{"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/transformer/papers/35","list_of":"/method/transformer","method":"Transformer","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":35,"pages_in_order":140,"rows_per_page":100,"rows":[3401,3500],"of":13999,"counts":{"archive_papers_tagged":13999,"with_a_code_link":6572,"where_syntology_ran_a_sample":2248,"not_listed_spam_title":0,"listed":13999,"listed_where_code_ran":2248,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1919,"every_run_a_failure_of_syntologys_instrument":329,"listed_with_a_run_with_no_instrument_failure":1919,"listed_every_run_a_failure_of_syntologys_instrument":329,"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/transformer","prev":"/method/transformer/papers/34","next":"/method/transformer/papers/36","papers":[{"paper":"/paper/bkdsnn-enhancing-the-performance-of-learning","slug":"bkdsnn-enhancing-the-performance-of-learning","title":"BKDSNN: Enhancing the Performance of Learning-based Spiking Neural Networks Training with Blurred Knowledge Distillation","date":"2024-07-12","arxiv_id":"2407.09083","n_code_links":1,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":1,"phrase":"0 ran · 1 unverified","official":{"repos":["intelligent-computing-research-group/bkdsnn"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"paper":null,"slug":"bora-biomedical-generalist-video-generation","title":"Bora: Biomedical Generalist Video Generation Model","date":"2024-07-12","arxiv_id":"2407.08944","n_code_links":0,"syntology":null},{"paper":null,"slug":"global-attention-guided-dual-domain-point","title":"Global Attention-Guided Dual-Domain Point Cloud Feature Learning for Classification and Segmentation","date":"2024-07-12","arxiv_id":"2407.08994","n_code_links":0,"syntology":null},{"paper":null,"slug":"inference-optimization-of-foundation-models","title":"Inference Optimization of Foundation Models on AI Accelerators","date":"2024-07-12","arxiv_id":"2407.09111","n_code_links":0,"syntology":null},{"paper":"/paper/leveraging-large-language-models-for-nano","slug":"leveraging-large-language-models-for-nano","title":"Leveraging large language models for nano synthesis mechanism explanation: solid foundations or mere conjectures?","date":"2024-07-12","arxiv_id":"2407.08922","n_code_links":1,"syntology":null},{"paper":null,"slug":"movie-recommendation-with-poster-attention","title":"Movie Recommendation with Poster Attention via Multi-modal Transformer Feature Fusion","date":"2024-07-12","arxiv_id":"2407.09157","n_code_links":0,"syntology":null},{"paper":null,"slug":"neural-based-video-compression-on-solar","title":"Neural-based Video Compression on Solar Dynamics Observatory Images","date":"2024-07-12","arxiv_id":"2407.15730","n_code_links":0,"syntology":null},{"paper":"/paper/refuse-whenever-you-feel-unsafe-improving","slug":"refuse-whenever-you-feel-unsafe-improving","title":"Refuse Whenever You Feel Unsafe: Improving Safety in LLMs via Decoupled Refusal Training","date":"2024-07-12","arxiv_id":"2407.09121","n_code_links":2,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"pointer_only":0,"phrase":"3 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; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["robustnlp/derta"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/region-attention-transformer-for-medical","slug":"region-attention-transformer-for-medical","title":"Region Attention Transformer for Medical Image Restoration","date":"2024-07-12","arxiv_id":"2407.09268","n_code_links":1,"syntology":null},{"paper":null,"slug":"self-evolving-gpt-a-lifelong-autonomous","title":"Self-Evolving GPT: A Lifelong Autonomous Experiential