{"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/66","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":66,"pages_in_order":140,"rows_per_page":100,"rows":[6501,6600],"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/65","next":"/method/transformer/papers/67","papers":[{"paper":null,"slug":"understanding-the-natural-language-of-dna","title":"Understanding the Natural Language of DNA using Encoder-Decoder Foundation Models with Byte-level Precision","date":"2023-11-04","arxiv_id":"2311.02333","n_code_links":0,"syntology":null},{"paper":null,"slug":"an-empirical-study-of-benchmarking-chinese","title":"An Empirical Study of Benchmarking Chinese Aspect Sentiment Quad Prediction","date":"2023-11-03","arxiv_id":"2311.01713","n_code_links":0,"syntology":null},{"paper":null,"slug":"capturing-local-and-global-features-in","title":"Capturing Local and Global Features in Medical Images by Using Ensemble CNN-Transformer","date":"2023-11-03","arxiv_id":"2311.01731","n_code_links":0,"syntology":null},{"paper":null,"slug":"depth-guided-free-space-segmentation-for-a","title":"Depth-guided Free-space Segmentation for a Mobile Robot","date":"2023-11-03","arxiv_id":"2311.01966","n_code_links":0,"syntology":null},{"paper":"/paper/dialogbench-evaluating-llms-as-human-like","slug":"dialogbench-evaluating-llms-as-human-like","title":"DialogBench: Evaluating LLMs as Human-like Dialogue Systems","date":"2023-11-03","arxiv_id":"2311.01677","n_code_links":1,"syntology":null},{"paper":null,"slug":"emergence-of-abstract-state-representations","title":"Emergence of Abstract State Representations in Embodied Sequence Modeling","date":"2023-11-03","arxiv_id":"2311.02171","n_code_links":0,"syntology":null},{"paper":"/paper/gateloop-fully-data-controlled-linear","slug":"gateloop-fully-data-controlled-linear","title":"GateLoop: Fully Data-Controlled Linear Recurrence for Sequence Modeling","date":"2023-11-03","arxiv_id":"2311.01927","n_code_links":3,"syntology":{"ran":3,"of":5,"n_ran_checked":3,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["tobiaskatsch/GateLoop"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/multi-scale-time-stepping-of-partial","slug":"multi-scale-time-stepping-of-partial","title":"Multi-scale Time-stepping of Partial Differential Equations with Transformers","date":"2023-11-03","arxiv_id":"2311.02225","n_code_links":1,"syntology":null},{"paper":"/paper/pptc-benchmark-evaluating-large-language","slug":"pptc-benchmark-evaluating-large-language","title":"PPTC Benchmark: Evaluating Large Language Models for PowerPoint Task Completion","date":"2023-11-03","arxiv_id":"2311.01767","n_code_links":1,"syntology":{"ran":13,"of":17,"n_ran_checked":13,"n_instrument":0,"unverified":4,"pointer_only":0,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","official":{"repos":["gydpku/pptc"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":13,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"the-potential-of-wearable-sensors-for","title":"The Potential of Wearable Sensors for Assessing Patient Acuity in Intensive Care Unit (ICU)","date":"2023-11-03","arxiv_id":"2311.02251","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-risks-of-risk-based-ai-regulation-taking","title":"The risks of risk-based AI regulation: taking liability seriously","date":"2023-11-03","arxiv_id":"2311.14684","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-a-unified-transformer-based-framework","title":"Towards a Unified Transformer-based Framework for Scene Graph Generation and Human-object Interaction Detection","date":"2023-11-03","arxiv_id":"2311.01755","n_code_links":0,"syntology":null},{"paper":null,"slug":"atgnn-audio-tagging-graph-neural-network","title":"ATGNN: Audio Tagging Graph Neural Network","date":"2023-11-02","arxiv_id":"2311.01526","n_code_links":0,"syntology":null},{"paper":null,"slug":"deep-double-descent-for-time-series","title":"Deep Double Descent for Time Series Forecasting: Avoiding Undertrained Models","date":"2023-11-02","arxiv_id":"2311.01442","n_code_links":0,"syntology":null},{"paper":null,"slug":"distilling-knowledge-from-cnn-transformer","title":"Distilling Knowledge from CNN-Transformer Models for Enhanced Human Action Recognition","date":"2023-11-02","arxiv_id":"2311.01283","n_code_links":0,"syntology":null},{"paper":null,"slug":"efficient-vision-transformer-for-accurate","title":"Efficient Vision Transformer for Accurate