{"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/attention/papers/93","list_of":"/method/attention","method":"Attention","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":93,"pages_in_order":316,"rows_per_page":100,"rows":[9201,9300],"of":31583,"counts":{"archive_papers_tagged":31583,"with_a_code_link":13473,"where_syntology_ran_a_sample":3998,"not_listed_spam_title":0,"listed":31583,"listed_where_code_ran":3998,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":3366,"every_run_a_failure_of_syntologys_instrument":632,"listed_with_a_run_with_no_instrument_failure":3366,"listed_every_run_a_failure_of_syntologys_instrument":632,"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/attention","prev":"/method/attention/papers/92","next":"/method/attention/papers/94","papers":[{"paper":null,"slug":"towards-a-deeper-understanding-of-transformer","title":"Towards a Deeper Understanding of Transformer for Residential Non-intrusive Load Monitoring","date":"2024-10-02","arxiv_id":"2410.03758","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-dynamic-graph-neural-networks-with","title":"Towards Dynamic Graph Neural Networks with Provably High-Order Expressive Power","date":"2024-10-02","arxiv_id":"2410.01367","n_code_links":0,"syntology":null},{"paper":null,"slug":"tracking-objects-that-change-in-appearance","title":"Tracking objects that change in appearance with phase synchrony","date":"2024-10-02","arxiv_id":"2410.02094","n_code_links":0,"syntology":null},{"paper":null,"slug":"ulcergpt-a-multimodal-approach-leveraging","title":"UlcerGPT: A Multimodal Approach Leveraging Large Language and Vision Models for Diabetic Foot Ulcer Image Transcription","date":"2024-10-02","arxiv_id":"2410.01989","n_code_links":0,"syntology":null},{"paper":null,"slug":"vectorgraphnet-graph-attention-networks-for","title":"VectorGraphNET: Graph Attention Networks for Accurate Segmentation of Complex Technical Drawings","date":"2024-10-02","arxiv_id":"2410.01336","n_code_links":0,"syntology":null},{"paper":null,"slug":"why-context-matters-in-vqa-and-reasoning","title":"Why context matters in VQA and Reasoning: Semantic interventions for VLM input modalities","date":"2024-10-02","arxiv_id":"2410.01690","n_code_links":0,"syntology":null},{"paper":null,"slug":"addition-is-all-you-need-for-energy-efficient","title":"Addition is All You Need for Energy-efficient Language Models","date":"2024-10-01","arxiv_id":"2410.00907","n_code_links":0,"syntology":null},{"paper":null,"slug":"advanced-arabic-alphabet-sign-language","title":"Advanced Arabic Alphabet Sign Language Recognition Using Transfer Learning and Transformer Models","date":"2024-10-01","arxiv_id":"2410.00681","n_code_links":0,"syntology":null},{"paper":"/paper/advancing-rvfl-networks-robust-classification","slug":"advancing-rvfl-networks-robust-classification","title":"Advancing RVFL networks: Robust classification with the HawkEye loss function","date":"2024-10-01","arxiv_id":"2410.00510","n_code_links":1,"syntology":null},{"paper":"/paper/adversarial-suffixes-may-be-features-too","slug":"adversarial-suffixes-may-be-features-too","title":"Unleashing the Unseen: Harnessing Benign Datasets for Jailbreaking Large Language Models","date":"2024-10-01","arxiv_id":"2410.00451","n_code_links":1,"syntology":null},{"paper":null,"slug":"ai-persuasion-bayesian-attribution-and-career","title":"AI Persuasion, Bayesian Attribution, and Career Concerns of Doctors","date":"2024-10-01","arxiv_id":"2410.01114","n_code_links":0,"syntology":null},{"paper":"/paper/alignsum-data-pyramid-hierarchical-fine","slug":"alignsum-data-pyramid-hierarchical-fine","title":"AlignSum: Data Pyramid Hierarchical Fine-tuning for Aligning with Human Summarization Preference","date":"2024-10-01","arxiv_id":"2410.00409","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["csyanghan/alignsum"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"an-innovative-attention-based-ensemble-system","title":"Explainable AI for Fraud Detection: An Attention-Based Ensemble of CNNs, GNNs, and