{"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/134","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":134,"pages_in_order":375,"rows_per_page":100,"rows":[13301,13400],"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/133","next":"/method/softmax/papers/135","papers":[{"paper":null,"slug":"feature-fusion-for-human-activity-recognition","title":"Feature Fusion for Human Activity Recognition using Parameter-Optimized Multi-Stage Graph Convolutional Network and Transformer Models","date":"2024-06-24","arxiv_id":"2406.16638","n_code_links":0,"syntology":null},{"paper":"/paper/finding-transformer-circuits-with-edge","slug":"finding-transformer-circuits-with-edge","title":"Finding Transformer Circuits with Edge Pruning","date":"2024-06-24","arxiv_id":"2406.16778","n_code_links":1,"syntology":{"ran":8,"of":8,"n_ran_checked":3,"n_instrument":5,"unverified":0,"pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 3 honoured, 0 violated, 0 with no contract checked; 5 where Syntology's instrument failed) · 0 unverified","official":{"repos":["princeton-nlp/edge-pruning"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/freetraj-tuning-free-trajectory-control-in","slug":"freetraj-tuning-free-trajectory-control-in","title":"FreeTraj: Tuning-Free Trajectory Control in Video Diffusion Models","date":"2024-06-24","arxiv_id":"2406.16863","n_code_links":1,"syntology":{"ran":12,"of":15,"n_ran_checked":10,"n_instrument":2,"unverified":3,"pointer_only":4,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 2 honoured, 1 violated, 7 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","official":{"repos":["arthur-qiu/freetraj"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"from-decoding-to-meta-generation-inference","title":"From Decoding to Meta-Generation: Inference-time Algorithms for Large Language Models","date":"2024-06-24","arxiv_id":"2406.16838","n_code_links":0,"syntology":null},{"paper":"/paper/geomformer-a-general-architecture-for","slug":"geomformer-a-general-architecture-for","title":"GeoMFormer: A General Architecture for Geometric Molecular Representation Learning","date":"2024-06-24","arxiv_id":"2406.16853","n_code_links":1,"syntology":null},{"paper":"/paper/gmt-guided-mask-transformer-for-leaf-instance","slug":"gmt-guided-mask-transformer-for-leaf-instance","title":"GMT: Guided Mask Transformer for Leaf Instance Segmentation","date":"2024-06-24","arxiv_id":"2406.17109","n_code_links":1,"syntology":null},{"paper":null,"slug":"hacking-a-surrogate-model-approach-to-xai","title":"Hacking a surrogate model approach to XAI","date":"2024-06-24","arxiv_id":"2406.16626","n_code_links":0,"syntology":null},{"paper":null,"slug":"large-language-models-in-student-assessment","title":"Large Language Models in Student Assessment: Comparing ChatGPT and Human Graders","date":"2024-06-24","arxiv_id":"2406.16510","n_code_links":0,"syntology":null},{"paper":null,"slug":"lesion-aware-cross-phase-attention-network","title":"Lesion-Aware Cross-Phase Attention Network for Renal Tumor Subtype Classification on Multi-Phase CT Scans","date":"2024-06-24","arxiv_id":"2406.16322","n_code_links":0,"syntology":null},{"paper":"/paper/make-graph-neural-networks-great-again-a","slug":"make-graph-neural-networks-great-again-a","title":"Make Graph Neural Networks Great Again: A Generic Integration Paradigm of Topology-Free Patterns for Traffic Speed Prediction","date":"2024-06-24","arxiv_id":"2406.16992","n_code_links":1,"syntology":null},{"paper":null,"slug":"metrik-measurement-efficient-randomized","title":"METRIK: Measurement-Efficient Randomized Controlled Trials using Transformers with Input