{"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/64","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":64,"pages_in_order":316,"rows_per_page":100,"rows":[6301,6400],"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/63","next":"/method/attention/papers/65","papers":[{"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":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":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},{"paper":null,"slug":"visymre-vision-guided-multimodal-symbolic","title":"ViSymRe: Vision-guided Multimodal Symbolic Regression","date":"2024-12-15","arxiv_id":"2412.11139","n_code_links":0,"syntology":null},{"paper":null,"slug":"accelerating-retrieval-augmented-generation","title":"Accelerating Retrieval-Augmented Generation","date":"2024-12-14","arxiv_id":"2412.15246","n_code_links":0,"syntology":null},{"paper":"/paper/attention-driven-gui-grounding-leveraging","slug":"attention-driven-gui-grounding-leveraging","title":"Attention-driven GUI Grounding: Leveraging Pretrained Multimodal Large Language Models without Fine-Tuning","date":"2024-12-14","arxiv_id":"2412.10840","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":2,"n_instrument":2,"unverified":0,"pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["heimingx/tag"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"boosting-vit-based-mri-reconstruction-from","title":"Boosting ViT-based MRI Reconstruction from the Perspectives of Frequency Modulation, Spatial Purification, and Scale Diversification","date":"2024-12-14","arxiv_id":"2412.10776","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/demo-decoupled-feature-based-mixture-of","slug":"demo-decoupled-feature-based-mixture-of","title":"DeMo: Decoupled Feature-Based Mixture of Experts for Multi-Modal Object Re-Identification","date":"2024-12-14","arxiv_id":"2412.10650","n_code_links":1,"syntology":{"ran":3,"of":4,"n_ran_checked":2,"n_instrument":1,"unverified":1,"pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["924973292/demo"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/do-large-language-vision-models-understand-3d","slug":"do-large-language-vision-models-understand-3d","title":"Do large language vision models understand 3D shapes?","date":"2024-12-14","arxiv_id":"2412.10908","n_code_links":1,"syntology":null},{"paper":null,"slug":"enhancing-road-crack-detection-accuracy-with","title":"Enhancing Road Crack Detection Accuracy with BsS-YOLO: Optimizing Feature Fusion and Attention Mechanisms","date":"2024-12-14","arxiv_id":"2412.10902","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":null,"slug":"graph-attention-hamiltonian-neural-networks-a","title":"Graph Attention Hamiltonian Neural Networks: A Lattice System Analysis Model Based on Structural Learning","date":"2024-12-14","arxiv_id":"2412.10821","n_code_links":0,"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":null,"slug":"inference-scaling-for-bridging-retrieval-and","title":"Inference Scaling for Bridging Retrieval and Augmented Generation","date":"2024-12-14","arxiv_id":"2412.10684","n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-semantic-aware-representation-in","title":"Learning Semantic-Aware Representation in Visual-Language Models for Multi-Label Recognition with Partial Labels","date":"2024-12-14","arxiv_id":"2412.10843","n_code_links":0,"syntology":null},{"paper":null,"slug":"linked-adapters-linking-past-and-future-to","title":"Linked Adapters: Linking Past and Future to Present for Effective Continual Learning","date":"2024-12-14","arxiv_id":"2412.10687","n_code_links":0,"syntology":null},{"paper":null,"slug":"masv-speaker-verification-with-global-and","title":"MASV: Speaker Verification with Global and Local Context Mamba","date":"2024-12-14","arxiv_id":"2412.10989","n_code_links":0,"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":"/paper/memory-efficient-matting-with-adaptive-token","slug":"memory-efficient-matting-with-adaptive-token","title":"Memory Efficient Matting with Adaptive Token Routing","date":"2024-12-14","arxiv_id":"2412.10702","n_code_links":1,"syntology":null},{"paper":null,"slug":"pop-out-vs-glue-a-study-on-the-pre-attentive","title":"Pop-out vs. Glue: A Study on the pre-attentive and focused attention stages in Visual Search tasks","date":"2024-12-14","arxiv_id":"2412.12198","n_code_links":0,"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":"sentiment-and-hashtag-aware-attentive-deep","title":"Sentiment and Hashtag-aware Attentive Deep Neural Network for Multimodal Post Popularity Prediction","date":"2024-12-14","arxiv_id":"2412.10737","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":"tokens-the-oft-overlooked-appetizer-large","title":"Tokens, the oft-overlooked appetizer: Large language models, the distributional hypothesis, and meaning","date":"2024-12-14","arxiv_id":"2412.10924","n_code_links":0,"syntology":null},{"paper":null,"slug":"visdom-multi-document-qa-with-visually-rich","title":"VisDoM: Multi-Document QA with Visually Rich Elements Using Multimodal Retrieval-Augmented Generation","date":"2024-12-14","arxiv_id":"2412.10704","n_code_links":0,"syntology":null},{"paper":"/paper/a-cascaded-dilated-convolution-approach-for","slug":"a-cascaded-dilated-convolution-approach-for","title":"A Cascaded Dilated Convolution Approach for Mpox Lesion Classification","date":"2024-12-13","arxiv_id":"2412.10106","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":null,"slug":"amused-an-attentive-deep-neural-network-for","title":"AMuSeD: An Attentive