A Confidence-Driven Gating Mechanism","date":"2024-10-01","arxiv_id":"2410.09069","n_code_links":0,"syntology":null},{"paper":"/paper/babelbench-an-omni-benchmark-for-code-driven","slug":"babelbench-an-omni-benchmark-for-code-driven","title":"BabelBench: An Omni Benchmark for Code-Driven Analysis of Multimodal and Multistructured Data","date":"2024-10-01","arxiv_id":"2410.00773","n_code_links":1,"syntology":null},{"paper":"/paper/creative-and-context-aware-translation-of","slug":"creative-and-context-aware-translation-of","title":"Creative and Context-Aware Translation of East Asian Idioms with GPT-4","date":"2024-10-01","arxiv_id":"2410.00988","n_code_links":1,"syntology":null},{"paper":null,"slug":"data-driven-framework-for-forward-and-inverse","title":"Data-driven Framework for Forward and Inverse Problems in Guided Waves-Based Structural Health Monitoring Under Varying Environmental and Operating Conditions","date":"2024-10-01","arxiv_id":"2410.01127","n_code_links":0,"syntology":null},{"paper":null,"slug":"decoding-hate-exploring-language-models","title":"Decoding Hate: Exploring Language Models' Reactions to Hate Speech","date":"2024-10-01","arxiv_id":"2410.00775","n_code_links":0,"syntology":null},{"paper":"/paper/deep-multimodal-fusion-for-semantic","slug":"deep-multimodal-fusion-for-semantic","title":"Deep Multimodal Fusion for Semantic Segmentation of Remote Sensing Earth Observation Data","date":"2024-10-01","arxiv_id":"2410.00469","n_code_links":0,"syntology":null},{"paper":"/paper/domain-aware-multi-task-pretraining-of-3d","slug":"domain-aware-multi-task-pretraining-of-3d","title":"Domain Aware Multi-Task Pretraining of 3D Swin Transformer for T1-weighted Brain MRI","date":"2024-10-01","arxiv_id":"2410.00410","n_code_links":1,"syntology":null},{"paper":"/paper/end-to-end-speech-recognition-with-pre","slug":"end-to-end-speech-recognition-with-pre","title":"End-to-End Speech Recognition with Pre-trained Masked Language Model","date":"2024-10-01","arxiv_id":"2410.00528","n_code_links":1,"syntology":null},{"paper":null,"slug":"exploring-the-learning-capabilities-of","title":"Exploring the Learning Capabilities of Language Models using LEVERWORLDS","date":"2024-10-01","arxiv_id":"2410.00519","n_code_links":0,"syntology":null},{"paper":"/paper/fce-yolov8-yolov8-with-feature-context","slug":"fce-yolov8-yolov8-with-feature-context","title":"Pediatric Wrist Fracture Detection Using Feature Context Excitation Modules in X-ray Images","date":"2024-10-01","arxiv_id":"2410.01031","n_code_links":1,"syntology":null},{"paper":null,"slug":"glmha-a-guided-low-rank-multi-head-self","title":"GLMHA A Guided Low-rank Multi-Head Self-Attention for Efficient Image Restoration and Spectral Reconstruction","date":"2024-10-01","arxiv_id":"2410.00380","n_code_links":0,"syntology":null},{"paper":"/paper/gspr-multimodal-place-recognition-using-3d","slug":"gspr-multimodal-place-recognition-using-3d","title":"GSPR: Multimodal Place Recognition Using 3D Gaussian Splatting for Autonomous Driving","date":"2024-10-01","arxiv_id":"2410.00299","n_code_links":1,"syntology":null},{"paper":null,"slug":"insight-a-multi-modal-diagnostic-pipeline","title":"Insight: A Multi-Modal Diagnostic Pipeline using LLMs for Ocular Surface Disease Diagnosis","date":"2024-10-01","arxiv_id":"2410.00292","n_code_links":0,"syntology":null},{"paper":null,"slug":"language-enhanced-model-for-eye-leme-an-open","title":"Language Enhanced Model for Eye (LEME): An Open-Source Ophthalmology-Specific Large Language Model","date":"2024-10-01","arxiv_id":"2410.03740","n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-adaptive-hydrodynamic-models-using","title":"Learning Adaptive Hydrodynamic Models Using Neural ODEs in Complex Conditions","date":"2024-10-01","arxiv_id":"2410.00490","n_code_links":0,"syntology":null},{"paper":null,"slug":"map-unleashing-hybrid-mamba-transformer","title":"MAP: Unleashing Hybrid Mamba-Transformer Vision Backbone's Potential with Masked Autoregressive