{"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/56","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":56,"pages_in_order":140,"rows_per_page":100,"rows":[5501,5600],"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/55","next":"/method/transformer/papers/57","papers":[{"paper":null,"slug":"breaking-symmetry-when-training-transformers","title":"Breaking Symmetry When Training Transformers","date":"2024-02-06","arxiv_id":"2402.05969","n_code_links":0,"syntology":null},{"paper":"/paper/can-mamba-learn-how-to-learn-a-comparative","slug":"can-mamba-learn-how-to-learn-a-comparative","title":"Can Mamba Learn How to Learn? A Comparative Study on In-Context Learning Tasks","date":"2024-02-06","arxiv_id":"2402.04248","n_code_links":2,"syntology":{"ran":11,"of":14,"n_ran_checked":9,"n_instrument":2,"unverified":3,"pointer_only":0,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 1 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","official":{"repos":["krafton-ai/mambaformer-icl"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"cast-clustering-self-attention-using","title":"CAST: Clustering Self-Attention using Surrogate Tokens for Efficient Transformers","date":"2024-02-06","arxiv_id":"2402.04239","n_code_links":0,"syntology":null},{"paper":null,"slug":"comparing-abstraction-in-humans-and-large","title":"Comparing Abstraction in Humans and Large Language Models Using Multimodal Serial Reproduction","date":"2024-02-06","arxiv_id":"2402.03618","n_code_links":0,"syntology":null},{"paper":null,"slug":"detection-transformer-for-teeth-detection","title":"Detection Transformer for Teeth Detection, Segmentation, and Numbering in Oral Rare Diseases: Focus on Data Augmentation and Inpainting Techniques","date":"2024-02-06","arxiv_id":"2402.04408","n_code_links":0,"syntology":null},{"paper":null,"slug":"endmember-extraction-algorithms-fusing-for","title":"Transformer based Endmember Fusion with Spatial Context for Hyperspectral Unmixing","date":"2024-02-06","arxiv_id":"2402.03835","n_code_links":0,"syntology":null},{"paper":"/paper/identifying-reasons-for-contraceptive","slug":"identifying-reasons-for-contraceptive","title":"Identifying Reasons for Contraceptive Switching from Real-World Data Using Large Language Models","date":"2024-02-06","arxiv_id":"2402.03597","n_code_links":1,"syntology":null},{"paper":null,"slug":"iterative-prompt-refinement-for-radiation","title":"Iterative Prompt Refinement for Radiation Oncology Symptom Extraction Using Teacher-Student Large Language Models","date":"2024-02-06","arxiv_id":"2402.04075","n_code_links":0,"syntology":null},{"paper":null,"slug":"large-language-models-as-moocs-graders","title":"Large Language Models As MOOCs Graders","date":"2024-02-06","arxiv_id":"2402.03776","n_code_links":0,"syntology":null},{"paper":null,"slug":"leak-cheat-repeat-data-contamination-and","title":"Leak, Cheat, Repeat: Data Contamination and Evaluation Malpractices in Closed-Source LLMs","date":"2024-02-06","arxiv_id":"2402.03927","n_code_links":0,"syntology":null},{"paper":null,"slug":"lens-a-foundation-model-for-network-traffic","title":"Lens: A Foundation Model for Network Traffic","date":"2024-02-06","arxiv_id":"2402.03646","n_code_links":0,"syntology":null},{"paper":null,"slug":"llm-agents-can-autonomously-hack-websites","title":"LLM Agents can Autonomously Hack Websites","date":"2024-02-06","arxiv_id":"2402.06664","n_code_links":0,"syntology":null},{"paper":null,"slug":"minds-versus-machines-rethinking-entailment","title":"Are Machines Better at Complex Reasoning? Unveiling Human-Machine Inference Gaps in Entailment Verification","date":"2024-02-06","arxiv_id":"2402.03686","n_code_links":0,"syntology":null},{"paper":"/paper/parameter-tuning-free-data-entry-error-1","slug":"parameter-tuning-free-data-entry-error-1","title":"Parameter-tuning-free data entry error unlearning with adaptive selective synaptic dampening","date":"2024-02-06","arxiv_id":"2402.10098","n_code_links":1,"syntology":null},{"paper":"/paper/pard-permutation-invariant-autoregressive","slug":"pard-permutation-invariant-autoregressive","title":"Pard: Permutation-Invariant Autoregressive Diffusion for Graph