{"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/linear-layer/papers/44","list_of":"/method/linear-layer","method":"Linear Layer","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":44,"pages_in_order":255,"rows_per_page":100,"rows":[4301,4400],"of":25421,"counts":{"archive_papers_tagged":25421,"with_a_code_link":11479,"where_syntology_ran_a_sample":3523,"not_listed_spam_title":0,"listed":25421,"listed_where_code_ran":3523,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":2976,"every_run_a_failure_of_syntologys_instrument":547,"listed_with_a_run_with_no_instrument_failure":2976,"listed_every_run_a_failure_of_syntologys_instrument":547,"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/linear-layer","prev":"/method/linear-layer/papers/43","next":"/method/linear-layer/papers/45","papers":[{"paper":null,"slug":"on-instruction-finetuning-neural-machine","title":"On Instruction-Finetuning Neural Machine Translation Models","date":"2024-10-07","arxiv_id":"2410.05553","n_code_links":0,"syntology":null},{"paper":null,"slug":"on-the-optimization-and-generalization-of-two","title":"On the Optimization and Generalization of Two-layer Transformers with Sign Gradient Descent","date":"2024-10-07","arxiv_id":"2410.04870","n_code_links":0,"syntology":null},{"paper":"/paper/predformer-transformers-are-effective-spatial","slug":"predformer-transformers-are-effective-spatial","title":"Video Prediction Transformers without Recurrence or Convolution","date":"2024-10-07","arxiv_id":"2410.04733","n_code_links":1,"syntology":null},{"paper":null,"slug":"restnet-defense-against-adversarial-policies","title":"ResTNet: Defense against Adversarial Policies via Transformer in Computer Go","date":"2024-10-07","arxiv_id":"2410.05347","n_code_links":0,"syntology":null},{"paper":"/paper/spatio-temporal-3d-point-clouds-from-wifi-csi","slug":"spatio-temporal-3d-point-clouds-from-wifi-csi","title":"Spatio-Temporal 3D Point Clouds from WiFi-CSI Data via Transformer Networks","date":"2024-10-07","arxiv_id":"2410.16303","n_code_links":1,"syntology":null},{"paper":"/paper/tidaldecode-fast-and-accurate-llm-decoding","slug":"tidaldecode-fast-and-accurate-llm-decoding","title":"TidalDecode: Fast and Accurate LLM Decoding with Position Persistent Sparse Attention","date":"2024-10-07","arxiv_id":"2410.05076","n_code_links":1,"syntology":{"ran":12,"of":13,"n_ran_checked":7,"n_instrument":5,"unverified":1,"pointer_only":4,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 1 violated, 5 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified","official":{"repos":["DerrickYLJ/TidalDecode"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/timer-xl-long-context-transformers-for","slug":"timer-xl-long-context-transformers-for","title":"Timer-XL: Long-Context Transformers for Unified Time Series Forecasting","date":"2024-10-07","arxiv_id":"2410.04803","n_code_links":2,"syntology":null},{"paper":null,"slug":"copylens-dynamically-flagging-copyrighted-sub","title":"Inner-Probe: Discovering Copyright-related Data Generation in LLM Architecture","date":"2024-10-06","arxiv_id":"2410.04454","n_code_links":0,"syntology":null},{"paper":null,"slug":"diagnosing-robotics-systems-issues-with-large","title":"Diagnosing Robotics Systems Issues with Large Language Models","date":"2024-10-06","arxiv_id":"2410.09084","n_code_links":0,"syntology":null},{"paper":"/paper/enhancing-3d-human-pose-estimation-amidst","slug":"enhancing-3d-human-pose-estimation-amidst","title":"Enhancing 3D Human Pose Estimation Amidst Severe Occlusion with Dual Transformer Fusion","date":"2024-10-06","arxiv_id":"2410.04574","n_code_links":1,"syntology":null},{"paper":"/paper/famma-a-benchmark-for-financial-domain","slug":"famma-a-benchmark-for-financial-domain","title":"FAMMA: A Benchmark