Pretraining","date":"2024-10-01","arxiv_id":"2410.00871","n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-scale-temporal-transformer-for-speech","title":"Multi-Scale Temporal Transformer For Speech Emotion Recognition","date":"2024-10-01","arxiv_id":"2410.00390","n_code_links":0,"syntology":null},{"paper":null,"slug":"ngpt-normalized-transformer-with","title":"nGPT: Normalized Transformer with Representation Learning on the Hypersphere","date":"2024-10-01","arxiv_id":"2410.01131","n_code_links":0,"syntology":null},{"paper":"/paper/optimizing-and-evaluating-enterprise","slug":"optimizing-and-evaluating-enterprise","title":"Optimizing and Evaluating Enterprise Retrieval-Augmented Generation (RAG): A Content Design Perspective","date":"2024-10-01","arxiv_id":"2410.12812","n_code_links":1,"syntology":null},{"paper":"/paper/pclgpt-a-large-language-model-for-patronizing","slug":"pclgpt-a-large-language-model-for-patronizing","title":"PclGPT: A Large Language Model for Patronizing and Condescending Language Detection","date":"2024-10-01","arxiv_id":"2410.00361","n_code_links":1,"syntology":null},{"paper":null,"slug":"quantifying-reliance-on-external-information","title":"Quantifying reliance on external information over parametric knowledge during Retrieval Augmented Generation (RAG) using mechanistic analysis","date":"2024-10-01","arxiv_id":"2410.00857","n_code_links":0,"syntology":null},{"paper":"/paper/rationalyst-pre-training-process-supervision","slug":"rationalyst-pre-training-process-supervision","title":"RATIONALYST: Pre-training Process-Supervision for Improving Reasoning","date":"2024-10-01","arxiv_id":"2410.01044","n_code_links":1,"syntology":null},{"paper":"/paper/replacing-paths-with-connection-biased","slug":"replacing-paths-with-connection-biased","title":"Replacing Paths with Connection-Biased Attention for Knowledge Graph Completion","date":"2024-10-01","arxiv_id":"2410.00876","n_code_links":1,"syntology":null},{"paper":null,"slug":"revisiting-the-role-of-texture-in-3d-person","title":"Revisiting the Role of Texture in 3D Person Re-identification","date":"2024-10-01","arxiv_id":"2410.00348","n_code_links":0,"syntology":null},{"paper":"/paper/robust-traffic-forecasting-against-spatial","slug":"robust-traffic-forecasting-against-spatial","title":"Robust Traffic Forecasting against Spatial Shift over Years","date":"2024-10-01","arxiv_id":"2410.00373","n_code_links":1,"syntology":{"ran":10,"of":13,"n_ran_checked":10,"n_instrument":0,"unverified":3,"pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["dreamzz5/st-expert"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"scene-graph-disentanglement-and-composition","title":"Scene Graph Disentanglement and Composition for Generalizable Complex Image Generation","date":"2024-10-01","arxiv_id":"2410.00447","n_code_links":0,"syntology":null},{"paper":"/paper/scinet-spatial-and-contrast-interactive-super","slug":"scinet-spatial-and-contrast-interactive-super","title":"SCINet: Spatial and Contrast Interactive Super-Resolution Assisted Infrared UAV Target Detection","date":"2024-10-01","arxiv_id":null,"n_code_links":2,"syntology":null},{"paper":null,"slug":"simplified-priors-for-object-centric-learning","title":"Simplified priors for Object-Centric Learning","date":"2024-10-01","arxiv_id":"2410.00728","n_code_links":0,"syntology":null},{"paper":"/paper/sparse-attention-decomposition-applied-to","slug":"sparse-attention-decomposition-applied-to","title":"Sparse Attention Decomposition Applied to Circuit Tracing","date":"2024-10-01","arxiv_id":"2410.00340","n_code_links":1,"syntology":null},{"paper":"/paper/spatial-action-unit-cues-for-interpretable","slug":"spatial-action-unit-cues-for-interpretable","title":"Spatial Action Unit Cues for Interpretable Deep Facial Expression Recognition","date":"2024-10-01","arxiv_id":"2410.01848","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"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) · 0 