{"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/107","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":107,"pages_in_order":316,"rows_per_page":100,"rows":[10601,10700],"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/106","next":"/method/attention/papers/108","papers":[{"paper":"/paper/mambaevt-event-stream-based-visual-object","slug":"mambaevt-event-stream-based-visual-object","title":"MambaEVT: Event Stream based Visual Object Tracking using State Space Model","date":"2024-08-20","arxiv_id":"2408.10487","n_code_links":1,"syntology":{"ran":9,"of":10,"n_ran_checked":9,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["event-ahu/mambaevt"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"multichannel-attention-networks-with","title":"Multichannel Attention Networks with Ensembled Transfer Learning to Recognize Bangla Handwritten Charecter","date":"2024-08-20","arxiv_id":"2408.10955","n_code_links":0,"syntology":null},{"paper":"/paper/navigating-spatio-temporal-heterogeneity-a","slug":"navigating-spatio-temporal-heterogeneity-a","title":"Navigating Spatio-Temporal Heterogeneity: A Graph Transformer Approach for Traffic Forecasting","date":"2024-08-20","arxiv_id":"2408.10822","n_code_links":1,"syntology":null},{"paper":null,"slug":"novel-change-detection-framework-in-remote","title":"Hierarchical Attention Diffusion Networks with Object Priors for Video Change Detection","date":"2024-08-20","arxiv_id":"2408.10619","n_code_links":0,"syntology":null},{"paper":null,"slug":"on-the-potential-of-open-vocabulary-models","title":"On the Potential of Open-Vocabulary Models for Object Detection in Unusual Street Scenes","date":"2024-08-20","arxiv_id":"2408.11221","n_code_links":0,"syntology":null},{"paper":null,"slug":"open-finllms-open-multimodal-large-language","title":"Open-FinLLMs: Open Multimodal Large Language Models for Financial Applications","date":"2024-08-20","arxiv_id":"2408.11878","n_code_links":0,"syntology":null},{"paper":null,"slug":"optimization-of-multi-agent-flying-sidekick","title":"Optimization of Multi-Agent Flying Sidekick Traveling Salesman Problem over Road Networks","date":"2024-08-20","arxiv_id":"2408.11187","n_code_links":0,"syntology":null},{"paper":"/paper/out-of-distribution-detection-with-attention","slug":"out-of-distribution-detection-with-attention","title":"Out-of-Distribution Detection with Attention Head Masking for Multimodal Document Classification","date":"2024-08-20","arxiv_id":"2408.11237","n_code_links":1,"syntology":null},{"paper":null,"slug":"perception-guided-jailbreak-against-text-to","title":"Perception-guided Jailbreak against Text-to-Image Models","date":"2024-08-20","arxiv_id":"2408.10848","n_code_links":0,"syntology":null},{"paper":"/paper/prformer-pyramidal-recurrent-transformer-for","slug":"prformer-pyramidal-recurrent-transformer-for","title":"PRformer: Pyramidal Recurrent Transformer for Multivariate Time Series Forecasting","date":"2024-08-20","arxiv_id":"2408.10483","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: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["usualheart/prformer"],"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":null,"slug":"prompt-your-brain-scaffold-prompt-tuning-for","title":"Prompt Your Brain: Scaffold Prompt Tuning for Efficient Adaptation of fMRI Pre-trained Model","date":"2024-08-20","arxiv_id":"2408.10567","n_code_links":0,"syntology":null},{"paper":"/paper/quantum-inverse-contextual-vision","slug":"quantum-inverse-contextual-vision","title":"Quantum Inverse Contextual Vision Transformers (Q-ICVT): A New Frontier in 3D Object Detection for AVs","date":"2024-08-20","arxiv_id":"2408.11207","n_code_links":1,"syntology":null},{"paper":null,"slug":"reading-with-intent","title":"Reading with