for Financial Domain Multilingual Multimodal Question Answering","date":"2024-10-06","arxiv_id":"2410.04526","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":["famma-bench/bench-script"],"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":"inference-scaling-for-long-context-retrieval","title":"Inference Scaling for Long-Context Retrieval Augmented Generation","date":"2024-10-06","arxiv_id":"2410.04343","n_code_links":0,"syntology":null},{"paper":"/paper/large-language-model-inference-acceleration-a","slug":"large-language-model-inference-acceleration-a","title":"Large Language Model Inference Acceleration: A Comprehensive Hardware Perspective","date":"2024-10-06","arxiv_id":"2410.04466","n_code_links":1,"syntology":null},{"paper":null,"slug":"large-language-models-for-knowledge-free","title":"Large Language Models for Knowledge-Free Network Management: Feasibility Study and Opportunities","date":"2024-10-06","arxiv_id":"2410.17259","n_code_links":0,"syntology":null},{"paper":"/paper/mindscope-exploring-cognitive-biases-in-large","slug":"mindscope-exploring-cognitive-biases-in-large","title":"MindScope: Exploring cognitive biases in large language models through Multi-Agent Systems","date":"2024-10-06","arxiv_id":"2410.04452","n_code_links":1,"syntology":null},{"paper":null,"slug":"protocollm-automatic-evaluation-framework-of","title":"ProtocoLLM: Automatic Evaluation Framework of LLMs on Domain-Specific Scientific Protocol Formulation Tasks","date":"2024-10-06","arxiv_id":"2410.04601","n_code_links":0,"syntology":null},{"paper":null,"slug":"assessing-the-performance-of-human-capable","title":"Assessing the Performance of Human-Capable LLMs -- Are LLMs Coming for Your Job?","date":"2024-10-05","arxiv_id":"2410.16285","n_code_links":0,"syntology":null},{"paper":"/paper/beyond-language-applying-mlx-transformers-to","slug":"beyond-language-applying-mlx-transformers-to","title":"Beyond Language: Applying MLX Transformers to Engineering Physics","date":"2024-10-05","arxiv_id":"2410.04167","n_code_links":1,"syntology":null},{"paper":null,"slug":"can-the-variation-of-model-weights-be-used-as","title":"Can the Variation of Model Weights be used as a Criterion for Self-Paced Multilingual NMT?","date":"2024-10-05","arxiv_id":"2410.04147","n_code_links":0,"syntology":null},{"paper":"/paper/cross-resolution-encoding-decoding-for","slug":"cross-resolution-encoding-decoding-for","title":"Cross Resolution Encoding-Decoding For Detection Transformers","date":"2024-10-05","arxiv_id":"2410.04088","n_code_links":1,"syntology":null},{"paper":null,"slug":"deep-transfer-learning-based-peer-review","title":"Deep Transfer Learning Based Peer Review Aggregation and Meta-review Generation for Scientific Articles","date":"2024-10-05","arxiv_id":"2410.04202","n_code_links":0,"syntology":null},{"paper":"/paper/defog-discrete-flow-matching-for-graph","slug":"defog-discrete-flow-matching-for-graph","title":"DeFoG: Discrete Flow Matching for Graph Generation","date":"2024-10-05","arxiv_id":"2410.04263","n_code_links":1,"syntology":{"ran":12,"of":15,"n_ran_checked":11,"n_instrument":1,"unverified":3,"pointer_only":1,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 0 violated, 10 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","official":{"repos":["manuelmlmadeira/DeFoG"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"designing-concise-convnets-with-columnar","title":"Designing Concise ConvNets with Columnar Stages","date":"2024-10-05","arxiv_id":"2410.04089","n_code_links":0,"syntology":null},{"paper":"/paper/econ-on-the-detection-and-resolution-of","slug":"econ-on-the-detection-and-resolution-of","title":"ECon: On the Detection and Resolution of Evidence