Masking","date":"2024-06-24","arxiv_id":"2406.16351","n_code_links":0,"syntology":null},{"paper":null,"slug":"minimax-optimality-in-contextual-dynamic","title":"Minimax Optimality in Contextual Dynamic Pricing with General Valuation Models","date":"2024-06-24","arxiv_id":"2406.17184","n_code_links":0,"syntology":null},{"paper":null,"slug":"modeling-a-novel-dataset-for-testing","title":"modeLing: A Novel Dataset for Testing Linguistic Reasoning in Language Models","date":"2024-06-24","arxiv_id":"2406.17038","n_code_links":0,"syntology":null},{"paper":"/paper/multi-logieval-towards-evaluating-multi-step","slug":"multi-logieval-towards-evaluating-multi-step","title":"Multi-LogiEval: Towards Evaluating Multi-Step Logical Reasoning Ability of Large Language Models","date":"2024-06-24","arxiv_id":"2406.17169","n_code_links":1,"syntology":null},{"paper":null,"slug":"multi-modal-vision-transformers-for-crop","title":"Multi-Modal Vision Transformers for Crop Mapping from Satellite Image Time Series","date":"2024-06-24","arxiv_id":"2406.16513","n_code_links":0,"syntology":null},{"paper":null,"slug":"on-the-role-of-long-tail-knowledge-in","title":"On the Role of Long-tail Knowledge in Retrieval Augmented Large Language Models","date":"2024-06-24","arxiv_id":"2406.16367","n_code_links":0,"syntology":null},{"paper":"/paper/otce-hybrid-ssm-and-attention-with-cross","slug":"otce-hybrid-ssm-and-attention-with-cross","title":"OTCE: Hybrid SSM and Attention with Cross Domain Mixture of Experts to construct Observer-Thinker-Conceiver-Expresser","date":"2024-06-24","arxiv_id":"2406.16495","n_code_links":1,"syntology":null},{"paper":"/paper/panza-a-personalized-text-writing-assistant","slug":"panza-a-personalized-text-writing-assistant","title":"Panza: Design and Analysis of a Fully-Local Personalized Text Writing Assistant","date":"2024-06-24","arxiv_id":"2407.10994","n_code_links":1,"syntology":null},{"paper":null,"slug":"plagbench-exploring-the-duality-of-large","title":"PlagBench: Exploring the Duality of Large Language Models in Plagiarism Generation and Detection","date":"2024-06-24","arxiv_id":"2406.16288","n_code_links":0,"syntology":null},{"paper":null,"slug":"priorformer-a-ugc-vqa-method-with-content-and","title":"Priorformer: A UGC-VQA Method with content and distortion priors","date":"2024-06-24","arxiv_id":"2406.16297","n_code_links":0,"syntology":null},{"paper":"/paper/ragnarok-a-reusable-rag-framework-and","slug":"ragnarok-a-reusable-rag-framework-and","title":"Ragnarök: A Reusable RAG Framework and Baselines for TREC 2024 Retrieval-Augmented Generation Track","date":"2024-06-24","arxiv_id":"2406.16828","n_code_links":2,"syntology":{"ran":19,"of":23,"n_ran_checked":19,"n_instrument":0,"unverified":4,"pointer_only":0,"phrase":"19 ran (of which 0 constructed an object rather than computing a result; 19 with no instrument failure: 0 honoured, 0 violated, 19 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","official":{"repos":["castorini/ragnarok"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":3,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/repairing-catastrophic-neglect-in-text-to","slug":"repairing-catastrophic-neglect-in-text-to","title":"Repairing Catastrophic-Neglect in Text-to-Image Diffusion Models via Attention-Guided Feature Enhancement","date":"2024-06-24","arxiv_id":"2406.16272","n_code_links":1,"syntology":null},{"paper":"/paper/scaling-laws-for-linear-complexity-language","slug":"scaling-laws-for-linear-complexity-language","title":"Scaling Laws for Linear Complexity Language Models","date":"2024-06-24","arxiv_id":"2406.16690","n_code_links":1,"syntology":null},{"paper":"/paper/shadowllm-predictor-based-contextual-sparsity","slug":"shadowllm-predictor-based-contextual-sparsity","title":"ShadowLLM: Predictor-based Contextual Sparsity for Large Language Models","date":"2024-06-24","arxiv_id":"2406.16635","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":1,"n_instrument":1,"unverified":1,"pointer_only":3,"phrase":"2 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; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["abdelfattah-lab/shadow_llm"],"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":null,"slug":"sparser-is-faster-and-less-is-more-efficient","title":"Sparser is Faster and Less is More: Efficient Sparse Attention for Long-Range Transformers","date":"2024-06-24","arxiv_id":"2406.16747","n_code_links":0,"syntology":null},{"paper":"/paper/the-gpt-writingprompts-dataset-a-comparative","slug":"the-gpt-writingprompts-dataset-a-comparative","title":"The GPT-WritingPrompts Dataset: A Comparative Analysis of Character Portrayal in Short Stories","date":"2024-06-24","arxiv_id":"2406.16767","n_code_links":1,"syntology":null},{"paper":null,"slug":"the-progression-of-transformers-from-language","title":"The Progression of Transformers from Language to Vision to MOT: A Literature Review on Multi-Object Tracking with Transformers","date":"2024-06-24","arxiv_id":"2406.16784","n_code_links":0,"syntology":null},{"paper":null,"slug":"theory-on-mixture-of-experts-in-continual","title":"Theory on Mixture-of-Experts in Continual Learning","date":"2024-06-24","arxiv_id":"2406.16437","n_code_links":0,"syntology":null},{"paper":"/paper/towards-better-graph-based-cross-document","slug":"towards-better-graph-based-cross-document","title":"Towards Better Graph-based Cross-document Relation Extraction via Non-bridge Entity Enhancement and Prediction Debiasing","date":"2024-06-24","arxiv_id":"2406.16529","n_code_links":1,"syntology":null},{"paper":"/paper/training-free-exponential-extension-of","slug":"training-free-exponential-extension-of","title":"Training-Free Exponential Context Extension via Cascading KV Cache","date":"2024-06-24","arxiv_id":"2406.17808","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":["jeffwillette/cascading_kv_cache"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/unambiguous-recognition-should-not-rely","slug":"unambiguous-recognition-should-not-rely","title":"MixTex: Unambiguous Recognition Should Not Rely Solely on Real Data","date":"2024-06-24","arxiv_id":"2406.17148","n_code_links":1,"syntology":null},{"paper":null,"slug":"uno-arena-for-evaluating-sequential-decision","title":"UNO Arena for Evaluating Sequential Decision-Making Capability of Large Language Models","date":"2024-06-24","arxiv_id":"2406.16382","n_code_links":0,"syntology":null},{"paper":null,"slug":"usdc-a-dataset-of-underline-u-ser-underline-s","title":"USDC: A Dataset of $\\underline{U}$ser $\\underline{S}$tance and $\\underline{D}$ogmatism in Long $\\underline{C}$onversations","date":"2024-06-24","arxiv_id":"2406.16833","n_code_links":0,"syntology":null},{"paper":null,"slug":"venturing-into-uncharted-waters-the","title":"Venturing into Uncharted Waters: The Navigation Compass from Transformer to Mamba","date":"2024-06-24","arxiv_id":"2406.16722","n_code_links":0,"syntology":null},{"paper":null,"slug":"video-infinity-distributed-long-video","title":"Video-Infinity: Distributed Long Video Generation","date":"2024-06-24","arxiv_id":"2406.16260","n_code_links":0,"syntology":null},{"paper":null,"slug":"vision-mamba-based-autonomous-crack","title":"Vision Mamba-based autonomous crack segmentation on concrete, asphalt, and masonry surfaces","date":"2024-06-24","arxiv_id":"2406.16518","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-first-running-time-analysis-of-the-strength","title":"A First Running Time Analysis of