{"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/68","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":68,"pages_in_order":375,"rows_per_page":100,"rows":[6701,6800],"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/67","next":"/method/softmax/papers/69","papers":[{"paper":null,"slug":"graph-spring-neural-odes-for-link-sign","title":"Graph Spring Neural ODEs for Link Sign Prediction","date":"2024-12-17","arxiv_id":"2412.12916","n_code_links":0,"syntology":null},{"paper":"/paper/harnessing-event-sensory-data-for-error","slug":"harnessing-event-sensory-data-for-error","title":"Harnessing Event Sensory Data for Error Pattern Prediction in Vehicles: A Language Model Approach","date":"2024-12-17","arxiv_id":"2412.13041","n_code_links":1,"syntology":null},{"paper":null,"slug":"identification-of-epileptic-spasms-eses","title":"Identification of Epileptic Spasms (ESES) Phases Using EEG Signals: A Vision Transformer Approach","date":"2024-12-17","arxiv_id":"2412.13028","n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-the-transferability-of-3d-point","title":"Improving the Transferability of 3D Point Cloud Attack via Spectral-aware Admix and Optimization Designs","date":"2024-12-17","arxiv_id":"2412.12626","n_code_links":0,"syntology":null},{"paper":"/paper/judgeblender-ensembling-judgments-for","slug":"judgeblender-ensembling-judgments-for","title":"JudgeBlender: Ensembling Judgments for Automatic Relevance Assessment","date":"2024-12-17","arxiv_id":"2412.13268","n_code_links":1,"syntology":null},{"paper":null,"slug":"license-plate-detection-and-character","title":"License Plate Detection and Character Recognition Using Deep Learning and Font Evaluation","date":"2024-12-17","arxiv_id":"2412.12572","n_code_links":0,"syntology":null},{"paper":null,"slug":"llm-based-discriminative-reasoning-for","title":"LLM-based Discriminative Reasoning for Knowledge Graph Question Answering","date":"2024-12-17","arxiv_id":"2412.12643","n_code_links":0,"syntology":null},{"paper":null,"slug":"llm-is-knowledge-graph-reasoner-llm-s","title":"LLM is Knowledge Graph Reasoner: LLM's Intuition-aware Knowledge Graph Reasoning for Cold-start Sequential Recommendation","date":"2024-12-17","arxiv_id":"2412.12464","n_code_links":0,"syntology":null},{"paper":null,"slug":"llmcl-gec-advancing-grammatical-error","title":"LLMCL-GEC: Advancing Grammatical Error Correction with LLM-Driven Curriculum Learning","date":"2024-12-17","arxiv_id":"2412.12541","n_code_links":0,"syntology":null},{"paper":null,"slug":"llms-are-also-effective-embedding-models-an","title":"LLMs are Also Effective Embedding Models: An In-depth Overview","date":"2024-12-17","arxiv_id":"2412.12591","n_code_links":0,"syntology":null},{"paper":null,"slug":"motion-2-to-3-leveraging-2d-motion-data-to","title":"Motion-2-to-3: Leveraging 2D Motion Data to Boost 3D Motion Generation","date":"2024-12-17","arxiv_id":"2412.13111","n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-scale-cross-fusion-and-edge-supervision","title":"Multi-Scale Cross-Fusion and Edge-Supervision Network for Image Splicing Localization","date":"2024-12-17","arxiv_id":"2412.12503","n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-uav-collaborative-trajectory-planning","title":"Multi-UAV Collaborative Trajectory Planning for Seamless Data Collection and Transmission","date":"2024-12-17","arxiv_id":"2412.12494","n_code_links":0,"syntology":null},{"paper":null,"slug":"numerical-pruning-for-efficient","title":"Numerical Pruning for Efficient Autoregressive Models","date":"2024-12-17","arxiv_id":"2412.12441","n_code_links":0,"syntology":null},{"paper":"/paper/omnieval-an-omnidirectional-and-automatic-rag","slug":"omnieval-an-omnidirectional-and-automatic-rag","title":"OmniEval: An Omnidirectional and Automatic RAG Evaluation Benchmark in Financial Domain","date":"2024-12-17","arxiv_id":"2412.13018","n_code_links":1,"syntology":null},{"paper":null,"slug":"perc-plan-as-query-example-retrieval-for","title":"PERC: