n_code_links":0,"syntology":null},{"paper":"/paper/spectf-transformers-enable-data-driven","slug":"spectf-transformers-enable-data-driven","title":"SpecTf: Transformers Enable Data-Driven Imaging Spectroscopy Cloud Detection","date":"2025-01-09","arxiv_id":"2501.04916","n_code_links":1,"syntology":null},{"paper":null,"slug":"the-dynamics-of-meaning-through-time","title":"The dynamics of meaning through time: Assessment of Large Language Models","date":"2025-01-09","arxiv_id":"2501.05552","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-more-polypersonal-the-better-a-short-look","title":"The more polypersonal the better -- a short look on space geometry of fine-tuned layers","date":"2025-01-09","arxiv_id":"2501.05503","n_code_links":0,"syntology":null},{"paper":"/paper/uav-vla-vision-language-action-system-for","slug":"uav-vla-vision-language-action-system-for","title":"UAV-VLA: Vision-Language-Action System for Large Scale Aerial Mission Generation","date":"2025-01-09","arxiv_id":"2501.05014","n_code_links":1,"syntology":null},{"paper":null,"slug":"advancing-retrieval-augmented-generation-for","title":"Advancing Retrieval-Augmented Generation for Persian: Development of Language Models, Comprehensive Benchmarks, and Best Practices for Optimization","date":"2025-01-08","arxiv_id":"2501.04858","n_code_links":0,"syntology":null},{"paper":null,"slug":"circuit-complexity-bounds-for-visual","title":"Circuit Complexity Bounds for Visual Autoregressive Model","date":"2025-01-08","arxiv_id":"2501.04299","n_code_links":0,"syntology":null}],"record_sha256":"ecb6e4364fe85623dda52d2eff7545bfee11f72ebe38f6e167aa3f0a3669b9b5","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}