{"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/40","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":40,"pages_in_order":316,"rows_per_page":100,"rows":[3901,4000],"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/39","next":"/method/attention/papers/41","papers":[{"paper":null,"slug":"flipconcept-tuning-free-multi-concept","title":"FlipConcept: Tuning-Free Multi-Concept Personalization for Text-to-Image Generation","date":"2025-02-21","arxiv_id":"2502.15203","n_code_links":0,"syntology":null},{"paper":"/paper/generalization-guarantees-for-representation","slug":"generalization-guarantees-for-representation","title":"Generalization Guarantees for Representation Learning via Data-Dependent Gaussian Mixture Priors","date":"2025-02-21","arxiv_id":"2502.15540","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["PiotrKrasnowski/Gaussian_Mixture_Priors_for_Representation_Learning"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"gnn-coder-boosting-semantic-code-retrieval","title":"GNN-Coder: Boosting Semantic Code Retrieval with Combined GNNs and Transformer","date":"2025-02-21","arxiv_id":"2502.15202","n_code_links":0,"syntology":null},{"paper":null,"slug":"graph-attention-convolutional-u-net-a","title":"Graph Attention Convolutional U-NET: A Semantic Segmentation Model for Identifying Flooded Areas","date":"2025-02-21","arxiv_id":"2502.15907","n_code_links":0,"syntology":null},{"paper":null,"slug":"graph-based-deep-learning-on-stereo-eeg-for","title":"Graph-Based Deep Learning on Stereo EEG for Predicting Seizure Freedom in Epilepsy Patients","date":"2025-02-21","arxiv_id":"2502.15198","n_code_links":0,"syntology":null},{"paper":null,"slug":"interleaved-block-based-learned-image","title":"Interleaved Block-based Learned Image Compression with Feature Enhancement and Quantization Error Compensation","date":"2025-02-21","arxiv_id":"2502.15188","n_code_links":0,"syntology":null},{"paper":null,"slug":"jeffrey-s-update-rule-as-a-minimizer-of","title":"Jeffrey's update rule as a minimizer of Kullback-Leibler divergence","date":"2025-02-21","arxiv_id":"2502.15504","n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-with-limited-shared-information-in","title":"Learning with Limited Shared Information in Multi-agent Multi-armed Bandit","date":"2025-02-21","arxiv_id":"2502.15338","n_code_links":0,"syntology":null},{"paper":null,"slug":"lightthinker-thinking-step-by-step","title":"LightThinker: Thinking Step-by-Step Compression","date":"2025-02-21","arxiv_id":"2502.15589","n_code_links":0,"syntology":null},{"paper":"/paper/lightweight-yet-efficient-an-external","slug":"lightweight-yet-efficient-an-external","title":"Lightweight yet Efficient: An External Attentive Graph Convolutional Network with Positional Prompts for Sequential Recommendation","date":"2025-02-21","arxiv_id":"2502.15331","n_code_links":1,"syntology":null},{"paper":null,"slug":"lumina-net-low-light-upgrade-through-multi","title":"LUMINA-Net: Low-light Upgrade through Multi-stage Illumination and Noise Adaptation Network for Image Enhancement","date":"2025-02-21","arxiv_id":"2502.15186","n_code_links":0,"syntology":null},{"paper":null,"slug":"m2lads-demo-a-system-for-generating","title":"M2LADS Demo: A System for Generating Multimodal Learning Analytics Dashboards","date":"2025-02-21","arxiv_id":"2502.15363","n_code_links":0,"syntology":null},{"paper":"/paper/mantis-lightweight-calibrated-foundation","slug":"mantis-lightweight-calibrated-foundation","title":"Mantis: Lightweight Calibrated Foundation Model for User-Friendly Time Series Classification","date":"2025-02-21","arxiv_id":"2502.15637","n_code_links":1,"syntology":{"ran":4,"of":5,"n_ran_checked":4,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"4 