{"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/66","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":66,"pages_in_order":316,"rows_per_page":100,"rows":[6501,6600],"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/65","next":"/method/attention/papers/67","papers":[{"paper":null,"slug":"progdf-progressive-gaussian-differential","title":"ProGDF: Progressive Gaussian Differential Field for Controllable and Flexible 3D Editing","date":"2024-12-11","arxiv_id":"2412.08152","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":"static-dynamic-class-level-perception","title":"Static-Dynamic Class-level Perception Consistency in Video Semantic Segmentation","date":"2024-12-11","arxiv_id":"2412.08034","n_code_links":0,"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":null,"slug":"turboattention-efficient-attention","title":"TurboAttention: Efficient Attention Approximation For High Throughputs LLMs","date":"2024-12-11","arxiv_id":"2412.08585","n_code_links":0,"syntology":null},{"paper":null,"slug":"3a-yolo-new-real-time-object-detectors-with","title":"3A-YOLO: New Real-Time Object Detectors with Triple Discriminative Awareness and Coordinated Representations","date":"2024-12-10","arxiv_id":"2412.07168","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-dynamical-systems-inspired-pruning-strategy","title":"A Dynamical Systems-Inspired Pruning Strategy for Addressing Oversmoothing in Graph Neural Networks","date":"2024-12-10","arxiv_id":"2412.07243","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-generative-victim-model-for-segmentation","title":"A Generative Victim Model for Segmentation","date":"2024-12-10","arxiv_id":"2412.07274","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":"/paper/adapting-to-non-stationary-environments-multi","slug":"adapting-to-non-stationary-environments-multi","title":"Adapting to Non-Stationary Environments: Multi-Armed Bandit Enhanced Retrieval-Augmented Generation on Knowledge Graphs","date":"2024-12-10","arxiv_id":"2412.07618","n_code_links":1,"syntology":{"ran":5,"of":7,"n_ran_checked":5,"n_instrument":0,"unverified":2,"pointer_only":7,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 1 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["futureeeeee/dynamic-rag"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/adversarial-filtering-based-evasion-and","slug":"adversarial-filtering-based-evasion-and","title":"Adversarial Filtering Based Evasion and Backdoor Attacks to EEG-Based Brain-Computer Interfaces","date":"2024-12-10","arxiv_id":"2412.07231","n_code_links":1,"syntology":null},{"paper":null,"slug":"attention-head-purification-a-new-perspective","title":"Attention Head Purification: A New Perspective to Harness CLIP for Domain Generalization","date":"2024-12-10","arxiv_id":"2412.07226","n_code_links":0,"syntology":null},{"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":null,"slug":"benet-a-cross-domain-robust-network-for","title":"BENet: A Cross-domain Robust Network for Detecting Face Forgeries via Bias Expansion and Latent-space Attention","date":"2024-12-10","arxiv_id":"2412.07431","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":"breaking-the-stage-barrier-a-novel-single","title":"Breaking the Stage Barrier: A Novel Single-Stage Approach to Long Context Extension for Large Language Models","date":"2024-12-10","arxiv_id":"2412.07171","n_code_links":0,"syntology":null},{"paper":null,"slug":"bumblebee-foundation-model-for-particle","title":"Bumblebee: Foundation Model for Particle Physics Discovery","date":"2024-12-10","arxiv_id":"2412.07867","n_code_links":0,"syntology":null},{"paper":"/paper/can-linguists-better-understand-dna","slug":"can-linguists-better-understand-dna","title":"Can linguists better understand DNA?","date":"2024-12-10","arxiv_id":"2412.07678","n_code_links":1,"syntology":null},{"paper":"/paper/causal-world-representation-in-the-gpt-model","slug":"causal-world-representation-in-the-gpt-model","title":"A