Intent","date":"2024-08-20","arxiv_id":"2408.11189","n_code_links":0,"syntology":null},{"paper":null,"slug":"reconciling-methodological-paradigms","title":"Reconciling Methodological Paradigms: Employing Large Language Models as Novice Qualitative Research Assistants in Talent Management Research","date":"2024-08-20","arxiv_id":"2408.11043","n_code_links":0,"syntology":null},{"paper":null,"slug":"rethinking-video-segmentation-with-masked","title":"Rethinking Video Segmentation with Masked Video Consistency: Did the Model Learn as Intended?","date":"2024-08-20","arxiv_id":"2408.10627","n_code_links":0,"syntology":null},{"paper":"/paper/revisiting-verilogeval-newer-llms-in-context","slug":"revisiting-verilogeval-newer-llms-in-context","title":"Revisiting VerilogEval: A Year of Improvements in Large-Language Models for Hardware Code Generation","date":"2024-08-20","arxiv_id":"2408.11053","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["nvlabs/verilog-eval"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"sdi-net-toward-sufficient-dual-view","title":"SDI-Net: Toward Sufficient Dual-View Interaction for Low-light Stereo Image Enhancement","date":"2024-08-20","arxiv_id":"2408.10934","n_code_links":0,"syntology":null},{"paper":"/paper/soda-eval-open-domain-dialogue-evaluation-in","slug":"soda-eval-open-domain-dialogue-evaluation-in","title":"Soda-Eval: Open-Domain Dialogue Evaluation in the age of LLMs","date":"2024-08-20","arxiv_id":"2408.10902","n_code_links":1,"syntology":null},{"paper":null,"slug":"target-prompt-online-graph-collaborative","title":"GACL: Graph Attention Collaborative Learning for Temporal QoS Prediction","date":"2024-08-20","arxiv_id":"2408.10555","n_code_links":0,"syntology":null},{"paper":"/paper/tds-clip-temporal-difference-side-network-for","slug":"tds-clip-temporal-difference-side-network-for","title":"TDS-CLIP: Temporal Difference Side Network for Image-to-Video Transfer Learning","date":"2024-08-20","arxiv_id":"2408.10688","n_code_links":1,"syntology":null},{"paper":null,"slug":"towardseffective-teaching-assistants-from","title":"Towardseffective teaching assistants: From intent-based chatbots to LLM-poweredteachingassistants","date":"2024-08-20","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"tracing-privacy-leakage-of-language-models-to","title":"Tracing Privacy Leakage of Language Models to Training Data via Adjusted Influence Functions","date":"2024-08-20","arxiv_id":"2408.10468","n_code_links":0,"syntology":null},{"paper":null,"slug":"trustworthy-compression-impact-of-ai-based","title":"Trustworthy Compression? Impact of AI-based Codecs on Biometrics for Law Enforcement","date":"2024-08-20","arxiv_id":"2408.10823","n_code_links":0,"syntology":null},{"paper":"/paper/uie-unfold-deep-unfolding-network-with-color","slug":"uie-unfold-deep-unfolding-network-with-color","title":"UIE-UnFold: Deep Unfolding Network with Color Priors and Vision Transformer for Underwater Image Enhancement","date":"2024-08-20","arxiv_id":"2408.10653","n_code_links":1,"syntology":null},{"paper":"/paper/while-github-copilot-excels-at-coding-does-it","slug":"while-github-copilot-excels-at-coding-does-it","title":"Security Attacks on LLM-based Code Completion Tools","date":"2024-08-20","arxiv_id":"2408.11006","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-more-accurate-approximation-of-activation","title":"A More Accurate Approximation of Activation Function with Few Spikes Neurons","date":"2024-08-19","arxiv_id":"2409.00044","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-strategy-to-combine-1stgen-transformers-and","title":"A Strategy to Combine 1stGen Transformers and Open LLMs for Automatic Text Classification","date":"2024-08-19","arxiv_id":"2408.09629","n_code_links":0,"syntology":null},{"paper":"/paper/acquiring-bidirectionality-via-large-and","slug":"acquiring-bidirectionality-via-large-and","title":"Acquiring