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; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["vfeofanov/mantis"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"optimizing-pre-training-data-mixtures-with","title":"Optimizing Pre-Training Data Mixtures with Mixtures of Data Expert Models","date":"2025-02-21","arxiv_id":"2502.15950","n_code_links":0,"syntology":null},{"paper":null,"slug":"retrieval-augmented-speech-recognition","title":"Retrieval-Augmented Speech Recognition Approach for Domain Challenges","date":"2025-02-21","arxiv_id":"2502.15264","n_code_links":0,"syntology":null},{"paper":"/paper/robust-bias-detection-in-mlms-and-its","slug":"robust-bias-detection-in-mlms-and-its","title":"Robust Bias Detection in MLMs and its Application to Human Trait Ratings","date":"2025-02-21","arxiv_id":"2502.15600","n_code_links":1,"syntology":null},{"paper":null,"slug":"round-attention-a-novel-round-level-attention","title":"Round Attention: A Novel Round-Level Attention Mechanism to Accelerate LLM Inference","date":"2025-02-21","arxiv_id":"2502.15294","n_code_links":0,"syntology":null},{"paper":"/paper/sentiformer-metadata-enhanced-transformer-for","slug":"sentiformer-metadata-enhanced-transformer-for","title":"SentiFormer: Metadata Enhanced Transformer for Image Sentiment Analysis","date":"2025-02-21","arxiv_id":"2502.15322","n_code_links":1,"syntology":null},{"paper":null,"slug":"single-pass-detection-of-jailbreaking-input","title":"Single-pass Detection of Jailbreaking Input in Large Language Models","date":"2025-02-21","arxiv_id":"2502.15435","n_code_links":0,"syntology":null},{"paper":null,"slug":"soybean-pod-and-seed-counting-in-both-outdoor","title":"Soybean pod and seed counting in both outdoor fields and indoor laboratories using unions of deep neural networks","date":"2025-02-21","arxiv_id":"2502.15286","n_code_links":0,"syntology":null},{"paper":null,"slug":"sparks-of-cognitive-flexibility-self-guided","title":"Sparks of cognitive flexibility: self-guided context inference for flexible stimulus-response mapping by attentional routing","date":"2025-02-21","arxiv_id":"2502.15634","n_code_links":0,"syntology":null},{"paper":null,"slug":"svdq-1-25-bit-and-410x-key-cache-compression","title":"SVDq: 1.25-bit and 410x Key Cache Compression for LLM Attention","date":"2025-02-21","arxiv_id":"2502.15304","n_code_links":0,"syntology":null},{"paper":null,"slug":"tokenization-is-sensitive-to-language","title":"Tokenization is Sensitive to Language Variation","date":"2025-02-21","arxiv_id":"2502.15343","n_code_links":0,"syntology":null},{"paper":null,"slug":"transmamba-fast-universal-architecture","title":"TransMamba: Fast Universal Architecture Adaption from Transformers to Mamba","date":"2025-02-21","arxiv_id":"2502.15130","n_code_links":0,"syntology":null},{"paper":"/paper/turbofuzzllm-turbocharging-mutation-based","slug":"turbofuzzllm-turbocharging-mutation-based","title":"TurboFuzzLLM: Turbocharging Mutation-based Fuzzing for Effectively Jailbreaking Large Language Models in Practice","date":"2025-02-21","arxiv_id":"2502.18504","n_code_links":1,"syntology":null},{"paper":null,"slug":"utilizing-sequential-information-of-general","title":"Utilizing Sequential Information of General Lab-test Results and Diagnoses History for Differential Diagnosis of Dementia","date":"2025-02-21","arxiv_id":"2502.15317","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-socratic-rag-approach-to-connect-natural","title":"A Socratic RAG Approach to Connect Natural Language Queries on Research Topics with Knowledge Organization Systems","date":"2025-02-20","arxiv_id":"2502.15005","n_code_links":0,"syntology":null},{"paper":"/paper/adaptive-convolution-for-cnn-based-speech","slug":"adaptive-convolution-for-cnn-based-speech","title":"Adaptive Convolution for CNN-based Speech Enhancement