Learner","date":"2024-07-12","arxiv_id":"2407.08937","n_code_links":0,"syntology":null},{"paper":null,"slug":"self-prompt-tuning-enable-autonomous-role","title":"Self-Prompt Tuning: Enable Autonomous Role-Playing in LLMs","date":"2024-07-12","arxiv_id":"2407.08995","n_code_links":0,"syntology":null},{"paper":"/paper/show-don-t-tell-evaluating-large-language","slug":"show-don-t-tell-evaluating-large-language","title":"Show, Don't Tell: Evaluating Large Language Models Beyond Textual Understanding with ChildPlay","date":"2024-07-12","arxiv_id":"2407.11068","n_code_links":1,"syntology":null},{"paper":null,"slug":"telecomgpt-a-framework-to-build-telecom","title":"TelecomGPT: A Framework to Build Telecom-Specfic Large Language Models","date":"2024-07-12","arxiv_id":"2407.09424","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-heterophilic-graph-learning-handbook","title":"The Heterophilic Graph Learning Handbook: Benchmarks, Models, Theoretical Analysis, Applications and Challenges","date":"2024-07-12","arxiv_id":"2407.09618","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-two-sides-of-the-coin-hallucination","title":"The Two Sides of the Coin: Hallucination Generation and Detection with LLMs as Evaluators for LLMs","date":"2024-07-12","arxiv_id":"2407.09152","n_code_links":0,"syntology":null},{"paper":null,"slug":"brain-tumor-segmentation-in-mri-images-with","title":"Brain Tumor Segmentation in MRI Images with 3D U-Net and Contextual Transformer","date":"2024-07-11","arxiv_id":"2407.08470","n_code_links":0,"syntology":null},{"paper":null,"slug":"converging-paradigms-the-synergy-of-symbolic","title":"Converging Paradigms: The Synergy of Symbolic and Connectionist AI in LLM-Empowered Autonomous Agents","date":"2024-07-11","arxiv_id":"2407.08516","n_code_links":0,"syntology":null},{"paper":null,"slug":"fault-diagnosis-in-power-grids-with-large","title":"Fault Diagnosis in Power Grids with Large Language Model","date":"2024-07-11","arxiv_id":"2407.08836","n_code_links":0,"syntology":null},{"paper":"/paper/flashattention-3-fast-and-accurate-attention","slug":"flashattention-3-fast-and-accurate-attention","title":"FlashAttention-3: Fast and Accurate Attention with Asynchrony and Low-precision","date":"2024-07-11","arxiv_id":"2407.08608","n_code_links":2,"syntology":{"ran":16,"of":18,"n_ran_checked":15,"n_instrument":1,"unverified":2,"pointer_only":10,"phrase":"16 ran (of which 0 constructed an object rather than computing a result; 15 with no instrument failure: 2 honoured, 0 violated, 13 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","official":{"repos":["dao-ailab/flash-attention"],"state":"official (archive's flag): 16 ran","n_ran":16,"n_constructed":0,"n_ran_no_instrument_failure":15,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"gpt-4-is-judged-more-human-than-humans-in","title":"GPT-4 is judged more human than humans in displaced and inverted Turing tests","date":"2024-07-11","arxiv_id":"2407.08853","n_code_links":0,"syntology":null},{"paper":"/paper/graphmamba-an-efficient-graph-structure","slug":"graphmamba-an-efficient-graph-structure","title":"GraphMamba: An Efficient Graph Structure Learning Vision Mamba for Hyperspectral Image Classification","date":"2024-07-11","arxiv_id":"2407.08255","n_code_links":1,"syntology":null},{"paper":"/paper/gta-a-benchmark-for-general-tool-agents","slug":"gta-a-benchmark-for-general-tool-agents","title":"GTA: A Benchmark for General Tool Agents","date":"2024-07-11","arxiv_id":"2407.08713","n_code_links":1,"syntology":null},{"paper":null,"slug":"hdt-hierarchical-document-transformer","title":"HDT: Hierarchical Document