{"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/transformer/papers/18","list_of":"/method/transformer","method":"Transformer","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":18,"pages_in_order":140,"rows_per_page":100,"rows":[1701,1800],"of":13999,"counts":{"archive_papers_tagged":13999,"with_a_code_link":6572,"where_syntology_ran_a_sample":2248,"not_listed_spam_title":0,"listed":13999,"listed_where_code_ran":2248,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1919,"every_run_a_failure_of_syntologys_instrument":329,"listed_with_a_run_with_no_instrument_failure":1919,"listed_every_run_a_failure_of_syntologys_instrument":329,"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/transformer","prev":"/method/transformer/papers/17","next":"/method/transformer/papers/19","papers":[{"paper":"/paper/self-attentive-transformer-for-fast-and","slug":"self-attentive-transformer-for-fast-and","title":"Self-attentive Transformer for Fast and Accurate Postprocessing of Temperature and Wind Speed Forecasts","date":"2024-12-18","arxiv_id":"2412.13957","n_code_links":1,"syntology":null},{"paper":null,"slug":"covnet-covariance-information-assisted-csi","title":"CovNet: Covariance Information-Assisted CSI Feedback for FDD Massive MIMO Systems","date":"2024-12-17","arxiv_id":"2412.12875","n_code_links":0,"syntology":null},{"paper":"/paper/efficient-diffusion-transformer-policies-with","slug":"efficient-diffusion-transformer-policies-with","title":"Efficient Diffusion Transformer Policies with Mixture of Expert Denoisers for Multitask Learning","date":"2024-12-17","arxiv_id":"2412.12953","n_code_links":1,"syntology":{"ran":10,"of":11,"n_ran_checked":7,"n_instrument":3,"unverified":1,"pointer_only":3,"phrase":"10 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; 3 where Syntology's instrument failed) · 1 unverified","official":null}},{"paper":null,"slug":"enhanced-momentum-with-momentum-transformers","title":"Enhanced Momentum with Momentum Transformers","date":"2024-12-17","arxiv_id":"2412.12516","n_code_links":0,"syntology":null},{"paper":null,"slug":"falcon-faster-and-parallel-inference-of-large","title":"Falcon: Faster and Parallel Inference of Large Language Models through Enhanced Semi-Autoregressive Drafting and Custom-Designed Decoding Tree","date":"2024-12-17","arxiv_id":"2412.12639","n_code_links":0,"syntology":null},{"paper":"/paper/gausstr-foundation-model-aligned-gaussian","slug":"gausstr-foundation-model-aligned-gaussian","title":"GaussTR: Foundation Model-Aligned Gaussian Transformer for Self-Supervised 3D Spatial Understanding","date":"2024-12-17","arxiv_id":"2412.13193","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":0,"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":["hustvl/gausstr"],"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/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":"/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":"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":"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":"/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":"/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":"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/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":"/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":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":"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":"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":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":"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":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":"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":"/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":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/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},{"paper":null,"slug":"centaur-bridging-the-impossible-trinity-of","title":"CENTAUR: Bridging the Impossible Trinity of Privacy, Efficiency, and Performance in Privacy-Preserving Transformer