Models","date":"2025-02-20","arxiv_id":"2502.14224","n_code_links":1,"syntology":null},{"paper":null,"slug":"argument-based-comparative-question-answering","title":"Argument-Based Comparative Question Answering Evaluation Benchmark","date":"2025-02-20","arxiv_id":"2502.14476","n_code_links":0,"syntology":null},{"paper":"/paper/asymmetric-co-training-for-source-free-few","slug":"asymmetric-co-training-for-source-free-few","title":"Asymmetric Co-Training for Source-Free Few-Shot Domain Adaptation","date":"2025-02-20","arxiv_id":"2502.14214","n_code_links":1,"syntology":null},{"paper":"/paper/bridging-text-and-vision-a-multi-view-text","slug":"bridging-text-and-vision-a-multi-view-text","title":"Bridging Text and Vision: A Multi-View Text-Vision Registration Approach for Cross-Modal Place Recognition","date":"2025-02-20","arxiv_id":"2502.14195","n_code_links":1,"syntology":null},{"paper":null,"slug":"cardiac-evidence-backtracking-for-eating","title":"Cardiac Evidence Backtracking for Eating Behavior Monitoring using Collocative Electrocardiogram Imagining","date":"2025-02-20","arxiv_id":"2502.14430","n_code_links":0,"syntology":null},{"paper":null,"slug":"deeprtl-bridging-verilog-understanding-and","title":"DeepRTL: Bridging Verilog Understanding and Generation with a Unified Representation Model","date":"2025-02-20","arxiv_id":"2502.15832","n_code_links":0,"syntology":null},{"paper":null,"slug":"designing-parameter-and-compute-efficient","title":"Designing Parameter and Compute Efficient Diffusion Transformers using Distillation","date":"2025-02-20","arxiv_id":"2502.14226","n_code_links":0,"syntology":null},{"paper":null,"slug":"do-llms-consider-security-an-empirical-study","title":"Do LLMs Consider Security? An Empirical Study on Responses to Programming Questions","date":"2025-02-20","arxiv_id":"2502.14202","n_code_links":0,"syntology":null},{"paper":"/paper/does-time-have-its-place-temporal-heads-where","slug":"does-time-have-its-place-temporal-heads-where","title":"Does Time Have Its Place? Temporal Heads: Where Language Models Recall Time-specific Information","date":"2025-02-20","arxiv_id":"2502.14258","n_code_links":1,"syntology":null},{"paper":"/paper/earlier-tokens-contribute-more-learning","slug":"earlier-tokens-contribute-more-learning","title":"Earlier Tokens Contribute More: Learning Direct Preference Optimization From Temporal Decay Perspective","date":"2025-02-20","arxiv_id":"2502.14340","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":1,"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":["lotusrc/d2po"],"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":null,"slug":"effects-of-prompt-length-on-domain-specific","title":"Effects of Prompt Length on Domain-specific Tasks for Large Language Models","date":"2025-02-20","arxiv_id":"2502.14255","n_code_links":0,"syntology":null},{"paper":null,"slug":"entropy-uid-a-method-for-optimizing","title":"Entropy-UID: A Method for Optimizing Information Density","date":"2025-02-20","arxiv_id":"2502.14366","n_code_links":0,"syntology":null},{"paper":"/paper/exploring-rwkv-for-sentence-embeddings-layer","slug":"exploring-rwkv-for-sentence-embeddings-layer","title":"Exploring RWKV for Sentence Embeddings: Layer-wise Analysis and Baseline Comparison for Semantic Similarity","date":"2025-02-20","arxiv_id":"2502.14620","n_code_links":1,"syntology":null},{"paper":null,"slug":"find-fine-grained-information-density-guided","title":"FIND: Fine-grained Information Density Guided Adaptive Retrieval-Augmented Generation for Disease Diagnosis","date":"2025-02-20","arxiv_id":"2502.14614","n_code_links":0,"syntology":null},{"paper":"/paper/forecasting-local-ionospheric-parameters","slug":"forecasting-local-ionospheric-parameters","title":"Forecasting Local Ionospheric Parameters Using