Bidirectionality via Large and Small Language Models","date":"2024-08-19","arxiv_id":"2408.09640","n_code_links":1,"syntology":null},{"paper":null,"slug":"active-learning-for-identifying-disaster","title":"Active Learning for Identifying Disaster-Related Tweets: A Comparison with Keyword Filtering and Generic Fine-Tuning","date":"2024-08-19","arxiv_id":"2408.09914","n_code_links":0,"syntology":null},{"paper":null,"slug":"attention-is-a-smoothed-cubic-spline","title":"Attention is a smoothed cubic spline","date":"2024-08-19","arxiv_id":"2408.09624","n_code_links":0,"syntology":null},{"paper":null,"slug":"benchmarking-llms-for-translating-classical","title":"Large Language Models for Classical Chinese Poetry Translation: Benchmarking, Evaluating, and Improving","date":"2024-08-19","arxiv_id":"2408.09945","n_code_links":0,"syntology":null},{"paper":null,"slug":"caption-driven-explorations-aligning-image","title":"Caption-Driven Explorations: Aligning Image and Text Embeddings through Human-Inspired Foveated Vision","date":"2024-08-19","arxiv_id":"2408.09948","n_code_links":0,"syntology":null},{"paper":null,"slug":"carbon-footprint-accounting-driven-by-large","title":"Carbon Footprint Accounting Driven by Large Language Models and Retrieval-augmented Generation","date":"2024-08-19","arxiv_id":"2408.09713","n_code_links":0,"syntology":null},{"paper":null,"slug":"coarse-fine-view-attention-alignment-based","title":"Coarse-Fine View Attention Alignment-Based GAN for CT Reconstruction from Biplanar X-Rays","date":"2024-08-19","arxiv_id":"2408.09736","n_code_links":0,"syntology":null},{"paper":null,"slug":"edge-cloud-collaborative-motion-planning-for","title":"Edge-Cloud Collaborative Motion Planning for Autonomous Driving with Large Language Models","date":"2024-08-19","arxiv_id":"2408.09972","n_code_links":0,"syntology":null},{"paper":"/paper/enhance-lifelong-model-editing-with","slug":"enhance-lifelong-model-editing-with","title":"ELDER: Enhancing Lifelong Model Editing with Mixture-of-LoRA","date":"2024-08-19","arxiv_id":"2408.11869","n_code_links":1,"syntology":null},{"paper":null,"slug":"enhanced-document-retrieval-with-topic","title":"Enhanced document retrieval with topic embeddings","date":"2024-08-19","arxiv_id":"2408.10435","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancing-reinforcement-learning-through","title":"Enhancing Reinforcement Learning Through Guided Search","date":"2024-08-19","arxiv_id":"2408.10113","n_code_links":0,"syntology":null},{"paper":"/paper/event-stream-based-human-action-recognition-a","slug":"event-stream-based-human-action-recognition-a","title":"Event Stream based Human Action Recognition: A High-Definition Benchmark Dataset and Algorithms","date":"2024-08-19","arxiv_id":"2408.09764","n_code_links":1,"syntology":null},{"paper":null,"slug":"exploiting-fine-grained-prototype","title":"Exploiting Fine-Grained Prototype Distribution for Boosting Unsupervised Class Incremental Learning","date":"2024-08-19","arxiv_id":"2408.10046","n_code_links":0,"syntology":null},{"paper":null,"slug":"factorized-dreamer-training-a-high-quality","title":"Factorized-Dreamer: Training A High-Quality Video Generator with Limited and Low-Quality Data","date":"2024-08-19","arxiv_id":"2408.10119","n_code_links":0,"syntology":null},{"paper":null,"slug":"faster-adaptive-decentralized-learning","title":"Faster Adaptive Decentralized Learning Algorithms","date":"2024-08-19","arxiv_id":"2408.09775","n_code_links":0,"syntology":null},{"paper":"/paper/federated-frank-wolfe-algorithm","slug":"federated-frank-wolfe-algorithm","title":"Federated Frank-Wolfe Algorithm","date":"2024-08-19","arxiv_id":"2408.10090","n_code_links":1,"syntology":null},{"paper":"/paper/goldfish-monolingual-language-models-for-350","slug":"goldfish-monolingual-language-models-for-350","title":"Goldfish: Monolingual Language Models for 350 Languages","date":"2024-08-19","arxiv_id":"2408.10441","n_code_links":1,"syntology":{"ran":4,"of":5,"n_ran_checked":4,"n_instrument":0,"unverified":1,"pointer_only":5,"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":["tylerachang/goldfish"],"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":"gpt-augmented-reinforcement-learning-with","title":"GARLIC: GPT-Augmented Reinforcement Learning with Intelligent Control for Vehicle Dispatching","date":"2024-08-19","arxiv_id":"2408.10286","n_code_links":0,"syntology":null},{"paper":null,"slug":"harmonizing-attention-training-free-texture","title":"Harmonizing Attention: Training-free Texture-aware Geometry Transfer","date":"2024-08-19","arxiv_id":"2408.10846","n_code_links":0,"syntology":null},{"paper":null,"slug":"image-based-freeform-handwriting","title":"Image-based Freeform Handwriting Authentication with Energy-oriented Self-Supervised Learning","date":"2024-08-19","arxiv_id":"2408.09676","n_code_links":0,"syntology":null},{"paper":"/paper/instruction-based-molecular-graph-generation","slug":"instruction-based-molecular-graph-generation","title":"Instruction-Based Molecular Graph Generation with Unified Text-Graph Diffusion Model","date":"2024-08-19","arxiv_id":"2408.09896","n_code_links":1,"syntology":null},{"paper":null,"slug":"learning-precise-affordances-from-egocentric","title":"Learning Precise Affordances from Egocentric Videos for Robotic Manipulation","date":"2024-08-19","arxiv_id":"2408.10123","n_code_links":0,"syntology":null},{"paper":"/paper/legalbench-rag-a-benchmark-for-retrieval","slug":"legalbench-rag-a-benchmark-for-retrieval","title":"LegalBench-RAG: A Benchmark for Retrieval-Augmented Generation in the Legal Domain","date":"2024-08-19","arxiv_id":"2408.10343","n_code_links":1,"syntology":{"ran":7,"of":8,"n_ran_checked":7,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["zeroentropy-cc/legalbenchrag"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"lightweather-harnessing-absolute-positional","title":"LightWeather: Harnessing Absolute Positional Encoding to Efficient and Scalable Global Weather Forecasting","date":"2024-08-19","arxiv_id":"2408.09695","n_code_links":0,"syntology":null},{"paper":null,"slug":"modegpt-modular-decomposition-for-large","title":"MoDeGPT: Modular Decomposition for Large Language Model Compression","date":"2024-08-19","arxiv_id":"2408.09632","n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-scale-representation-learning-for-image","title":"Multi-Scale Representation Learning for Image Restoration with State-Space Model","date":"2024-08-19","arxiv_id":"2408.10145","n_code_links":0,"syntology":null},{"paper":null,"slug":"mutually-aware-feature-learning-for-few-shot","title":"Mutually-Aware Feature Learning for Few-Shot Object Counting","date":"2024-08-19","arxiv_id":"2408.09734","n_code_links":0,"syntology":null},{"paper":"/paper/pedestrian-attribute-recognition-a-new","slug":"pedestrian-attribute-recognition-a-new","title":"Pedestrian Attribute Recognition: A New Benchmark Dataset and A Large Language Model Augmented Framework","date":"2024-08-19","arxiv_id":"2408.09720","n_code_links":2,"syntology":null},{"paper":null,"slug":"plutus-a-well-pre-trained-large-unified","title":"PLUTUS: A Well Pre-trained Large Unified Transformer can Unveil Financial Time Series Regularities","date":"2024-08-19","arxiv_id":"2408.10111","n_code_links":0,"syntology":null},{"paper":null,"slug":"preoperative-rotator-cuff-tear-prediction","title":"Preoperative Rotator Cuff Tear Prediction from Shoulder Radiographs using a Convolutional Block Attention Module-Integrated Neural