the Strength Pareto Evolutionary Algorithm 2 (SPEA2)","date":"2024-06-23","arxiv_id":"2406.16116","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-mechanism-for-optimizing-media-recommender","title":"A Mechanism for Optimizing Media Recommender Systems","date":"2024-06-23","arxiv_id":"2406.16212","n_code_links":0,"syntology":null},{"paper":"/paper/breaking-the-frame-image-retrieval-by-visual","slug":"breaking-the-frame-image-retrieval-by-visual","title":"Breaking the Frame: Visual Place Recognition by Overlap Prediction","date":"2024-06-23","arxiv_id":"2406.16204","n_code_links":1,"syntology":{"ran":4,"of":5,"n_ran_checked":4,"n_instrument":0,"unverified":1,"pointer_only":5,"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) · 1 unverified","official":{"repos":["weitong8591/vop"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/dv-3dlane-end-to-end-multi-modal-3d-lane","slug":"dv-3dlane-end-to-end-multi-modal-3d-lane","title":"DV-3DLane: End-to-end Multi-modal 3D Lane Detection with Dual-view Representation","date":"2024-06-23","arxiv_id":"2406.16072","n_code_links":1,"syntology":null},{"paper":null,"slug":"editfollower-tunable-car-following-models-for","title":"EditFollower: Tunable Car Following Models for Customizable Adaptive Cruise Control Systems","date":"2024-06-23","arxiv_id":"2407.02516","n_code_links":0,"syntology":null},{"paper":"/paper/enhancing-commentary-strategies-for-imperfect","slug":"enhancing-commentary-strategies-for-imperfect","title":"Enhancing Commentary Strategies for Imperfect Information Card Games: A Study of Large Language Models in Guandan Commentary","date":"2024-06-23","arxiv_id":"2406.17807","n_code_links":1,"syntology":null},{"paper":null,"slug":"evaluating-ensemble-methods-for-news","title":"Evaluating Ensemble Methods for News Recommender Systems","date":"2024-06-23","arxiv_id":"2406.16106","n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluating-the-effectiveness-of-the","title":"Evaluating the Effectiveness of the Foundational Models for Q&A Classification in Mental Health care","date":"2024-06-23","arxiv_id":"2406.15966","n_code_links":0,"syntology":null},{"paper":null,"slug":"found-in-the-middle-calibrating-positional","title":"Found in the Middle: Calibrating Positional Attention Bias Improves Long Context Utilization","date":"2024-06-23","arxiv_id":"2406.16008","n_code_links":0,"syntology":null},{"paper":null,"slug":"grapheval2000-benchmarking-and-improving","title":"GraphEval2000: Benchmarking and Improving Large Language Models on Graph Datasets","date":"2024-06-23","arxiv_id":"2406.16176","n_code_links":0,"syntology":null},{"paper":"/paper/intensity-confusion-matters-an-intensity","slug":"intensity-confusion-matters-an-intensity","title":"Intensity Confusion Matters: An Intensity-Distance Guided Loss for Bronchus Segmentation","date":"2024-06-23","arxiv_id":"2406.16150","n_code_links":1,"syntology":null},{"paper":"/paper/learning-accurate-and-enriched-features-for","slug":"learning-accurate-and-enriched-features-for","title":"Learning Accurate and Enriched Features for Stereo Image Super-Resolution","date":"2024-06-23","arxiv_id":"2406.16001","n_code_links":1,"syntology":null},{"paper":null,"slug":"multi-scale-temporal-difference-transformer","title":"Multi-Scale Temporal Difference Transformer for Video-Text Retrieval","date":"2024-06-23","arxiv_id":"2406.16111","n_code_links":0,"syntology":null},{"paper":"/paper/simce-simplifying-cross-entropy-loss-for","slug":"simce-simplifying-cross-entropy-loss-for","title":"SimCE: Simplifying Cross-Entropy Loss for Collaborative Filtering","date":"2024-06-23","arxiv_id":"2406.16170","n_code_links":1,"syntology":null},{"paper":"/paper/wound-tissue-segmentation-in-diabetic-foot","slug":"wound-tissue-segmentation-in-diabetic-foot","title":"Wound