Transformer","date":"2024-07-11","arxiv_id":"2407.08330","n_code_links":0,"syntology":null},{"paper":"/paper/multimodal-contrastive-learning-for-spatial","slug":"multimodal-contrastive-learning-for-spatial","title":"Multimodal contrastive learning for spatial gene expression prediction using histology images","date":"2024-07-11","arxiv_id":"2407.08216","n_code_links":1,"syntology":{"ran":8,"of":9,"n_ran_checked":7,"n_instrument":1,"unverified":1,"pointer_only":9,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["shizhiceng/mclstexp"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/projecting-points-to-axes-oriented-object","slug":"projecting-points-to-axes-oriented-object","title":"Projecting Points to Axes: Oriented Object Detection via Point-Axis Representation","date":"2024-07-11","arxiv_id":"2407.08489","n_code_links":1,"syntology":null},{"paper":"/paper/salsa-swift-adaptive-lightweight-self","slug":"salsa-swift-adaptive-lightweight-self","title":"SALSA: Swift Adaptive Lightweight Self-Attention for Enhanced LiDAR Place Recognition","date":"2024-07-11","arxiv_id":"2407.08260","n_code_links":1,"syntology":null},{"paper":null,"slug":"skywork-math-data-scaling-laws-for","title":"Skywork-Math: Data Scaling Laws for Mathematical Reasoning in Large Language Models -- The Story Goes On","date":"2024-07-11","arxiv_id":"2407.08348","n_code_links":0,"syntology":null},{"paper":null,"slug":"spiking-tucker-fusion-transformer-for-audio","title":"Spiking Tucker Fusion Transformer for Audio-Visual Zero-Shot Learning","date":"2024-07-11","arxiv_id":"2407.08130","n_code_links":0,"syntology":null},{"paper":"/paper/stentrans-transformer-based-deep-learning-for","slug":"stentrans-transformer-based-deep-learning-for","title":"stEnTrans: Transformer-based deep learning for spatial transcriptomics enhancement","date":"2024-07-11","arxiv_id":"2407.08224","n_code_links":1,"syntology":null},{"paper":null,"slug":"synthetic-electroretinogram-signal-generation","title":"Synthetic Electroretinogram Signal Generation Using Conditional Generative Adversarial Network for Enhancing Classification of Autism Spectrum Disorder","date":"2024-07-11","arxiv_id":"2407.08166","n_code_links":0,"syntology":null},{"paper":null,"slug":"tractgraphformer-anatomically-informed-hybrid","title":"TractGraphFormer: Anatomically Informed Hybrid Graph CNN-Transformer Network for Classification from Diffusion MRI Tractography","date":"2024-07-11","arxiv_id":"2407.08883","n_code_links":0,"syntology":null},{"paper":"/paper/arabic-automatic-story-generation-with-large","slug":"arabic-automatic-story-generation-with-large","title":"Arabic Automatic Story Generation with Large Language Models","date":"2024-07-10","arxiv_id":"2407.07551","n_code_links":1,"syntology":null},{"paper":"/paper/deep-er-reconstruction-of-imaging-cherenkov","slug":"deep-er-reconstruction-of-imaging-cherenkov","title":"Deep(er) Reconstruction of Imaging Cherenkov Detectors with Swin Transformers and Normalizing Flow Models","date":"2024-07-10","arxiv_id":"2407.07376","n_code_links":1,"syntology":null},{"paper":"/paper/evaluating-large-language-models-with-grid","slug":"evaluating-large-language-models-with-grid","title":"Evaluating Large Language Models with Grid-Based Game Competitions: An Extensible LLM Benchmark and Leaderboard","date":"2024-07-10","arxiv_id":"2407.07796","n_code_links":1,"syntology":null},{"paper":"/paper/federated-foundation-model-for-cardiac-ct","slug":"federated-foundation-model-for-cardiac-ct","title":"Real World Federated Learning with a Knowledge Distilled Transformer for Cardiac CT Imaging","date":"2024-07-10","arxiv_id":"2407.07557","n_code_links":2,"syntology":null},{"paper":"/paper/h-fcbformer-hierarchical-fully-convolutional","slug":"h-fcbformer-hierarchical-fully-convolutional","title":"H-FCBFormer