Inference","date":"2024-12-14","arxiv_id":"2412.10652","n_code_links":0,"syntology":null},{"paper":"/paper/fairgp-a-scalable-and-fair-graph-transformer","slug":"fairgp-a-scalable-and-fair-graph-transformer","title":"FairGP: A Scalable and Fair Graph Transformer Using Graph Partitioning","date":"2024-12-14","arxiv_id":"2412.10669","n_code_links":1,"syntology":null},{"paper":"/paper/heterogeneous-graph-transformer-for-multiple","slug":"heterogeneous-graph-transformer-for-multiple","title":"Heterogeneous Graph Transformer for Multiple Tiny Object Tracking in RGB-T Videos","date":"2024-12-14","arxiv_id":"2412.10861","n_code_links":1,"syntology":null},{"paper":"/paper/medg-krp-medical-graph-knowledge","slug":"medg-krp-medical-graph-knowledge","title":"MedG-KRP: Medical Graph Knowledge Representation Probing","date":"2024-12-14","arxiv_id":"2412.10982","n_code_links":1,"syntology":null},{"paper":null,"slug":"rat-adversarial-attacks-on-deep-reinforcement","title":"RAT: Adversarial Attacks on Deep Reinforcement Agents for Targeted Behaviors","date":"2024-12-14","arxiv_id":"2412.10713","n_code_links":0,"syntology":null},{"paper":null,"slug":"styledit-a-unified-framework-for-diverse","title":"StyleDiT: A Unified Framework for Diverse Child and Partner Faces Synthesis with Style Latent Diffusion Transformer","date":"2024-12-14","arxiv_id":"2412.10785","n_code_links":0,"syntology":null},{"paper":"/paper/susgen-gpt-a-data-centric-llm-for-financial","slug":"susgen-gpt-a-data-centric-llm-for-financial","title":"SusGen-GPT: A Data-Centric LLM for Financial NLP and Sustainability Report Generation","date":"2024-12-14","arxiv_id":"2412.10906","n_code_links":1,"syntology":null},{"paper":null,"slug":"advances-in-transformers-for-robotic","title":"Advances in Transformers for Robotic Applications: A Review","date":"2024-12-13","arxiv_id":"2412.10599","n_code_links":0,"syntology":null},{"paper":"/paper/byte-latent-transformer-patches-scale-better","slug":"byte-latent-transformer-patches-scale-better","title":"Byte Latent Transformer: Patches Scale Better Than Tokens","date":"2024-12-13","arxiv_id":"2412.09871","n_code_links":1,"syntology":{"ran":16,"of":22,"n_ran_checked":16,"n_instrument":0,"unverified":6,"pointer_only":22,"phrase":"16 ran (of which 0 constructed an object rather than computing a result; 16 with no instrument failure: 0 honoured, 0 violated, 16 with no contract checked; 0 where Syntology's instrument failed) · 6 unverified","official":{"repos":["facebookresearch/blt"],"state":"official (archive's flag): 16 ran","n_ran":16,"n_constructed":0,"n_ran_no_instrument_failure":16,"n_unverified":6,"ran_from_kinds":["official"]}}},{"paper":"/paper/crossvit-augmented-geospatial-intelligence","slug":"crossvit-augmented-geospatial-intelligence","title":"CrossVIT-augmented Geospatial-Intelligence Visualization System for Tracking Economic Development Dynamics","date":"2024-12-13","arxiv_id":"2412.10474","n_code_links":1,"syntology":null},{"paper":null,"slug":"csl-l2m-controllable-song-level-lyric-to","title":"CSL-L2M: Controllable Song-Level Lyric-to-Melody Generation Based on Conditional Transformer with Fine-Grained Lyric and Musical Controls","date":"2024-12-13","arxiv_id":"2412.09887","n_code_links":0,"syntology":null},{"paper":null,"slug":"edge-ai-based-radio-frequency-fingerprinting","title":"Edge AI-based Radio Frequency Fingerprinting for IoT Networks","date":"2024-12-13","arxiv_id":"2412.10553","n_code_links":0,"syntology":null},{"paper":"/paper/efficient-large-scale-traffic-forecasting","slug":"efficient-large-scale-traffic-forecasting","title":"Efficient Large-Scale Traffic Forecasting with Transformers: A Spatial Data Management Perspective","date":"2024-12-13","arxiv_id":"2412.09972","n_code_links":3,"syntology":{"ran":5,"of":6,"n_ran_checked":4,"n_instrument":1,"unverified":1,"pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 1 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["lmissher/patchstg"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"paper":null,"slug":"mango-multimodal-acuity-transformer-for","title":"MANGO: Multimodal Acuity traNsformer for intelliGent ICU Outcomes","date":"2024-12-13","arxiv_id":"2412.17832","n_code_links":0,"syntology":null},{"paper":null,"slug":"spt-sequence-prompt-transformer-for","title":"SPT: Sequence Prompt Transformer for Interactive Image Segmentation","date":"2024-12-13","arxiv_id":"2412.10224","n_code_links":0,"syntology":null},{"paper":null,"slug":"ultra-high-resolution-segmentation-via","title":"Ultra-High Resolution Segmentation via Boundary-Enhanced Patch-Merging Transformer","date":"2024-12-13","arxiv_id":"2412.10181","n_code_links":0,"syntology":null},{"paper":null,"slug":"what-if-exploring-branching-narratives-by","title":"WHAT-IF: Exploring Branching Narratives by Meta-Prompting Large Language Models","date":"2024-12-13","arxiv_id":"2412.10582","n_code_links":0,"syntology":null},{"paper":"/paper/xyscannet-an-interpretable-state-space-model","slug":"xyscannet-an-interpretable-state-space-model","title":"XYScanNet: A State Space Model for Single Image Deblurring","date":"2024-12-13","arxiv_id":"2412.10338","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-novel-ensemble-based-deep-learning-model","title":"A Novel Ensemble-Based Deep Learning Model with Explainable AI for Accurate Kidney Disease Diagnosis","date":"2024-12-12","arxiv_id":"2412.09472","n_code_links":0,"syntology":null},{"paper":"/paper/advancing-attribution-based-neural-network","slug":"advancing-attribution-based-neural-network","title":"Advancing Attribution-Based Neural Network Explainability through Relative Absolute Magnitude Layer-Wise Relevance Propagation and Multi-Component Evaluation","date":"2024-12-12","arxiv_id":"2412.09311","n_code_links":1,"syntology":null},{"paper":"/paper/federated-foundation-models-on-heterogeneous","slug":"federated-foundation-models-on-heterogeneous","title":"Federated Foundation Models on Heterogeneous Time Series","date":"2024-12-12","arxiv_id":"2412.08906","n_code_links":1,"syntology":{"ran":5,"of":7,"n_ran_checked":3,"n_instrument":2,"unverified":2,"pointer_only":1,"phrase":"5 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; 2 where Syntology's instrument failed) · 2 unverified","official":{"repos":["shengchaochen82/FFTS"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"foundation-models-and-adaptive-feature","title":"Foundation Models and Adaptive Feature Selection: A Synergistic Approach to Video Question Answering","date":"2024-12-12","arxiv_id":"2412.09230","n_code_links":0,"syntology":null},{"paper":"/paper/in-dataset-trajectory-return-regularization","slug":"in-dataset-trajectory-return-regularization","title":"In-Dataset Trajectory Return Regularization for Offline Preference-based Reinforcement Learning","date":"2024-12-12","arxiv_id":"2412.09104","n_code_links":1,"syntology":null},{"paper":"/paper/motif-guided-graph-transformer-with","slug":"motif-guided-graph-transformer-with","title":"Motif Guided Graph Transformer with Combinatorial Skeleton Prototype Learning for Skeleton-Based Person Re-Identification","date":"2024-12-12","arxiv_id":"2412.09044","n_code_links":1,"syntology":null},{"paper":"/paper/ringformer-a-ring-enhanced-graph-transformer","slug":"ringformer-a-ring-enhanced-graph-transformer","title":"RingFormer: A Ring-Enhanced Graph Transformer for Organic Solar Cell Property Prediction","date":"2024-12-12","arxiv_id":"2412.09030","n_code_links":1,"syntology":null},{"paper":null,"slug":"segt-a-general-spatial-expansion-group","title":"SEGT: A General Spatial Expansion Group Transformer for nuScenes Lidar-based Object Detection Task","date":"2024-12-12","arxiv_id":"2412.09658","n_code_links":0,"syntology":null},{"paper":"/paper/selective-visual-prompting-in-vision-mamba","slug":"selective-visual-prompting-in-vision-mamba","title":"Selective Visual Prompting in Vision Mamba","date":"2024-12-12","arxiv_id":"2412.08947","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["zhoujiahuan1991/aaai2025-svp"],"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/smmf-square-matricized-momentum-factorization","slug":"smmf-square-matricized-momentum-factorization","title":"SMMF: Square-Matricized Momentum Factorization for Memory-Efficient Optimization","date":"2024-12-12","arxiv_id":"2412.08894","n_code_links":1,"syntology":null},{"paper":"/paper/speech-forensics-towards-comprehensive","slug":"speech-forensics-towards-comprehensive","title":"Speech-Forensics: Towards Comprehensive Synthetic Speech Dataset Establishment and Analysis","date":"2024-12-12","arxiv_id":"2412.09032","n_code_links":0,"syntology":{"ran":11,"of":11,"n_ran_checked":9,"n_instrument":2,"unverified":0,"pointer_only":11,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":null,"slug":"a-review-of-intelligent-device-fault","title":"A Review of Intelligent Device Fault Diagnosis Technologies Based on Machine Vision","date":"2024-12-11","arxiv_id":"2412.08148","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-survey-on-private-transformer-inference","title":"A Survey on Private Transformer Inference","date":"2024-12-11","arxiv_id":"2412.08145","n_code_links":0,"syntology":null},{"paper":"/paper/adversarial-vulnerabilities-in-large-language","slug":"adversarial-vulnerabilities-in-large-language","title":"Adversarial Vulnerabilities in Large Language Models for Time Series Forecasting","date":"2024-12-11","arxiv_id":"2412.08099","n_code_links":1,"syntology":null},{"paper":null,"slug":"assessing-personalized-ai-mentoring-with","title":"Assessing Personalized AI Mentoring with Large Language Models in the Computing Field","date":"2024-12-11","arxiv_id":"2412.08430","n_code_links":0,"syntology":null},{"paper":"/paper/eov-seg-efficient-open-vocabulary-panoptic","slug":"eov-seg-efficient-open-vocabulary-panoptic","title":"EOV-Seg: Efficient Open-Vocabulary Panoptic Segmentation","date":"2024-12-11","arxiv_id":"2412.08628","n_code_links":1,"syntology":null},{"paper":null,"slug":"gn-fr-generalizable-neural-radiance-fields","title":"GN-FR:Generalizable Neural Radiance Fields for Flare Removal","date":"2024-12-11","arxiv_id":"2412.08200","n_code_links":0,"syntology":null},{"paper":"/paper/protoocc-accurate-efficient-3d-occupancy","slug":"protoocc-accurate-efficient-3d-occupancy","title":"ProtoOcc: Accurate, Efficient 3D Occupancy Prediction Using Dual Branch Encoder-Prototype Query Decoder","date":"2024-12-11","arxiv_id":"2412.08774","n_code_links":1,"syntology":null},{"paper":"/paper/sam-mamba-mamba-guided-sam-architecture-for","slug":"sam-mamba-mamba-guided-sam-architecture-for","title":"SAM-Mamba: Mamba Guided SAM Architecture for Generalized Zero-Shot Polyp Segmentation","date":"2024-12-11","arxiv_id":"2412.08482","n_code_links":1,"syntology":null},{"paper":null,"slug":"svgfusion-scalable-text-to-svg-generation-via","title":"SVGFusion: Scalable Text-to-SVG Generation via Vector Space Diffusion","date":"2024-12-11","arxiv_id":"2412.10437","n_code_links":0,"syntology":null},{"paper":"/paper/acdit-interpolating-autoregressive","slug":"acdit-interpolating-autoregressive","title":"ACDiT: Interpolating Autoregressive Conditional Modeling and Diffusion Transformer","date":"2024-12-10","arxiv_id":"2412.07720","n_code_links":1,"syntology":{"ran":5,"of":6,"n_ran_checked":4,"n_instrument":1,"unverified":1,"pointer_only":0,"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) · 1 unverified","official":{"repos":["thunlp/acdit"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"automatic-item-generation-for-personality","title":"Automatic Item Generation for Personality Situational Judgment Tests with Large Language Models","date":"2024-12-10","arxiv_id":"2412.12144","n_code_links":0,"syntology":null},{"paper":"/paper/bimedix2-bio-medical-expert-lmm-for-diverse","slug":"bimedix2-bio-medical-expert-lmm-for-diverse","title":"BiMediX2: Bio-Medical EXpert LMM for Diverse Medical Modalities","date":"2024-12-10","arxiv_id":"2412.07769","n_code_links":1,"syntology":null},{"paper":null,"slug":"comateformer-combined-attention-transformer","title":"Comateformer: Combined Attention Transformer for Semantic Sentence Matching","date":"2024-12-10","arxiv_id":"2412.07220","n_code_links":0,"syntology":null},{"paper":"/paper/conceptsearch-towards-efficient-program","slug":"conceptsearch-towards-efficient-program","title":"ConceptSearch: Towards Efficient Program Search Using LLMs for Abstraction and Reasoning Corpus (ARC)","date":"2024-12-10","arxiv_id":"2412.07322","n_code_links":1,"syntology":null},{"paper":null,"slug":"demystifying-workload-imbalances-in-large","title":"Demystifying