Conflicts","date":"2024-10-05","arxiv_id":"2410.04068","n_code_links":1,"syntology":null},{"paper":"/paper/equivariant-neural-functional-networks-for","slug":"equivariant-neural-functional-networks-for","title":"Equivariant Neural Functional Networks for Transformers","date":"2024-10-05","arxiv_id":"2410.04209","n_code_links":0,"syntology":{"ran":4,"of":6,"n_ran_checked":4,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"4 ran (of which 3 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) · 2 unverified","official":null}},{"paper":null,"slug":"fundamental-limitations-on-subquadratic","title":"Fundamental Limitations on Subquadratic Alternatives to Transformers","date":"2024-10-05","arxiv_id":"2410.04271","n_code_links":0,"syntology":null},{"paper":"/paper/gamified-crowd-sourcing-of-high-quality-data","slug":"gamified-crowd-sourcing-of-high-quality-data","title":"Gamified crowd-sourcing of high-quality data for visual fine-tuning","date":"2024-10-05","arxiv_id":"2410.04038","n_code_links":0,"syntology":null},{"paper":null,"slug":"metadata-based-data-exploration-with","title":"Metadata-based Data Exploration with Retrieval-Augmented Generation for Large Language Models","date":"2024-10-05","arxiv_id":"2410.04231","n_code_links":0,"syntology":null},{"paper":"/paper/multimodal-large-language-models-for-inverse","slug":"multimodal-large-language-models-for-inverse","title":"Multimodal Large Language Models for Inverse Molecular Design with Retrosynthetic Planning","date":"2024-10-05","arxiv_id":"2410.04223","n_code_links":1,"syntology":{"ran":9,"of":11,"n_ran_checked":9,"n_instrument":0,"unverified":2,"pointer_only":1,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["liugangcode/Llamole"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/optimizing-medical-image-segmentation-with","slug":"optimizing-medical-image-segmentation-with","title":"Optimizing Medical Image Segmentation with Advanced Decoder Design","date":"2024-10-05","arxiv_id":"2410.04128","n_code_links":1,"syntology":null},{"paper":null,"slug":"self-supervised-anomaly-detection-in-the-wild","title":"Self-Supervised Anomaly Detection in the Wild: Favor Joint Embeddings Methods","date":"2024-10-05","arxiv_id":"2410.04289","n_code_links":0,"syntology":null},{"paper":"/paper/take-it-easy-label-adaptive-self","slug":"take-it-easy-label-adaptive-self","title":"Take It Easy: Label-Adaptive Self-Rationalization for Fact Verification and Explanation Generation","date":"2024-10-05","arxiv_id":"2410.04002","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":2,"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":["jingyng/label-adaptive-self-rationalization"],"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/visualising-feature-learning-in-deep-neural","slug":"visualising-feature-learning-in-deep-neural","title":"Visualising Feature Learning in Deep Neural Networks by Diagonalizing the Forward Feature Map","date":"2024-10-05","arxiv_id":"2410.04264","n_code_links":0,"syntology":{"ran":3,"of":5,"n_ran_checked":3,"n_instrument":0,"unverified":2,"pointer_only":5,"phrase":"3 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":null}},{"paper":"/paper/action-selection-learning-for-multi-label","slug":"action-selection-learning-for-multi-label","title":"Action Selection Learning for Multi-label Multi-view Action Recognition","date":"2024-10-04","arxiv_id":"2410.03302","n_code_links":1,"syntology":null},{"paper":null,"slug":"an-x-ray-is-worth-15-features-sparse","title":"An X-Ray Is Worth 15 Features: Sparse Autoencoders for Interpretable Radiology Report Generation","date":"2024-10-04","arxiv_id":"2410.03334","n_code_links":0,"syntology":null},{"paper":null,"slug":"audio-agent-leveraging-llms-for-audio","title":"Audio-Agent: Leveraging LLMs For Audio Generation, Editing and