Hierarchical Fully Convolutional Branch Transformer for Occlusal Contact Segmentation with Articulating Paper","date":"2024-07-10","arxiv_id":"2407.07604","n_code_links":1,"syntology":null},{"paper":null,"slug":"haformer-unleashing-the-power-of-hierarchy","title":"HAFormer: Unleashing the Power of Hierarchy-Aware Features for Lightweight Semantic Segmentation","date":"2024-07-10","arxiv_id":"2407.07441","n_code_links":0,"syntology":null},{"paper":"/paper/litsearch-a-retrieval-benchmark-for","slug":"litsearch-a-retrieval-benchmark-for","title":"LitSearch: A Retrieval Benchmark for Scientific Literature Search","date":"2024-07-10","arxiv_id":"2407.18940","n_code_links":1,"syntology":{"ran":7,"of":7,"n_ran_checked":7,"n_instrument":0,"unverified":0,"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) · 0 unverified","official":{"repos":["princeton-nlp/litsearch"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"mixsumm-topic-based-data-augmentation-using","title":"A Guide To Effectively Leveraging LLMs for Low-Resource Text Summarization: Data Augmentation and Semi-supervised Approaches","date":"2024-07-10","arxiv_id":"2407.07341","n_code_links":0,"syntology":null},{"paper":null,"slug":"probability-of-differentiation-reveals","title":"Probability of Differentiation Reveals Brittleness of Homogeneity Bias in GPT-4","date":"2024-07-10","arxiv_id":"2407.07329","n_code_links":0,"syntology":null},{"paper":null,"slug":"rag-vs-long-context-examining-frontier-large","title":"Examining Long-Context Large Language Models for Environmental Review Document Comprehension","date":"2024-07-10","arxiv_id":"2407.07321","n_code_links":0,"syntology":null},{"paper":null,"slug":"rt-la-voce-real-time-low-snr-audio-visual","title":"RT-LA-VocE: Real-Time Low-SNR Audio-Visual Speech Enhancement","date":"2024-07-10","arxiv_id":"2407.07825","n_code_links":0,"syntology":null},{"paper":"/paper/swin-smt-global-sequential-modeling-in-3d","slug":"swin-smt-global-sequential-modeling-in-3d","title":"Swin SMT: Global Sequential Modeling in 3D Medical Image Segmentation","date":"2024-07-10","arxiv_id":"2407.07514","n_code_links":1,"syntology":null},{"paper":null,"slug":"teaching-transformers-causal-reasoning","title":"Teaching Transformers Causal Reasoning through Axiomatic Training","date":"2024-07-10","arxiv_id":"2407.07612","n_code_links":0,"syntology":null},{"paper":null,"slug":"toto-time-series-optimized-transformer-for","title":"Toto: Time Series Optimized Transformer for Observability","date":"2024-07-10","arxiv_id":"2407.07874","n_code_links":0,"syntology":null},{"paper":null,"slug":"video-in-context-learning","title":"Video In-context Learning","date":"2024-07-10","arxiv_id":"2407.07356","n_code_links":0,"syntology":null},{"paper":null,"slug":"when-to-accept-automated-predictions-and-when","title":"When to Accept Automated Predictions and When to Defer to Human Judgment?","date":"2024-07-10","arxiv_id":"2407.07821","n_code_links":0,"syntology":null},{"paper":null,"slug":"worldapis-the-world-is-worth-how-many-apis-a","title":"WorldAPIs: The World Is Worth How Many APIs? A Thought Experiment","date":"2024-07-10","arxiv_id":"2407.07778","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-predictive-model-based-on-transformer-with","title":"A Predictive Model Based on Transformer with Statistical Feature Embedding in Manufacturing Sensor Dataset","date":"2024-07-09","arxiv_id":"2407.06682","n_code_links":0,"syntology":null},{"paper":"/paper/automated-peer-reviewing-in-paper-sea","slug":"automated-peer-reviewing-in-paper-sea","title":"Automated Peer Reviewing in Paper SEA: Standardization, Evaluation, and