Transformers","date":"2025-02-20","arxiv_id":"2502.15093","n_code_links":1,"syntology":null},{"paper":null,"slug":"from-knowledge-generation-to-knowledge","title":"From Knowledge Generation to Knowledge Verification: Examining the BioMedical Generative Capabilities of ChatGPT","date":"2025-02-20","arxiv_id":"2502.14714","n_code_links":0,"syntology":null},{"paper":"/paper/from-rag-to-memory-non-parametric-continual","slug":"from-rag-to-memory-non-parametric-continual","title":"From RAG to Memory: Non-Parametric Continual Learning for Large Language Models","date":"2025-02-20","arxiv_id":"2502.14802","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":1,"n_instrument":1,"unverified":1,"pointer_only":1,"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) · 1 unverified","official":{"repos":["osu-nlp-group/hipporag"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"fuia-model-inversion-attack-against-federated","title":"Model Inversion Attack against Federated Unlearning","date":"2025-02-20","arxiv_id":"2502.14558","n_code_links":0,"syntology":null},{"paper":null,"slug":"full-step-dpo-self-supervised-preference","title":"Full-Step-DPO: Self-Supervised Preference Optimization with Step-wise Rewards for Mathematical Reasoning","date":"2025-02-20","arxiv_id":"2502.14356","n_code_links":0,"syntology":null},{"paper":"/paper/h3de-net-efficient-and-accurate-3d-landmark","slug":"h3de-net-efficient-and-accurate-3d-landmark","title":"H3DE-Net: Efficient and Accurate 3D Landmark Detection in Medical Imaging","date":"2025-02-20","arxiv_id":"2502.14221","n_code_links":1,"syntology":null},{"paper":null,"slug":"hallucination-detection-in-large-language","title":"Hallucination Detection in Large Language Models with Metamorphic Relations","date":"2025-02-20","arxiv_id":"2502.15844","n_code_links":0,"syntology":null},{"paper":null,"slug":"hardware-friendly-static-quantization-method","title":"Hardware-Friendly Static Quantization Method for Video Diffusion Transformers","date":"2025-02-20","arxiv_id":"2502.15077","n_code_links":0,"syntology":null},{"paper":"/paper/how-far-are-llms-from-being-our-digital-twins","slug":"how-far-are-llms-from-being-our-digital-twins","title":"How Far are LLMs from Being Our Digital Twins? A Benchmark for Persona-Based Behavior Chain Simulation","date":"2025-02-20","arxiv_id":"2502.14642","n_code_links":1,"syntology":null},{"paper":null,"slug":"is-relevance-propagated-from-retriever-to","title":"Is Relevance Propagated from Retriever to Generator in RAG?","date":"2025-02-20","arxiv_id":"2502.15025","n_code_links":0,"syntology":null},{"paper":null,"slug":"kitab-bench-a-comprehensive-multi-domain","title":"KITAB-Bench: A Comprehensive Multi-Domain Benchmark for Arabic OCR and Document Understanding","date":"2025-02-20","arxiv_id":"2502.14949","n_code_links":0,"syntology":null},{"paper":null,"slug":"lift-improving-long-context-understanding-of","title":"LIFT: Improving Long Context Understanding of Large Language Models through Long Input Fine-Tuning","date":"2025-02-20","arxiv_id":"2502.14644","n_code_links":0,"syntology":null},{"paper":"/paper/lserve-efficient-long-sequence-llm-serving","slug":"lserve-efficient-long-sequence-llm-serving","title":"LServe: Efficient Long-sequence LLM Serving with Unified Sparse Attention","date":"2025-02-20","arxiv_id":"2502.14866","n_code_links":2,"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":["mit-han-lab/omniserve"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed"]}}},{"paper":null,"slug":"mechanistic-understanding-of-language-models","title":"Mechanistic Understanding of Language Models in Syntactic Code Completion","date":"2025-02-20","arxiv_id":"2502.18499","n_code_links":0,"syntology":null},{"paper":"/paper/multiscale-byte-language-models-a","slug":"multiscale-byte-language-models-a","title":"Multiscale Byte Language