Tissue Segmentation in Diabetic Foot Ulcer Images Using Deep Learning: A Pilot Study","date":"2024-06-23","arxiv_id":"2406.16012","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-multi-speaker-multi-lingual-voice-cloning","title":"A multi-speaker multi-lingual voice cloning system based on vits2 for limmits 2024 challenge","date":"2024-06-22","arxiv_id":"2406.17801","n_code_links":0,"syntology":null},{"paper":"/paper/are-language-models-actually-useful-for-time","slug":"are-language-models-actually-useful-for-time","title":"Are Language Models Actually Useful for Time Series Forecasting?","date":"2024-06-22","arxiv_id":"2406.16964","n_code_links":3,"syntology":{"ran":5,"of":5,"n_ran_checked":4,"n_instrument":1,"unverified":0,"pointer_only":2,"phrase":"5 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; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["bennytmt/llmsfortimeseries","bennytmt/ts_models"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"paper":null,"slug":"beyond-individual-facts-investigating","title":"Beyond Individual Facts: Investigating Categorical Knowledge Locality of Taxonomy and Meronomy Concepts in GPT Models","date":"2024-06-22","arxiv_id":"2406.15940","n_code_links":0,"syntology":null},{"paper":null,"slug":"can-llms-generate-visualizations-with","title":"Can LLMs Generate Visualizations with Dataless Prompts?","date":"2024-06-22","arxiv_id":"2406.17805","n_code_links":0,"syntology":null},{"paper":"/paper/decentralized-transformers-with-centralized","slug":"decentralized-transformers-with-centralized","title":"Decentralized Transformers with Centralized Aggregation are Sample-Efficient Multi-Agent World Models","date":"2024-06-22","arxiv_id":"2406.15836","n_code_links":1,"syntology":null},{"paper":"/paper/enhancing-solar-driver-forecasting-with","slug":"enhancing-solar-driver-forecasting-with","title":"Enhancing Solar Driver Forecasting with Multivariate Transformers","date":"2024-06-22","arxiv_id":"2406.15847","n_code_links":1,"syntology":null},{"paper":null,"slug":"fair-clustering-critique-caveats-and-future","title":"Fair Clustering: Critique, Caveats, and Future Directions","date":"2024-06-22","arxiv_id":"2406.15960","n_code_links":0,"syntology":null},{"paper":"/paper/fast-tree-field-integrators-from-low","slug":"fast-tree-field-integrators-from-low","title":"Fast Tree-Field Integrators: From Low Displacement Rank to Topological Transformers","date":"2024-06-22","arxiv_id":"2406.15881","n_code_links":1,"syntology":{"ran":5,"of":5,"n_ran_checked":0,"n_instrument":5,"unverified":0,"pointer_only":5,"phrase":"5 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; 5 where Syntology's instrument failed) · 0 unverified","official":{"repos":["brcsomnath/fasttreeintegrator"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/injectivity-of-relu-layers-perspectives-from","slug":"injectivity-of-relu-layers-perspectives-from","title":"Injectivity of ReLU-layers: Tools from Frame Theory","date":"2024-06-22","arxiv_id":"2406.15856","n_code_links":1,"syntology":null},{"paper":null,"slug":"integrating-attentional-factors-and-spacing","title":"Integrating Attentional Factors and Spacing in Logistic Knowledge Tracing Models to Explore the Impact of Training Sequences on Category Learning","date":"2024-06-22","arxiv_id":"2407.15020","n_code_links":0,"syntology":null},{"paper":"/paper/ladder-a-model-agnostic-framework-boosting","slug":"ladder-a-model-agnostic-framework-boosting","title":"Ladder: A Model-Agnostic Framework Boosting LLM-based Machine Translation to the Next