unverified","official":{"repos":["sbelharbi/interpretable-fer-aus"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/stgformer-efficient-spatiotemporal-graph","slug":"stgformer-efficient-spatiotemporal-graph","title":"STGformer: Efficient Spatiotemporal Graph Transformer for Traffic Forecasting","date":"2024-10-01","arxiv_id":"2410.00385","n_code_links":1,"syntology":null},{"paper":"/paper/tavrnn-temporal-attention-enhanced","slug":"tavrnn-temporal-attention-enhanced","title":"Graph-Based Representation Learning of Neuronal Dynamics and Behavior","date":"2024-10-01","arxiv_id":"2410.00665","n_code_links":1,"syntology":null},{"paper":"/paper/tfct-i2p-three-stream-fusion-network-with","slug":"tfct-i2p-three-stream-fusion-network-with","title":"TFCT-I2P: Three stream fusion network with color aware transformer for image-to-point cloud registration","date":"2024-10-01","arxiv_id":"2410.00360","n_code_links":1,"syntology":null},{"paper":"/paper/tpn-transferable-proto-learning-network","slug":"tpn-transferable-proto-learning-network","title":"TPN: Transferable Proto-Learning Network towards Few-shot Document-Level Relation Extraction","date":"2024-10-01","arxiv_id":"2410.00412","n_code_links":1,"syntology":null},{"paper":"/paper/transresnet-integrating-the-strengths-of-vits","slug":"transresnet-integrating-the-strengths-of-vits","title":"TransResNet: Integrating the Strengths of ViTs and CNNs for High Resolution Medical Image Segmentation via Feature Grafting","date":"2024-10-01","arxiv_id":"2410.00986","n_code_links":1,"syntology":null},{"paper":null,"slug":"y-ca-net-a-convolutional-attention-based","title":"Y-CA-Net: A Convolutional Attention Based Network for Volumetric Medical Image Segmentation","date":"2024-10-01","arxiv_id":"2410.01003","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-looming-replication-crisis-in-evaluating","title":"A Looming Replication Crisis in Evaluating Behavior in Language Models? Evidence and Solutions","date":"2024-09-30","arxiv_id":"2409.20303","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-methodology-for-explainable-large-language","title":"A Methodology for Explainable Large Language Models with Integrated Gradients and Linguistic Analysis in Text Classification","date":"2024-09-30","arxiv_id":"2410.00250","n_code_links":0,"syntology":null},{"paper":null,"slug":"ace-all-round-creator-and-editor-following","title":"ACE: All-round Creator and Editor Following Instructions via Diffusion Transformer","date":"2024-09-30","arxiv_id":"2410.00086","n_code_links":0,"syntology":null},{"paper":null,"slug":"adapting-llms-for-the-medical-domain-in","title":"Adapting LLMs for the Medical Domain in Portuguese: A Study on Fine-Tuning and Model Evaluation","date":"2024-09-30","arxiv_id":"2410.00163","n_code_links":0,"syntology":null},{"paper":"/paper/asquery-a-query-based-model-for-action","slug":"asquery-a-query-based-model-for-action","title":"ASQuery: A Query-based Model for Action Segmentation","date":"2024-09-30","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"bsharedrag-backbone-shared-retrieval","title":"BSharedRAG: Backbone Shared Retrieval-Augmented Generation for the E-commerce Domain","date":"2024-09-30","arxiv_id":"2409.20075","n_code_links":0,"syntology":null},{"paper":null,"slug":"cbam-swint-bl-small-rail-surface-detect","title":"CBAM-SwinT-BL: Small Rail Surface Defect Detection Method Based on Swin Transformer with Block Level CBAM Enhancement","date":"2024-09-30","arxiv_id":"2409.20113","n_code_links":0,"syntology":null},{"paper":null,"slug":"characterizing-and-efficiently-accelerating","title":"Characterizing and Efficiently Accelerating Multimodal Generation Model Inference","date":"2024-09-30","arxiv_id":"2410.00215","n_code_links":0,"syntology":null},{"paper":"/paper/climb-an-ai-enabled-partner-for-clinical","slug":"climb-an-ai-enabled-partner-for-clinical","title":"CliMB: An AI-enabled Partner for Clinical Predictive Modeling","date":"2024-09-30","arxiv_id":"2410.03736","n_code_links":1,"syntology":{"ran":7,"of":10,"n_ran_checked":7,"n_instrument":0,"unverified":3,"pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["vanderschaarlab/climb"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/clr-gan-improving-gans-stability-and-quality","slug":"clr-gan-improving-gans-stability-and-quality","title":"CLR-GAN: Improving GANs Stability and Quality via Consistent Latent Representation and Reconstruction","date":"2024-09-30","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"contrastive-token-learning-with-similarity","title":"Contrastive Token Learning with Similarity Decay for Repetition Suppression in Machine Translation","date":"2024-09-30","arxiv_id":"2409.19877","n_code_links":0,"syntology":null},{"paper":null,"slug":"depression-detection-in-social-media-posts-1","title":"Depression detection in social media posts using transformer-based models and auxiliary features","date":"2024-09-30","arxiv_id":"2409.20048","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancing-romanian-offensive-language","title":"Enhancing Romanian Offensive Language Detection through Knowledge Distillation, Multi-Task Learning, and Data Augmentation","date":"2024-09-30","arxiv_id":"2409.20498","n_code_links":0,"syntology":null},{"paper":"/paper/evaluating-the-fairness-of-task-adaptive","slug":"evaluating-the-fairness-of-task-adaptive","title":"Evaluating the fairness of task-adaptive pretraining on unlabeled test data before few-shot text classification","date":"2024-09-30","arxiv_id":"2410.00179","n_code_links":1,"syntology":null},{"paper":null,"slug":"freemask-rethinking-the-importance-of","title":"FreeMask: Rethinking the Importance of Attention Masks for Zero-Shot Video Editing","date":"2024-09-30","arxiv_id":"2409.20500","n_code_links":0,"syntology":null},{"paper":null,"slug":"gtranspdm-a-graph-embedded-transformer-with","title":"GTransPDM: A Graph-embedded Transformer with Positional Decoupling for Pedestrian Crossing Intention Prediction","date":"2024-09-30","arxiv_id":"2409.20223","n_code_links":0,"syntology":null},{"paper":"/paper/helpd-mitigating-hallucination-of-lvlms-by","slug":"helpd-mitigating-hallucination-of-lvlms-by","title":"HELPD: Mitigating Hallucination of LVLMs by Hierarchical Feedback Learning with Vision-enhanced Penalty Decoding","date":"2024-09-30","arxiv_id":"2409.20429","n_code_links":1,"syntology":null},{"paper":"/paper/immersepro-end-to-end-stereo-video-synthesis","slug":"immersepro-end-to-end-stereo-video-synthesis","title":"ImmersePro: End-to-End Stereo Video Synthesis Via Implicit Disparity Learning","date":"2024-09-30","arxiv_id":"2410.00262","n_code_links":1,"syntology":null},{"paper":null,"slug":"ingest-and-ground-dispelling-hallucinations","title":"Ingest-And-Ground: Dispelling Hallucinations from Continually-Pretrained LLMs with RAG","date":"2024-09-30","arxiv_id":"2410.02825","n_code_links":0,"syntology":null},{"paper":null,"slug":"is-preference-alignment-always-the-best","title":"Is Preference Alignment Always the Best Option to Enhance LLM-Based Translation? An Empirical Analysis","date":"2024-09-30","arxiv_id":"2409.20059","n_code_links":0,"syntology":null},{"paper":"/paper/kv-compress-paged-kv-cache-compression-with","slug":"kv-compress-paged-kv-cache-compression-with","title":"KV-Compress: Paged KV-Cache Compression with Variable Compression Rates per Attention Head","date":"2024-09-30","arxiv_id":"2410.00161","n_code_links":1,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"0 ran · 1 unverified","official":{"repos":["IsaacRe/vllm-kvcompress"],"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/learning-multimodal-latent-generative-models","slug":"learning-multimodal-latent-generative-models","title":"Learning Multimodal Latent Generative Models with Energy-Based Prior","date":"2024-09-30","arxiv_id":"2409.19862","n_code_links":1,"syntology":null},{"paper":"/paper/maia-2-a-unified-model-for-human-ai-alignment","slug":"maia-2-a-unified-model-for-human-ai-alignment","title":"Maia-2: A Unified Model for Human-AI Alignment in Chess","date":"2024-09-30","arxiv_id":"2409.20553","n_code_links":2,"syntology":{"ran":8,"of":18,"n_ran_checked":8,"n_instrument":0,"unverified":10,"pointer_only":11,"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) · 