Causal World Model Underlying Next Token Prediction: Exploring GPT in a Controlled Environment","date":"2024-12-10","arxiv_id":"2412.07446","n_code_links":1,"syntology":null},{"paper":"/paper/cbramod-a-criss-cross-brain-foundation-model","slug":"cbramod-a-criss-cross-brain-foundation-model","title":"CBraMod: A Criss-Cross Brain Foundation Model for EEG Decoding","date":"2024-12-10","arxiv_id":"2412.07236","n_code_links":1,"syntology":{"ran":2,"of":5,"n_ran_checked":1,"n_instrument":1,"unverified":3,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","official":{"repos":["wjq-learning/cbramod"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"cogsimulator-a-model-for-simulating-user","title":"CogSimulator: A Model for Simulating User Cognition & Behavior with Minimal Data for Tailored Cognitive Enhancement","date":"2024-12-10","arxiv_id":"2412.14188","n_code_links":0,"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":"defensive-dual-masking-for-robust-adversarial","title":"Defensive Dual Masking for Robust Adversarial Defense","date":"2024-12-10","arxiv_id":"2412.07078","n_code_links":0,"syntology":null},{"paper":"/paper/delay-estimation-based-on-multiple-stage","slug":"delay-estimation-based-on-multiple-stage","title":"Delay Estimation Based on Multiple Stage Message Passing With Attention Mechanism Using a Real Network Communication Dataset","date":"2024-12-10","arxiv_id":null,"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":"diffusion-based-attention-warping-for","title":"Diffusion-Based Attention Warping for Consistent 3D Scene Editing","date":"2024-12-10","arxiv_id":"2412.07984","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":"fast-occupancy-network","title":"Fast Occupancy Network","date":"2024-12-10","arxiv_id":"2412.07163","n_code_links":0,"syntology":null},{"paper":null,"slug":"from-slow-bidirectional-to-fast-causal-video","title":"From Slow Bidirectional to Fast Autoregressive Video Diffusion Models","date":"2024-12-10","arxiv_id":"2412.07772","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":null,"slug":"gpt-2-through-the-lens-of-vector-symbolic","title":"GPT-2 Through the Lens of Vector Symbolic Architectures","date":"2024-12-10","arxiv_id":"2412.07947","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":"hierarchical-split-federated-learning","title":"Hierarchical Split Federated Learning: Convergence Analysis and System Optimization","date":"2024-12-10","arxiv_id":"2412.07197","n_code_links":0,"syntology":null},{"paper":"/paper/intellectseeker-a-personalized-literature","slug":"intellectseeker-a-personalized-literature","title":"IntellectSeeker: A Personalized Literature Management System with the Probabilistic Model and Large Language Model","date":"2024-12-10","arxiv_id":"2412.07213","n_code_links":1,"syntology":null},{"paper":null,"slug":"learning-self-supervised-audio-visual","title":"Learning Self-Supervised Audio-Visual Representations for Sound Recommendations","date":"2024-12-10","arxiv_id":"2412.07406","n_code_links":0,"syntology":null},{"paper":null,"slug":"modeling-high-resolution-spatio-temporal-wind","title":"Modeling High-Resolution Spatio-Temporal Wind with Deep Echo State Networks and Stochastic Partial Differential Equations","date":"2024-12-10","arxiv_id":"2412.07265","n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-modal-environmental-sensing-based-path","title":"Multi-Modal Environmental Sensing Based Path Loss Prediction for V2I Communications","date":"2024-12-10","arxiv_id":"2412.07681","n_code_links":0,"syntology":null},{"paper":null,"slug":"multimodal-sentiment-analysis-based-on-causal","title":"Multimodal Sentiment Analysis Based on Causal Reasoning","date":"2024-12-10","arxiv_id":"2412.07292","n_code_links":0,"syntology":null},{"paper":null,"slug":"on-motion-blur-and-deblurring-in-visual-place","title":"On Motion Blur and Deblurring in Visual Place