Generation","date":"2024-02-06","arxiv_id":"2402.03687","n_code_links":1,"syntology":null},{"paper":"/paper/pre-training-of-lightweight-vision","slug":"pre-training-of-lightweight-vision","title":"Pre-training of Lightweight Vision Transformers on Small Datasets with Minimally Scaled Images","date":"2024-02-06","arxiv_id":"2402.03752","n_code_links":0,"syntology":null},{"paper":null,"slug":"professional-agents-evolving-large-language","title":"Professional Agents -- Evolving Large Language Models into Autonomous Experts with Human-Level Competencies","date":"2024-02-06","arxiv_id":"2402.03628","n_code_links":0,"syntology":null},{"paper":null,"slug":"reinforcement-learning-from-bagged-reward-a","title":"Reinforcement Learning from Bagged Reward","date":"2024-02-06","arxiv_id":"2402.03771","n_code_links":0,"syntology":null},{"paper":null,"slug":"return-aligned-decision-transformer","title":"Return-Aligned Decision Transformer","date":"2024-02-06","arxiv_id":"2402.03923","n_code_links":0,"syntology":null},{"paper":"/paper/self-discover-large-language-models-self","slug":"self-discover-large-language-models-self","title":"Self-Discover: Large Language Models Self-Compose Reasoning Structures","date":"2024-02-06","arxiv_id":"2402.03620","n_code_links":3,"syntology":{"ran":0,"of":3,"n_ran_checked":0,"n_instrument":0,"unverified":3,"pointer_only":0,"phrase":"0 ran · 3 unverified","official":null}},{"paper":null,"slug":"texttt-nercc-nested-regression-coded","title":"NeRCC: Nested-Regression Coded Computing for Resilient Distributed Prediction Serving Systems","date":"2024-02-06","arxiv_id":"2402.04377","n_code_links":0,"syntology":null},{"paper":"/paper/the-hedgehog-the-porcupine-expressive-linear","slug":"the-hedgehog-the-porcupine-expressive-linear","title":"The Hedgehog & the Porcupine: Expressive Linear Attentions with Softmax Mimicry","date":"2024-02-06","arxiv_id":"2402.04347","n_code_links":1,"syntology":null},{"paper":"/paper/u-shaped-vision-mamba-for-single-image","slug":"u-shaped-vision-mamba-for-single-image","title":"U-shaped Vision Mamba for Single Image Dehazing","date":"2024-02-06","arxiv_id":"2402.04139","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-survey-on-transformer-compression","title":"A Survey on Transformer Compression","date":"2024-02-05","arxiv_id":"2402.05964","n_code_links":0,"syntology":null},{"paper":"/paper/conversation-reconstruction-attack-against","slug":"conversation-reconstruction-attack-against","title":"Reconstruct Your Previous Conversations! Comprehensively Investigating Privacy Leakage Risks in Conversations with GPT Models","date":"2024-02-05","arxiv_id":"2402.02987","n_code_links":1,"syntology":null},{"paper":"/paper/cross-domain-few-shot-object-detection-via","slug":"cross-domain-few-shot-object-detection-via","title":"Cross-Domain Few-Shot Object Detection via Enhanced Open-Set Object Detector","date":"2024-02-05","arxiv_id":"2402.03094","n_code_links":2,"syntology":{"ran":9,"of":11,"n_ran_checked":9,"n_instrument":0,"unverified":2,"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) · 2 unverified","official":{"repos":["lovelyqian/CDFSOD-benchmark"],"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/deepseekmath-pushing-the-limits-of","slug":"deepseekmath-pushing-the-limits-of","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","date":"2024-02-05","arxiv_id":"2402.03300","n_code_links":5,"syntology":{"ran":14,"of":24,"n_ran_checked":10,"n_instrument":4,"unverified":10,"pointer_only":3,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 4 where Syntology's instrument failed) · 10 unverified","official":{"repos":["deepseek-ai/deepseek-math"],"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":["listed","official"]}}},{"paper":null,"slug":"diffsformer-a-diffusion-transformer-on-stock","title":"DiffsFormer: A Diffusion Transformer on Stock Factor Augmentation","date":"2024-02-05","arxiv_id":"2402.06656","n_code_links":0,"syntology":null},{"paper":"/paper/graph-enhanced-large-language-models-in","slug":"graph-enhanced-large-language-models-in","title":"Graph-enhanced Large Language Models in Asynchronous Plan