Workload Imbalances in Large Transformer Model Training over Variable-length Sequences","date":"2024-12-10","arxiv_id":"2412.07894","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancing-radioisotope-identification-in","title":"Enhancing radioisotope identification in gamma spectra via supervised domain adaptation","date":"2024-12-10","arxiv_id":"2412.07069","n_code_links":0,"syntology":null},{"paper":null,"slug":"generating-knowledge-graphs-from-large","title":"Generating Knowledge Graphs from Large Language Models: A Comparative Study of GPT-4, LLaMA 2, and BERT","date":"2024-12-10","arxiv_id":"2412.07412","n_code_links":0,"syntology":null},{"paper":"/paper/harp-hesitation-aware-reframing-in","slug":"harp-hesitation-aware-reframing-in","title":"HARP: Hesitation-Aware Reframing in Transformer Inference Pass","date":"2024-12-10","arxiv_id":"2412.07282","n_code_links":1,"syntology":null},{"paper":null,"slug":"ontology-driven-prompt-tuning-for-llm-based","title":"Ontology-driven Prompt Tuning for LLM-based Task and Motion Planning","date":"2024-12-10","arxiv_id":"2412.07493","n_code_links":0,"syntology":null},{"paper":"/paper/post-training-statistical-calibration-for","slug":"post-training-statistical-calibration-for","title":"Post-Training Statistical Calibration for Higher Activation Sparsity","date":"2024-12-10","arxiv_id":"2412.07174","n_code_links":1,"syntology":{"ran":3,"of":5,"n_ran_checked":3,"n_instrument":0,"unverified":2,"pointer_only":0,"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) · 2 unverified","official":{"repos":["intellabs/scap"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"rethinking-emotion-annotations-in-the-era-of","title":"Rethinking Emotion Annotations in the Era of Large Language Models","date":"2024-12-10","arxiv_id":"2412.07906","n_code_links":0,"syntology":null},{"paper":null,"slug":"stiv-scalable-text-and-image-conditioned","title":"STIV: Scalable Text and Image Conditioned Video Generation","date":"2024-12-10","arxiv_id":"2412.07730","n_code_links":0,"syntology":null},{"paper":"/paper/towards-automated-cross-domain-exploratory","slug":"towards-automated-cross-domain-exploratory","title":"Towards Automated Cross-domain Exploratory Data Analysis through Large Language Models","date":"2024-12-10","arxiv_id":"2412.07214","n_code_links":2,"syntology":null},{"paper":null,"slug":"anchoring-bias-in-large-language-models-an","title":"Anchoring Bias in Large Language Models: An Experimental Study","date":"2024-12-09","arxiv_id":"2412.06593","n_code_links":0,"syntology":null},{"paper":"/paper/bridging-the-divide-reconsidering-softmax-and","slug":"bridging-the-divide-reconsidering-softmax-and","title":"Bridging the Divide: Reconsidering Softmax and Linear Attention","date":"2024-12-09","arxiv_id":"2412.06590","n_code_links":1,"syntology":{"ran":17,"of":22,"n_ran_checked":13,"n_instrument":4,"unverified":5,"pointer_only":22,"phrase":"17 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 1 honoured, 0 violated, 12 with no contract checked; 4 where Syntology's instrument failed) · 5 unverified","official":{"repos":["leaplabthu/inline"],"state":"official (archive's flag): 17 ran","n_ran":17,"n_constructed":0,"n_ran_no_instrument_failure":13,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"efficient-user-history-modeling-with","title":"Efficient user history modeling with amortized inference for deep learning recommendation models","date":"2024-12-09","arxiv_id":"2412.06924","n_code_links":0,"syntology":null},{"paper":"/paper/emov2-pushing-5m-vision-model-frontier","slug":"emov2-pushing-5m-vision-model-frontier","title":"EMOv2: Pushing 5M Vision Model Frontier","date":"2024-12-09","arxiv_id":"2412.06674","n_code_links":1,"syntology":null},{"paper":null,"slug":"exploring-memorization-and-copyright","title":"Exploring Memorization and Copyright Violation in Frontier LLMs: A Study of the New York Times v. OpenAI 2023 Lawsuit","date":"2024-12-09","arxiv_id":"2412.06370","n_code_links":0,"syntology":null},{"paper":"/paper/inverting-visual-representations-with-1","slug":"inverting-visual-representations-with-1","title":"Inverting