{"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/55","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":55,"pages_in_order":140,"rows_per_page":100,"rows":[5401,5500],"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/54","next":"/method/transformer/papers/56","papers":[{"paper":"/paper/llasmol-advancing-large-language-models-for","slug":"llasmol-advancing-large-language-models-for","title":"LlaSMol: Advancing Large Language Models for Chemistry with a Large-Scale, Comprehensive, High-Quality Instruction Tuning Dataset","date":"2024-02-14","arxiv_id":"2402.09391","n_code_links":1,"syntology":{"ran":8,"of":9,"n_ran_checked":8,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["osu-nlp-group/llm4chem"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/pyramid-attention-network-for-medical-image","slug":"pyramid-attention-network-for-medical-image","title":"Pyramid Attention Network for Medical Image Registration","date":"2024-02-14","arxiv_id":"2402.09016","n_code_links":1,"syntology":null},{"paper":null,"slug":"research-and-application-of-transformer-based","title":"Research and application of Transformer based anomaly detection model: A literature review","date":"2024-02-14","arxiv_id":"2402.08975","n_code_links":0,"syntology":null},{"paper":"/paper/scaling-the-authoring-of-autotutors-with","slug":"scaling-the-authoring-of-autotutors-with","title":"AutoTutor meets Large Language Models: A Language Model Tutor with Rich Pedagogy and Guardrails","date":"2024-02-14","arxiv_id":"2402.09216","n_code_links":1,"syntology":{"ran":4,"of":10,"n_ran_checked":4,"n_instrument":0,"unverified":6,"pointer_only":10,"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) · 6 unverified","official":{"repos":["eth-lre/mwptutor"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":6,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"stochastic-spiking-attention-accelerating","title":"Stochastic Spiking Attention: Accelerating Attention with Stochastic Computing in Spiking Networks","date":"2024-02-14","arxiv_id":"2402.09109","n_code_links":0,"syntology":null},{"paper":"/paper/tdvit-temporal-dilated-video-transformer-for","slug":"tdvit-temporal-dilated-video-transformer-for","title":"TDViT: Temporal Dilated Video Transformer for Dense Video Tasks","date":"2024-02-14","arxiv_id":"2402.09257","n_code_links":1,"syntology":null},{"paper":"/paper/towards-next-level-post-training-quantization","slug":"towards-next-level-post-training-quantization","title":"Towards Next-Level Post-Training Quantization of Hyper-Scale Transformers","date":"2024-02-14","arxiv_id":"2402.08958","n_code_links":0,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"pointer_only":3,"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":null}},{"paper":"/paper/bbox-adapter-lightweight-adapting-for-black","slug":"bbox-adapter-lightweight-adapting-for-black","title":"BBox-Adapter: Lightweight Adapting for Black-Box Large Language Models","date":"2024-02-13","arxiv_id":"2402.08219","n_code_links":1,"syntology":{"ran":5,"of":5,"n_ran_checked":5,"n_instrument":0,"unverified":0,"pointer_only":5,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["haotiansun14/bbox-adapter"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/befunet-a-hybrid-cnn-transformer-architecture","slug":"befunet-a-hybrid-cnn-transformer-architecture","title":"BEFUnet: A Hybrid CNN-Transformer Architecture for Precise Medical Image Segmentation","date":"2024-02-13","arxiv_id":"2402.08793","n_code_links":1,"syntology":null},{"paper":null,"slug":"combining-insights-from-multiple-large","title":"Combining Insights From Multiple Large Language Models Improves Diagnostic Accuracy","date":"2024-02-13","arxiv_id":"2402.08806","n_code_links":0,"syntology":null},{"paper":"/paper/ecellm-generalizing-large-language-models-for","slug":"ecellm-generalizing-large-language-models-for","title":"eCeLLM: Generalizing Large Language Models for E-commerce from