Reasoning","date":"2024-02-05","arxiv_id":"2402.02805","n_code_links":1,"syntology":{"ran":6,"of":7,"n_ran_checked":0,"n_instrument":6,"unverified":1,"pointer_only":0,"phrase":"6 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; 6 where Syntology's instrument failed) · 1 unverified","official":{"repos":["fangru-lin/graph-llm-asynchow-plan"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"hamlet-graph-transformer-neural-operator-for","title":"HAMLET: Graph Transformer Neural Operator for Partial Differential Equations","date":"2024-02-05","arxiv_id":"2402.03541","n_code_links":0,"syntology":null},{"paper":null,"slug":"harnessing-pubmed-user-query-logs-for-post","title":"Harnessing PubMed User Query Logs for Post Hoc Explanations of Recommended Similar Articles","date":"2024-02-05","arxiv_id":"2402.03484","n_code_links":0,"syntology":null},{"paper":null,"slug":"illuminate-a-novel-approach-for-depression","title":"Illuminate: A novel approach for depression detection with explainable analysis and proactive therapy using prompt engineering","date":"2024-02-05","arxiv_id":"2402.05127","n_code_links":0,"syntology":null},{"paper":"/paper/is-mamba-capable-of-in-context-learning","slug":"is-mamba-capable-of-in-context-learning","title":"Is Mamba Capable of In-Context Learning?","date":"2024-02-05","arxiv_id":"2402.03170","n_code_links":1,"syntology":{"ran":7,"of":8,"n_ran_checked":6,"n_instrument":1,"unverified":1,"pointer_only":8,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["automl/is_mamba_capable_of_icl"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"mobilitygpt-enhanced-human-mobility-modeling","title":"MobilityGPT: Enhanced Human Mobility Modeling with a GPT model","date":"2024-02-05","arxiv_id":"2402.03264","n_code_links":0,"syntology":null},{"paper":"/paper/swag-storytelling-with-action-guidance","slug":"swag-storytelling-with-action-guidance","title":"SWAG: Storytelling With Action Guidance","date":"2024-02-05","arxiv_id":"2402.03483","n_code_links":1,"syntology":null},{"paper":null,"slug":"toward-human-ai-alignment-in-large-scale","title":"Toward Human-AI Alignment in Large-Scale Multi-Player Games","date":"2024-02-05","arxiv_id":"2402.03575","n_code_links":0,"syntology":null},{"paper":"/paper/unimem-towards-a-unified-view-of-long-context","slug":"unimem-towards-a-unified-view-of-long-context","title":"UniMem: Towards a Unified View of Long-Context Large Language Models","date":"2024-02-05","arxiv_id":"2402.03009","n_code_links":1,"syntology":null},{"paper":null,"slug":"aligner-achieving-efficient-alignment-through","title":"Aligner: Efficient Alignment by Learning to Correct","date":"2024-02-04","arxiv_id":"2402.02416","n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluating-large-language-models-in-analysing","title":"Evaluating Large Language Models in Analysing Classroom Dialogue","date":"2024-02-04","arxiv_id":"2402.02380","n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-assessment-of-tutoring-practices","title":"Improving Assessment of Tutoring Practices using Retrieval-Augmented Generation","date":"2024-02-04","arxiv_id":"2402.14594","n_code_links":0,"syntology":null},{"paper":"/paper/invit-a-generalizable-routing-problem-solver","slug":"invit-a-generalizable-routing-problem-solver","title":"INViT: A Generalizable Routing Problem Solver with Invariant Nested View Transformer","date":"2024-02-04","arxiv_id":"2402.02317","n_code_links":1,"syntology":{"ran":8,"of":12,"n_ran_checked":6,"n_instrument":2,"unverified":4,"pointer_only":12,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified","official":{"repos":["kasumigaoka-utaha/invit"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"key-graph-transformer-for-image-restoration","title":"Key-Graph Transformer for Image Restoration","date":"2024-02-04","arxiv_id":"2402.02634","n_code_links":0,"syntology":null},{"paper":"/paper/minusformer-improving-time-series-forecasting","slug":"minusformer-improving-time-series-forecasting","title":"Minusformer: Improving Time Series Forecasting by Progressively Learning Residuals","date":"2024-02-04","arxiv_id":"2402.02332","n_code_links":1,"syntology":null},{"paper":"/paper/pathformer-multi-scale-transformers-with","slug":"pathformer-multi-scale-transformers-with","title":"Pathformer: Multi-scale Transformers with Adaptive Pathways for Time Series Forecasting","date":"2024-02-04","arxiv_id":"2402.05956","n_code_links":1,"syntology":{"ran":6,"of":11,"n_ran_checked":6,"n_instrument":0,"unverified":5,"pointer_only":11,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","official":{"repos":["decisionintelligence/pathformer"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"prosac-provably-safe-certification-for","title":"PROSAC: Provably Safe Certification for Machine Learning Models under Adversarial Attacks","date":"2024-02-04","arxiv_id":"2402.02629","n_code_links":0,"syntology":null},{"paper":null,"slug":"spctnet-a-series-parallel-cnn-and-transformer","title":"SPCTNet: A Series-Parallel CNN and Transformer Network for 3D Medical Image Segmentation","date":"2024-02-04","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"spin-an-efficient-secure-computation","title":"Spin: An Efficient Secure Computation Framework with GPU Acceleration","date":"2024-02-04","arxiv_id":"2402.02320","n_code_links":0,"syntology":null},{"paper":"/paper/timer-transformers-for-time-series-analysis","slug":"timer-transformers-for-time-series-analysis","title":"Timer: Generative Pre-trained Transformers Are Large Time Series Models","date":"2024-02-04","arxiv_id":"2402.02368","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":["thuml/Large-Time-Series-Model"],"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":"/paper/unified-training-of-universal-time-series","slug":"unified-training-of-universal-time-series","title":"Unified Training of Universal Time Series Forecasting Transformers","date":"2024-02-04","arxiv_id":"2402.02592","n_code_links":1,"syntology":null},{"paper":null,"slug":"betterv-controlled-verilog-generation-with","title":"BetterV: Controlled Verilog Generation with Discriminative Guidance","date":"2024-02-03","arxiv_id":"2402.03375","n_code_links":0,"syntology":null},{"paper":null,"slug":"diffvein-a-unified-diffusion-network-for","title":"DiffVein: A Unified Diffusion Network for Finger Vein Segmentation and Authentication","date":"2024-02-03","arxiv_id":"2402.02060","n_code_links":0,"syntology":null},{"paper":null,"slug":"do-moral-judgment-and-reasoning-capability-of","title":"Do Moral Judgment and Reasoning Capability of LLMs Change with Language? A Study using the Multilingual Defining Issues Test","date":"2024-02-03","arxiv_id":"2402.02135","n_code_links":0,"syntology":null},{"paper":"/paper/effibench-benchmarking-the-efficiency-of","slug":"effibench-benchmarking-the-efficiency-of","title":"EffiBench: Benchmarking the Efficiency of Automatically Generated Code","date":"2024-02-03","arxiv_id":"2402.02037","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 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","official":{"repos":["huangd1999/EffiBench"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/how-well-do-llms-cite-relevant-medical","slug":"how-well-do-llms-cite-relevant-medical","title":"How well do LLMs cite relevant medical references? An evaluation framework and analyses","date":"2024-02-03","arxiv_id":"2402.02008","n_code_links":1,"syntology":null},{"paper":null,"slug":"imusic-imu-based-facial-expression-capture","title":"IMUSE: IMU-based Facial Expression Capture","date":"2024-02-03","arxiv_id":"2402.03944","n_code_links":0,"syntology":null},{"paper":"/paper/parzc-parametric-zero-cost-proxies-for","slug":"parzc-parametric-zero-cost-proxies-for","title":"ParZC: Parametric Zero-Cost Proxies for Efficient NAS","date":"2024-02-03","arxiv_id":"2402.02105","n_code_links":0,"syntology":null},{"paper":"/paper/scribformer-transformer-makes-cnn-work-better","slug":"scribformer-transformer-makes-cnn-work-better","title":"ScribFormer: Transformer Makes CNN Work Better for Scribble-based Medical Image Segmentation","date":"2024-02-03","arxiv_id":"2402.02029","n_code_links":1,"syntology":null},{"paper":null,"slug":"tci-former-thermal-conduction-inspired","title":"TCI-Former: Thermal Conduction-Inspired Transformer for Infrared Small Target