Plan-As-Query Example Retrieval for Underrepresented Code Generation","date":"2024-12-17","arxiv_id":"2412.12447","n_code_links":0,"syntology":null},{"paper":null,"slug":"phoneme-level-feature-discrepancies-a-key-to","title":"Phoneme-Level Feature Discrepancies: A Key to Detecting Sophisticated Speech Deepfakes","date":"2024-12-17","arxiv_id":"2412.12619","n_code_links":0,"syntology":null},{"paper":"/paper/po3ad-predicting-point-offsets-toward-better","slug":"po3ad-predicting-point-offsets-toward-better","title":"PO3AD: Predicting Point Offsets toward Better 3D Point Cloud Anomaly Detection","date":"2024-12-17","arxiv_id":"2412.12617","n_code_links":0,"syntology":null},{"paper":null,"slug":"promptdet-a-lightweight-3d-object-detection","title":"PromptDet: A Lightweight 3D Object Detection Framework with LiDAR Prompts","date":"2024-12-17","arxiv_id":"2412.12460","n_code_links":0,"syntology":null},{"paper":null,"slug":"pt-a-plain-transformer-is-good-hospital","title":"PT: A Plain Transformer is Good Hospital Readmission Predictor","date":"2024-12-17","arxiv_id":"2412.12909","n_code_links":0,"syntology":null},{"paper":null,"slug":"rag-star-enhancing-deliberative-reasoning","title":"RAG-Star: Enhancing Deliberative Reasoning with Retrieval Augmented Verification and Refinement","date":"2024-12-17","arxiv_id":"2412.12881","n_code_links":0,"syntology":null},{"paper":"/paper/rctrans-radar-camera-transformer-via-radar","slug":"rctrans-radar-camera-transformer-via-radar","title":"RCTrans: Radar-Camera Transformer via Radar Densifier and Sequential Decoder for 3D Object Detection","date":"2024-12-17","arxiv_id":"2412.12799","n_code_links":1,"syntology":null},{"paper":null,"slug":"remoterag-a-privacy-preserving-llm-cloud-rag","title":"RemoteRAG: A Privacy-Preserving LLM Cloud RAG Service","date":"2024-12-17","arxiv_id":"2412.12775","n_code_links":0,"syntology":null},{"paper":null,"slug":"shared-attention-based-autoencoder-with","title":"Shared Attention-based Autoencoder with Hierarchical Fusion-based Graph Convolution Network for sEEG SOZ Identification","date":"2024-12-17","arxiv_id":"2412.12651","n_code_links":0,"syntology":null},{"paper":"/paper/simgrag-leveraging-similar-subgraphs-for","slug":"simgrag-leveraging-similar-subgraphs-for","title":"SimGRAG: Leveraging Similar Subgraphs for Knowledge Graphs Driven Retrieval-Augmented Generation","date":"2024-12-17","arxiv_id":"2412.15272","n_code_links":1,"syntology":null},{"paper":null,"slug":"synthetic-time-series-data-generation-for","title":"Synthetic Time Series Data Generation for Healthcare Applications: A PCG Case Study","date":"2024-12-17","arxiv_id":"2412.16207","n_code_links":0,"syntology":null},{"paper":"/paper/timecheat-a-channel-harmony-strategy-for","slug":"timecheat-a-channel-harmony-strategy-for","title":"TimeCHEAT: A Channel Harmony Strategy for Irregularly Sampled Multivariate Time Series Analysis","date":"2024-12-17","arxiv_id":"2412.12886","n_code_links":1,"syntology":{"ran":8,"of":9,"n_ran_checked":8,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["Alrash/TimeCHEAT"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"transferable-and-forecastable-user-targeting","title":"Transferable and Forecastable User Targeting Foundation Model","date":"2024-12-17","arxiv_id":"2412.12468","n_code_links":0,"syntology":null},{"paper":"/paper/versatile-ordering-network-an-attention-based","slug":"versatile-ordering-network-an-attention-based","title":"Versatile Ordering Network: An Attention-based Neural Network for Ordering Across Scales and Quality Metrics","date":"2024-12-17","arxiv_id":"2412.12759","n_code_links":1,"syntology":null},{"paper":null,"slug":"what-external-knowledge-is-preferred-by-llms","title":"What External Knowledge is Preferred by LLMs? Characterizing and Exploring Chain of Evidence in Imperfect