Large-scale, High-quality Instruction Data","date":"2024-02-13","arxiv_id":"2402.08831","n_code_links":1,"syntology":{"ran":3,"of":5,"n_ran_checked":2,"n_instrument":1,"unverified":2,"pointer_only":5,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","official":{"repos":["ninglab/ecellm"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/instructgraph-boosting-large-language-models","slug":"instructgraph-boosting-large-language-models","title":"InstructGraph: Boosting Large Language Models via Graph-centric Instruction Tuning and Preference Alignment","date":"2024-02-13","arxiv_id":"2402.08785","n_code_links":1,"syntology":null},{"paper":"/paper/large-language-models-for-the-automated","slug":"large-language-models-for-the-automated","title":"Large Language Models for the Automated Analysis of Optimization Algorithms","date":"2024-02-13","arxiv_id":"2402.08472","n_code_links":1,"syntology":null},{"paper":"/paper/llaga-large-language-and-graph-assistant","slug":"llaga-large-language-and-graph-assistant","title":"LLaGA: Large Language and Graph Assistant","date":"2024-02-13","arxiv_id":"2402.08170","n_code_links":2,"syntology":{"ran":5,"of":7,"n_ran_checked":2,"n_instrument":3,"unverified":2,"pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","official":{"repos":["chenrunjin/llaga","vita-group/llaga"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"metatra-meta-learning-for-generalized","title":"MetaTra: Meta-Learning for Generalized Trajectory Prediction in Unseen Domain","date":"2024-02-13","arxiv_id":"2402.08221","n_code_links":0,"syntology":null},{"paper":null,"slug":"on-limitations-of-the-transformer","title":"On Limitations of the Transformer Architecture","date":"2024-02-13","arxiv_id":"2402.08164","n_code_links":0,"syntology":null},{"paper":"/paper/optimized-information-flow-for-transformer","slug":"optimized-information-flow-for-transformer","title":"Optimized Information Flow for Transformer Tracking","date":"2024-02-13","arxiv_id":"2402.08195","n_code_links":1,"syntology":null},{"paper":"/paper/prompt-optimization-in-multi-step-tasks","slug":"prompt-optimization-in-multi-step-tasks","title":"PRompt Optimization in Multi-Step Tasks (PROMST): Integrating Human Feedback and Heuristic-based Sampling","date":"2024-02-13","arxiv_id":"2402.08702","n_code_links":1,"syntology":{"ran":9,"of":12,"n_ran_checked":9,"n_instrument":0,"unverified":3,"pointer_only":0,"phrase":"9 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; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["yongchao98/promst"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"the-last-jitai-the-unreasonable-effectiveness","title":"The Last JITAI? Exploring Large Language Models for Issuing Just-in-Time Adaptive Interventions: Fostering Physical Activity in a Conceptual Cardiac Rehabilitation Setting","date":"2024-02-13","arxiv_id":"2402.08658","n_code_links":0,"syntology":null},{"paper":null,"slug":"transformer-mechanisms-mimic-frontostriatal","title":"Transformer Mechanisms Mimic Frontostriatal Gating Operations When Trained on Human Working Memory Tasks","date":"2024-02-13","arxiv_id":"2402.08211","n_code_links":0,"syntology":null},{"paper":"/paper/translating-images-to-road-network-a-non-1","slug":"translating-images-to-road-network-a-non-1","title":"Translating Images to Road Network: A Sequence-to-Sequence Perspective","date":"2024-02-13","arxiv_id":"2402.08207","n_code_links":3,"syntology":null},{"paper":"/paper/addressing-cognitive-bias-in-medical-language","slug":"addressing-cognitive-bias-in-medical-language","title":"Addressing cognitive bias in medical language models","date":"2024-02-12","arxiv_id":"2402.08113","n_code_links":1,"syntology":{"ran":5,"of":6,"n_ran_checked":5,"n_instrument":0,"unverified":1,"pointer_only":6,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["carlwharris/cog-bias-med-llms"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/air-bench-benchmarking-large-audio-language","slug":"air-bench-benchmarking-large-audio-language","title":"AIR-Bench: Benchmarking Large Audio-Language Models via Generative Comprehension","date":"2024-02-12","arxiv_id":"2402.07729","n_code_links":1,"syntology":null},{"paper":"/paper/aydiv-adaptable-yielding-3d-object-detection","slug":"aydiv-adaptable-yielding-3d-object-detection","title":"AYDIV: Adaptable Yielding 3D Object Detection via Integrated Contextual Vision Transformer","date":"2024-02-12","arxiv_id":"2402.07680","n_code_links":1,"syntology":null},{"paper":null,"slug":"base-tts-lessons-from-building-a-billion","title":"BASE TTS: Lessons from building a billion-parameter Text-to-Speech model on 100K hours of data","date":"2024-02-12","arxiv_id":"2402.08093","n_code_links":0,"syntology":null},{"paper":"/paper/clustertabnet-supervised-clustering-method","slug":"clustertabnet-supervised-clustering-method","title":"ClusterTabNet: Supervised clustering method for table detection and table structure recognition","date":"2024-02-12","arxiv_id":"2402.07502","n_code_links":1,"syntology":{"ran":16,"of":16,"n_ran_checked":13,"n_instrument":3,"unverified":0,"pointer_only":4,"phrase":"16 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 1 honoured, 0 violated, 12 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["sap-samples/clustertabnet"],"state":"official (archive's flag): 16 ran","n_ran":16,"n_constructed":0,"n_ran_no_instrument_failure":13,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/dolares-or-dollars-unraveling-the-bilingual","slug":"dolares-or-dollars-unraveling-the-bilingual","title":"Dólares or Dollars? Unraveling the Bilingual Prowess of Financial LLMs Between Spanish and English","date":"2024-02-12","arxiv_id":"2402.07405","n_code_links":1,"syntology":null},{"paper":null,"slug":"enhancing-multi-criteria-decision-analysis","title":"Enhancing Multi-Criteria Decision Analysis with AI: Integrating Analytic Hierarchy Process and GPT-4 for Automated Decision Support","date":"2024-02-12","arxiv_id":"2402.07404","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancing-programming-error-messages-in-real","title":"Enhancing Programming Error Messages in Real Time with Generative AI","date":"2024-02-12","arxiv_id":"2402.08072","n_code_links":0,"syntology":null},{"paper":null,"slug":"fourier-circuits-in-neural-networks-unlocking","title":"Fourier Circuits in Neural Networks and Transformers: A Case Study of Modular Arithmetic with Multiple Inputs","date":"2024-02-12","arxiv_id":"2402.09469","n_code_links":0,"syntology":null},{"paper":null,"slug":"large-language-models-ad-referendum-how-good","title":"Large Language Models \"Ad Referendum\": How Good Are They at Machine Translation in the Legal Domain?","date":"2024-02-12","arxiv_id":"2402.07681","n_code_links":0,"syntology":null},{"paper":"/paper/large-language-models-are-few-shot-generators","slug":"large-language-models-are-few-shot-generators","title":"Large Language Models are Few-shot Generators: Proposing Hybrid Prompt Algorithm To Generate Webshell Escape Samples","date":"2024-02-12","arxiv_id":"2402.07408","n_code_links":1,"syntology":null},{"paper":null,"slug":"leveraging-ai-to-advance-science-and","title":"Leveraging AI to Advance Science and Computing Education across Africa: Challenges, Progress and Opportunities","date":"2024-02-12","arxiv_id":"2402.07397","n_code_links":0,"syntology":null},{"paper":null,"slug":"message-detouring-a-simple-yet-effective","title":"Message Detouring: A Simple Yet Effective Cycle Representation for Expressive Graph Learning","date":"2024-02-12","arxiv_id":"2402.08085","n_code_links":0,"syntology":null},{"paper":null,"slug":"on-the-self-verification-limitations-of-large","title":"On the Self-Verification Limitations of Large Language Models on Reasoning and Planning Tasks","date":"2024-02-12","arxiv_id":"2402.08115","n_code_links":0,"syntology":null},{"paper":"/paper/only-the-curve-shape-matters-training","slug":"only-the-curve-shape-matters-training","title":"Only