10 unverified","official":{"repos":["csslab/maia2"],"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":["listed","official"]}}},{"paper":null,"slug":"maskmamba-a-hybrid-mamba-transformer-model","title":"MaskMamba: A Hybrid Mamba-Transformer Model for Masked Image Generation","date":"2024-09-30","arxiv_id":"2409.19937","n_code_links":0,"syntology":null},{"paper":null,"slug":"mechanism-design-with-endogenous-perception","title":"Mechanism Design with Endogenous Perception","date":"2024-09-30","arxiv_id":"2409.19853","n_code_links":0,"syntology":null},{"paper":null,"slug":"modelando-procesos-cognitivos-de-la-lectura","title":"Modelando procesos cognitivos de la lectura natural con GPT-2","date":"2024-09-30","arxiv_id":"2409.20174","n_code_links":0,"syntology":null},{"paper":"/paper/numerically-robust-fixed-point-smoothing","slug":"numerically-robust-fixed-point-smoothing","title":"Numerically Robust Fixed-Point Smoothing Without State Augmentation","date":"2024-09-30","arxiv_id":"2409.20004","n_code_links":1,"syntology":null},{"paper":null,"slug":"on-large-uni-and-multi-modal-models-for","title":"Exploring Social Media Image Categorization Using Large Models with Different Adaptation Methods: A Case Study on Cultural Nature's Contributions to People","date":"2024-09-30","arxiv_id":"2410.00275","n_code_links":0,"syntology":null},{"paper":"/paper/on-the-planning-abilities-of-openai-s-o1","slug":"on-the-planning-abilities-of-openai-s-o1","title":"On The Planning Abilities of OpenAI's o1 Models: Feasibility, Optimality, and Generalizability","date":"2024-09-30","arxiv_id":"2409.19924","n_code_links":2,"syntology":null},{"paper":"/paper/qaencoder-towards-aligned-representation","slug":"qaencoder-towards-aligned-representation","title":"QAEncoder: Towards Aligned Representation Learning in Question Answering System","date":"2024-09-30","arxiv_id":"2409.20434","n_code_links":1,"syntology":null},{"paper":null,"slug":"social-conjuring-multi-user-runtime","title":"Social Conjuring: Multi-User Runtime Collaboration with AI in Building Virtual 3D Worlds","date":"2024-09-30","arxiv_id":"2410.00274","n_code_links":0,"syntology":null},{"paper":"/paper/swim-short-window-cnn-integrated-with-mamba","slug":"swim-short-window-cnn-integrated-with-mamba","title":"SWIM: Short-Window CNN Integrated with Mamba for EEG-Based Auditory Spatial Attention Decoding","date":"2024-09-30","arxiv_id":"2409.19884","n_code_links":1,"syntology":null},{"paper":null,"slug":"systemic-risk-asymptotics-in-a-renewal-model","title":"Systemic Risk Asymptotics in a Renewal Model with Multiple Business Lines and Heterogeneous Claims","date":"2024-09-30","arxiv_id":"2410.00158","n_code_links":0,"syntology":null},{"paper":"/paper/t-kaer-transparency-enhanced-knowledge","slug":"t-kaer-transparency-enhanced-knowledge","title":"T-KAER: Transparency-enhanced Knowledge-Augmented Entity Resolution Framework","date":"2024-09-30","arxiv_id":"2410.00218","n_code_links":1,"syntology":null},{"paper":null,"slug":"the-age-of-spiritual-machines-language","title":"The age of spiritual machines: Language quietus induces synthetic altered states of consciousness in artificial intelligence","date":"2024-09-30","arxiv_id":"2410.00257","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-open-vocabulary-semantic-segmentation","title":"Towards Open-Vocabulary Semantic Segmentation Without Semantic Labels","date":"2024-09-30","arxiv_id":"2409.19846","n_code_links":0,"syntology":null},{"paper":"/paper/whole-graph-representation-learning-for-the","slug":"whole-graph-representation-learning-for-the","title":"Whole-Graph Representation Learning For the Classification of Signed Networks","date":"2024-09-30","arxiv_id":"2409.20073","n_code_links":1,"syntology":null},{"paper":"/paper/2d-tpe-two-dimensional-positional-encoding","slug":"2d-tpe-two-dimensional-positional-encoding","title":"2D-TPE: Two-Dimensional Positional Encoding Enhances Table Understanding for Large