Level","date":"2024-06-22","arxiv_id":"2406.15741","n_code_links":3,"syntology":{"ran":2,"of":8,"n_ran_checked":0,"n_instrument":2,"unverified":6,"pointer_only":8,"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) · 6 unverified","official":{"repos":["fzp0424/ladder","fzp0424/mt-ladder"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":6,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"lanesegnet-design-study","title":"LaneSegNet Design Study","date":"2024-06-22","arxiv_id":"2406.15946","n_code_links":0,"syntology":null},{"paper":"/paper/mvoc-a-training-free-multiple-video-object","slug":"mvoc-a-training-free-multiple-video-object","title":"MVOC: a training-free multiple video object composition method with diffusion models","date":"2024-06-22","arxiv_id":"2406.15829","n_code_links":1,"syntology":null},{"paper":null,"slug":"remaining-useful-life-prediction-of-rolling","title":"Remaining useful life prediction of rolling bearings based on refined composite multi-scale attention entropy and dispersion entropy","date":"2024-06-22","arxiv_id":"2406.16967","n_code_links":0,"syntology":null},{"paper":null,"slug":"rethinking-entity-level-unlearning-for-large","title":"Unveiling Entity-Level Unlearning for Large Language Models: A Comprehensive Analysis","date":"2024-06-22","arxiv_id":"2406.15796","n_code_links":0,"syntology":null},{"paper":"/paper/rethinking-the-diffusion-models-for-numerical","slug":"rethinking-the-diffusion-models-for-numerical","title":"Rethinking the Diffusion Models for Numerical Tabular Data Imputation from the Perspective of Wasserstein Gradient Flow","date":"2024-06-22","arxiv_id":"2406.15762","n_code_links":1,"syntology":null},{"paper":null,"slug":"scaling-laws-for-fact-memorization-of-large","title":"Scaling Laws for Fact Memorization of Large Language Models","date":"2024-06-22","arxiv_id":"2406.15720","n_code_links":0,"syntology":null},{"paper":"/paper/smart-feature-is-what-you-need","slug":"smart-feature-is-what-you-need","title":"Smart Feature is What You Need","date":"2024-06-22","arxiv_id":"2406.15805","n_code_links":1,"syntology":null},{"paper":"/paper/soft-masked-mamba-diffusion-model-for-ct-to","slug":"soft-masked-mamba-diffusion-model-for-ct-to","title":"Soft Masked Mamba Diffusion Model for CT to MRI Conversion","date":"2024-06-22","arxiv_id":"2406.15910","n_code_links":1,"syntology":null},{"paper":"/paper/ss-bench-a-benchmark-for-social-story","slug":"ss-bench-a-benchmark-for-social-story","title":"SS-GEN: A Social Story Generation Framework with Large Language Models","date":"2024-06-22","arxiv_id":"2406.15695","n_code_links":2,"syntology":null},{"paper":"/paper/tacolm-gated-attention-equipped-codec","slug":"tacolm-gated-attention-equipped-codec","title":"TacoLM: GaTed Attention Equipped Codec Language Model are Efficient Zero-Shot Text to Speech Synthesizers","date":"2024-06-22","arxiv_id":"2406.15752","n_code_links":1,"syntology":null},{"paper":null,"slug":"teach-better-or-show-smarter-on-instructions","title":"Teach Better or Show Smarter? On Instructions and Exemplars in Automatic Prompt Optimization","date":"2024-06-22","arxiv_id":"2406.15708","n_code_links":0,"syntology":null},{"paper":"/paper/unveiling-and-harnessing-hidden-attention","slug":"unveiling-and-harnessing-hidden-attention","title":"Unveiling and Harnessing Hidden Attention Sinks: Enhancing Large Language Models without Training through Attention Calibration","date":"2024-06-22","arxiv_id":"2406.15765","n_code_links":1,"syntology":{"ran":5,"of":13,"n_ran_checked":2,"n_instrument":3,"unverified":8,"pointer_only":13,"phrase":"5 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; 3 where Syntology's instrument failed) · 8 