Analysis","date":"2024-07-09","arxiv_id":"2407.12857","n_code_links":1,"syntology":{"ran":7,"of":14,"n_ran_checked":7,"n_instrument":0,"unverified":7,"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) · 7 unverified","official":{"repos":["ecnu-sea/SEA"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":7,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"capformer-compression-aware-pre-trained","title":"CAPformer: Compression-Aware Pre-trained Transformer for Low-Light Image Enhancement","date":"2024-07-09","arxiv_id":"2407.07056","n_code_links":0,"syntology":null},{"paper":null,"slug":"convnlp-image-based-ai-text-detection","title":"ConvNLP: Image-based AI Text Detection","date":"2024-07-09","arxiv_id":"2407.07225","n_code_links":0,"syntology":null},{"paper":null,"slug":"cormult-a-semi-supervised-modality","title":"CorMulT: A Semi-supervised Modality Correlation-aware Multimodal Transformer for Sentiment Analysis","date":"2024-07-09","arxiv_id":"2407.07046","n_code_links":0,"syntology":null},{"paper":"/paper/fine-tuning-linear-layers-only-is-a-simple","slug":"fine-tuning-linear-layers-only-is-a-simple","title":"Fine-Tuning Attention Modules Only: Enhancing Weight Disentanglement in Task Arithmetic","date":"2024-07-09","arxiv_id":"2407.07089","n_code_links":2,"syntology":{"ran":3,"of":5,"n_ran_checked":0,"n_instrument":3,"unverified":2,"pointer_only":0,"phrase":"3 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; 3 where Syntology's instrument failed) · 2 unverified","official":{"repos":["kyrie-23/task_arithmetic_tangent","kyrie-23/linear_task_arithmetic"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"mixture-of-modules-reinventing-transformers","title":"Mixture-of-Modules: Reinventing Transformers as Dynamic Assemblies of Modules","date":"2024-07-09","arxiv_id":"2407.06677","n_code_links":0,"syntology":null},{"paper":"/paper/parameter-efficient-and-memory-efficient","slug":"parameter-efficient-and-memory-efficient","title":"Parameter-Efficient and Memory-Efficient Tuning for Vision Transformer: A Disentangled Approach","date":"2024-07-09","arxiv_id":"2407.06964","n_code_links":1,"syntology":null},{"paper":"/paper/peer-expertizing-domain-specific-tasks-with-a","slug":"peer-expertizing-domain-specific-tasks-with-a","title":"PEER: Expertizing Domain-Specific Tasks with a Multi-Agent Framework and Tuning Methods","date":"2024-07-09","arxiv_id":"2407.06985","n_code_links":1,"syntology":null},{"paper":null,"slug":"prompting-techniques-for-secure-code","title":"Prompting Techniques for Secure Code Generation: A Systematic Investigation","date":"2024-07-09","arxiv_id":"2407.07064","n_code_links":0,"syntology":null},{"paper":"/paper/source-code-summarization-in-the-era-of-large","slug":"source-code-summarization-in-the-era-of-large","title":"Source Code Summarization in the Era of Large Language Models","date":"2024-07-09","arxiv_id":"2407.07959","n_code_links":1,"syntology":null},{"paper":"/paper/trackformers-in-search-of-transformer-based","slug":"trackformers-in-search-of-transformer-based","title":"TrackFormers: In Search of Transformer-Based Particle Tracking for the High-Luminosity LHC Era","date":"2024-07-09","arxiv_id":"2407.07179","n_code_links":1,"syntology":null},{"paper":null,"slug":"using-large-language-models-for-generating","title":"Using Large Language Models for Generating Smart Contracts for Health Insurance from Textual Policies","date":"2024-07-09","arxiv_id":"2407.07019","n_code_links":0,"syntology":null},{"paper":"/paper/3d-vision-and-language-pretraining-with-large","slug":"3d-vision-and-language-pretraining-with-large","title":"3D Vision and Language Pretraining with Large-Scale Synthetic