{"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/softmax/papers/90","list_of":"/method/softmax","method":"Softmax","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":90,"pages_in_order":375,"rows_per_page":100,"rows":[8901,9000],"of":37443,"counts":{"archive_papers_tagged":37443,"with_a_code_link":15869,"where_syntology_ran_a_sample":4578,"not_listed_spam_title":0,"listed":37443,"listed_where_code_ran":4578,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":3835,"every_run_a_failure_of_syntologys_instrument":743,"listed_with_a_run_with_no_instrument_failure":3835,"listed_every_run_a_failure_of_syntologys_instrument":743,"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/softmax","prev":"/method/softmax/papers/89","next":"/method/softmax/papers/91","papers":[{"paper":null,"slug":"celi-controller-embedded-language-model","title":"CELI: Controller-Embedded Language Model Interactions","date":"2024-10-18","arxiv_id":"2410.14627","n_code_links":0,"syntology":null},{"paper":"/paper/croc-pretraining-large-multimodal-models-with","slug":"croc-pretraining-large-multimodal-models-with","title":"Croc: Pretraining Large Multimodal Models with Cross-Modal Comprehension","date":"2024-10-18","arxiv_id":"2410.14332","n_code_links":1,"syntology":null},{"paper":null,"slug":"dflow-diverse-dialogue-flow-simulation-with","title":"DFlow: Diverse Dialogue Flow Simulation with Large Language Models","date":"2024-10-18","arxiv_id":"2410.14853","n_code_links":0,"syntology":null},{"paper":null,"slug":"effects-of-soft-domain-transfer-and-named","title":"Effects of Soft-Domain Transfer and Named Entity Information on Deception Detection","date":"2024-10-18","arxiv_id":"2410.14814","n_code_links":0,"syntology":null},{"paper":null,"slug":"fashionr2r-texture-preserving-rendered-to","title":"FashionR2R: Texture-preserving Rendered-to-Real Image Translation with Diffusion Models","date":"2024-10-18","arxiv_id":"2410.14429","n_code_links":0,"syntology":null},{"paper":null,"slug":"feint-and-attack-attention-based-strategies","title":"Feint and Attack: Attention-Based Strategies for Jailbreaking and Protecting LLMs","date":"2024-10-18","arxiv_id":"2410.16327","n_code_links":0,"syntology":null},{"paper":null,"slug":"flame-quality-monitoring-of-flare-stack-based","title":"Flame quality monitoring of flare stack based on deep visual features","date":"2024-10-18","arxiv_id":"2410.19823","n_code_links":0,"syntology":null},{"paper":null,"slug":"gesh-net-graph-enhanced-spherical-harmonic","title":"GESH-Net: Graph-Enhanced Spherical Harmonic Convolutional Networks for Cortical Surface Registration","date":"2024-10-18","arxiv_id":"2410.14805","n_code_links":0,"syntology":null},{"paper":null,"slug":"good-parenting-is-all-you-need-multi-agentic","title":"Good Parenting is all you need -- Multi-agentic LLM Hallucination Mitigation","date":"2024-10-18","arxiv_id":"2410.14262","n_code_links":0,"syntology":null},{"paper":null,"slug":"graph-contrastive-learning-via-cluster","title":"Graph Contrastive Learning via Cluster-refined Negative Sampling for Semi-supervised Text Classification","date":"2024-10-18","arxiv_id":"2410.18130","n_code_links":0,"syntology":null},{"paper":null,"slug":"implicit-regularization-of-sharpness-aware","title":"Implicit Regularization of Sharpness-Aware Minimization for Scale-Invariant Problems","date":"2024-10-18","arxiv_id":"2410.14802","n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-vision-transformers-by-overlapping","title":"Improving Vision Transformers by Overlapping Heads in Multi-Head Self-Attention","date":"2024-10-18","arxiv_id":"2410.14874","n_code_links":0,"syntology":null},{"paper":null,"slug":"llm-the-genius-paradox-a-linguistic-and-math","title":"LLM The Genius Paradox: A Linguistic and Math Expert's Struggle with Simple Word-based Counting