Network","date":"2024-08-19","arxiv_id":"2408.09894","n_code_links":0,"syntology":null},{"paper":null,"slug":"privacy-checklist-privacy-violation-detection","title":"Privacy Checklist: Privacy Violation Detection Grounding on Contextual Integrity Theory","date":"2024-08-19","arxiv_id":"2408.10053","n_code_links":0,"syntology":null},{"paper":null,"slug":"propagating-the-prior-from-shallow-to-deep","title":"Propagating the prior from shallow to deep with a pre-trained velocity-model Generative Transformer network","date":"2024-08-19","arxiv_id":"2408.09767","n_code_links":0,"syntology":null},{"paper":"/paper/r2gencsr-retrieving-context-samples-for-large","slug":"r2gencsr-retrieving-context-samples-for-large","title":"R2GenCSR: Retrieving Context Samples for Large Language Model based X-ray Medical Report Generation","date":"2024-08-19","arxiv_id":"2408.09743","n_code_links":1,"syntology":null},{"paper":"/paper/revisiting-reciprocal-recommender-systems","slug":"revisiting-reciprocal-recommender-systems","title":"Revisiting Reciprocal Recommender Systems: Metrics, Formulation, and Method","date":"2024-08-19","arxiv_id":"2408.09748","n_code_links":1,"syntology":null},{"paper":null,"slug":"rhyme-aware-chinese-lyric-generator-based-on","title":"Rhyme-aware Chinese lyric generator based on GPT","date":"2024-08-19","arxiv_id":"2408.10130","n_code_links":0,"syntology":null},{"paper":"/paper/sam-unet-enhancing-zero-shot-segmentation-of","slug":"sam-unet-enhancing-zero-shot-segmentation-of","title":"SAM-UNet:Enhancing Zero-Shot Segmentation of SAM for Universal Medical Images","date":"2024-08-19","arxiv_id":"2408.09886","n_code_links":1,"syntology":null},{"paper":null,"slug":"self-directed-turing-test-for-large-language","title":"Self-Directed Turing Test for Large Language Models","date":"2024-08-19","arxiv_id":"2408.09853","n_code_links":0,"syntology":null},{"paper":"/paper/sliced-maximal-information-coefficient-a","slug":"sliced-maximal-information-coefficient-a","title":"Sliced Maximal Information Coefficient: A Training-Free Approach for Image Quality Assessment Enhancement","date":"2024-08-19","arxiv_id":"2408.09920","n_code_links":1,"syntology":null},{"paper":"/paper/solving-oscillator-odes-via-soft-constrained","slug":"solving-oscillator-odes-via-soft-constrained","title":"Characteristic Performance Study on Solving Oscillator ODEs via Soft-constrained Physics-informed Neural Network with Small Data","date":"2024-08-19","arxiv_id":"2408.11077","n_code_links":1,"syntology":null},{"paper":null,"slug":"stransformer-a-modular-approach-for","title":"sTransformer: A Modular Approach for Extracting Inter-Sequential and Temporal Information for Time-Series Forecasting","date":"2024-08-19","arxiv_id":"2408.09723","n_code_links":0,"syntology":null},{"paper":null,"slug":"tba-faster-large-language-model-training","title":"SSDTrain: An Activation Offloading Framework to SSDs for Faster Large Language Model Training","date":"2024-08-19","arxiv_id":"2408.10013","n_code_links":0,"syntology":null},{"paper":null,"slug":"toward-large-scale-spiking-neural-networks-a","title":"Toward Large-scale Spiking Neural Networks: A Comprehensive Survey and Future Directions","date":"2024-08-19","arxiv_id":"2409.02111","n_code_links":0,"syntology":null},{"paper":"/paper/transformers-to-ssms-distilling-quadratic","slug":"transformers-to-ssms-distilling-quadratic","title":"Transformers to SSMs: Distilling Quadratic Knowledge to Subquadratic Models","date":"2024-08-19","arxiv_id":"2408.10189","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-unified-framework-for-interpretable","title":"A Unified Framework for Interpretable Transformers Using PDEs and Information Theory","date":"2024-08-18","arxiv_id":"2408.09523","n_code_links":0,"syntology":null},{"paper":null,"slug":"advances-in-multiple-instance-learning-for","title":"Advances