Recognition","date":"2024-12-10","arxiv_id":"2412.07751","n_code_links":0,"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":"/paper/ptsbench-a-comprehensive-post-training","slug":"ptsbench-a-comprehensive-post-training","title":"PTSBench: A Comprehensive Post-Training Sparsity Benchmark Towards Algorithms and Models","date":"2024-12-10","arxiv_id":"2412.07268","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["modeltc/msbench"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/radio-amplified-improved-baselines-for","slug":"radio-amplified-improved-baselines-for","title":"RADIO Amplified: Improved Baselines for Agglomerative Vision Foundation Models","date":"2024-12-10","arxiv_id":"2412.07679","n_code_links":1,"syntology":null},{"paper":"/paper/rag-based-question-answering-over","slug":"rag-based-question-answering-over","title":"RAG-based Question Answering over Heterogeneous Data and Text","date":"2024-12-10","arxiv_id":"2412.07420","n_code_links":0,"syntology":null},{"paper":"/paper/rap-sr-restoration-prior-enhancement-in","slug":"rap-sr-restoration-prior-enhancement-in","title":"RAP-SR: RestorAtion Prior Enhancement in Diffusion Models for Realistic Image Super-Resolution","date":"2024-12-10","arxiv_id":"2412.07149","n_code_links":1,"syntology":null},{"paper":null,"slug":"retaining-and-enhancing-pre-trained-knowledge","title":"Retaining and Enhancing Pre-trained Knowledge in Vision-Language Models with Prompt Ensembling","date":"2024-12-10","arxiv_id":"2412.07077","n_code_links":0,"syntology":null},{"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/storyweaver-a-unified-world-model-for","slug":"storyweaver-a-unified-world-model-for","title":"StoryWeaver: A Unified World Model for Knowledge-Enhanced Story Character Customization","date":"2024-12-10","arxiv_id":"2412.07375","n_code_links":1,"syntology":null},{"paper":"/paper/streaming-private-continual-counting-via","slug":"streaming-private-continual-counting-via","title":"Streaming Private Continual Counting via Binning","date":"2024-12-10","arxiv_id":"2412.07093","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: 2 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["jodander/streaming-via-binning"],"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/superficial-consciousness-hypothesis-for","slug":"superficial-consciousness-hypothesis-for","title":"Superficial Consciousness Hypothesis for Autoregressive Transformers","date":"2024-12-10","arxiv_id":"2412.07278","n_code_links":1,"syntology":null},{"paper":"/paper/survbeta-ensemble-based-survival-models-using","slug":"survbeta-ensemble-based-survival-models-using","title":"SurvBETA: Ensemble-Based Survival Models Using Beran Estimators and Several Attention Mechanisms","date":"2024-12-10","arxiv_id":"2412.07638","n_code_links":1,"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":"towards-predictive-communication-with-brain","title":"Towards Predictive Communication with Brain-Computer Interfaces integrating Large Language Models","date":"2024-12-10","arxiv_id":"2412.07355","n_code_links":0,"syntology":null},{"paper":null,"slug":"ttvd-towards-a-geometric-framework-for-test","title":"TTVD: Towards a Geometric Framework for Test-Time Adaptation Based on Voronoi Diagram","date":"2024-12-10","arxiv_id":"2412.07980","n_code_links":0,"syntology":null},{"paper":null,"slug":"untapped-potential-in-self-optimization-of","title":"Untapped Potential in Self-Optimization of Hopfield Networks: The Creativity of Unsupervised Learning","date":"2024-12-10","arxiv_id":"2501.04007","n_code_links":0,"syntology":null},{"paper":"/paper/video-motion-transfer-with-diffusion","slug":"video-motion-transfer-with-diffusion","title":"Video Motion Transfer with Diffusion Transformers","date":"2024-12-10","arxiv_id":"2412.07776","n_code_links":1,"syntology":null},{"paper":null,"slug":"3d-graph-attention-networks-for-high-fidelity","title":"3D Graph Attention Networks for High Fidelity Pediatric Glioma Segmentation","date":"2024-12-09","arxiv_id":"2412.06743","n_code_links":0,"syntology":null},{"paper":null,"slug":"advancing-extended-reality-with-3d-gaussian","title":"Advancing