Data","date":"2024-07-08","arxiv_id":"2407.06084","n_code_links":1,"syntology":{"ran":10,"of":10,"n_ran_checked":9,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["idejie/3DSyn"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/a-single-transformer-for-scalable-vision","slug":"a-single-transformer-for-scalable-vision","title":"SOLO: A Single Transformer for Scalable Vision-Language Modeling","date":"2024-07-08","arxiv_id":"2407.06438","n_code_links":1,"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":["yangyi-chen/solo"],"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":null,"slug":"charss-character-level-transformer-model-for","title":"CharSS: Character-Level Transformer Model for Sanskrit Word Segmentation","date":"2024-07-08","arxiv_id":"2407.06331","n_code_links":0,"syntology":null},{"paper":"/paper/codeupdatearena-benchmarking-knowledge","slug":"codeupdatearena-benchmarking-knowledge","title":"CodeUpdateArena: Benchmarking Knowledge Editing on API Updates","date":"2024-07-08","arxiv_id":"2407.06249","n_code_links":1,"syntology":null},{"paper":null,"slug":"cross-domain-few-shot-in-context-learning-for","title":"Cross-domain Few-shot In-context Learning for Enhancing Traffic Sign Recognition","date":"2024-07-08","arxiv_id":"2407.05814","n_code_links":0,"syntology":null},{"paper":null,"slug":"deep-learning-based-anomaly-detection-and-log","title":"Deep Learning-based Anomaly Detection and Log Analysis for Computer Networks","date":"2024-07-08","arxiv_id":"2407.05639","n_code_links":0,"syntology":null},{"paper":"/paper/empowering-1000-tokens-second-on-device-llm","slug":"empowering-1000-tokens-second-on-device-llm","title":"Fast On-device LLM Inference with NPUs","date":"2024-07-08","arxiv_id":"2407.05858","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":["ubiquitouslearning/mllm"],"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":"generative-debunking-of-climate","title":"Generative Debunking of Climate Misinformation","date":"2024-07-08","arxiv_id":"2407.05599","n_code_links":0,"syntology":null},{"paper":"/paper/inversecoder-unleashing-the-power-of","slug":"inversecoder-unleashing-the-power-of","title":"InverseCoder: Self-improving Instruction-Tuned Code LLMs with Inverse-Instruct","date":"2024-07-08","arxiv_id":"2407.05700","n_code_links":1,"syntology":{"ran":11,"of":11,"n_ran_checked":11,"n_instrument":0,"unverified":0,"pointer_only":11,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["wyt2000/InverseCoder"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"learning-lane-graphs-from-aerial-imagery","title":"Learning Lane Graphs from Aerial Imagery Using Transformers","date":"2024-07-08","arxiv_id":"2407.05687","n_code_links":0,"syntology":null},{"paper":"/paper/llm-based-open-domain-integrated-task-and","slug":"llm-based-open-domain-integrated-task-and","title":"Controllable and Reliable Knowledge-Intensive Task-Oriented Conversational Agents with Declarative Genie Worksheets","date":"2024-07-08","arxiv_id":"2407.05674","n_code_links":1,"syntology":null},{"paper":"/paper/meme-analysis-using-llm-based-contextual","slug":"meme-analysis-using-llm-based-contextual","title":"Meme Analysis using LLM-based Contextual Information and U-net Encapsulated Transformer","date":"2024-07-08","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"mstf-multiscale-transformer-for-incomplete","title":"MSTF: Multiscale Transformer for Incomplete Trajectory Prediction","date":"2024-07-08","arxiv_id":"2407.05671","n_code_links":0,"syntology":null},{"paper":"/paper/multi-label-plant-species-classification-with","slug":"multi-label-plant-species-classification-with","title":"Multi-Label Plant Species Classification with Self-Supervised Vision