Problems","date":"2024-10-18","arxiv_id":"2410.14166","n_code_links":0,"syntology":null},{"paper":null,"slug":"ludvig-learning-free-uplifting-of-2d-visual","title":"LUDVIG: Learning-free Uplifting of 2D Visual features to Gaussian Splatting scenes","date":"2024-10-18","arxiv_id":"2410.14462","n_code_links":0,"syntology":null},{"paper":null,"slug":"machine-learning-aided-modeling-of-granular","title":"Machine Learning Aided Modeling of Granular Materials: A Review","date":"2024-10-18","arxiv_id":"2410.14767","n_code_links":0,"syntology":null},{"paper":"/paper/mambasci-efficient-mamba-unet-for-quad-bayer","slug":"mambasci-efficient-mamba-unet-for-quad-bayer","title":"MambaSCI: Efficient Mamba-UNet for Quad-Bayer Patterned Video Snapshot Compressive Imaging","date":"2024-10-18","arxiv_id":"2410.14214","n_code_links":0,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":null,"slug":"mixed-attention-transformer-enhanced-channel","title":"Mixed Attention Transformer Enhanced Channel Estimation for Extremely Large-Scale MIMO Systems","date":"2024-10-18","arxiv_id":"2410.14439","n_code_links":0,"syntology":null},{"paper":null,"slug":"multiorg-a-multi-rater-organoid-detection","title":"MultiOrg: A Multi-rater Organoid-detection Dataset","date":"2024-10-18","arxiv_id":"2410.14612","n_code_links":0,"syntology":null},{"paper":null,"slug":"novel-development-of-llm-driven-mcode-data","title":"Novel Development of LLM Driven mCODE Data Model for Improved Clinical Trial Matching to Enable Standardization and Interoperability in Oncology Research","date":"2024-10-18","arxiv_id":"2410.19826","n_code_links":0,"syntology":null},{"paper":null,"slug":"optimizing-attention-with-mirror-descent","title":"Optimizing Attention with Mirror Descent: Generalized Max-Margin Token Selection","date":"2024-10-18","arxiv_id":"2410.14581","n_code_links":0,"syntology":null},{"paper":null,"slug":"optimizing-retrieval-augmented-generation","title":"Optimizing Retrieval-Augmented Generation with Elasticsearch for Enhanced Question-Answering Systems","date":"2024-10-18","arxiv_id":"2410.14167","n_code_links":0,"syntology":null},{"paper":"/paper/paths-over-graph-knowledge-graph-enpowered","slug":"paths-over-graph-knowledge-graph-enpowered","title":"Paths-over-Graph: Knowledge Graph Empowered Large Language Model Reasoning","date":"2024-10-18","arxiv_id":"2410.14211","n_code_links":1,"syntology":{"ran":9,"of":12,"n_ran_checked":9,"n_instrument":0,"unverified":3,"pointer_only":2,"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) · 3 unverified","official":null}},{"paper":"/paper/personalized-image-generation-with-large","slug":"personalized-image-generation-with-large","title":"Personalized Image Generation with Large Multimodal Models","date":"2024-10-18","arxiv_id":"2410.14170","n_code_links":1,"syntology":{"ran":3,"of":5,"n_ran_checked":2,"n_instrument":1,"unverified":2,"pointer_only":5,"phrase":"3 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; 1 where Syntology's instrument failed) · 2 unverified","official":{"repos":["yiyanxu/pigeon"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/privacy-for-free-in-the-over-parameterized","slug":"privacy-for-free-in-the-over-parameterized","title":"Privacy for Free in the Overparameterized Regime","date":"2024-10-18","arxiv_id":"2410.14787","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":1,"n_instrument":2,"unverified":0,"pointer_only":3,"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) · 0 unverified","official":{"repos":["simone-bombari/privacy-for-free"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"provable-in-context-learning-for-mixture-of","title":"Provable In-context Learning for Mixture of Linear Regressions using Transformers","date":"2024-10-18","arxiv_id":"2410.14183","n_code_links":0,"syntology":null},{"paper":null,"slug":"pseudo-label-refinement-for-improving-self","title":"Pseudo-label Refinement for Improving Self-Supervised Learning