Context","date":"2024-12-17","arxiv_id":"2412.12632","n_code_links":0,"syntology":null},{"paper":"/paper/xtransplant-a-probe-into-the-upper-bound","slug":"xtransplant-a-probe-into-the-upper-bound","title":"Exploring Cross-lingual Latent Transplantation: Mutual Opportunities and Open Challenges","date":"2024-12-17","arxiv_id":"2412.12686","n_code_links":1,"syntology":null},{"paper":"/paper/a-benchmark-and-robustness-study-of-in","slug":"a-benchmark-and-robustness-study-of-in","title":"A Benchmark and Robustness Study of In-Context-Learning with Large Language Models in Music Entity Detection","date":"2024-12-16","arxiv_id":"2412.11851","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-lora-is-worth-a-thousand-pictures","title":"A LoRA is Worth a Thousand Pictures","date":"2024-12-16","arxiv_id":"2412.12048","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-survey-on-large-language-models-for-4","title":"A Survey on Large Language Models for Communication, Network, and Service Management: Application Insights, Challenges, and Future Directions","date":"2024-12-16","arxiv_id":"2412.19823","n_code_links":0,"syntology":null},{"paper":null,"slug":"advancements-and-challenges-in-bangla","title":"Advancements and Challenges in Bangla Question Answering Models: A Comprehensive Review","date":"2024-12-16","arxiv_id":"2412.11823","n_code_links":0,"syntology":null},{"paper":null,"slug":"attention-with-dependency-parsing","title":"Attention with Dependency Parsing Augmentation for Fine-Grained Attribution","date":"2024-12-16","arxiv_id":"2412.11404","n_code_links":0,"syntology":null},{"paper":"/paper/biobridge-unified-bio-embedding-with-bridging","slug":"biobridge-unified-bio-embedding-with-bridging","title":"BioBridge: Unified Bio-Embedding with Bridging Modality in Code-Switched EMR","date":"2024-12-16","arxiv_id":"2412.11671","n_code_links":1,"syntology":null},{"paper":null,"slug":"can-language-models-rival-mathematics","title":"Can Language Models Rival Mathematics Students? Evaluating Mathematical Reasoning through Textual Manipulation and Human Experiments","date":"2024-12-16","arxiv_id":"2412.11908","n_code_links":0,"syntology":null},{"paper":"/paper/causal-diffusion-transformers-for-generative","slug":"causal-diffusion-transformers-for-generative","title":"Causal Diffusion Transformers for Generative Modeling","date":"2024-12-16","arxiv_id":"2412.12095","n_code_links":1,"syntology":{"ran":8,"of":10,"n_ran_checked":6,"n_instrument":2,"unverified":2,"pointer_only":10,"phrase":"8 ran (of which 3 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","official":{"repos":["causalfusion/causalfusion"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":3,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official","unlocated"]}}},{"paper":null,"slug":"csr-achieving-1-bit-key-value-cache-via","title":"CSR:Achieving 1 Bit Key-Value Cache via Sparse Representation","date":"2024-12-16","arxiv_id":"2412.11741","n_code_links":0,"syntology":null},{"paper":null,"slug":"discrepancy-aware-attention-network-for","title":"Discrepancy-Aware Attention Network for Enhanced Audio-Visual Zero-Shot Learning","date":"2024-12-16","arxiv_id":"2412.11715","n_code_links":0,"syntology":null},{"paper":"/paper/drivegazen-event-based-driving-status","slug":"drivegazen-event-based-driving-status","title":"DriveGazen: Event-Based Driving Status Recognition using Conventional Camera","date":"2024-12-16","arxiv_id":"2412.11753","n_code_links":1,"syntology":null},{"paper":"/paper/edformer-embedded-decomposition-transformer","slug":"edformer-embedded-decomposition-transformer","title":"EDformer: Embedded Decomposition Transformer for Interpretable Multivariate Time Series Predictions","date":"2024-12-16","arxiv_id":"2412.12227","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["sanjaylopa22/EDformer-Feature-Importance"],"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":null,"slug":"egp3d-edge-guided-geometric-preserving-3d","title":"EGP3D: Edge-guided Geometric