Transformers","date":"2024-07-08","arxiv_id":"2407.06298","n_code_links":1,"syntology":null},{"paper":null,"slug":"on-the-power-of-convolution-augmented","title":"On the Power of Convolution Augmented Transformer","date":"2024-07-08","arxiv_id":"2407.05591","n_code_links":0,"syntology":null},{"paper":null,"slug":"potential-of-multimodal-large-language-models","title":"Potential of Multimodal Large Language Models for Data Mining of Medical Images and Free-text Reports","date":"2024-07-08","arxiv_id":"2407.05758","n_code_links":0,"syntology":null},{"paper":"/paper/pruning-large-language-models-to-intra-module","slug":"pruning-large-language-models-to-intra-module","title":"Pruning Large Language Models to Intra-module Low-rank Architecture with Transitional Activations","date":"2024-07-08","arxiv_id":"2407.05690","n_code_links":1,"syntology":null},{"paper":null,"slug":"stmr-spiral-transformer-for-hand-mesh","title":"STMR: Spiral Transformer for Hand Mesh Reconstruction","date":"2024-07-08","arxiv_id":"2407.05967","n_code_links":0,"syntology":null},{"paper":null,"slug":"surprising-gender-biases-in-gpt","title":"Surprising gender biases in GPT","date":"2024-07-08","arxiv_id":"2407.06003","n_code_links":0,"syntology":null},{"paper":null,"slug":"t2vsafetybench-evaluating-the-safety-of-text","title":"T2VSafetyBench: Evaluating the Safety of Text-to-Video Generative Models","date":"2024-07-08","arxiv_id":"2407.05965","n_code_links":0,"syntology":null},{"paper":null,"slug":"tailor3d-customized-3d-assets-editing-and","title":"Tailor3D: Customized 3D Assets Editing and Generation with Dual-Side Images","date":"2024-07-08","arxiv_id":"2407.06191","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-optimizing-and-evaluating-a-retrieval","title":"Towards Optimizing and Evaluating a Retrieval Augmented QA Chatbot using LLMs with Human in the Loop","date":"2024-07-08","arxiv_id":"2407.05925","n_code_links":0,"syntology":null},{"paper":"/paper/transma-an-explainable-multi-modal-deep","slug":"transma-an-explainable-multi-modal-deep","title":"TransMA: an explainable multi-modal deep learning model for predicting properties of ionizable lipid nanoparticles in mRNA delivery","date":"2024-07-08","arxiv_id":"2407.05736","n_code_links":1,"syntology":null},{"paper":"/paper/wsi-vqa-interpreting-whole-slide-images-by","slug":"wsi-vqa-interpreting-whole-slide-images-by","title":"WSI-VQA: Interpreting Whole Slide Images by Generative Visual Question Answering","date":"2024-07-08","arxiv_id":"2407.05603","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":0,"n_instrument":1,"unverified":1,"pointer_only":2,"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) · 1 unverified","official":{"repos":["cpystan/wsi-vqa"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"enhancing-computer-programming-education-with","title":"Enhancing Computer Programming Education with LLMs: A Study on Effective Prompt Engineering for Python Code Generation","date":"2024-07-07","arxiv_id":"2407.05437","n_code_links":0,"syntology":null},{"paper":"/paper/just-read-twice-closing-the-recall-gap-for","slug":"just-read-twice-closing-the-recall-gap-for","title":"Just read twice: closing the recall gap for recurrent language models","date":"2024-07-07","arxiv_id":"2407.05483","n_code_links":1,"syntology":{"ran":3,"of":5,"n_ran_checked":3,"n_instrument":0,"unverified":2,"pointer_only":5,"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":["HazyResearch/prefix-linear-attention"],"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":null,"slug":"large-language-model-as-an-assignment","title":"Large Language Model as an Assignment Evaluator: Insights, Feedback, and Challenges in a 1000+ Student