Composition","date":"2024-10-04","arxiv_id":"2410.03335","n_code_links":0,"syntology":null},{"paper":null,"slug":"auto-gda-automatic-domain-adaptation-for","title":"Auto-GDA: Automatic Domain Adaptation for Efficient Grounding Verification in Retrieval Augmented Generation","date":"2024-10-04","arxiv_id":"2410.03461","n_code_links":0,"syntology":null},{"paper":"/paper/autoregressive-action-sequence-learning-for","slug":"autoregressive-action-sequence-learning-for","title":"Autoregressive Action Sequence Learning for Robotic Manipulation","date":"2024-10-04","arxiv_id":"2410.03132","n_code_links":1,"syntology":{"ran":13,"of":14,"n_ran_checked":13,"n_instrument":0,"unverified":1,"pointer_only":14,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 1 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["mlzxy/arp"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":13,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/autoregressive-moving-average-attention","slug":"autoregressive-moving-average-attention","title":"Autoregressive Moving-average Attention Mechanism for Time Series Forecasting","date":"2024-10-04","arxiv_id":"2410.03159","n_code_links":1,"syntology":{"ran":6,"of":6,"n_ran_checked":1,"n_instrument":5,"unverified":0,"pointer_only":0,"phrase":"6 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; 5 where Syntology's instrument failed) · 0 unverified","official":{"repos":["ljc-fvnr/arma-attention"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/beyond-film-subtitles-is-youtube-the-best","slug":"beyond-film-subtitles-is-youtube-the-best","title":"Beyond Film Subtitles: Is YouTube the Best Approximation of Spoken Vocabulary?","date":"2024-10-04","arxiv_id":"2410.03240","n_code_links":1,"syntology":null},{"paper":null,"slug":"crafting-narrative-closures-zero-shot","title":"Crafting Narrative Closures: Zero-Shot Learning with SSM Mamba for Short Story Ending Generation","date":"2024-10-04","arxiv_id":"2410.10848","n_code_links":0,"syntology":null},{"paper":null,"slug":"cross-lingual-transfer-for-automatic-question","title":"Cross-lingual Transfer for Automatic Question Generation by Learning Interrogative Structures in Target Languages","date":"2024-10-04","arxiv_id":"2410.03197","n_code_links":0,"syntology":null},{"paper":null,"slug":"detecting-machine-generated-long-form-content","title":"Detecting Machine-Generated Long-Form Content with Latent-Space Variables","date":"2024-10-04","arxiv_id":"2410.03856","n_code_links":0,"syntology":null},{"paper":"/paper/dynamic-diffusion-transformer","slug":"dynamic-diffusion-transformer","title":"Dynamic Diffusion Transformer","date":"2024-10-04","arxiv_id":"2410.03456","n_code_links":2,"syntology":{"ran":16,"of":19,"n_ran_checked":10,"n_instrument":6,"unverified":3,"pointer_only":19,"phrase":"16 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 5 honoured, 0 violated, 5 with no contract checked; 6 where Syntology's instrument failed) · 3 unverified","official":{"repos":["nus-hpc-ai-lab/dynamic-diffusion-transformer"],"state":"official (archive's flag): 16 ran","n_ran":16,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"from-epilepsy-seizures-classification-to","title":"From Epilepsy Seizures Classification to Detection: A Deep Learning-based Approach for Raw EEG Signals","date":"2024-10-04","arxiv_id":"2410.03385","n_code_links":0,"syntology":null},{"paper":"/paper/how-language-models-prioritize-contextual","slug":"how-language-models-prioritize-contextual","title":"How Language Models Prioritize Contextual Grammatical Cues?","date":"2024-10-04","arxiv_id":"2410.03447","n_code_links":1,"syntology":null},{"paper":null,"slug":"learning-semantic-structure-through-first","title":"Learning Semantic Structure through First-Order-Logic