Preserving 3D Point Cloud Super-resolution for RGB-D camera","date":"2024-12-16","arxiv_id":"2412.11680","n_code_links":0,"syntology":null},{"paper":"/paper/embodied-cot-distillation-from-llm-to-off-the","slug":"embodied-cot-distillation-from-llm-to-off-the","title":"Embodied CoT Distillation From LLM To Off-the-shelf Agents","date":"2024-12-16","arxiv_id":"2412.11499","n_code_links":1,"syntology":{"ran":2,"of":5,"n_ran_checked":2,"n_instrument":0,"unverified":3,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["osu-nlp-group/llm-planner"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"ensemble-learning-and-3d-pix2pix-for","title":"Ensemble Learning and 3D Pix2Pix for Comprehensive Brain Tumor Analysis in Multimodal MRI","date":"2024-12-16","arxiv_id":"2412.11849","n_code_links":0,"syntology":null},{"paper":null,"slug":"explainable-procedural-mistake-detection","title":"Explainable Procedural Mistake Detection","date":"2024-12-16","arxiv_id":"2412.11927","n_code_links":0,"syntology":null},{"paper":"/paper/fast-and-slow-gradient-approximation-for","slug":"fast-and-slow-gradient-approximation-for","title":"Fast and Slow Gradient Approximation for Binary Neural Network Optimization","date":"2024-12-16","arxiv_id":"2412.11777","n_code_links":1,"syntology":null},{"paper":"/paper/geox-geometric-problem-solving-through","slug":"geox-geometric-problem-solving-through","title":"GeoX: Geometric Problem Solving Through Unified Formalized Vision-Language Pre-training","date":"2024-12-16","arxiv_id":"2412.11863","n_code_links":2,"syntology":{"ran":7,"of":7,"n_ran_checked":5,"n_instrument":2,"unverified":0,"pointer_only":7,"phrase":"7 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; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["alpha-innovator/geox","unimodal4reasoning/geox"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/glimpse-enabling-white-box-methods-to-use","slug":"glimpse-enabling-white-box-methods-to-use","title":"Glimpse: Enabling White-Box Methods to Use Proprietary Models for Zero-Shot LLM-Generated Text Detection","date":"2024-12-16","arxiv_id":"2412.11506","n_code_links":1,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":1,"phrase":"0 ran · 1 unverified","official":{"repos":["baoguangsheng/glimpse"],"state":"official: not harvested","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":[]}}},{"paper":null,"slug":"graph-guided-textual-explanation-generation","title":"Graph-Guided Textual Explanation Generation Framework","date":"2024-12-16","arxiv_id":"2412.12318","n_code_links":0,"syntology":null},{"paper":null,"slug":"groupface-imbalanced-age-estimation-based-on","title":"GroupFace: Imbalanced Age Estimation Based on Multi-hop Attention Graph Convolutional Network and Group-aware Margin Optimization","date":"2024-12-16","arxiv_id":"2412.11450","n_code_links":0,"syntology":null},{"paper":null,"slug":"high-speed-and-high-quality-vision","title":"High-speed and High-quality Vision Reconstruction of Spike Camera with Spike Stability Theorem","date":"2024-12-16","arxiv_id":"2412.11639","n_code_links":0,"syntology":null},{"paper":null,"slug":"hresformer-hybrid-residual-transformer-for","title":"HResFormer: Hybrid Residual Transformer for Volumetric Medical Image Segmentation","date":"2024-12-16","arxiv_id":"2412.11458","n_code_links":0,"syntology":null},{"paper":null,"slug":"idarb-intrinsic-decomposition-for-arbitrary","title":"IDArb: Intrinsic Decomposition for Arbitrary Number of Input Views and Illuminations","date":"2024-12-16","arxiv_id":"2412.12083","n_code_links":0,"syntology":null},{"paper":"/paper/inferring-functionality-of-attention-heads","slug":"inferring-functionality-of-attention-heads","title":"Inferring Functionality of Attention Heads from their Parameters","date":"2024-12-16","arxiv_id":"2412.11965","n_code_links":1,"syntology":{"ran":6,"of":6,"n_ran_checked":6,"n_instrument":0,"unverified":0,"pointer_only":6,"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":{"repos":["amitelhelo/maps"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"investigating-mixture-of-experts-in-dense","title":"Investigating