Course","date":"2024-07-07","arxiv_id":"2407.05216","n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-motion-blur-robust-vision","title":"Learning Motion Blur Robust Vision Transformers with Dynamic Early Exit for Real-Time UAV Tracking","date":"2024-07-07","arxiv_id":"2407.05383","n_code_links":0,"syntology":null},{"paper":null,"slug":"mamba-hawkes-process","title":"Mamba Hawkes Process","date":"2024-07-07","arxiv_id":"2407.05302","n_code_links":0,"syntology":null},{"paper":null,"slug":"mindecho-role-playing-language-agents-for-key","title":"MINDECHO: Role-Playing Language Agents for Key Opinion Leaders","date":"2024-07-07","arxiv_id":"2407.05305","n_code_links":0,"syntology":null},{"paper":"/paper/multimodal-prompt-learning-with-missing","slug":"multimodal-prompt-learning-with-missing","title":"Multimodal Prompt Learning with Missing Modalities for Sentiment Analysis and Emotion Recognition","date":"2024-07-07","arxiv_id":"2407.05374","n_code_links":1,"syntology":{"ran":2,"of":6,"n_ran_checked":2,"n_instrument":0,"unverified":4,"pointer_only":0,"phrase":"2 ran (of which 2 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) · 4 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","official":{"repos":["zrguo/MPLMM"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/ptarl-prototype-based-tabular-representation-1","slug":"ptarl-prototype-based-tabular-representation-1","title":"PTaRL: Prototype-based Tabular Representation Learning via Space Calibration","date":"2024-07-07","arxiv_id":"2407.05364","n_code_links":1,"syntology":{"ran":4,"of":7,"n_ran_checked":4,"n_instrument":0,"unverified":3,"pointer_only":1,"phrase":"4 ran (of which 3 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) · 3 unverified","official":null}},{"paper":"/paper/clipvqa-video-quality-assessment-via-clip","slug":"clipvqa-video-quality-assessment-via-clip","title":"CLIPVQA:Video Quality Assessment via CLIP","date":"2024-07-06","arxiv_id":"2407.04928","n_code_links":1,"syntology":null},{"paper":null,"slug":"eva-score-evaluation-of-long-form","title":"EVA-Score: Evaluating Abstractive Long-form Summarization on Informativeness through Extraction and Validation","date":"2024-07-06","arxiv_id":"2407.04969","n_code_links":0,"syntology":null},{"paper":"/paper/how-do-you-know-that-teaching-generative","slug":"how-do-you-know-that-teaching-generative","title":"How do you know that? Teaching Generative Language Models to Reference Answers to Biomedical Questions","date":"2024-07-06","arxiv_id":"2407.05015","n_code_links":1,"syntology":null},{"paper":null,"slug":"integer-only-quantized-transformers-for","title":"Integer-only Quantized Transformers for Embedded FPGA-based Time-series Forecasting in AIoT","date":"2024-07-06","arxiv_id":"2407.11041","n_code_links":0,"syntology":null},{"paper":"/paper/prance-joint-token-optimization-and","slug":"prance-joint-token-optimization-and","title":"PRANCE: Joint Token-Optimization and Structural Channel-Pruning for Adaptive ViT Inference","date":"2024-07-06","arxiv_id":"2407.05010","n_code_links":1,"syntology":null},{"paper":"/paper/solving-for-x-and-beyond-can-large-language","slug":"solving-for-x-and-beyond-can-large-language","title":"Solving for X and Beyond: Can Large Language Models Solve Complex Math Problems with More-Than-Two Unknowns?","date":"2024-07-06","arxiv_id":"2407.05134","n_code_links":1,"syntology":null},{"paper":null,"slug":"the-solution-for-the-aigc-inference","title":"The Solution for the AIGC Inference Performance Optimization Competition","date":"2024-07-06","arxiv_id":"2407.04991","n_code_links":0,"syntology":null}],"record_sha256":"22f3c4653bd87a6c7093a8d7faa962460aa8b98a01e3a1d1e17c07a5dffa70f0","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}