Translation","date":"2024-10-04","arxiv_id":"2410.03203","n_code_links":0,"syntology":null},{"paper":"/paper/mare-multi-aspect-rationale-extractor-on","slug":"mare-multi-aspect-rationale-extractor-on","title":"MARE: Multi-Aspect Rationale Extractor on Unsupervised Rationale Extraction","date":"2024-10-04","arxiv_id":"2410.03531","n_code_links":0,"syntology":{"ran":7,"of":8,"n_ran_checked":7,"n_instrument":0,"unverified":1,"pointer_only":8,"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) · 1 unverified","official":null}},{"paper":"/paper/melodi-exploring-memory-compression-for-long","slug":"melodi-exploring-memory-compression-for-long","title":"MELODI: Exploring Memory Compression for Long Contexts","date":"2024-10-04","arxiv_id":"2410.03156","n_code_links":1,"syntology":null},{"paper":null,"slug":"metadata-matters-for-time-series-informative","title":"Metadata Matters for Time Series: Informative Forecasting with Transformers","date":"2024-10-04","arxiv_id":"2410.03806","n_code_links":0,"syntology":null},{"paper":"/paper/predictive-coding-for-decision-transformer","slug":"predictive-coding-for-decision-transformer","title":"Predictive Coding for Decision Transformer","date":"2024-10-04","arxiv_id":"2410.03408","n_code_links":1,"syntology":null},{"paper":null,"slug":"prf-parallel-resonate-and-fire-neuron-for","title":"PRF: Parallel Resonate and Fire Neuron for Long Sequence Learning in Spiking Neural Networks","date":"2024-10-04","arxiv_id":"2410.03530","n_code_links":0,"syntology":null},{"paper":null,"slug":"sag-style-aligned-article-generation-via","title":"SAG: Style-Aligned Article Generation via Model Collaboration","date":"2024-10-04","arxiv_id":"2410.03137","n_code_links":0,"syntology":null},{"paper":"/paper/sda-grin-for-adaptive-spatial-temporal","slug":"sda-grin-for-adaptive-spatial-temporal","title":"SDA-GRIN for Adaptive Spatial-Temporal Multivariate Time Series Imputation","date":"2024-10-04","arxiv_id":"2410.03954","n_code_links":1,"syntology":null},{"paper":null,"slug":"selective-transformer-for-hyperspectral-image","title":"Selective Transformer for Hyperspectral Image Classification","date":"2024-10-04","arxiv_id":"2410.03171","n_code_links":0,"syntology":null},{"paper":"/paper/steering-large-language-models-between-code","slug":"steering-large-language-models-between-code","title":"Steering Large Language Models between Code Execution and Textual Reasoning","date":"2024-10-04","arxiv_id":"2410.03524","n_code_links":1,"syntology":null},{"paper":null,"slug":"still-not-quite-there-evaluating-large","title":"Still Not Quite There! Evaluating Large Language Models for Comorbid Mental Health Diagnosis","date":"2024-10-04","arxiv_id":"2410.03908","n_code_links":0,"syntology":null},{"paper":null,"slug":"structured-list-grounded-question-answering","title":"Structured List-Grounded Question Answering","date":"2024-10-04","arxiv_id":"2410.03950","n_code_links":0,"syntology":null},{"paper":"/paper/swiftkv-fast-prefill-optimized-inference-with","slug":"swiftkv-fast-prefill-optimized-inference-with","title":"SwiftKV: Fast Prefill-Optimized Inference with Knowledge-Preserving Model Transformation","date":"2024-10-04","arxiv_id":"2410.03960","n_code_links":2,"syntology":null},{"paper":null,"slug":"towards-linguistically-aware-and-language","title":"Towards Linguistically-Aware and Language-Independent Tokenization for Large Language Models (LLMs)","date":"2024-10-04","arxiv_id":"2410.03568","n_code_links":0,"syntology":null},{"paper":"/paper/trustemg-net-using-representation-masking","slug":"trustemg-net-using-representation-masking","title":"TrustEMG-Net: Using Representation-Masking Transformer with U-Net for Surface Electromyography Enhancement","date":"2024-10-04","arxiv_id":"2410.03843","n_code_links":1,"syntology":null},{"paper":null,"slug":"using-prompts-to-guide-large-language-models","title":"Using