Mixture of Experts in Dense Retrieval","date":"2024-12-16","arxiv_id":"2412.11864","n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-implicit-features-with-flow-infused","title":"Learning Implicit Features with Flow Infused Attention for Realistic Virtual Try-On","date":"2024-12-16","arxiv_id":"2412.11435","n_code_links":0,"syntology":null},{"paper":"/paper/llm-rg4-flexible-and-factual-radiology-report","slug":"llm-rg4-flexible-and-factual-radiology-report","title":"LLM-RG4: Flexible and Factual Radiology Report Generation across Diverse Input Contexts","date":"2024-12-16","arxiv_id":"2412.12001","n_code_links":1,"syntology":null},{"paper":"/paper/look-ahead-text-understanding-and-llm","slug":"look-ahead-text-understanding-and-llm","title":"Look Ahead Text Understanding and LLM Stitching","date":"2024-12-16","arxiv_id":"2412.17836","n_code_links":1,"syntology":null},{"paper":null,"slug":"magnetic-field-data-calibration-with","title":"Magnetic Field Data Calibration with Transformer Model Using Physical Constraints: A Scalable Method for Satellite Missions, Illustrated by Tianwen-1","date":"2024-12-16","arxiv_id":"2501.00020","n_code_links":0,"syntology":null},{"paper":"/paper/mpq-dm-mixed-precision-quantization-for","slug":"mpq-dm-mixed-precision-quantization-for","title":"MPQ-DM: Mixed Precision Quantization for Extremely Low Bit Diffusion Models","date":"2024-12-16","arxiv_id":"2412.11549","n_code_links":1,"syntology":{"ran":11,"of":13,"n_ran_checked":6,"n_instrument":5,"unverified":2,"pointer_only":3,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 2 violated, 4 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified","official":{"repos":["cantbebetter2/mpq-dm"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/no-more-adam-learning-rate-scaling-at","slug":"no-more-adam-learning-rate-scaling-at","title":"No More Adam: Learning Rate Scaling at Initialization is All You Need","date":"2024-12-16","arxiv_id":"2412.11768","n_code_links":1,"syntology":null},{"paper":null,"slug":"no-more-tuning-prioritized-multi-task","title":"No More Tuning: Prioritized Multi-Task Learning with Lagrangian Differential Multiplier Methods","date":"2024-12-16","arxiv_id":"2412.12092","n_code_links":0,"syntology":null},{"paper":"/paper/on-the-role-of-surrogates-in-conformal","slug":"on-the-role-of-surrogates-in-conformal","title":"On the Role of Surrogates in Conformal Inference of Individual Causal Effects","date":"2024-12-16","arxiv_id":"2412.12365","n_code_links":1,"syntology":null},{"paper":null,"slug":"openreviewer-a-specialized-large-language","title":"OpenReviewer: A Specialized Large Language Model for Generating Critical Scientific Paper Reviews","date":"2024-12-16","arxiv_id":"2412.11948","n_code_links":0,"syntology":null},{"paper":null,"slug":"optimized-quran-passage-retrieval-using-an","title":"Optimized Quran Passage Retrieval Using an Expanded QA Dataset and Fine-Tuned Language Models","date":"2024-12-16","arxiv_id":"2412.11431","n_code_links":0,"syntology":null},{"paper":"/paper/pansplat-4k-panorama-synthesis-with-feed","slug":"pansplat-4k-panorama-synthesis-with-feed","title":"PanSplat: 4K Panorama Synthesis with Feed-Forward Gaussian Splatting","date":"2024-12-16","arxiv_id":"2412.12096","n_code_links":1,"syntology":null},{"paper":null,"slug":"priority-aware-model-distributed-inference-at","title":"Priority-Aware Model-Distributed Inference at Edge Networks","date":"2024-12-16","arxiv_id":"2412.12371","n_code_links":0,"syntology":null},{"paper":null,"slug":"radarsat-constellation-mission-compact","title":"RADARSAT Constellation Mission Compact Polarisation SAR Data for Burned Area Mapping with Deep