in Multiple Instance Learning for Whole Slide Image Analysis: Techniques, Challenges, and Future Directions","date":"2024-08-18","arxiv_id":"2408.09476","n_code_links":0,"syntology":null},{"paper":null,"slug":"agentic-retrieval-augmented-generation-for","title":"Agentic Retrieval-Augmented Generation for Time Series Analysis","date":"2024-08-18","arxiv_id":"2408.14484","n_code_links":0,"syntology":null},{"paper":null,"slug":"an-introduction-to-cognidynamics","title":"An Introduction to Cognidynamics","date":"2024-08-18","arxiv_id":"2408.13112","n_code_links":0,"syntology":null},{"paper":null,"slug":"comparison-between-the-structures-of-word-co","title":"Comparison between the Structures of Word Co-occurrence and Word Similarity Networks for Ill-formed and Well-formed Texts in Taiwan Mandarin","date":"2024-08-18","arxiv_id":"2408.09404","n_code_links":0,"syntology":null},{"paper":null,"slug":"deep-limit-model-free-prediction-in","title":"Deep Limit Model-free Prediction in Regression","date":"2024-08-18","arxiv_id":"2408.09532","n_code_links":0,"syntology":null},{"paper":null,"slug":"elastic-efficient-linear-attention-for","title":"ELASTIC: Efficient Linear Attention for Sequential Interest Compression","date":"2024-08-18","arxiv_id":"2408.09380","n_code_links":0,"syntology":null},{"paper":null,"slug":"fd2talk-towards-generalized-talking-head","title":"FD2Talk: Towards Generalized Talking Head Generation with Facial Decoupled Diffusion Model","date":"2024-08-18","arxiv_id":"2408.09384","n_code_links":0,"syntology":null},{"paper":null,"slug":"improvement-of-bayesian-pinn-training","title":"Enhanced BPINN Training Convergence in Solving General and Multi-scale Elliptic PDEs with Noise","date":"2024-08-18","arxiv_id":"2408.09340","n_code_links":0,"syntology":null},{"paper":null,"slug":"ou-covit-copula-enhanced-bi-channel-multi","title":"OU-CoViT: Copula-Enhanced Bi-Channel Multi-Task Vision Transformers with Dual Adaptation for OU-UWF Images","date":"2024-08-18","arxiv_id":"2408.09395","n_code_links":0,"syntology":null},{"paper":"/paper/out-of-distribution-generalization-via-1","slug":"out-of-distribution-generalization-via-1","title":"Out-of-distribution generalization via composition: a lens through induction heads in Transformers","date":"2024-08-18","arxiv_id":"2408.09503","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["jiajunsong629/ood-generalization-via-composition"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"threshold-filtering-packing-for-supervised","title":"Threshold Filtering Packing for Supervised Fine-Tuning: Training Related Samples within Packs","date":"2024-08-18","arxiv_id":"2408.09327","n_code_links":0,"syntology":null},{"paper":null,"slug":"conversum-a-contrastive-learning-based","title":"ConVerSum: A Contrastive Learning-based Approach for Data-Scarce Solution of Cross-Lingual Summarization Beyond Direct Equivalents","date":"2024-08-17","arxiv_id":"2408.09273","n_code_links":0,"syntology":null},{"paper":"/paper/cross-species-data-integration-for-enhanced","slug":"cross-species-data-integration-for-enhanced","title":"Cross-Species Data Integration for Enhanced Layer Segmentation in Kidney Pathology","date":"2024-08-17","arxiv_id":"2408.09278","n_code_links":1,"syntology":null},{"paper":null,"slug":"eeg-scmm-soft-contrastive-masked-modeling-for","title":"EEG-SCMM: Soft Contrastive Masked Modeling for Cross-Corpus EEG-Based Emotion Recognition","date":"2024-08-17","arxiv_id":"2408.09186","n_code_links":0,"syntology":null},{"paper":"/paper/graph-classification-with-gnns-optimisation","slug":"graph-classification-with-gnns-optimisation","title":"Graph Classification with GNNs: Optimisation, Representation and Inductive