Prompts to Guide Large Language Models in Imitating a Real Person's Language Style","date":"2024-10-04","arxiv_id":"2410.03848","n_code_links":0,"syntology":null},{"paper":"/paper/variational-language-concepts-for","slug":"variational-language-concepts-for","title":"Variational Language Concepts for Interpreting Foundation Language Models","date":"2024-10-04","arxiv_id":"2410.03964","n_code_links":1,"syntology":null},{"paper":"/paper/vulnerability-detection-via-topological","slug":"vulnerability-detection-via-topological","title":"Vulnerability Detection via Topological Analysis of Attention Maps","date":"2024-10-04","arxiv_id":"2410.03470","n_code_links":1,"syntology":null},{"paper":"/paper/ward-provable-rag-dataset-inference-via-llm","slug":"ward-provable-rag-dataset-inference-via-llm","title":"Ward: Provable RAG Dataset Inference via LLM Watermarks","date":"2024-10-04","arxiv_id":"2410.03537","n_code_links":0,"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":null}},{"paper":null,"slug":"a-comprehensive-survey-of-retrieval-augmented","title":"A Comprehensive Survey of Retrieval-Augmented Generation (RAG): Evolution, Current Landscape and Future Directions","date":"2024-10-03","arxiv_id":"2410.12837","n_code_links":0,"syntology":null},{"paper":null,"slug":"adapting-segment-anything-model-to-melanoma","title":"Adapting Segment Anything Model to Melanoma Segmentation in Microscopy Slide Images","date":"2024-10-03","arxiv_id":"2410.02207","n_code_links":0,"syntology":null},{"paper":null,"slug":"adaptive-inference-time-compute-llms-can","title":"Adaptive Inference-Time Compute: LLMs Can Predict if They Can Do Better, Even Mid-Generation","date":"2024-10-03","arxiv_id":"2410.02725","n_code_links":0,"syntology":null},{"paper":null,"slug":"alphaintegrator-transformer-action-search-for","title":"AlphaIntegrator: Transformer Action Search for Symbolic Integration Proofs","date":"2024-10-03","arxiv_id":"2410.02666","n_code_links":0,"syntology":null},{"paper":null,"slug":"braintransformers-snn-llm","title":"BrainTransformers: SNN-LLM","date":"2024-10-03","arxiv_id":"2410.14687","n_code_links":0,"syntology":null},{"paper":"/paper/can-llms-reliably-simulate-human-learner","slug":"can-llms-reliably-simulate-human-learner","title":"Can LLMs Reliably Simulate Human Learner Actions? A Simulation Authoring Framework for Open-Ended Learning Environments","date":"2024-10-03","arxiv_id":"2410.02110","n_code_links":1,"syntology":null},{"paper":"/paper/cax-cellular-automata-accelerated-in-jax","slug":"cax-cellular-automata-accelerated-in-jax","title":"CAX: Cellular Automata Accelerated in JAX","date":"2024-10-03","arxiv_id":"2410.02651","n_code_links":1,"syntology":null},{"paper":null,"slug":"coal-mining-question-answering-with-llms","title":"Coal Mining Question Answering with LLMs","date":"2024-10-03","arxiv_id":"2410.02959","n_code_links":0,"syntology":null},{"paper":"/paper/codejudge-evaluating-code-generation-with","slug":"codejudge-evaluating-code-generation-with","title":"CodeJudge: Evaluating Code Generation with Large Language Models","date":"2024-10-03","arxiv_id":"2410.02184","n_code_links":1,"syntology":{"ran":15,"of":23,"n_ran_checked":14,"n_instrument":1,"unverified":8,"pointer_only":2,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 2 honoured, 0 violated, 12 with no contract checked; 1 where Syntology's instrument failed) · 8 unverified","official":{"repos":["VichyTong/CodeJudge"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":7,"ran_from_kinds":["found_in_text","official"]}}},{"paper":"/paper/controlled-generation-of-natural-adversarial","slug":"controlled-generation-of-natural-adversarial","title":"Adversarial Decoding: Generating Readable Documents for Adversarial