the Curve Shape Matters: Training Foundation Models for Zero-Shot Multivariate Time Series Forecasting through Next Curve Shape Prediction","date":"2024-02-12","arxiv_id":"2402.07570","n_code_links":0,"syntology":null},{"paper":null,"slug":"secret-collusion-among-generative-ai-agents","title":"Secret Collusion among Generative AI Agents: Multi-Agent Deception via Steganography","date":"2024-02-12","arxiv_id":"2402.07510","n_code_links":0,"syntology":null},{"paper":"/paper/sheet-music-transformer-end-to-end-optical","slug":"sheet-music-transformer-end-to-end-optical","title":"Sheet Music Transformer: End-To-End Optical Music Recognition Beyond Monophonic Transcription","date":"2024-02-12","arxiv_id":"2402.07596","n_code_links":1,"syntology":null},{"paper":null,"slug":"suppressing-pink-elephants-with-direct","title":"Suppressing Pink Elephants with Direct Principle Feedback","date":"2024-02-12","arxiv_id":"2402.07896","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-i-o-complexity-of-attention-or-how","title":"The I/O Complexity of Attention, or How Optimal is Flash Attention?","date":"2024-02-12","arxiv_id":"2402.07443","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-an-understanding-of-stepwise","title":"Towards an Understanding of Stepwise Inference in Transformers: A Synthetic Graph Navigation Model","date":"2024-02-12","arxiv_id":"2402.07757","n_code_links":0,"syntology":null},{"paper":null,"slug":"transaxx-efficient-transformers-with","title":"TransAxx: Efficient Transformers with Approximate Computing","date":"2024-02-12","arxiv_id":"2402.07545","n_code_links":0,"syntology":null},{"paper":"/paper/vcr-video-representation-for-contextual","slug":"vcr-video-representation-for-contextual","title":"VCR: Video representation for Contextual Retrieval","date":"2024-02-12","arxiv_id":"2402.07466","n_code_links":1,"syntology":null},{"paper":null,"slug":"how-do-large-language-models-navigate","title":"How do Large Language Models Navigate Conflicts between Honesty and Helpfulness?","date":"2024-02-11","arxiv_id":"2402.07282","n_code_links":0,"syntology":null},{"paper":null,"slug":"large-language-model-empowered-dose-volume","title":"Large-Language-Model Empowered Dose Volume Histogram Prediction for Intensity Modulated Radiotherapy","date":"2024-02-11","arxiv_id":"2402.07167","n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-modal-emotion-recognition-by-text","title":"Multi-Modal Emotion Recognition by Text, Speech and Video Using Pretrained Transformers","date":"2024-02-11","arxiv_id":"2402.07327","n_code_links":0,"syntology":null},{"paper":null,"slug":"natural-language-reinforcement-learning","title":"Natural Language Reinforcement Learning","date":"2024-02-11","arxiv_id":"2402.07157","n_code_links":0,"syntology":null},{"paper":"/paper/semi-mamba-unet-pixel-level-contrastive-cross","slug":"semi-mamba-unet-pixel-level-contrastive-cross","title":"Semi-Mamba-UNet: Pixel-Level Contrastive and Pixel-Level Cross-Supervised Visual Mamba-based UNet for Semi-Supervised Medical Image Segmentation","date":"2024-02-11","arxiv_id":"2402.07245","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":1,"n_instrument":2,"unverified":0,"pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["ziyangwang007/mamba-unet"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/chemllm-a-chemical-large-language-model","slug":"chemllm-a-chemical-large-language-model","title":"ChemLLM: A Chemical Large Language Model","date":"2024-02-10","arxiv_id":"2402.06852","n_code_links":1,"syntology":null},{"paper":"/paper/gemini-goes-to-med-school-exploring-the","slug":"gemini-goes-to-med-school-exploring-the","title":"Gemini Goes to Med School: Exploring the Capabilities of Multimodal Large Language Models on Medical Challenge Problems & Hallucinations","date":"2024-02-10","arxiv_id":"2402.07023","n_code_links":1,"syntology":null},{"paper":null,"slug":"nlp-for-knowledge-discovery-and-information","title":"NLP