Systems","date":"2024-10-18","arxiv_id":"2410.14242","n_code_links":0,"syntology":null},{"paper":"/paper/rag-confusionqa-a-benchmark-for-evaluating","slug":"rag-confusionqa-a-benchmark-for-evaluating","title":"ELOQ: Resources for Enhancing LLM Detection of Out-of-Scope Questions","date":"2024-10-18","arxiv_id":"2410.14567","n_code_links":1,"syntology":null},{"paper":"/paper/real-time-fake-news-from-adversarial-feedback","slug":"real-time-fake-news-from-adversarial-feedback","title":"Real-time Fake News from Adversarial Feedback","date":"2024-10-18","arxiv_id":"2410.14651","n_code_links":1,"syntology":null},{"paper":"/paper/rethinking-transformer-for-long-contextual","slug":"rethinking-transformer-for-long-contextual","title":"Rethinking Transformer for Long Contextual Histopathology Whole Slide Image Analysis","date":"2024-10-18","arxiv_id":"2410.14195","n_code_links":1,"syntology":{"ran":4,"of":6,"n_ran_checked":2,"n_instrument":2,"unverified":2,"pointer_only":6,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","official":{"repos":["invoker-ll/long-mil"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"self-satisfied-an-end-to-end-framework-for","title":"Self-Satisfied: An end-to-end framework for SAT generation and prediction","date":"2024-10-18","arxiv_id":"2410.14888","n_code_links":0,"syntology":null},{"paper":null,"slug":"sentiment-analysis-based-on-roberta-for","title":"Sentiment Analysis Based on RoBERTa for Amazon Review: An Empirical Study on Decision Making","date":"2024-10-18","arxiv_id":"2411.00796","n_code_links":0,"syntology":null},{"paper":"/paper/signattention-on-the-interpretability-of","slug":"signattention-on-the-interpretability-of","title":"SignAttention: On the Interpretability of Transformer Models for Sign Language Translation","date":"2024-10-18","arxiv_id":"2410.14506","n_code_links":1,"syntology":{"ran":0,"of":3,"n_ran_checked":0,"n_instrument":0,"unverified":3,"pointer_only":3,"phrase":"0 ran · 3 unverified","official":{"repos":["pedroodb/sign_attention"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":[]}}},{"paper":"/paper/sprig-improving-large-language-model","slug":"sprig-improving-large-language-model","title":"SPRIG: Improving Large Language Model Performance by System Prompt Optimization","date":"2024-10-18","arxiv_id":"2410.14826","n_code_links":1,"syntology":{"ran":16,"of":19,"n_ran_checked":15,"n_instrument":1,"unverified":3,"pointer_only":19,"phrase":"16 ran (of which 0 constructed an object rather than computing a result; 15 with no instrument failure: 0 honoured, 0 violated, 15 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","official":{"repos":["orange0629/prompting"],"state":"official (archive's flag): 16 ran","n_ran":16,"n_constructed":0,"n_ran_no_instrument_failure":15,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/st-moe-bert-a-spatial-temporal-mixture-of","slug":"st-moe-bert-a-spatial-temporal-mixture-of","title":"ST-MoE-BERT: A Spatial-Temporal Mixture-of-Experts Framework for Long-Term Cross-City Mobility Prediction","date":"2024-10-18","arxiv_id":"2410.14099","n_code_links":1,"syntology":{"ran":4,"of":7,"n_ran_checked":4,"n_instrument":0,"unverified":3,"pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["he-h/HuMob"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"step-guided-reasoning-improving-mathematical","title":"Step Guided Reasoning: Improving Mathematical Reasoning using Guidance Generation and Step Reasoning","date":"2024-10-18","arxiv_id":"2410.19817","n_code_links":0,"syntology":null},{"paper":null,"slug":"supervised-chain-of-thought","title":"Supervised Chain of Thought","date":"2024-10-18","arxiv_id":"2410.14198","n_code_links":0,"syntology":null},{"paper":"/paper/timeseriesexam-a-time-series-understanding","slug":"timeseriesexam-a-time-series-understanding","title":"TimeSeriesExam: A time series understanding