Transformer-based Vision Models","date":"2024-12-09","arxiv_id":"2412.06534","n_code_links":2,"syntology":null},{"paper":"/paper/normalizing-flows-are-capable-generative","slug":"normalizing-flows-are-capable-generative","title":"Normalizing Flows are Capable Generative Models","date":"2024-12-09","arxiv_id":"2412.06329","n_code_links":3,"syntology":{"ran":4,"of":4,"n_ran_checked":3,"n_instrument":1,"unverified":0,"pointer_only":1,"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":["apple/ml-tarflow"],"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":["listed","official"]}}},{"paper":null,"slug":"optimizing-multi-task-learning-for-enhanced","title":"Optimizing Multi-Task Learning for Enhanced Performance in Large Language Models","date":"2024-12-09","arxiv_id":"2412.06249","n_code_links":0,"syntology":null},{"paper":null,"slug":"s-2-ft-efficient-scalable-and-generalizable","title":"S$^{2}$FT: Efficient, Scalable and Generalizable LLM Fine-tuning by Structured Sparsity","date":"2024-12-09","arxiv_id":"2412.06289","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-computational-limits-of-state-space","title":"The Computational Limits of State-Space Models and Mamba via the Lens of Circuit Complexity","date":"2024-12-09","arxiv_id":"2412.06148","n_code_links":0,"syntology":null},{"paper":"/paper/toward-non-invasive-diagnosis-of-bankart","slug":"toward-non-invasive-diagnosis-of-bankart","title":"Toward Non-Invasive Diagnosis of Bankart Lesions with Deep Learning","date":"2024-12-09","arxiv_id":"2412.06717","n_code_links":1,"syntology":null},{"paper":null,"slug":"enhanced-computationally-efficient-long-lora","title":"Enhanced Computationally Efficient Long LoRA Inspired Perceiver Architectures for Auto-Regressive Language Modeling","date":"2024-12-08","arxiv_id":"2412.06106","n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluating-robustness-of-llms-on-crisis","title":"Evaluating Robustness of LLMs on Crisis-Related Microblogs across Events, Information Types, and Linguistic Features","date":"2024-12-08","arxiv_id":"2412.10413","n_code_links":0,"syntology":null},{"paper":"/paper/fully-open-source-moxin-7b-technical-report","slug":"fully-open-source-moxin-7b-technical-report","title":"Fully Open Source Moxin-7B Technical Report","date":"2024-12-08","arxiv_id":"2412.06845","n_code_links":1,"syntology":null},{"paper":null,"slug":"kite-ddi-a-knowledge-graph-integrated","title":"KITE-DDI: A Knowledge graph Integrated Transformer Model for accurately predicting Drug-Drug Interaction Events from Drug SMILES and Biomedical Knowledge Graph","date":"2024-12-08","arxiv_id":"2412.05770","n_code_links":0,"syntology":null},{"paper":null,"slug":"language-guided-image-tokenization-for","title":"Language-Guided Image Tokenization for Generation","date":"2024-12-08","arxiv_id":"2412.05796","n_code_links":0,"syntology":null},{"paper":"/paper/learning-to-correction-explainable-feedback","slug":"learning-to-correction-explainable-feedback","title":"Learning to Correction: Explainable Feedback Generation for Visual Commonsense Reasoning Distractor","date":"2024-12-08","arxiv_id":"2412.07801","n_code_links":1,"syntology":null},{"paper":"/paper/m-3-20m-a-large-scale-multi-modal-molecule","slug":"m-3-20m-a-large-scale-multi-modal-molecule","title":"M$^{3}$-20M: A Large-Scale Multi-Modal Molecule Dataset for AI-driven Drug Design and Discovery","date":"2024-12-08","arxiv_id":"2412.06847","n_code_links":1,"syntology":null},{"paper":null,"slug":"paddy-disease-detection-and-classification","title":"Paddy Disease Detection and Classification Using Computer Vision Techniques: A Mobile Application to Detect Paddy Disease","date":"2024-12-08","arxiv_id":"2412.05996","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-comparative-study-on-code-generation-with","title":"A Comparative Study on Code Generation with Transformers","date":"2024-12-07","arxiv_id":"2412.05749","n_code_links":0,"syntology":null}],"record_sha256":"c4de01958f024624df8f96f3431b99b92a6ecbdef5ae708321a07031f0344c56","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}