for Knowledge Discovery and Information Extraction from Energetics Corpora","date":"2024-02-10","arxiv_id":"2402.06964","n_code_links":0,"syntology":null},{"paper":"/paper/openfedllm-training-large-language-models-on","slug":"openfedllm-training-large-language-models-on","title":"OpenFedLLM: Training Large Language Models on Decentralized Private Data via Federated Learning","date":"2024-02-10","arxiv_id":"2402.06954","n_code_links":3,"syntology":null},{"paper":"/paper/urbankgent-a-unified-large-language-model","slug":"urbankgent-a-unified-large-language-model","title":"UrbanKGent: A Unified Large Language Model Agent Framework for Urban Knowledge Graph Construction","date":"2024-02-10","arxiv_id":"2402.06861","n_code_links":1,"syntology":{"ran":3,"of":5,"n_ran_checked":1,"n_instrument":2,"unverified":2,"pointer_only":5,"phrase":"3 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","official":{"repos":["usail-hkust/urbankgent"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"ai-enhanced-data-assimilation-and-uncertainty","title":"AI enhanced data assimilation and uncertainty quantification applied to Geological Carbon Storage","date":"2024-02-09","arxiv_id":"2402.06110","n_code_links":0,"syntology":null},{"paper":"/paper/bryndza-at-climateactivism-2024-stance-target","slug":"bryndza-at-climateactivism-2024-stance-target","title":"Bryndza at ClimateActivism 2024: Stance, Target and Hate Event Detection via Retrieval-Augmented GPT-4 and LLaMA","date":"2024-02-09","arxiv_id":"2402.06549","n_code_links":2,"syntology":null},{"paper":"/paper/culturellm-incorporating-cultural-differences","slug":"culturellm-incorporating-cultural-differences","title":"CultureLLM: Incorporating Cultural Differences into Large Language Models","date":"2024-02-09","arxiv_id":"2402.10946","n_code_links":2,"syntology":{"ran":3,"of":3,"n_ran_checked":2,"n_instrument":1,"unverified":0,"pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["scarelette/culturellm"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"curveformer-3d-lane-detection-by-curve-1","title":"CurveFormer++: 3D Lane Detection by Curve Propagation with Temporal Curve Queries and Attention","date":"2024-02-09","arxiv_id":"2402.06423","n_code_links":0,"syntology":null},{"paper":"/paper/inducing-systematicity-in-transformers-by","slug":"inducing-systematicity-in-transformers-by","title":"Inducing Systematicity in Transformers by Attending to Structurally Quantized Embeddings","date":"2024-02-09","arxiv_id":"2402.06492","n_code_links":1,"syntology":null},{"paper":null,"slug":"jointly-learning-representations-for-map","title":"Jointly Learning Representations for Map Entities via Heterogeneous Graph Contrastive Learning","date":"2024-02-09","arxiv_id":"2402.06135","n_code_links":0,"syntology":null},{"paper":null,"slug":"llava-docent-instruction-tuning-with","title":"LLaVA-Docent: Instruction Tuning with Multimodal Large Language Model to Support Art Appreciation Education","date":"2024-02-09","arxiv_id":"2402.06264","n_code_links":0,"syntology":null},{"paper":null,"slug":"masked-logonet-fast-and-accurate-3d-image","title":"Masked LoGoNet: Fast and Accurate 3D Image Analysis for Medical Domain","date":"2024-02-09","arxiv_id":"2402.06190","n_code_links":0,"syntology":null},{"paper":"/paper/rarebench-can-llms-serve-as-rare-diseases","slug":"rarebench-can-llms-serve-as-rare-diseases","title":"RareBench: Can LLMs Serve as Rare Diseases Specialists?","date":"2024-02-09","arxiv_id":"2402.06341","n_code_links":1,"syntology":null},{"paper":"/paper/resumeflow-an-llm-facilitated-pipeline-for","slug":"resumeflow-an-llm-facilitated-pipeline-for","title":"ResumeFlow: An LLM-facilitated Pipeline for Personalized Resume Generation and