Extended Reality with 3D Gaussian Splatting: Innovations and Prospects","date":"2024-12-09","arxiv_id":"2412.06257","n_code_links":0,"syntology":null},{"paper":null,"slug":"agentalign-misalignment-adapted-multi-agent","title":"AgentAlign: Misalignment-Adapted Multi-Agent Perception for Resilient Inter-Agent Sensor Correlations","date":"2024-12-09","arxiv_id":"2412.06142","n_code_links":0,"syntology":null},{"paper":null,"slug":"analysing-public-transport-user-sentiment-on","title":"Analysing Public Transport User Sentiment on Low Resource Multilingual Data","date":"2024-12-09","arxiv_id":"2412.06951","n_code_links":0,"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":null,"slug":"anomalycontrol-learning-cross-modal-semantic","title":"AnomalyControl: Learning Cross-modal Semantic Features for Controllable Anomaly Synthesis","date":"2024-12-09","arxiv_id":"2412.06510","n_code_links":0,"syntology":null},{"paper":null,"slug":"asgdiffusion-parallel-high-resolution","title":"ASGDiffusion: Parallel High-Resolution Generation with Asynchronous Structure Guidance","date":"2024-12-09","arxiv_id":"2412.06163","n_code_links":0,"syntology":null},{"paper":"/paper/attention-enhanced-lightweight-hourglass","slug":"attention-enhanced-lightweight-hourglass","title":"Attention-Enhanced Lightweight Hourglass Network for Human Pose Estimation","date":"2024-12-09","arxiv_id":"2412.06227","n_code_links":1,"syntology":null},{"paper":"/paper/batchtopk-sparse-autoencoders","slug":"batchtopk-sparse-autoencoders","title":"BatchTopK Sparse Autoencoders","date":"2024-12-09","arxiv_id":"2412.06410","n_code_links":2,"syntology":{"ran":2,"of":3,"n_ran_checked":2,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["bartbussmann/batchtopk"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"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":"edge-delayed-deep-deterministic-policy","title":"Edge Delayed Deep Deterministic Policy Gradient: efficient continuous control for edge scenarios","date":"2024-12-09","arxiv_id":"2412.06390","n_code_links":0,"syntology":null},{"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":null,"slug":"flexible-and-scalable-deep-dendritic-spiking","title":"Flexible and Scalable Deep Dendritic Spiking Neural Networks with Multiple Nonlinear Branching","date":"2024-12-09","arxiv_id":"2412.06355","n_code_links":0,"syntology":null},{"paper":"/paper/gated-delta-networks-improving-mamba2-with","slug":"gated-delta-networks-improving-mamba2-with","title":"Gated Delta Networks: Improving Mamba2 with Delta Rule","date":"2024-12-09","arxiv_id":"2412.06464","n_code_links":4,"syntology":{"ran":11,"of":13,"n_ran_checked":11,"n_instrument":0,"unverified":2,"pointer_only":7,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["NVlabs/GatedDeltaNet"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["listed","official"]}}},{"paper":null,"slug":"hes-unet-a-u-net-for-hepatic-echinococcosis","title":"HES-UNet: A U-Net for Hepatic Echinococcosis Lesion Segmentation","date":"2024-12-09","arxiv_id":"2412.06530","n_code_links":0,"syntology":null},{"paper":"/paper/hsda-high-frequency-shuffle-data-augmentation","slug":"hsda-high-frequency-shuffle-data-augmentation","title":"HSDA: High-frequency Shuffle Data Augmentation for Bird's-Eye-View Map Segmentation","date":"2024-12-09","arxiv_id":"2412.06127","n_code_links":1,"syntology":null},{"paper":"/paper/hybrid-attention-network-an-efficient","slug":"hybrid-attention-network-an-efficient","title":"HYATT-Net is Grand: A Hybrid Attention Network for Performant Anatomical Landmark Detection","date":"2024-12-09","arxiv_id":"2412.06499","n_code_links":1,"syntology":null},{"paper":null,"slug":"instantrestore-single-step-personalized-face","title":"InstantRestore: Single-Step Personalized Face Restoration with Shared-Image