Bias","date":"2024-08-17","arxiv_id":"2408.09266","n_code_links":1,"syntology":null},{"paper":null,"slug":"hybridocc-nerf-enhanced-transformer-based","title":"HybridOcc: NeRF Enhanced Transformer-based Multi-Camera 3D Occupancy Prediction","date":"2024-08-17","arxiv_id":"2408.09104","n_code_links":0,"syntology":null},{"paper":"/paper/improving-rare-word-translation-with","slug":"improving-rare-word-translation-with","title":"Improving Rare Word Translation With Dictionaries and Attention Masking","date":"2024-08-17","arxiv_id":"2408.09075","n_code_links":1,"syntology":null},{"paper":"/paper/linear-attention-is-enough-in-spatial","slug":"linear-attention-is-enough-in-spatial","title":"Linear Attention is Enough in Spatial-Temporal Forecasting","date":"2024-08-17","arxiv_id":"2408.09158","n_code_links":1,"syntology":null},{"paper":null,"slug":"magicid-flexible-id-fidelity-generation","title":"MagicID: Flexible ID Fidelity Generation System","date":"2024-08-17","arxiv_id":"2408.09248","n_code_links":0,"syntology":null},{"paper":null,"slug":"maskbev-towards-a-unified-framework-for-bev","title":"MaskBEV: Towards A Unified Framework for BEV Detection and Map Segmentation","date":"2024-08-17","arxiv_id":"2408.09122","n_code_links":0,"syntology":null},{"paper":"/paper/on-the-improvement-of-generalization-and","slug":"on-the-improvement-of-generalization-and","title":"On the Improvement of Generalization and Stability of Forward-Only Learning via Neural Polarization","date":"2024-08-17","arxiv_id":"2408.09210","n_code_links":1,"syntology":null},{"paper":null,"slug":"on-the-kl-divergence-based-robust-satisficing","title":"On the KL-Divergence-based Robust Satisficing Model","date":"2024-08-17","arxiv_id":"2408.09157","n_code_links":0,"syntology":null},{"paper":"/paper/padetbench-towards-benchmarking-physical","slug":"padetbench-towards-benchmarking-physical","title":"PADetBench: Towards Benchmarking Physical Attacks against Object Detection","date":"2024-08-17","arxiv_id":"2408.09181","n_code_links":2,"syntology":null},{"paper":null,"slug":"quality-assessment-in-the-era-of-large-models","title":"Quality Assessment in the Era of Large Models: A Survey","date":"2024-08-17","arxiv_id":"2409.00031","n_code_links":0,"syntology":null},{"paper":"/paper/selective-prompt-anchoring-for-code","slug":"selective-prompt-anchoring-for-code","title":"Selective Prompt Anchoring for Code Generation","date":"2024-08-17","arxiv_id":"2408.09121","n_code_links":1,"syntology":{"ran":7,"of":11,"n_ran_checked":3,"n_instrument":4,"unverified":4,"pointer_only":1,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 4 where Syntology's instrument failed) · 4 unverified","official":{"repos":["magic-yuantian/selective-prompt-anchoring"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"sentiment-analysis-of-preservice-teachers","title":"Sentiment analysis of preservice teachers' reflections using a large language model","date":"2024-08-17","arxiv_id":"2408.11862","n_code_links":0,"syntology":null},{"paper":null,"slug":"siamese-multiple-attention-temporal","title":"Siamese Multiple Attention Temporal Convolution Networks for Human Mobility Signature Identification","date":"2024-08-17","arxiv_id":"2408.09230","n_code_links":0,"syntology":null},{"paper":null,"slug":"tablebench-a-comprehensive-and-complex","title":"TableBench: A Comprehensive and Complex Benchmark for Table Question Answering","date":"2024-08-17","arxiv_id":"2408.09174","n_code_links":0,"syntology":null},{"paper":"/paper/tc-rag-turing-complete-rag-s-case-study-on","slug":"tc-rag-turing-complete-rag-s-case-study-on","title":"TC-RAG:Turing-Complete RAG's Case study on Medical LLM Systems","date":"2024-08-17","arxiv_id":"2408.09199","n_code_links":2,"syntology":null}],"record_sha256":"6496d3231a29fde7cde51ca7d6e3a94feff84694bf1e40acac3266f05113526f","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}