exam","date":"2024-10-18","arxiv_id":"2410.14752","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":1,"n_instrument":1,"unverified":0,"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) · 0 unverified","official":null}},{"paper":null,"slug":"transbox-el-closed-ontology-embedding","title":"TransBox: EL++-closed Ontology Embedding","date":"2024-10-18","arxiv_id":"2410.14571","n_code_links":0,"syntology":null},{"paper":null,"slug":"transfer-learning-on-transformers-for","title":"Transfer Learning on Transformers for Building Energy Consumption Forecasting -- A Comparative Study","date":"2024-10-18","arxiv_id":"2410.14107","n_code_links":0,"syntology":null},{"paper":null,"slug":"using-sentiment-and-technical-analysis-to","title":"Using Sentiment and Technical Analysis to Predict Bitcoin with Machine Learning","date":"2024-10-18","arxiv_id":"2410.14532","n_code_links":0,"syntology":null},{"paper":"/paper/xpert-extended-persistence-transformer","slug":"xpert-extended-persistence-transformer","title":"xPerT: Extended Persistence Transformer","date":"2024-10-18","arxiv_id":"2410.14193","n_code_links":2,"syntology":null},{"paper":null,"slug":"360u-former-hdr-illumination-estimation-with","title":"360U-Former: HDR Illumination Estimation with Panoramic Adapted Vision Transformers","date":"2024-10-17","arxiv_id":"2410.13566","n_code_links":0,"syntology":null},{"paper":"/paper/a-comparative-study-on-reasoning-patterns-of","slug":"a-comparative-study-on-reasoning-patterns-of","title":"A Comparative Study on Reasoning Patterns of OpenAI's o1 Model","date":"2024-10-17","arxiv_id":"2410.13639","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, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["open-source-o1/o1_reasoning_patterns_study"],"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/a-pattern-to-align-them-all-integrating","slug":"a-pattern-to-align-them-all-integrating","title":"A Pattern to Align Them All: Integrating Different Modalities to Define Multi-Modal Entities","date":"2024-10-17","arxiv_id":"2410.13803","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-simplifying-and-learnable-graph","title":"A Simplifying and Learnable Graph Convolutional Attention Network for Unsupervised Knowledge Graphs Alignment","date":"2024-10-17","arxiv_id":"2410.13263","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-systematic-investigation-of-knowledge","title":"How Does Knowledge Selection Help Retrieval Augmented Generation?","date":"2024-10-17","arxiv_id":"2410.13258","n_code_links":0,"syntology":null},{"paper":"/paper/ab-initio-nonparametric-variable-selection","slug":"ab-initio-nonparametric-variable-selection","title":"Ab Initio Nonparametric Variable Selection for Scalable Symbolic Regression with Large $p$","date":"2024-10-17","arxiv_id":"2410.13681","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["mattsheng/PAN_SR"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/active-dormant-attention-heads","slug":"active-dormant-attention-heads","title":"Active-Dormant Attention Heads: Mechanistically Demystifying Extreme-Token Phenomena in LLMs","date":"2024-10-17","arxiv_id":"2410.13835","n_code_links":1,"syntology":{"ran":1,"of":6,"n_ran_checked":1,"n_instrument":0,"unverified":5,"pointer_only":6,"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) · 5 unverified","official":{"repos":["guotianyu2000/active-dormant-attention"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"addressing-heterogeneity-and-heterophily-in","title":"Addressing Heterogeneity and Heterophily in Graphs: A Heterogeneous Heterophilic Spectral Graph Neural Network","date":"2024-10-17","arxiv_id":"2410.13373","n_code_links":0,"syntology":null},{"paper":null,"slug":"adversarial-testing-as-a-tool-for","title":"Adversarial Testing as a Tool for Interpretability: Length-based Overfitting of Elementary Functions in