Refinement","date":"2024-02-09","arxiv_id":"2402.06221","n_code_links":1,"syntology":{"ran":5,"of":9,"n_ran_checked":5,"n_instrument":0,"unverified":4,"pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","official":{"repos":["Ztrimus/job-llm"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/a-prompt-response-to-the-demand-for-automatic","slug":"a-prompt-response-to-the-demand-for-automatic","title":"A Prompt Response to the Demand for Automatic Gender-Neutral Translation","date":"2024-02-08","arxiv_id":"2402.06041","n_code_links":1,"syntology":null},{"paper":null,"slug":"ai4fapar-how-artificial-intelligence-can-help","title":"Ai4Fapar: How artificial intelligence can help to forecast the seasonal earth observation signal","date":"2024-02-08","arxiv_id":"2402.06684","n_code_links":0,"syntology":null},{"paper":"/paper/attnlrp-attention-aware-layer-wise-relevance","slug":"attnlrp-attention-aware-layer-wise-relevance","title":"AttnLRP: Attention-Aware Layer-Wise Relevance Propagation for Transformers","date":"2024-02-08","arxiv_id":"2402.05602","n_code_links":2,"syntology":null},{"paper":"/paper/diffspeaker-speech-driven-3d-facial-animation","slug":"diffspeaker-speech-driven-3d-facial-animation","title":"DiffSpeaker: Speech-Driven 3D Facial Animation with Diffusion Transformer","date":"2024-02-08","arxiv_id":"2402.05712","n_code_links":1,"syntology":null},{"paper":null,"slug":"gpt-4-generated-narratives-of-life-events","title":"GPT-4 Generated Narratives of Life Events using a Structured Narrative Prompt: A Validation Study","date":"2024-02-08","arxiv_id":"2402.05435","n_code_links":0,"syntology":null},{"paper":null,"slug":"guiding-large-language-models-with-divide-and","title":"An Examination on the Effectiveness of Divide-and-Conquer Prompting in Large Language Models","date":"2024-02-08","arxiv_id":"2402.05359","n_code_links":0,"syntology":null},{"paper":"/paper/how-do-transformers-perform-in-context","slug":"how-do-transformers-perform-in-context","title":"How do Transformers perform In-Context Autoregressive Learning?","date":"2024-02-08","arxiv_id":"2402.05787","n_code_links":0,"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":null}},{"paper":"/paper/how-well-can-llms-negotiate-negotiationarena","slug":"how-well-can-llms-negotiate-negotiationarena","title":"How Well Can LLMs Negotiate? NegotiationArena Platform and Analysis","date":"2024-02-08","arxiv_id":"2402.05863","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":2,"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":["vinid/negotiationarena"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/in-context-principle-learning-from-mistakes","slug":"in-context-principle-learning-from-mistakes","title":"In-Context Principle Learning from Mistakes","date":"2024-02-08","arxiv_id":"2402.05403","n_code_links":1,"syntology":null},{"paper":null,"slug":"large-language-model-meets-graph-neural","title":"Large Language Model Meets Graph Neural Network in Knowledge Distillation","date":"2024-02-08","arxiv_id":"2402.05894","n_code_links":0,"syntology":null},{"paper":null,"slug":"large-language-models-for-psycholinguistic","title":"Large Language Models for Psycholinguistic Plausibility Pretesting","date":"2024-02-08","arxiv_id":"2402.05455","n_code_links":0,"syntology":null},{"paper":"/paper/limits-of-transformer-language-models-on","slug":"limits-of-transformer-language-models-on","title":"Limits of Transformer Language Models on Learning to Compose Algorithms","date":"2024-02-08","arxiv_id":"2402.05785","n_code_links":1,"syntology":{"ran":3,"of":8,"n_ran_checked":3,"n_instrument":0,"unverified":5,"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) · 5 unverified","official":{"repos":["ibm/limitations-lm-algorithmic-compositional-learning"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"llms-among-us-generative-ai-participating-in","title":"LLMs Among Us: Generative AI Participating in Digital Discourse","date":"2024-02-08","arxiv_id":"2402.07940","n_code_links":0,"syntology":null},{"paper":"/paper/mamba-nd-selective-state-space-modeling-for","slug":"mamba-nd-selective-state-space-modeling-for","title":"Mamba-ND: Selective State Space Modeling for Multi-Dimensional Data","date":"2024-02-08","arxiv_id":"2402.05892","n_code_links":1,"syntology":{"ran":9,"of":11,"n_ran_checked":9,"n_instrument":0,"unverified":2,"pointer_only":11,"phrase":"9 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; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["jacklishufan/mamba-nd"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/noise-contrastive-alignment-of-language","slug":"noise-contrastive-alignment-of-language","title":"Noise Contrastive Alignment of Language Models with Explicit Rewards","date":"2024-02-08","arxiv_id":"2402.05369","n_code_links":3,"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":["thu-ml/noise-contrastive-alignment"],"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":"on-convolutional-vision-transformers-for","title":"On Convolutional Vision Transformers for Yield Prediction","date":"2024-02-08","arxiv_id":"2402.05557","n_code_links":0,"syntology":null},{"paper":null,"slug":"question-aware-vision-transformer-for","title":"Question Aware Vision Transformer for Multimodal Reasoning","date":"2024-02-08","arxiv_id":"2402.05472","n_code_links":0,"syntology":null},{"paper":null,"slug":"self-alignment-of-large-language-models-via","title":"Self-Alignment of Large Language Models via Monopolylogue-based Social Scene Simulation","date":"2024-02-08","arxiv_id":"2402.05699","n_code_links":0,"syntology":null},{"paper":null,"slug":"sparse-vq-transformer-an-ffn-free-framework","title":"Sparse-VQ Transformer: An FFN-Free Framework with Vector Quantization for Enhanced Time Series Forecasting","date":"2024-02-08","arxiv_id":"2402.05830","n_code_links":0,"syntology":null},{"paper":null,"slug":"timearena-shaping-efficient-multitasking","title":"TimeArena: Shaping Efficient Multitasking Language Agents in a Time-Aware Simulation","date":"2024-02-08","arxiv_id":"2402.05733","n_code_links":0,"syntology":null},{"paper":null,"slug":"unleashing-the-infinity-power-of-geometry-a","title":"Unleashing the Infinity Power of Geometry: A Novel Geometry-Aware Transformer (GOAT) for Whole Slide Histopathology Image Analysis","date":"2024-02-08","arxiv_id":"2402.05373","n_code_links":0,"syntology":null},{"paper":"/paper/you-only-need-one-color-space-an-efficient","slug":"you-only-need-one-color-space-an-efficient","title":"You Only Need One Color Space: An Efficient Network for Low-light Image Enhancement","date":"2024-02-08","arxiv_id":"2402.05809","n_code_links":1,"syntology":null},{"paper":null,"slug":"zero-shot-chain-of-thought-reasoning-guided","title":"Zero-Shot Chain-of-Thought Reasoning Guided by Evolutionary Algorithms in Large Language Models","date":"2024-02-08","arxiv_id":"2402.05376","n_code_links":0,"syntology":null},{"paper":"/paper/can-large-language-model-agents-simulate","slug":"can-large-language-model-agents-simulate","title":"Can Large Language Model Agents Simulate Human Trust Behavior?","date":"2024-02-07","arxiv_id":"2402.04559","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":1,"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":["camel-ai/agent-trust"],"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":"chatbots-in-knowledge-intensive-contexts","title":"Conversational Assistants in Knowledge-Intensive Contexts: An Evaluation of LLM- versus Intent-based Systems","date":"2024-02-07","arxiv_id":"2402.04955","n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-cross-domain-low-resource-text","title":"Improving Cross-Domain Low-Resource Text Generation through LLM Post-Editing: A Programmer-Interpreter Approach","date":"2024-02-07","arxiv_id":"2402.04609","n_code_links":0,"syntology":null},{"paper":"/paper/latent-plan-transformer-planning-as-latent","slug":"latent-plan-transformer-planning-as-latent","title":"Latent Plan Transformer for Trajectory Abstraction: Planning as Latent Space