unverified","official":{"repos":["gatech-eic/act"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":8,"ran_from_kinds":["official"]}}},{"paper":"/paper/what-matters-in-transformers-not-all","slug":"what-matters-in-transformers-not-all","title":"What Matters in Transformers? Not All Attention is Needed","date":"2024-06-22","arxiv_id":"2406.15786","n_code_links":2,"syntology":{"ran":5,"of":10,"n_ran_checked":5,"n_instrument":0,"unverified":5,"pointer_only":3,"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) · 5 unverified","official":{"repos":["case-lab-umd/llm-drop","shwai-he/llm-drop"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":"/paper/a-dual-attention-aided-densenet-121-for","slug":"a-dual-attention-aided-densenet-121-for","title":"A Dual Attention-aided DenseNet-121 for Classification of Glaucoma from Fundus Images","date":"2024-06-21","arxiv_id":"2406.15113","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-gpt-based-code-review-system-for","title":"A GPT-based Code Review System for Programming Language Learning","date":"2024-06-21","arxiv_id":"2407.04722","n_code_links":0,"syntology":null},{"paper":"/paper/a-smart-mnemonic-sounds-like-glue-tonic","slug":"a-smart-mnemonic-sounds-like-glue-tonic","title":"A SMART Mnemonic Sounds like \"Glue Tonic\": Mixing LLMs with Student Feedback to Make Mnemonic Learning Stick","date":"2024-06-21","arxiv_id":"2406.15352","n_code_links":1,"syntology":null},{"paper":"/paper/a-tale-of-trust-and-accuracy-base-vs-instruct","slug":"a-tale-of-trust-and-accuracy-base-vs-instruct","title":"A Tale of Trust and Accuracy: Base vs. Instruct LLMs in RAG Systems","date":"2024-06-21","arxiv_id":"2406.14972","n_code_links":1,"syntology":null},{"paper":"/paper/a-wavelet-guided-attention-module-for-skin","slug":"a-wavelet-guided-attention-module-for-skin","title":"A Wavelet Guided Attention Module for Skin Cancer Classification with Gradient-based Feature Fusion","date":"2024-06-21","arxiv_id":"2406.15128","n_code_links":1,"syntology":null},{"paper":null,"slug":"accessible-at-home-detection-of-parkinson-s","title":"Accessible, At-Home Detection of Parkinson's Disease via Multi-task Video Analysis","date":"2024-06-21","arxiv_id":"2406.14856","n_code_links":0,"syntology":null},{"paper":null,"slug":"adaptive-self-supervised-consistency-guided","title":"Self-Supervised Adversarial Diffusion Models for Fast MRI Reconstruction","date":"2024-06-21","arxiv_id":"2406.15656","n_code_links":0,"syntology":null},{"paper":null,"slug":"anime-popularity-prediction-before-huge","title":"Anime Popularity Prediction Before Huge Investments: a Multimodal Approach Using Deep Learning","date":"2024-06-21","arxiv_id":"2406.16961","n_code_links":0,"syntology":null},{"paper":"/paper/brain-like-language-processing-via-a-shallow","slug":"brain-like-language-processing-via-a-shallow","title":"Brain-Like Language Processing via a Shallow Untrained Multihead Attention Network","date":"2024-06-21","arxiv_id":"2406.15109","n_code_links":1,"syntology":null},{"paper":null,"slug":"data-efficient-evaluation-of-large-language","title":"Data Efficient Evaluation of Large Language Models and Text-to-Image Models via Adaptive Sampling","date":"2024-06-21","arxiv_id":"2406.15527","n_code_links":0,"syntology":null},{"paper":null,"slug":"efficient-continual-pre-training-by","title":"Efficient Continual Pre-training by Mitigating the Stability Gap","date":"2024-06-21","arxiv_id":"2406.14833","n_code_links":0,"syntology":null},{"paper":"/paper/esc-eval-evaluating-emotion-support","slug":"esc-eval-evaluating-emotion-support","title":"ESC-Eval: Evaluating Emotion Support Conversations in Large Language Models","date":"2024-06-21","arxiv_id":"2406.14952","n_code_links":3,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":1,"phrase":"0 