Transformers","date":"2024-10-17","arxiv_id":"2410.13802","n_code_links":0,"syntology":null},{"paper":"/paper/an-evolved-universal-transformer-memory","slug":"an-evolved-universal-transformer-memory","title":"An Evolved Universal Transformer Memory","date":"2024-10-17","arxiv_id":"2410.13166","n_code_links":1,"syntology":{"ran":11,"of":12,"n_ran_checked":11,"n_instrument":0,"unverified":1,"pointer_only":12,"phrase":"11 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; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["sakanaai/evo-memory"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"asymkv-enabling-1-bit-quantization-of-kv","title":"AsymKV: Enabling 1-Bit Quantization of KV Cache with Layer-Wise Asymmetric Quantization Configurations","date":"2024-10-17","arxiv_id":"2410.13212","n_code_links":0,"syntology":null},{"paper":null,"slug":"better-to-ask-in-english-evaluation-of-large","title":"Better to Ask in English: Evaluation of Large Language Models on English, Low-resource and Cross-Lingual Settings","date":"2024-10-17","arxiv_id":"2410.13153","n_code_links":0,"syntology":null},{"paper":null,"slug":"co-segmentation-without-any-pixel-level","title":"Co-Segmentation without any Pixel-level Supervision with Application to Large-Scale Sketch Classification","date":"2024-10-17","arxiv_id":"2410.13582","n_code_links":0,"syntology":null},{"paper":"/paper/cohex-a-generalized-framework-for-cohort","slug":"cohex-a-generalized-framework-for-cohort","title":"CohEx: A Generalized Framework for Cohort Explanation","date":"2024-10-17","arxiv_id":"2410.13190","n_code_links":1,"syntology":null},{"paper":null,"slug":"computational-approaches-to-arabic-english","title":"Computational Approaches to Arabic-English Code-Switching","date":"2024-10-17","arxiv_id":"2410.13318","n_code_links":0,"syntology":null},{"paper":"/paper/d-fine-redefine-regression-task-in-detrs-as","slug":"d-fine-redefine-regression-task-in-detrs-as","title":"D-FINE: Redefine Regression Task in DETRs as Fine-grained Distribution Refinement","date":"2024-10-17","arxiv_id":"2410.13842","n_code_links":5,"syntology":{"ran":10,"of":14,"n_ran_checked":10,"n_instrument":0,"unverified":4,"pointer_only":0,"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) · 4 unverified","official":{"repos":["Peterande/D-FINE"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/data-driven-rainfall-prediction-at-a-regional","slug":"data-driven-rainfall-prediction-at-a-regional","title":"Data-driven rainfall prediction at a regional scale: a case study with Ghana","date":"2024-10-17","arxiv_id":"2410.14062","n_code_links":1,"syntology":null},{"paper":"/paper/detecting-ai-generated-texts-in-cross-domains","slug":"detecting-ai-generated-texts-in-cross-domains","title":"Detecting AI-Generated Texts in Cross-Domains","date":"2024-10-17","arxiv_id":"2410.13966","n_code_links":1,"syntology":null},{"paper":null,"slug":"direcnetv2-a-transformer-enhanced-network-for","title":"DiRecNetV2: A Transformer-Enhanced Network for Aerial Disaster Recognition","date":"2024-10-17","arxiv_id":"2410.13663","n_code_links":0,"syntology":null},{"paper":"/paper/dn-4dgs-denoised-deformable-network-with","slug":"dn-4dgs-denoised-deformable-network-with","title":"DN-4DGS: Denoised Deformable Network with Temporal-Spatial Aggregation for Dynamic Scene Rendering","date":"2024-10-17","arxiv_id":"2410.13607","n_code_links":1,"syntology":null},{"paper":null,"slug":"dreamvideo-2-zero-shot-subject-driven-video","title":"DreamVideo-2: Zero-Shot Subject-Driven Video Customization with Precise Motion Control","date":"2024-10-17","arxiv_id":"2410.13830","n_code_links":0,"syntology":null},{"paper":null,"slug":"durian-e-2-duration-informed-attention","title":"DurIAN-E 2: Duration Informed Attention Network with Adaptive Variational Autoencoder and Adversarial Learning for Expressive Text-to-Speech