Detection","date":"2024-02-03","arxiv_id":"2402.02046","n_code_links":0,"syntology":null},{"paper":"/paper/topology-informed-graph-transformer","slug":"topology-informed-graph-transformer","title":"Topology-Informed Graph Transformer","date":"2024-02-03","arxiv_id":"2402.02005","n_code_links":2,"syntology":{"ran":17,"of":21,"n_ran_checked":17,"n_instrument":0,"unverified":4,"pointer_only":21,"phrase":"17 ran (of which 0 constructed an object rather than computing a result; 17 with no instrument failure: 0 honoured, 2 violated, 15 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","official":{"repos":["leemingo/tigt"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":3,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/tsis-a-supplementary-algorithm-to-t-smiles","slug":"tsis-a-supplementary-algorithm-to-t-smiles","title":"Hierarchical Structure Enhances the Convergence and Generalizability of Linear Molecular Representation","date":"2024-02-03","arxiv_id":"2402.02164","n_code_links":1,"syntology":null},{"paper":"/paper/a-data-driven-analysis-of-robust-automatic","slug":"a-data-driven-analysis-of-robust-automatic","title":"A Data-Driven Analysis of Robust Automatic Piano Transcription","date":"2024-02-02","arxiv_id":"2402.01424","n_code_links":0,"syntology":null},{"paper":"/paper/alert-transformer-bridging-asynchronous-and","slug":"alert-transformer-bridging-asynchronous-and","title":"ALERT-Transformer: Bridging Asynchronous and Synchronous Machine Learning for Real-Time Event-based Spatio-Temporal Data","date":"2024-02-02","arxiv_id":"2402.01393","n_code_links":0,"syntology":null},{"paper":null,"slug":"an-introduction-to-graphical-tensor-notation","title":"An introduction to graphical tensor notation for mechanistic interpretability","date":"2024-02-02","arxiv_id":"2402.01790","n_code_links":0,"syntology":null},{"paper":null,"slug":"bat-learning-to-reason-about-spatial-sounds","title":"BAT: Learning to Reason about Spatial Sounds with Large Language Models","date":"2024-02-02","arxiv_id":"2402.01591","n_code_links":0,"syntology":null},{"paper":"/paper/cross-view-masked-diffusion-transformers-for","slug":"cross-view-masked-diffusion-transformers-for","title":"Cross-view Masked Diffusion Transformers for Person Image Synthesis","date":"2024-02-02","arxiv_id":"2402.01516","n_code_links":1,"syntology":{"ran":2,"of":5,"n_ran_checked":2,"n_instrument":0,"unverified":3,"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) · 3 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","official":{"repos":["trungpx/xmdpt"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"faster-inference-of-integer-swin-transformer","title":"Faster Inference of Integer SWIN Transformer by Removing the GELU Activation","date":"2024-02-02","arxiv_id":"2402.01169","n_code_links":0,"syntology":null},{"paper":null,"slug":"how-can-generative-ai-enhance-the-well-being","title":"How Can Generative AI Enhance the Well-being of Blind?","date":"2024-02-02","arxiv_id":"2402.07919","n_code_links":0,"syntology":null},{"paper":"/paper/integrating-large-language-models-in-causal","slug":"integrating-large-language-models-in-causal","title":"Integrating Large Language Models in Causal Discovery: A Statistical Causal Approach","date":"2024-02-02","arxiv_id":"2402.01454","n_code_links":2,"syntology":null},{"paper":null,"slug":"lotr-low-tensor-rank-weight-adaptation","title":"LoTR: Low Tensor Rank Weight Adaptation","date":"2024-02-02","arxiv_id":"2402.01376","n_code_links":0,"syntology":null},{"paper":null,"slug":"todyformer-towards-holistic-dynamic-graph","title":"Todyformer: Towards Holistic Dynamic Graph Transformers with Structure-Aware Tokenization","date":"2024-02-02","arxiv_id":"2402.05944","n_code_links":0,"syntology":null},{"paper":null,"slug":"transformers-learn-nonlinear-features-in","title":"Transformers Learn Nonlinear Features In Context: Nonconvex Mean-field Dynamics on the Attention Landscape","date":"2024-02-02","arxiv_id":"2402.01258","n_code_links":0,"syntology":null},{"paper":"/paper/travelplanner-a-benchmark-for-real-world","slug":"travelplanner-a-benchmark-for-real-world","title":"TravelPlanner: A Benchmark for Real-World Planning with Language