Inference","date":"2024-02-07","arxiv_id":"2402.04647","n_code_links":1,"syntology":{"ran":6,"of":6,"n_ran_checked":4,"n_instrument":2,"unverified":0,"pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 2 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["mingluzhao/latent-plan-transformer"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/long-is-more-for-alignment-a-simple-but-tough","slug":"long-is-more-for-alignment-a-simple-but-tough","title":"Long Is More for Alignment: A Simple but Tough-to-Beat Baseline for Instruction Fine-Tuning","date":"2024-02-07","arxiv_id":"2402.04833","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":1,"n_instrument":1,"unverified":0,"pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["tml-epfl/long-is-more-for-alignment"],"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","unlocated"]}}},{"paper":null,"slug":"navigating-the-knowledge-sea-planet-scale","title":"Navigating the Knowledge Sea: Planet-scale answer retrieval using LLMs","date":"2024-02-07","arxiv_id":"2402.05318","n_code_links":0,"syntology":null},{"paper":"/paper/opening-the-ai-black-box-program-synthesis","slug":"opening-the-ai-black-box-program-synthesis","title":"Opening the AI black box: program synthesis via mechanistic interpretability","date":"2024-02-07","arxiv_id":"2402.05110","n_code_links":1,"syntology":{"ran":3,"of":4,"n_ran_checked":3,"n_instrument":0,"unverified":1,"pointer_only":4,"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) · 1 unverified","official":{"repos":["ejmichaud/neural-verification"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"simulated-overparameterization","title":"Majority Kernels: An Approach to Leverage Big Model Dynamics for Efficient Small Model Training","date":"2024-02-07","arxiv_id":"2402.05033","n_code_links":0,"syntology":null},{"paper":null,"slug":"stablemask-refining-causal-masking-in-decoder","title":"StableMask: Refining Causal Masking in Decoder-only Transformer","date":"2024-02-07","arxiv_id":"2402.04779","n_code_links":0,"syntology":null},{"paper":null,"slug":"toward-accurate-camera-based-3d-object","title":"Toward Accurate Camera-based 3D Object Detection via Cascade Depth Estimation and Calibration","date":"2024-02-07","arxiv_id":"2402.04883","n_code_links":0,"syntology":null},{"paper":"/paper/transllama-llm-based-simultaneous-translation","slug":"transllama-llm-based-simultaneous-translation","title":"TransLLaMa: LLM-based Simultaneous Translation System","date":"2024-02-07","arxiv_id":"2402.04636","n_code_links":1,"syntology":null},{"paper":"/paper/triplet-interaction-improves-graph","slug":"triplet-interaction-improves-graph","title":"Triplet Interaction Improves Graph Transformers: Accurate Molecular Graph Learning with Triplet Graph Transformers","date":"2024-02-07","arxiv_id":"2402.04538","n_code_links":3,"syntology":{"ran":10,"of":13,"n_ran_checked":10,"n_instrument":0,"unverified":3,"pointer_only":0,"phrase":"10 ran (of which 1 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) · 3 unverified","official":{"repos":["shamim-hussain/tgt"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":2,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/anytool-self-reflective-hierarchical-agents","slug":"anytool-self-reflective-hierarchical-agents","title":"AnyTool: Self-Reflective, Hierarchical Agents for Large-Scale API Calls","date":"2024-02-06","arxiv_id":"2402.04253","n_code_links":1,"syntology":{"ran":4,"of":6,"n_ran_checked":4,"n_instrument":0,"unverified":2,"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) · 2 unverified","official":{"repos":["dyabel/anytool"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"behind-the-screen-investigating-chatgpt-s","title":"Behind the Screen: Investigating ChatGPT's Dark Personality Traits and Conspiracy Beliefs","date":"2024-02-06","arxiv_id":"2402.04110","n_code_links":0,"syntology":null}],"record_sha256":"fac14d5879656f56eaff73acf6c4fc3c4cdd7f055b2ea509dc413605f4ab4592","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}