Synthesis","date":"2024-10-17","arxiv_id":"2410.13288","n_code_links":0,"syntology":null},{"paper":"/paper/enhanced-prompt-leveraged-weakly-supervised","slug":"enhanced-prompt-leveraged-weakly-supervised","title":"EP-SAM: Weakly Supervised Histopathology Segmentation via Enhanced Prompt with Segment Anything","date":"2024-10-17","arxiv_id":"2410.13621","n_code_links":2,"syntology":null},{"paper":null,"slug":"enhancing-generalization-in-sparse-mixture-of","title":"Enhancing Generalization in Sparse Mixture of Experts Models: The Case for Increased Expert Activation in Compositional Tasks","date":"2024-10-17","arxiv_id":"2410.13964","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancing-text-generation-in-joint-nlg-nlu","title":"Enhancing Text Generation in Joint NLG/NLU Learning Through Curriculum Learning, Semi-Supervised Training, and Advanced Optimization Techniques","date":"2024-10-17","arxiv_id":"2410.13498","n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluating-self-generated-documents-for","title":"Evaluating Self-Generated Documents for Enhancing Retrieval-Augmented Generation with Large Language Models","date":"2024-10-17","arxiv_id":"2410.13192","n_code_links":0,"syntology":null},{"paper":"/paper/faithbench-a-diverse-hallucination-benchmark","slug":"faithbench-a-diverse-hallucination-benchmark","title":"FaithBench: A Diverse Hallucination Benchmark for Summarization by Modern LLMs","date":"2024-10-17","arxiv_id":"2410.13210","n_code_links":2,"syntology":null},{"paper":null,"slug":"fedpae-peer-adaptive-ensemble-learning-for","title":"FedPAE: Peer-Adaptive Ensemble Learning for Asynchronous and Model-Heterogeneous Federated Learning","date":"2024-10-17","arxiv_id":"2410.14075","n_code_links":0,"syntology":null},{"paper":"/paper/fluid-scaling-autoregressive-text-to-image","slug":"fluid-scaling-autoregressive-text-to-image","title":"Fluid: Scaling Autoregressive Text-to-image Generative Models with Continuous Tokens","date":"2024-10-17","arxiv_id":"2410.13863","n_code_links":1,"syntology":null},{"paper":"/paper/g-mod-exploring-mixture-of-depth-adaptation","slug":"g-mod-exploring-mixture-of-depth-adaptation","title":"$γ-$MoD: Exploring Mixture-of-Depth Adaptation for Multimodal Large Language Models","date":"2024-10-17","arxiv_id":"2410.13859","n_code_links":0,"syntology":null},{"paper":"/paper/help-me-identify-is-an-llm-vqa-system-all-we","slug":"help-me-identify-is-an-llm-vqa-system-all-we","title":"Help Me Identify: Is an LLM+VQA System All We Need to Identify Visual Concepts?","date":"2024-10-17","arxiv_id":"2410.13651","n_code_links":1,"syntology":null},{"paper":"/paper/hiformer-hybrid-frequency-feature-enhancement","slug":"hiformer-hybrid-frequency-feature-enhancement","title":"Hiformer: Hybrid Frequency Feature Enhancement Inverted Transformer for Long-Term Wind Power Prediction","date":"2024-10-17","arxiv_id":"2410.13303","n_code_links":1,"syntology":null},{"paper":null,"slug":"integrating-temporal-representations-for","title":"Integrating Temporal Representations for Dynamic Memory Retrieval and Management in Large Language Models","date":"2024-10-17","arxiv_id":"2410.13553","n_code_links":0,"syntology":null},{"paper":null,"slug":"iterselecttune-an-iterative-training","title":"IterSelectTune: An Iterative Training Framework for Efficient Instruction-Tuning Data Selection","date":"2024-10-17","arxiv_id":"2410.13464","n_code_links":0,"syntology":null},{"paper":null,"slug":"jailbreaking-llm-controlled-robots","title":"Jailbreaking LLM-Controlled Robots","date":"2024-10-17","arxiv_id":"2410.13691","n_code_links":0,"syntology":null},{"paper":null,"slug":"latent-image-and-video-resolution-prediction","title":"Latent Image and Video Resolution Prediction using Convolutional Neural Networks","date":"2024-10-17","arxiv_id":"2410.13227","n_code_links":0,"syntology":null},{"paper":"/paper/learning-graph-quantized-tokenizers-for","slug":"learning-graph-quantized-tokenizers-for","title":"Learning Graph Quantized