Deep Neural Network for Multimodal Sarcasm Detection Incorporating Bi-modal Data Augmentation","date":"2024-12-13","arxiv_id":"2412.10103","n_code_links":0,"syntology":null},{"paper":null,"slug":"arbitrary-reading-order-scene-text-spotter","title":"Arbitrary Reading Order Scene Text Spotter with Local Semantics Guidance","date":"2024-12-13","arxiv_id":"2412.10159","n_code_links":0,"syntology":null},{"paper":"/paper/automated-image-captioning-with-cnns-and","slug":"automated-image-captioning-with-cnns-and","title":"Automated Image Captioning with CNNs and Transformers","date":"2024-12-13","arxiv_id":"2412.10511","n_code_links":1,"syntology":null},{"paper":"/paper/autopatent-a-multi-agent-framework-for","slug":"autopatent-a-multi-agent-framework-for","title":"AutoPatent: A Multi-Agent Framework for Automatic Patent Generation","date":"2024-12-13","arxiv_id":"2412.09796","n_code_links":1,"syntology":null},{"paper":"/paper/building-a-multi-modal-spatiotemporal-expert","slug":"building-a-multi-modal-spatiotemporal-expert","title":"Building a Multi-modal Spatiotemporal Expert for Zero-shot Action Recognition with CLIP","date":"2024-12-13","arxiv_id":"2412.09895","n_code_links":1,"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/cognitioncapturer-decoding-visual-stimuli","slug":"cognitioncapturer-decoding-visual-stimuli","title":"CognitionCapturer: Decoding Visual Stimuli From Human EEG Signal With Multimodal Information","date":"2024-12-13","arxiv_id":"2412.10489","n_code_links":1,"syntology":null},{"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":"/paper/deepseek-vl2-mixture-of-experts-vision","slug":"deepseek-vl2-mixture-of-experts-vision","title":"DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding","date":"2024-12-13","arxiv_id":"2412.10302","n_code_links":1,"syntology":{"ran":11,"of":13,"n_ran_checked":10,"n_instrument":1,"unverified":2,"pointer_only":3,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","official":{"repos":["deepseek-ai/deepseek-vl2"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/does-multiple-choice-have-a-future-in-the-age","slug":"does-multiple-choice-have-a-future-in-the-age","title":"Does Multiple Choice Have a Future in the Age of Generative AI? A Posttest-only RCT","date":"2024-12-13","arxiv_id":"2412.10267","n_code_links":1,"syntology":null},{"paper":null,"slug":"dynamic-try-on-taming-video-virtual-try-on","title":"Dynamic Try-On: Taming Video Virtual Try-on with Dynamic Attention Mechanism","date":"2024-12-13","arxiv_id":"2412.09822","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":"/paper/enhancing-multimodal-large-language-models-2","slug":"enhancing-multimodal-large-language-models-2","title":"Enhancing Multimodal Large Language Models Complex Reason via Similarity Computation","date":"2024-12-13","arxiv_id":"2412.09817","n_code_links":1,"syntology":null},{"paper":null,"slug":"evidence-contextualization-and-counterfactual","title":"Evidence Contextualization and Counterfactual Attribution for Conversational QA over Heterogeneous Data with RAG Systems","date":"2024-12-13","arxiv_id":"2412.10571","n_code_links":0,"syntology":null},{"paper":null,"slug":"faceshield-defending-facial-image-against","title":"FaceShield: Defending Facial Image against Deepfake Threats","date":"2024-12-13","arxiv_id":"2412.09921","n_code_links":0,"syntology":null},{"paper":null,"slug":"hashevict-a-pre-attention-kv-cache-eviction","title":"HashEvict: A Pre-Attention KV Cache Eviction Strategy using Locality-Sensitive Hashing","date":"2024-12-13","arxiv_id":"2412.16187","n_code_links":0,"syntology":null},{"paper":"/paper/higher-order-transformers-enhancing-stock","slug":"higher-order-transformers-enhancing-stock","title":"Higher Order Transformers: Enhancing Stock Movement Prediction On Multimodal Time-Series Data","date":"2024-12-13","arxiv_id":"2412.10540","n_code_links":1,"syntology":null},{"paper":"/paper/infinite-dimensional-next-generation","slug":"infinite-dimensional-next-generation","title":"Infinite-dimensional next-generation reservoir computing","date":"2024-12-13","arxiv_id":"2412.09800","n_code_links":1,"syntology":{"ran":5,"of":5,"n_ran_checked":5,"n_instrument":0,"unverified":0,"pointer_only":5,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["learning-of-dynamic-processes/kernelngrcvolterra"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"iqvic-in-context-question-adaptive-vision","title":"IQViC: In-context, Question Adaptive Vision Compressor for Long-term Video Understanding LMMs","date":"2024-12-13","arxiv_id":"2412.09907","n_code_links":0,"syntology":null},{"paper":null,"slug":"label-template-based-few-shot-text","title":"Label-template based Few-Shot Text Classification with Contrastive Learning","date":"2024-12-13","arxiv_id":"2412.10110","n_code_links":0,"syntology":null},{"paper":null,"slug":"lingen-towards-high-resolution-minute-length","title":"LinGen: Towards High-Resolution Minute-Length Text-to-Video Generation with Linear Computational Complexity","date":"2024-12-13","arxiv_id":"2412.09856","n_code_links":0,"syntology":null},{"paper":null,"slug":"low-resource-fast-text-classification-based","title":"Low-Resource Fast Text Classification Based on Intra-Class and Inter-Class Distance Calculation","date":"2024-12-13","arxiv_id":"2412.09922","n_code_links":0,"syntology":null},{"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}],"record_sha256":"29fe3ffb981286839e76b8c83826421db34ddc352ee15a845228a11f1f8cdfc2","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}