Models -- A Hierarchical Architecture for Causal Million-Length Sequence Modeling","date":"2025-02-20","arxiv_id":"2502.14553","n_code_links":1,"syntology":null},{"paper":null,"slug":"nerf-3dtalker-neural-radiance-field-with-3d","title":"NeRF-3DTalker: Neural Radiance Field with 3D Prior Aided Audio Disentanglement for Talking Head Synthesis","date":"2025-02-20","arxiv_id":"2502.14178","n_code_links":0,"syntology":null},{"paper":"/paper/on-the-influence-of-context-size-and-model","slug":"on-the-influence-of-context-size-and-model","title":"On the Influence of Context Size and Model Choice in Retrieval-Augmented Generation Systems","date":"2025-02-20","arxiv_id":"2502.14759","n_code_links":1,"syntology":null},{"paper":null,"slug":"paperhelper-knowledge-based-llm-qa-paper","title":"PaperHelper: Knowledge-Based LLM QA Paper Reading Assistant","date":"2025-02-20","arxiv_id":"2502.14271","n_code_links":0,"syntology":null},{"paper":null,"slug":"parallelcomp-parallel-long-context-compressor","title":"ParallelComp: Parallel Long-Context Compressor for Length Extrapolation","date":"2025-02-20","arxiv_id":"2502.14317","n_code_links":0,"syntology":null},{"paper":null,"slug":"plphp-per-layer-per-head-vision-token-pruning","title":"PLPHP: Per-Layer Per-Head Vision Token Pruning for Efficient Large Vision-Language Models","date":"2025-02-20","arxiv_id":"2502.14504","n_code_links":0,"syntology":null},{"paper":null,"slug":"predicting-fetal-birthweight-from-high","title":"Predicting Fetal Birthweight from High Dimensional Data using Advanced Machine Learning","date":"2025-02-20","arxiv_id":"2502.14270","n_code_links":0,"syntology":null},{"paper":null,"slug":"quad-llm-mltc-large-language-models-ensemble","title":"QUAD-LLM-MLTC: Large Language Models Ensemble Learning for Healthcare Text Multi-Label Classification","date":"2025-02-20","arxiv_id":"2502.14189","n_code_links":0,"syntology":null},{"paper":null,"slug":"reinforcement-learning-with-graph-attention","title":"Reinforcement Learning with Graph Attention for Routing and Wavelength Assignment with Lightpath Reuse","date":"2025-02-20","arxiv_id":"2502.14741","n_code_links":0,"syntology":null},{"paper":null,"slug":"relactrl-relevance-guided-efficient-control","title":"RelaCtrl: Relevance-Guided Efficient Control for Diffusion Transformers","date":"2025-02-20","arxiv_id":"2502.14377","n_code_links":0,"syntology":null},{"paper":null,"slug":"rendbev-semantic-novel-view-synthesis-for","title":"RendBEV: Semantic Novel View Synthesis for Self-Supervised Bird's Eye View Segmentation","date":"2025-02-20","arxiv_id":"2502.14792","n_code_links":0,"syntology":null},{"paper":"/paper/revealing-and-mitigating-over-attention-in","slug":"revealing-and-mitigating-over-attention-in","title":"Revealing and Mitigating Over-Attention in Knowledge Editing","date":"2025-02-20","arxiv_id":"2502.14838","n_code_links":1,"syntology":null},{"paper":null,"slug":"tabular-embeddings-for-tables-with-bi","title":"Tabular Embeddings for Tables with Bi-Dimensional Hierarchical Metadata and Nesting","date":"2025-02-20","arxiv_id":"2502.15819","n_code_links":0,"syntology":null},{"paper":null,"slug":"textured-3d-regenerative-morphing-with-3d","title":"Textured 3D Regenerative Morphing with 3D Diffusion Prior","date":"2025-02-20","arxiv_id":"2502.14316","n_code_links":0,"syntology":null},{"paper":null,"slug":"topology-aware-wavelet-mamba-for-airway","title":"Topology-Aware Wavelet Mamba for Airway Structure Segmentation in Postoperative Recurrent Nasopharyngeal Carcinoma CT Scans","date":"2025-02-20","arxiv_id":"2502.14363","n_code_links":0,"syntology":null},{"paper":"/paper/towards-economical-inference-enabling","slug":"towards-economical-inference-enabling","title":"Towards Economical Inference: Enabling DeepSeek's Multi-Head Latent Attention in Any