Tokenizers","date":"2024-10-17","arxiv_id":"2410.13798","n_code_links":1,"syntology":{"ran":11,"of":13,"n_ran_checked":7,"n_instrument":4,"unverified":2,"pointer_only":3,"phrase":"11 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; 4 where Syntology's instrument failed) · 2 unverified","official":{"repos":["limei0307/GQT"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"lecture-ii-communicative-justice-and-the","title":"Lecture II: Communicative Justice and the Distribution of Attention","date":"2024-10-17","arxiv_id":"2410.20718","n_code_links":0,"syntology":null},{"paper":null,"slug":"linguistically-grounded-analysis-of-language","title":"Linguistically Grounded Analysis of Language Models using Shapley Head Values","date":"2024-10-17","arxiv_id":"2410.13396","n_code_links":0,"syntology":null},{"paper":"/paper/loldu-low-rank-adaptation-via-lower-diag","slug":"loldu-low-rank-adaptation-via-lower-diag","title":"LoLDU: Low-Rank Adaptation via Lower-Diag-Upper Decomposition for Parameter-Efficient Fine-Tuning","date":"2024-10-17","arxiv_id":"2410.13618","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":3,"n_instrument":1,"unverified":0,"pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["skddj/loldu"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/looking-inward-language-models-can-learn","slug":"looking-inward-language-models-can-learn","title":"Looking Inward: Language Models Can Learn About Themselves by Introspection","date":"2024-10-17","arxiv_id":"2410.13787","n_code_links":1,"syntology":{"ran":3,"of":4,"n_ran_checked":3,"n_instrument":0,"unverified":1,"pointer_only":4,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["felixbinder/introspection_self_prediction"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"marineformer-a-transformer-based-navigation","title":"MarineFormer: A Spatio-Temporal Attention Model for USV Navigation in Dynamic Marine Environments","date":"2024-10-17","arxiv_id":"2410.13973","n_code_links":0,"syntology":null},{"paper":"/paper/mcqg-srefine-multiple-choice-question","slug":"mcqg-srefine-multiple-choice-question","title":"MCQG-SRefine: Multiple Choice Question Generation and Evaluation with Iterative Self-Critique, Correction, and Comparison Feedback","date":"2024-10-17","arxiv_id":"2410.13191","n_code_links":1,"syntology":null},{"paper":"/paper/measuring-and-modifying-the-readability-of","slug":"measuring-and-modifying-the-readability-of","title":"Measuring and Modifying the Readability of English Texts with GPT-4","date":"2024-10-17","arxiv_id":"2410.14028","n_code_links":1,"syntology":null},{"paper":null,"slug":"metacognitive-monitoring-a-human-ability","title":"Judgment of Learning: A Human Ability Beyond Generative Artificial Intelligence","date":"2024-10-17","arxiv_id":"2410.13392","n_code_links":0,"syntology":null},{"paper":"/paper/mirage-bench-automatic-multilingual-benchmark","slug":"mirage-bench-automatic-multilingual-benchmark","title":"MIRAGE-Bench: Automatic Multilingual Benchmark Arena for Retrieval-Augmented Generation Systems","date":"2024-10-17","arxiv_id":"2410.13716","n_code_links":1,"syntology":null},{"paper":"/paper/mitigating-the-backdoor-effect-for-multi-task","slug":"mitigating-the-backdoor-effect-for-multi-task","title":"Mitigating the Backdoor Effect for Multi-Task Model Merging via Safety-Aware Subspace","date":"2024-10-17","arxiv_id":"2410.13910","n_code_links":1,"syntology":{"ran":5,"of":5,"n_ran_checked":5,"n_instrument":0,"unverified":0,"pointer_only":5,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["yangjinluan/dam"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"on-partial-prototype-collapse-in-the-dino","title":"On Partial Prototype Collapse in the DINO Family of Self-Supervised Methods","date":"2024-10-17","arxiv_id":"2410.14060","n_code_links":0,"syntology":null},{"paper":null,"slug":"on-the-learn-to-optimize-capabilities-of","title":"On