Agents","date":"2024-02-02","arxiv_id":"2402.01622","n_code_links":2,"syntology":{"ran":17,"of":17,"n_ran_checked":13,"n_instrument":4,"unverified":0,"pointer_only":4,"phrase":"17 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 1 honoured, 0 violated, 12 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","official":{"repos":["OSU-NLP-Group/TravelPlanner"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/dendritic-learning-incorporated-vision","slug":"dendritic-learning-incorporated-vision","title":"Dendritic Learning-incorporated Vision Transformer for Image Recognition","date":"2024-02-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"fuseformer-a-transformer-for-visual-and","title":"FuseFormer: A Transformer for Visual and Thermal Image Fusion","date":"2024-02-01","arxiv_id":"2402.00971","n_code_links":0,"syntology":null},{"paper":null,"slug":"generation-distillation-and-evaluation-of","title":"Generation, Distillation and Evaluation of Motivational Interviewing-Style Reflections with a Foundational Language Model","date":"2024-02-01","arxiv_id":"2402.01051","n_code_links":0,"syntology":null},{"paper":null,"slug":"hierarchical-multi-label-classification-of-2","title":"Hierarchical Multi-Label Classification of Online Vaccine Concerns","date":"2024-02-01","arxiv_id":"2402.01783","n_code_links":0,"syntology":null},{"paper":"/paper/merging-multi-task-models-via-weight","slug":"merging-multi-task-models-via-weight","title":"Merging Multi-Task Models via Weight-Ensembling Mixture of Experts","date":"2024-02-01","arxiv_id":"2402.00433","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: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["tanganke/weight-ensembling_moe"],"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":"/paper/multivariate-probabilistic-time-series","slug":"multivariate-probabilistic-time-series","title":"Multivariate Probabilistic Time Series Forecasting with Correlated Errors","date":"2024-02-01","arxiv_id":"2402.01000","n_code_links":1,"syntology":{"ran":3,"of":4,"n_ran_checked":0,"n_instrument":3,"unverified":1,"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) · 1 unverified","official":{"repos":["rottenivy/mv_pts_correlatederr"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"ocassionally-secure-a-comparative-analysis-of","title":"Ocassionally Secure: A Comparative Analysis of Code Generation Assistants","date":"2024-02-01","arxiv_id":"2402.00689","n_code_links":0,"syntology":null},{"paper":null,"slug":"on-the-psychology-of-gpt-4-moderately-anxious","title":"On the Psychology of GPT-4: Moderately anxious, slightly masculine, honest, and humble","date":"2024-02-01","arxiv_id":"2402.01777","n_code_links":0,"syntology":null},{"paper":"/paper/recurrent-transformers-with-dynamic-halt","slug":"recurrent-transformers-with-dynamic-halt","title":"Investigating Recurrent Transformers with Dynamic Halt","date":"2024-02-01","arxiv_id":"2402.00976","n_code_links":1,"syntology":null},{"paper":null,"slug":"understanding-the-expressive-power-and","title":"Understanding the Expressive Power and Mechanisms of Transformer for Sequence Modeling","date":"2024-02-01","arxiv_id":"2402.00522","n_code_links":0,"syntology":null},{"paper":null,"slug":"code-aware-prompting-a-study-of-coverage","title":"Code-Aware Prompting: A study of Coverage Guided Test Generation in Regression Setting using LLM","date":"2024-01-31","arxiv_id":"2402.00097","n_code_links":0,"syntology":null},{"paper":null,"slug":"computation-and-parameter-efficient-multi","title":"Computation and Parameter Efficient Multi-Modal Fusion Transformer for Cued Speech Recognition","date":"2024-01-31","arxiv_id":"2401.17604","n_code_links":0,"syntology":null},{"paper":null,"slug":"document-structure-in-long-document","title":"Document Structure in Long Document Transformers","date":"2024-01-31","arxiv_id":"2401.17658","n_code_links":0,"syntology":null},{"paper":null,"slug":"exploring-the-limits-of-decoder-only-models","title":"Exploring the limits of decoder-only models trained on public speech recognition corpora","date":"2024-01-31","arxiv_id":"2402.00235","n_code_links":0,"syntology":null},{"paper":null,"slug":"global-liar-factuality-of-llms-over-time-and","title":"Global-Liar: Factuality of LLMs over Time and Geographic Regions","date":"2024-01-31","arxiv_id":"2401.17839","n_code_links":0,"syntology":null},{"paper":"/paper/graph-transformers-without-positional","slug":"graph-transformers-without-positional","title":"Graph Transformers without Positional Encodings","date":"2024-01-31","arxiv_id":"2401.17791","n_code_links":0,"syntology":null},{"paper":null,"slug":"head-and-neck-tumor-segmentation-from-18f-f","title":"Head and Neck Tumor Segmentation from [18F]F-FDG PET/CT Images Based on 3D Diffusion Model","date":"2024-01-31","arxiv_id":"2401.17593","n_code_links":0,"syntology":null},{"paper":"/paper/leveraging-swin-transformer-for-local-to","slug":"leveraging-swin-transformer-for-local-to","title":"Leveraging Swin Transformer for Local-to-Global Weakly Supervised Semantic Segmentation","date":"2024-01-31","arxiv_id":"2401.17828","n_code_links":1,"syntology":null},{"paper":"/paper/llm-voting-human-choices-and-ai-collective","slug":"llm-voting-human-choices-and-ai-collective","title":"LLM Voting: Human Choices and AI Collective Decision Making","date":"2024-01-31","arxiv_id":"2402.01766","n_code_links":1,"syntology":{"ran":0,"of":2,"n_ran_checked":0,"n_instrument":0,"unverified":2,"pointer_only":2,"phrase":"0 ran · 2 unverified","official":{"repos":["ethz-coss/LLM_voting"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":[]}}},{"paper":"/paper/local-feature-matching-using-deep-learning-a","slug":"local-feature-matching-using-deep-learning-a","title":"Local Feature Matching Using Deep Learning: A Survey","date":"2024-01-31","arxiv_id":"2401.17592","n_code_links":1,"syntology":null},{"paper":"/paper/positional-encoding-helps-recurrent-neural","slug":"positional-encoding-helps-recurrent-neural","title":"Positional Encoding Helps Recurrent Neural Networks Handle a Large Vocabulary","date":"2024-01-31","arxiv_id":"2402.00236","n_code_links":1,"syntology":null},{"paper":"/paper/raptor-recursive-abstractive-processing-for","slug":"raptor-recursive-abstractive-processing-for","title":"RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval","date":"2024-01-31","arxiv_id":"2401.18059","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":["parthsarthi03/RAPTOR"],"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/scape-searching-conceptual-architecture","slug":"scape-searching-conceptual-architecture","title":"SCAPE: Searching Conceptual Architecture Prompts using Evolution","date":"2024-01-31","arxiv_id":"2402.00089","n_code_links":1,"syntology":null},{"paper":null,"slug":"scavenging-hyena-distilling-transformers-into","title":"Scavenging Hyena: Distilling Transformers into Long Convolution Models","date":"2024-01-31","arxiv_id":"2401.17574","n_code_links":0,"syntology":null},{"paper":null,"slug":"supporting-anticipatory-governance-using-llms","title":"Evaluating the Capabilities of LLMs for Supporting Anticipatory Impact Assessment","date":"2024-01-31","arxiv_id":"2401.18028","n_code_links":0,"syntology":null},{"paper":"/paper/swea-changing-factual-knowledge-in-large","slug":"swea-changing-factual-knowledge-in-large","title":"SWEA: Updating Factual Knowledge in Large Language Models via Subject Word Embedding Altering","date":"2024-01-31","arxiv_id":"2401.17809","n_code_links":1,"syntology":{"ran":3,"of":6,"n_ran_checked":2,"n_instrument":1,"unverified":3,"pointer_only":6,"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) · 3 unverified","official":{"repos":["xpq-tech/swea"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/wsc-enhancing-the-winograd-schema-challenge","slug":"wsc-enhancing-the-winograd-schema-challenge","title":"WSC+: Enhancing The Winograd Schema Challenge Using Tree-of-Experts","date":"2024-01-31","arxiv_id":"2401.17703","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-cross-language-investigation-into-jailbreak","title":"A Cross-Language Investigation into Jailbreak Attacks in Large Language Models","date":"2024-01-30","arxiv_id":"2401.16765","n_code_links":0,"syntology":null}],"record_sha256":"0a34d2c3000fbd2fb9d0b6d3b26df8032042208d83eb4120bd5767f49365c399","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}