Transformer-based LLMs","date":"2025-02-20","arxiv_id":"2502.14837","n_code_links":1,"syntology":{"ran":10,"of":15,"n_ran_checked":10,"n_instrument":0,"unverified":5,"pointer_only":0,"phrase":"10 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; 0 where Syntology's instrument failed) · 5 unverified","official":{"repos":["JT-Ushio/MHA2MLA"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"unshackling-context-length-an-efficient","title":"Unshackling Context Length: An Efficient Selective Attention Approach through Query-Key Compression","date":"2025-02-20","arxiv_id":"2502.14477","n_code_links":0,"syntology":null},{"paper":null,"slug":"wavrag-audio-integrated-retrieval-augmented","title":"WavRAG: Audio-Integrated Retrieval Augmented Generation for Spoken Dialogue Models","date":"2025-02-20","arxiv_id":"2502.14727","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-consensus-set-for-the-aggregation-of","title":"A consensus set for the aggregation of partial rankings: the case of the Optimal Set of Bucket Orders Problem","date":"2025-02-19","arxiv_id":"2502.13769","n_code_links":0,"syntology":null},{"paper":null,"slug":"activation-aware-probe-query-effective-key","title":"Activation-aware Probe-Query: Effective Key-Value Retrieval for Long-Context LLMs Inference","date":"2025-02-19","arxiv_id":"2502.13542","n_code_links":0,"syntology":null},{"paper":null,"slug":"adapting-large-language-models-for-time","title":"Adapting Large Language Models for Time Series Modeling via a Novel Parameter-efficient Adaptation Method","date":"2025-02-19","arxiv_id":"2502.13725","n_code_links":0,"syntology":null},{"paper":null,"slug":"are-large-language-models-in-context-graph","title":"Are Large Language Models In-Context Graph Learners?","date":"2025-02-19","arxiv_id":"2502.13562","n_code_links":0,"syntology":null},{"paper":"/paper/building-age-estimation-a-new-multi-modal","slug":"building-age-estimation-a-new-multi-modal","title":"Building Age Estimation: A New Multi-Modal Benchmark Dataset and Community Challenge","date":"2025-02-19","arxiv_id":"2502.13818","n_code_links":1,"syntology":null},{"paper":null,"slug":"capturing-rich-behavior-representations-a","title":"Capturing Rich Behavior Representations: A Dynamic Action Semantic-Aware Graph Transformer for Video Captioning","date":"2025-02-19","arxiv_id":"2502.13754","n_code_links":0,"syntology":null},{"paper":"/paper/contrastive-learning-based-privacy-metrics-in","slug":"contrastive-learning-based-privacy-metrics-in","title":"Contrastive Learning-Based privacy metrics in Tabular Synthetic Datasets","date":"2025-02-19","arxiv_id":"2502.13833","n_code_links":1,"syntology":null},{"paper":null,"slug":"conveniently-identify-coils-in-inductive","title":"Conveniently Identify Coils in Inductive Power Transfer System Using Machine Learning","date":"2025-02-19","arxiv_id":"2502.13915","n_code_links":0,"syntology":null},{"paper":null,"slug":"dh-rag-a-dynamic-historical-context-powered","title":"DH-RAG: A Dynamic Historical Context-Powered Retrieval-Augmented Generation Method for Multi-Turn Dialogue","date":"2025-02-19","arxiv_id":"2502.13847","n_code_links":0,"syntology":null},{"paper":null,"slug":"diffusion-model-agnostic-social-influence","title":"Diffusion Model Agnostic Social Influence Maximization in Hyperbolic Space","date":"2025-02-19","arxiv_id":"2502.13571","n_code_links":0,"syntology":null},{"paper":null,"slug":"extracting-social-connections-from-finnish","title":"Extracting Social Connections from Finnish Karelian Refugee Interviews Using LLMs","date":"2025-02-19","arxiv_id":"2502.13566","n_code_links":0,"syntology":null},{"paper":null,"slug":"fairkv-balancing-per-head-kv-cache-for-fast","title":"FairKV: Balancing Per-Head KV Cache for Fast Multi-GPU