ran · 1 unverified","official":{"repos":["aiflames/esc-eval","haidequanbu/esc-eval","smartflowai/emollm"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"paper":"/paper/fa-net-a-fuzzy-attention-aided-deep-neural","slug":"fa-net-a-fuzzy-attention-aided-deep-neural","title":"FA-Net: A Fuzzy Attention-aided Deep Neural Network for Pneumonia Detection in Chest X-Rays","date":"2024-06-21","arxiv_id":"2406.15117","n_code_links":1,"syntology":null},{"paper":"/paper/fine-grained-attention-in-hierarchical","slug":"fine-grained-attention-in-hierarchical","title":"Fine-grained Attention in Hierarchical Transformers for Tabular Time-series","date":"2024-06-21","arxiv_id":"2406.15327","n_code_links":1,"syntology":null},{"paper":null,"slug":"fingerprint-membership-and-identity-inference","title":"Fingerprint Membership and Identity Inference Against Generative Adversarial Networks","date":"2024-06-21","arxiv_id":"2406.15253","n_code_links":0,"syntology":null},{"paper":null,"slug":"generating-music-with-structure-using-self","title":"Generating Music with Structure Using Self-Similarity as Attention","date":"2024-06-21","arxiv_id":"2406.15647","n_code_links":0,"syntology":null},{"paper":null,"slug":"giusberto-a-legal-language-model-for-personal","title":"GiusBERTo: A Legal Language Model for Personal Data De-identification in Italian Court of Auditors Decisions","date":"2024-06-21","arxiv_id":"2406.15032","n_code_links":0,"syntology":null},{"paper":"/paper/goal-a-generalist-combinatorial-optimization","slug":"goal-a-generalist-combinatorial-optimization","title":"GOAL: A Generalist Combinatorial Optimization Agent Learning","date":"2024-06-21","arxiv_id":"2406.15079","n_code_links":1,"syntology":{"ran":4,"of":7,"n_ran_checked":4,"n_instrument":0,"unverified":3,"pointer_only":7,"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":["naver/goal-co"],"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":"how-effective-is-gpt-4-turbo-in-generating","title":"How Effective is GPT-4 Turbo in Generating School-Level Questions from Textbooks Based on Bloom's Revised Taxonomy?","date":"2024-06-21","arxiv_id":"2406.15211","n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-interpretability-and-robustness-for","title":"Improving Interpretability and Robustness for the Detection of AI-Generated Images","date":"2024-06-21","arxiv_id":"2406.15035","n_code_links":0,"syntology":null},{"paper":null,"slug":"inferring-pluggable-types-with-machine","title":"Inferring Pluggable Types with Machine Learning","date":"2024-06-21","arxiv_id":"2406.15676","n_code_links":0,"syntology":null},{"paper":"/paper/internlm-law-an-open-source-chinese-legal","slug":"internlm-law-an-open-source-chinese-legal","title":"InternLM-Law: An Open Source Chinese Legal Large Language Model","date":"2024-06-21","arxiv_id":"2406.14887","n_code_links":1,"syntology":null},{"paper":null,"slug":"large-language-models-have-intrinsic-self","title":"Large Language Models have Intrinsic Self-Correction Ability","date":"2024-06-21","arxiv_id":"2406.15673","n_code_links":0,"syntology":null},{"paper":null,"slug":"logicbreaks-a-framework-for-understanding","title":"Logicbreaks: A Framework for Understanding Subversion of Rule-based Inference","date":"2024-06-21","arxiv_id":"2407.00075","n_code_links":0,"syntology":null},{"paper":null,"slug":"longrag-enhancing-retrieval-augmented","title":"LongRAG: Enhancing Retrieval-Augmented Generation with Long-context LLMs","date":"2024-06-21","arxiv_id":"2406.15319","n_code_links":0,"syntology":null}],"record_sha256":"2b41616a5550536722266deab456d6b624828ae82c35817fa3904251d591893a","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}