Language Models","date":"2024-09-29","arxiv_id":"2409.19700","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-multimodal-llm-for-the-non-invasive","title":"A multimodal LLM for the non-invasive decoding of spoken text from brain recordings","date":"2024-09-29","arxiv_id":"2409.19710","n_code_links":0,"syntology":null},{"paper":null,"slug":"abstractive-summarization-of-low-resourced","title":"Abstractive Summarization of Low resourced Nepali language using Multilingual Transformers","date":"2024-09-29","arxiv_id":"2409.19566","n_code_links":0,"syntology":null},{"paper":null,"slug":"adversarial-examples-for-dna-classification","title":"Adversarial Examples for DNA Classification","date":"2024-09-29","arxiv_id":"2409.19788","n_code_links":0,"syntology":null},{"paper":null,"slug":"black-box-segmentation-of-electronic-medical","title":"Black-Box Segmentation of Electronic Medical Records","date":"2024-09-29","arxiv_id":"2409.19796","n_code_links":0,"syntology":null},{"paper":null,"slug":"can-models-learn-skill-composition-from","title":"Can Models Learn Skill Composition from Examples?","date":"2024-09-29","arxiv_id":"2409.19808","n_code_links":0,"syntology":null},{"paper":null,"slug":"causal-deciphering-and-inpainting-in-spatio","title":"Causal Deciphering and Inpainting in Spatio-Temporal Dynamics via Diffusion Model","date":"2024-09-29","arxiv_id":"2409.19608","n_code_links":0,"syntology":null},{"paper":null,"slug":"crscore-grounding-automated-evaluation-of","title":"CRScore: Grounding Automated Evaluation of Code Review Comments in Code Claims and Smells","date":"2024-09-29","arxiv_id":"2409.19801","n_code_links":0,"syntology":null},{"paper":null,"slug":"differentially-private-bilevel-optimization","title":"Differentially Private Bilevel Optimization","date":"2024-09-29","arxiv_id":"2409.19800","n_code_links":0,"syntology":null},{"paper":null,"slug":"diit-a-domain-invariant-information-transfer","title":"DIIT: A Domain-Invariant Information Transfer Method for Industrial Cross-Domain Recommendation","date":"2024-09-29","arxiv_id":"2410.10835","n_code_links":0,"syntology":null},{"paper":null,"slug":"discerning-the-chaos-detecting-adversarial","title":"Discerning the Chaos: Detecting Adversarial Perturbations while Disentangling Intentional from Unintentional Noises","date":"2024-09-29","arxiv_id":"2409.19619","n_code_links":0,"syntology":null},{"paper":"/paper/does-rag-introduce-unfairness-in-llms","slug":"does-rag-introduce-unfairness-in-llms","title":"Does RAG Introduce Unfairness in LLMs? Evaluating Fairness in Retrieval-Augmented Generation Systems","date":"2024-09-29","arxiv_id":"2409.19804","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 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","official":{"repos":["elviswxy/rag_fairness"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"dual-attention-frequency-fusion-at-multi","title":"Dual-Attention Frequency Fusion at Multi-Scale for Joint Segmentation and Deformable Medical Image Registration","date":"2024-09-29","arxiv_id":"2409.19658","n_code_links":0,"syntology":null},{"paper":"/paper/federated-learning-from-vision-language","slug":"federated-learning-from-vision-language","title":"Federated Learning from Vision-Language Foundation Models: Theoretical Analysis and Method","date":"2024-09-29","arxiv_id":"2409.19610","n_code_links":1,"syntology":{"ran":7,"of":10,"n_ran_checked":3,"n_instrument":4,"unverified":3,"pointer_only":10,"phrase":"7 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; 4 where Syntology's instrument failed) · 3 unverified","official":{"repos":["PanBikang/PromptFolio"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"flipped-classroom-aligning-teacher-attention","title":"Flipped Classroom: Aligning Teacher Attention with Student in Generalized Category Discovery","date":"2024-09-29","arxiv_id":"2409.19659","n_code_links":0,"syntology":null}],"record_sha256":"b6b6cdbe6fcabc0bc04bcbbcca987580637eb5932dd5da45c945939e910a5098","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}