Inference","date":"2025-02-19","arxiv_id":"2502.15804","n_code_links":0,"syntology":null},{"paper":null,"slug":"flextok-resampling-images-into-1d-token","title":"FlexTok: Resampling Images into 1D Token Sequences of Flexible Length","date":"2025-02-19","arxiv_id":"2502.13967","n_code_links":0,"syntology":null},{"paper":null,"slug":"from-correctness-to-comprehension-ai-agents","title":"From Correctness to Comprehension: AI Agents for Personalized Error Diagnosis in Education","date":"2025-02-19","arxiv_id":"2502.13789","n_code_links":0,"syntology":null},{"paper":null,"slug":"generative-detail-enhancement-for-physically","title":"Generative Detail Enhancement for Physically Based Materials","date":"2025-02-19","arxiv_id":"2502.13994","n_code_links":0,"syntology":null},{"paper":null,"slug":"gimmick-globally-inclusive-multimodal","title":"GIMMICK -- Globally Inclusive Multimodal Multitask Cultural Knowledge Benchmarking","date":"2025-02-19","arxiv_id":"2502.13766","n_code_links":0,"syntology":null},{"paper":null,"slug":"giving-ai-personalities-leads-to-more-human","title":"Giving AI Personalities Leads to More Human-Like Reasoning","date":"2025-02-19","arxiv_id":"2502.14155","n_code_links":0,"syntology":null},{"paper":null,"slug":"hawkbench-investigating-resilience-of-rag","title":"HawkBench: Investigating Resilience of RAG Methods on Stratified Information-Seeking Tasks","date":"2025-02-19","arxiv_id":"2502.13465","n_code_links":0,"syntology":null},{"paper":"/paper/helix-mrna-a-hybrid-foundation-model-for-full","slug":"helix-mrna-a-hybrid-foundation-model-for-full","title":"Helix-mRNA: A Hybrid Foundation Model For Full Sequence mRNA Therapeutics","date":"2025-02-19","arxiv_id":"2502.13785","n_code_links":1,"syntology":null},{"paper":null,"slug":"hidden-darkness-in-llm-generated-designs","title":"Hidden Darkness in LLM-Generated Designs: Exploring Dark Patterns in Ecommerce Web Components Generated by LLMs","date":"2025-02-19","arxiv_id":"2502.13499","n_code_links":0,"syntology":null},{"paper":null,"slug":"in-place-updates-of-a-graph-index-for","title":"In-Place Updates of a Graph Index for Streaming Approximate Nearest Neighbor Search","date":"2025-02-19","arxiv_id":"2502.13826","n_code_links":0,"syntology":null},{"paper":null,"slug":"inner-thinking-transformer-leveraging-dynamic","title":"Inner Thinking Transformer: Leveraging Dynamic Depth Scaling to Foster Adaptive Internal Thinking","date":"2025-02-19","arxiv_id":"2502.13842","n_code_links":0,"syntology":null},{"paper":null,"slug":"integration-of-agentic-ai-with-6g-networks","title":"Integration of Agentic AI with 6G Networks for Mission-Critical Applications: Use-case and Challenges","date":"2025-02-19","arxiv_id":"2502.13476","n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-novel-transformer-architecture-for","title":"Learning Novel Transformer Architecture for Time-series Forecasting","date":"2025-02-19","arxiv_id":"2502.13721","n_code_links":0,"syntology":null},{"paper":null,"slug":"mambalitesr-image-super-resolution-with-low","title":"MambaLiteSR: Image Super-Resolution with Low-Rank Mamba using Knowledge Distillation","date":"2025-02-19","arxiv_id":"2502.14090","n_code_links":0,"syntology":null},{"paper":null,"slug":"maskprune-mask-based-llm-pruning-for-layer","title":"MaskPrune: Mask-based LLM Pruning for Layer-wise Uniform Structures","date":"2025-02-19","arxiv_id":"2502.14008","n_code_links":0,"syntology":null},{"paper":"/paper/medical-image-classification-with-kan","slug":"medical-image-classification-with-kan","title":"Medical Image Classification with KAN-Integrated Transformers and Dilated Neighborhood Attention","date":"2025-02-19","arxiv_id":"2502.13693","n_code_links":1,"syntology":null}],"record_sha256":"0334c701d739d1dc62ac1123eca1eb4a2920c35c4ca6d951483149c84540d349","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}