Learning","date":"2024-12-16","arxiv_id":"2412.11561","n_code_links":0,"syntology":null},{"paper":"/paper/rag-playground-a-framework-for-systematic","slug":"rag-playground-a-framework-for-systematic","title":"RAG Playground: A Framework for Systematic Evaluation of Retrieval Strategies and Prompt Engineering in RAG Systems","date":"2024-12-16","arxiv_id":"2412.12322","n_code_links":1,"syntology":null},{"paper":null,"slug":"second-language-arabic-acquisition-of-llms","title":"Second Language (Arabic) Acquisition of LLMs via Progressive Vocabulary Expansion","date":"2024-12-16","arxiv_id":"2412.12310","n_code_links":0,"syntology":null},{"paper":"/paper/segman-omni-scale-context-modeling-with-state","slug":"segman-omni-scale-context-modeling-with-state","title":"SegMAN: Omni-scale Context Modeling with State Space Models and Local Attention for Semantic Segmentation","date":"2024-12-16","arxiv_id":"2412.11890","n_code_links":1,"syntology":null},{"paper":"/paper/sepllm-accelerate-large-language-models-by","slug":"sepllm-accelerate-large-language-models-by","title":"SepLLM: Accelerate Large Language Models by Compressing One Segment into One Separator","date":"2024-12-16","arxiv_id":"2412.12094","n_code_links":1,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":1,"phrase":"0 ran · 1 unverified","official":{"repos":["HKUDS/SepLLM"],"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":"sp-2-t-sparse-proxy-attention-for-dual-stream","title":"SP$^2$T: Sparse Proxy Attention for Dual-stream Point Transformer","date":"2024-12-16","arxiv_id":"2412.11540","n_code_links":0,"syntology":null},{"paper":"/paper/speechprune-context-aware-token-pruning-for","slug":"speechprune-context-aware-token-pruning-for","title":"SpeechPrune: Context-aware Token Pruning for Speech Information Retrieval","date":"2024-12-16","arxiv_id":"2412.12009","n_code_links":1,"syntology":null},{"paper":null,"slug":"stepwise-reasoning-error-disruption-attack-of","title":"Stepwise Reasoning Error Disruption Attack of LLMs","date":"2024-12-16","arxiv_id":"2412.11934","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-impact-of-ai-assistance-on-radiology","title":"The Impact of AI Assistance on Radiology Reporting: A Pilot Study Using Simulated AI Draft Reports","date":"2024-12-16","arxiv_id":"2412.12042","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-open-source-advantage-in-large-language","title":"The Open Source Advantage in Large Language Models (LLMs)","date":"2024-12-16","arxiv_id":"2412.12004","n_code_links":0,"syntology":null},{"paper":null,"slug":"token-prepending-a-training-free-approach-for","title":"Token Prepending: A Training-Free Approach for Eliciting Better Sentence Embeddings from LLMs","date":"2024-12-16","arxiv_id":"2412.11556","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-a-universal-synthetic-video-detector","title":"Towards a Universal Synthetic Video Detector: From Face or Background Manipulations to Fully AI-Generated Content","date":"2024-12-16","arxiv_id":"2412.12278","n_code_links":0,"syntology":null},{"paper":"/paper/transferable-adversarial-face-attack-with","slug":"transferable-adversarial-face-attack-with","title":"Transferable Adversarial Face Attack with Text Controlled Attribute","date":"2024-12-16","arxiv_id":"2412.11735","n_code_links":2,"syntology":null},{"paper":null,"slug":"transformers-use-causal-world-models-in-maze","title":"Transformers Use Causal World Models in Maze-Solving Tasks","date":"2024-12-16","arxiv_id":"2412.11867","n_code_links":0,"syntology":null},{"paper":null,"slug":"ultra-high-definition-dynamic-multi-exposure","title":"Ultra-High-Definition Dynamic Multi-Exposure Image Fusion via Infinite Pixel Learning","date":"2024-12-16","arxiv_id":"2412.11685","n_code_links":0,"syntology":null},{"paper":null,"slug":"unanswerability-evaluation-for-retreival","title":"Unanswerability Evaluation for Retrieval Augmented Generation","date":"2024-12-16","arxiv_id":"2412.12300","n_code_links":0,"syntology":null},{"paper":null,"slug":"unma-capsumt-unified-and-multi-head-attention","title":"UnMA-CapSumT: Unified and Multi-Head Attention-driven Caption Summarization Transformer","date":"2024-12-16","arxiv_id":"2412.11836","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-comparative-study-on-dynamic-graph","title":"A Comparative Study on Dynamic Graph Embedding based on Mamba and Transformers","date":"2024-12-15","arxiv_id":"2412.11293","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-contextualized-bert-model-for-knowledge","title":"A Contextualized BERT model for Knowledge Graph Completion","date":"2024-12-15","arxiv_id":"2412.11016","n_code_links":0,"syntology":null},{"paper":"/paper/analyzing-the-attention-heads-for-pronoun","slug":"analyzing-the-attention-heads-for-pronoun","title":"Analyzing the Attention Heads for Pronoun Disambiguation in Context-aware Machine Translation Models","date":"2024-12-15","arxiv_id":"2412.11187","n_code_links":1,"syntology":null},{"paper":null,"slug":"eeg-gmacn-interpretable-eeg-graph-mutual","title":"EEG-GMACN: Interpretable EEG Graph Mutual Attention Convolutional Network","date":"2024-12-15","arxiv_id":"2412.17834","n_code_links":0,"syntology":null},{"paper":"/paper/from-votes-to-volatility-predicting-the-stock","slug":"from-votes-to-volatility-predicting-the-stock","title":"From Votes to Volatility Predicting the Stock Market on Election Day","date":"2024-12-15","arxiv_id":"2412.11192","n_code_links":1,"syntology":null},{"paper":"/paper/fsta-snn-frequency-based-spatial-temporal","slug":"fsta-snn-frequency-based-spatial-temporal","title":"FSTA-SNN:Frequency-based Spatial-Temporal Attention Module for Spiking Neural Networks","date":"2024-12-15","arxiv_id":"2501.14744","n_code_links":1,"syntology":null},{"paper":"/paper/more-class-patch-attention-needs","slug":"more-class-patch-attention-needs","title":"MoRe: Class Patch Attention Needs Regularization for Weakly Supervised Semantic Segmentation","date":"2024-12-15","arxiv_id":"2412.11076","n_code_links":1,"syntology":null},{"paper":"/paper/multi-graph-co-training-for-capturing-user","slug":"multi-graph-co-training-for-capturing-user","title":"Multi-Graph Co-Training for Capturing User Intent in Session-based Recommendation","date":"2024-12-15","arxiv_id":"2412.11105","n_code_links":1,"syntology":null},{"paper":"/paper/on-the-generalizability-of-iterative-patch","slug":"on-the-generalizability-of-iterative-patch","title":"On the Generalizability of Iterative Patch Selection for Memory-Efficient High-Resolution Image Classification","date":"2024-12-15","arxiv_id":"2412.11237","n_code_links":1,"syntology":null},{"paper":null,"slug":"one-shot-multilingual-font-generation-via-vit","title":"One-Shot Multilingual Font Generation Via ViT","date":"2024-12-15","arxiv_id":"2412.11342","n_code_links":0,"syntology":null},{"paper":"/paper/rolargesum-a-large-dialect-aware-romanian","slug":"rolargesum-a-large-dialect-aware-romanian","title":"RoLargeSum: A Large Dialect-Aware Romanian News Dataset for Summary, Headline, and Keyword Generation","date":"2024-12-15","arxiv_id":"2412.11317","n_code_links":1,"syntology":null},{"paper":"/paper/smaller-language-models-are-better","slug":"smaller-language-models-are-better","title":"Smaller Language Models Are Better Instruction Evolvers","date":"2024-12-15","arxiv_id":"2412.11231","n_code_links":1,"syntology":null},{"paper":null,"slug":"towards-context-aware-convolutional-network","title":"Towards Context-aware Convolutional Network for Image Restoration","date":"2024-12-15","arxiv_id":"2412.11008","n_code_links":0,"syntology":null},{"paper":null,"slug":"transformer-based-bearing-fault-detection","title":"Transformer-Based Bearing Fault Detection using Temporal Decomposition Attention Mechanism","date":"2024-12-15","arxiv_id":"2412.11245","n_code_links":0,"syntology":null}],"record_sha256":"3a51b15e751cc0db1bb0f74c1b353a399070d1ded34f2b229ad173f07bf18f9a","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}