Objectives","date":"2024-10-03","arxiv_id":"2410.02163","n_code_links":1,"syntology":null},{"paper":null,"slug":"defining-knowledge-bridging-epistemology-and","title":"Defining Knowledge: Bridging Epistemology and Large Language Models","date":"2024-10-03","arxiv_id":"2410.02499","n_code_links":0,"syntology":null},{"paper":null,"slug":"domain-specific-retrieval-augmented","title":"Domain-Specific Retrieval-Augmented Generation Using Vector Stores, Knowledge Graphs, and Tensor Factorization","date":"2024-10-03","arxiv_id":"2410.02721","n_code_links":0,"syntology":null},{"paper":null,"slug":"efficient-semantic-segmentation-via","title":"Efficient Semantic Segmentation via Lightweight Multiple-Information Interaction Network","date":"2024-10-03","arxiv_id":"2410.02224","n_code_links":0,"syntology":null},{"paper":"/paper/fan-fourier-analysis-networks","slug":"fan-fourier-analysis-networks","title":"FAN: Fourier Analysis Networks","date":"2024-10-03","arxiv_id":"2410.02675","n_code_links":2,"syntology":{"ran":6,"of":6,"n_ran_checked":3,"n_instrument":3,"unverified":0,"pointer_only":3,"phrase":"6 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; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["yihongdong/fan"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["community","listed","official"]}}},{"paper":null,"slug":"from-pixels-to-tokens-byte-pair-encoding-on","title":"From Pixels to Tokens: Byte-Pair Encoding on Quantized Visual Modalities","date":"2024-10-03","arxiv_id":"2410.02155","n_code_links":0,"syntology":null},{"paper":null,"slug":"grounding-large-language-models-in-embodied","title":"Grounding Large Language Models In Embodied Environment With Imperfect World Models","date":"2024-10-03","arxiv_id":"2410.02742","n_code_links":0,"syntology":null},{"paper":"/paper/helmet-how-to-evaluate-long-context-language","slug":"helmet-how-to-evaluate-long-context-language","title":"HELMET: How to Evaluate Long-Context Language Models Effectively and Thoroughly","date":"2024-10-03","arxiv_id":"2410.02694","n_code_links":1,"syntology":{"ran":6,"of":10,"n_ran_checked":4,"n_instrument":2,"unverified":4,"pointer_only":2,"phrase":"6 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; 2 where Syntology's instrument failed) · 4 unverified","official":{"repos":["princeton-nlp/helmet"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"hifiseg-high-frequency-information-enhanced","title":"HiFiSeg: High-Frequency Information Enhanced Polyp Segmentation with Global-Local Vision Transformer","date":"2024-10-03","arxiv_id":"2410.02528","n_code_links":0,"syntology":null},{"paper":null,"slug":"how-much-can-rag-help-the-reasoning-of-llm","title":"How Much Can RAG Help the Reasoning of LLM?","date":"2024-10-03","arxiv_id":"2410.02338","n_code_links":0,"syntology":null},{"paper":null,"slug":"indicsenteval-how-effectively-do-multilingual","title":"IndicSentEval: How Effectively do Multilingual Transformer Models encode Linguistic Properties for Indic Languages?","date":"2024-10-03","arxiv_id":"2410.02611","n_code_links":0,"syntology":null},{"paper":null,"slug":"intrinsic-evaluation-of-rag-systems-for-deep","title":"Intrinsic Evaluation of RAG Systems for Deep-Logic Questions","date":"2024-10-03","arxiv_id":"2410.02932","n_code_links":0,"syntology":null},{"paper":null,"slug":"iot-llm-enhancing-real-world-iot-task","title":"IoT-LLM: Enhancing Real-World IoT Task Reasoning with Large Language Models","date":"2024-10-03","arxiv_id":"2410.02429","n_code_links":0,"syntology":null},{"paper":"/paper/l-citeeval-do-long-context-models-truly","slug":"l-citeeval-do-long-context-models-truly","title":"L-CiteEval: Do Long-Context Models Truly Leverage Context for Responding?","date":"2024-10-03","arxiv_id":"2410.02115","n_code_links":2,"syntology":null},{"paper":null,"slug":"llava-critic-learning-to-evaluate-multimodal","title":"LLaVA-Critic: Learning to Evaluate Multimodal Models","date":"2024-10-03","arxiv_id":"2410.02712","n_code_links":0,"syntology":null},{"paper":null,"slug":"model-based-gnn-enabled-energy-efficient","title":"Model-Based GNN Enabled Energy-Efficient Beamforming for Ultra-Dense Wireless Networks","date":"2024-10-03","arxiv_id":"2410.02289","n_code_links":0,"syntology":null},{"paper":null,"slug":"morphological-evaluation-of-subwords","title":"Morphological evaluation of subwords vocabulary used by BETO language model","date":"2024-10-03","arxiv_id":"2410.02283","n_code_links":0,"syntology":null},{"paper":null,"slug":"plots-unlock-time-series-understanding-in","title":"Plots Unlock Time-Series Understanding in Multimodal Models","date":"2024-10-03","arxiv_id":"2410.02637","n_code_links":0,"syntology":null},{"paper":null,"slug":"reward-rag-enhancing-rag-with-reward-driven","title":"Reward-RAG: Enhancing RAG with Reward Driven Supervision","date":"2024-10-03","arxiv_id":"2410.03780","n_code_links":0,"syntology":null},{"paper":null,"slug":"sc-cdm-enhancing-quality-of-image-semantic","title":"SC-CDM: Enhancing Quality of Image Semantic Communication with a Compact Diffusion Model","date":"2024-10-03","arxiv_id":"2410.02121","n_code_links":0,"syntology":null},{"paper":"/paper/searching-for-efficient-linear-layers-over-a","slug":"searching-for-efficient-linear-layers-over-a","title":"Searching for Efficient Linear Layers over a Continuous Space of Structured Matrices","date":"2024-10-03","arxiv_id":"2410.02117","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":1,"n_instrument":1,"unverified":1,"pointer_only":0,"phrase":"2 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; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["andpotap/einsum-search"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/sieve-general-purpose-data-filtering-system","slug":"sieve-general-purpose-data-filtering-system","title":"GPT-4o as the Gold Standard: A Scalable and General Purpose Approach to Filter Language Model Pretraining Data","date":"2024-10-03","arxiv_id":"2410.02755","n_code_links":0,"syntology":null},{"paper":"/paper/theoretical-insights-into-fine-tuning","slug":"theoretical-insights-into-fine-tuning","title":"Theoretical Insights into Fine-Tuning Attention Mechanism: Generalization and Optimization","date":"2024-10-03","arxiv_id":"2410.02247","n_code_links":2,"syntology":{"ran":1,"of":5,"n_ran_checked":1,"n_instrument":0,"unverified":4,"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) · 4 unverified","official":{"repos":["chen123ctrls/efficientft","chen123CtrlS/LightweightAtt"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"towards-understanding-the-universality-of","title":"Towards Understanding the Universality of Transformers for Next-Token Prediction","date":"2024-10-03","arxiv_id":"2410.03011","n_code_links":0,"syntology":null},{"paper":"/paper/training-language-models-on-synthetic-edit","slug":"training-language-models-on-synthetic-edit","title":"Training Language Models on Synthetic Edit Sequences Improves Code Synthesis","date":"2024-10-03","arxiv_id":"2410.02749","n_code_links":1,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"0 ran · 1 unverified","official":{"repos":["upiterbarg/lintseq"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"paper":null,"slug":"training-nonlinear-transformers-for-chain-of","title":"Training Nonlinear Transformers for Chain-of-Thought Inference: A Theoretical Generalization Analysis","date":"2024-10-03","arxiv_id":"2410.02167","n_code_links":0,"syntology":null}],"record_sha256":"d8587a92f63154ddd1b14f83a157a34a176d03a5fb498abb7010f076f8b6feec","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}