Attention","date":"2024-12-09","arxiv_id":"2412.06753","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/knowledge-transfer-and-domain-adaptation-for","slug":"knowledge-transfer-and-domain-adaptation-for","title":"Knowledge Transfer and Domain Adaptation for Fine-Grained Remote Sensing Image Segmentation","date":"2024-12-09","arxiv_id":"2412.06664","n_code_links":1,"syntology":null},{"paper":null,"slug":"llm-as-hpc-expert-extending-rag-architecture","title":"LLM as HPC Expert: Extending RAG Architecture for HPC Data","date":"2024-12-09","arxiv_id":"2501.14733","n_code_links":0,"syntology":null},{"paper":null,"slug":"llm-bip-structured-pruning-for-large-language","title":"LLM-BIP: Structured Pruning for Large Language Models with Block-Wise Forward Importance Propagation","date":"2024-12-09","arxiv_id":"2412.06419","n_code_links":0,"syntology":null},{"paper":null,"slug":"local-attention-transformers-for-high-detail","title":"Local Attention Transformers for High-Detail Optical Flow Upsampling","date":"2024-12-09","arxiv_id":"2412.06439","n_code_links":0,"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":"open-vocabulary-high-resolution-3d-ovhr3d","title":"Open-Vocabulary High-Resolution 3D (OVHR3D) Data Segmentation and Annotation Framework","date":"2024-12-09","arxiv_id":"2412.06268","n_code_links":0,"syntology":null},{"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":"reconfigurable-holographic-surface-aided-1","title":"Reconfigurable Holographic Surface-aided Distributed MIMO Radar Systems","date":"2024-12-09","arxiv_id":"2412.06279","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":"/paper/sirerag-indexing-similar-and-related","slug":"sirerag-indexing-similar-and-related","title":"SiReRAG: Indexing Similar and Related Information for Multihop Reasoning","date":"2024-12-09","arxiv_id":"2412.06206","n_code_links":0,"syntology":{"ran":5,"of":5,"n_ran_checked":3,"n_instrument":2,"unverified":0,"pointer_only":5,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 1 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":null,"slug":"sparseaccelerate-efficient-long-context","title":"SparseAccelerate: Efficient Long-Context Inference for Mid-Range GPUs","date":"2024-12-09","arxiv_id":"2412.06198","n_code_links":0,"syntology":null},{"paper":"/paper/splatter-360-generalizable-360-circ-gaussian","slug":"splatter-360-generalizable-360-circ-gaussian","title":"Splatter-360: Generalizable 360$^{\\circ}$ Gaussian Splatting for Wide-baseline Panoramic Images","date":"2024-12-09","arxiv_id":"2412.06250","n_code_links":1,"syntology":null},{"paper":null,"slug":"static-key-attention-in-vision","title":"Static Key Attention in Vision","date":"2024-12-09","arxiv_id":"2412.07049","n_code_links":0,"syntology":null},{"paper":null,"slug":"stock-type-prediction-model-based-on","title":"Stock Type Prediction Model Based on Hierarchical Graph Neural Network","date":"2024-12-09","arxiv_id":"2412.06862","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":null,"slug":"the-rosetta-paradox-domain-specific","title":"The Rosetta Paradox: Domain-Specific Performance Inversions in Large Language Models","date":"2024-12-09","arxiv_id":"2412.17821","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":"uav-virtual-antenna-array-deployment-for","title":"UAV Virtual Antenna Array Deployment for Uplink Interference Mitigation in Data Collection Networks","date":"2024-12-09","arxiv_id":"2412.06456","n_code_links":0,"syntology":null},{"paper":null,"slug":"understanding-factual-recall-in-transformers","title":"Understanding Factual Recall in Transformers via Associative Memories","date":"2024-12-09","arxiv_id":"2412.06538","n_code_links":0,"syntology":null},{"paper":null,"slug":"unipaint-unified-space-time-video-inpainting","title":"UniPaint: Unified Space-time Video Inpainting via Mixture-of-Experts","date":"2024-12-09","arxiv_id":"2412.06340","n_code_links":0,"syntology":null}],"record_sha256":"b8312dcc05735482ba2a9f5946a6c86f225504537f24a3486ac647f7caff121f","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}