the Learn-to-Optimize Capabilities of Transformers in In-Context Sparse Recovery","date":"2024-10-17","arxiv_id":"2410.13981","n_code_links":0,"syntology":null},{"paper":"/paper/on-the-role-of-attention-heads-in-large","slug":"on-the-role-of-attention-heads-in-large","title":"On the Role of Attention Heads in Large Language Model Safety","date":"2024-10-17","arxiv_id":"2410.13708","n_code_links":1,"syntology":{"ran":16,"of":24,"n_ran_checked":8,"n_instrument":8,"unverified":8,"pointer_only":24,"phrase":"16 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 8 where Syntology's instrument failed) · 8 unverified","official":{"repos":["ydyjya/safetyheadattribution"],"state":"official (archive's flag): 16 ran","n_ran":16,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":8,"ran_from_kinds":["official"]}}},{"paper":"/paper/on-the-use-of-audio-to-improve-dialogue","slug":"on-the-use-of-audio-to-improve-dialogue","title":"On the Use of Audio to Improve Dialogue Policies","date":"2024-10-17","arxiv_id":"2410.13385","n_code_links":1,"syntology":null},{"paper":"/paper/orchid-a-chinese-debate-corpus-for-target","slug":"orchid-a-chinese-debate-corpus-for-target","title":"ORCHID: A Chinese Debate Corpus for Target-Independent Stance Detection and Argumentative Dialogue Summarization","date":"2024-10-17","arxiv_id":"2410.13667","n_code_links":1,"syntology":null},{"paper":"/paper/performance-of-gaussian-mixture-model","slug":"performance-of-gaussian-mixture-model","title":"Performance of Gaussian Mixture Model Classifiers on Embedded Feature Spaces","date":"2024-10-17","arxiv_id":"2410.13421","n_code_links":1,"syntology":null},{"paper":null,"slug":"personalized-adaptation-via-in-context","title":"Personalized Adaptation via In-Context Preference Learning","date":"2024-10-17","arxiv_id":"2410.14001","n_code_links":0,"syntology":null},{"paper":null,"slug":"precipitation-nowcasting-using-diffusion","title":"Precipitation Nowcasting Using Diffusion Transformer with Causal Attention","date":"2024-10-17","arxiv_id":"2410.13314","n_code_links":0,"syntology":null},{"paper":"/paper/preference-diffusion-for-recommendation","slug":"preference-diffusion-for-recommendation","title":"Preference Diffusion for Recommendation","date":"2024-10-17","arxiv_id":"2410.13117","n_code_links":1,"syntology":{"ran":15,"of":19,"n_ran_checked":11,"n_instrument":4,"unverified":4,"pointer_only":19,"phrase":"15 ran (of which 5 constructed an object rather than computing a result; 11 with no instrument failure: 4 honoured, 0 violated, 7 with no contract checked; 4 where Syntology's instrument failed) · 4 unverified","official":{"repos":["lswhim/preferdiff"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":5,"n_ran_no_instrument_failure":8,"n_unverified":4,"ran_from_kinds":["official","unlocated"]}}},{"paper":"/paper/rag-ddr-optimizing-retrieval-augmented","slug":"rag-ddr-optimizing-retrieval-augmented","title":"RAG-DDR: Optimizing Retrieval-Augmented Generation Using Differentiable Data Rewards","date":"2024-10-17","arxiv_id":"2410.13509","n_code_links":1,"syntology":{"ran":10,"of":10,"n_ran_checked":10,"n_instrument":0,"unverified":0,"pointer_only":0,"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) · 0 unverified","official":{"repos":["openmatch/rag-ddr"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"reducing-the-transformer-architecture-to-a","title":"Reducing the Transformer Architecture to a Minimum","date":"2024-10-17","arxiv_id":"2410.13732","n_code_links":0,"syntology":null},{"paper":null,"slug":"rgb-to-hyperspectral-spectral-reconstruction","title":"RGB to Hyperspectral: Spectral Reconstruction for Enhanced Surgical Imaging","date":"2024-10-17","arxiv_id":"2410.13570","n_code_links":0,"syntology":null}],"record_sha256":"ee3aa32735540f223c6c35d5046abc747765f6eba2394b660cb824881d84ebb3","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}