Traffic Sign Detection","date":"2023-11-02","arxiv_id":"2311.01429","n_code_links":0,"syntology":null},{"paper":null,"slug":"enriching-phrases-with-coupled-pixel-and","title":"Enriching Phrases with Coupled Pixel and Object Contexts for Panoptic Narrative Grounding","date":"2023-11-02","arxiv_id":"2311.01091","n_code_links":0,"syntology":null},{"paper":null,"slug":"generative-input-towards-next-generation","title":"Generative Input: Towards Next-Generation Input Methods Paradigm","date":"2023-11-02","arxiv_id":"2311.01166","n_code_links":0,"syntology":null},{"paper":"/paper/hybrid-fusion-transformer-for-multisequence","slug":"hybrid-fusion-transformer-for-multisequence","title":"Hybrid-Fusion Transformer for Multisequence MRI","date":"2023-11-02","arxiv_id":"2311.01308","n_code_links":1,"syntology":null},{"paper":null,"slug":"learning-unsupervised-world-models-for","title":"Copilot4D: Learning Unsupervised World Models for Autonomous Driving via Discrete Diffusion","date":"2023-11-02","arxiv_id":"2311.01017","n_code_links":0,"syntology":null},{"paper":"/paper/m-m3d-multi-dataset-training-and-efficient","slug":"m-m3d-multi-dataset-training-and-efficient","title":"M&M3D: Multi-Dataset Training and Efficient Network for Multi-view 3D Object Detection","date":"2023-11-02","arxiv_id":"2311.00986","n_code_links":1,"syntology":null},{"paper":null,"slug":"on-the-convergence-of-encoder-only-shallow","title":"On the Convergence of Encoder-only Shallow Transformers","date":"2023-11-02","arxiv_id":"2311.01575","n_code_links":0,"syntology":null},{"paper":null,"slug":"scattering-vision-transformer-spectral-mixing","title":"Scattering Vision Transformer: Spectral Mixing Matters","date":"2023-11-02","arxiv_id":"2311.01310","n_code_links":0,"syntology":null},{"paper":"/paper/video2music-suitable-music-generation-from","slug":"video2music-suitable-music-generation-from","title":"Video2Music: Suitable Music Generation from Videos using an Affective Multimodal Transformer model","date":"2023-11-02","arxiv_id":"2311.00968","n_code_links":1,"syntology":{"ran":1,"of":5,"n_ran_checked":0,"n_instrument":1,"unverified":4,"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) · 4 unverified","official":{"repos":["amaai-lab/video2music"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"1dformer-learning-1d-landmark-representations","title":"1DFormer: a Transformer Architecture Learning 1D Landmark Representations for Facial Landmark Tracking","date":"2023-11-01","arxiv_id":"2311.00241","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-spatial-temporal-transformer-based","title":"A Spatial-Temporal Transformer based Framework For Human Pose Assessment And Correction in Education Scenarios","date":"2023-11-01","arxiv_id":"2311.00401","n_code_links":0,"syntology":null},{"paper":null,"slug":"are-large-language-models-reliable-judges-a","title":"Are Large Language Models Reliable Judges? A Study on the Factuality Evaluation Capabilities of LLMs","date":"2023-11-01","arxiv_id":"2311.00681","n_code_links":0,"syntology":null},{"paper":null,"slug":"attention-alignment-and-flexible-positional","title":"Attention Alignment and Flexible Positional Embeddings Improve Transformer Length Extrapolation","date":"2023-11-01","arxiv_id":"2311.00684","n_code_links":0,"syntology":null},{"paper":null,"slug":"can-large-language-models-capture-public","title":"Can Large Language Models Capture Public Opinion about Global Warming? An Empirical Assessment of Algorithmic Fidelity and Bias","date":"2023-11-01","arxiv_id":"2311.00217","n_code_links":0,"syntology":null},{"paper":"/paper/costar-improved-temporal-counterfactual","slug":"costar-improved-temporal-counterfactual","title":"COSTAR: Improved Temporal Counterfactual Estimation with Self-Supervised Learning","date":"2023-11-01","arxiv_id":"2311.00886","n_code_links":1,"syntology":null},{"paper":null,"slug":"detecting-visual-cues-in-the-intensive-care","title":"Detecting Visual Cues in the Intensive Care Unit and Association with Patient Clinical Status","date":"2023-11-01","arxiv_id":"2311.00565","n_code_links":0,"syntology":null},{"paper":"/paper/from-text-to-structure-using-large-language","slug":"from-text-to-structure-using-large-language","title":"From Text to Structure: Using Large Language Models to Support the Development of Legal Expert Systems","date":"2023-11-01","arxiv_id":"2311.04911","n_code_links":1,"syntology":null},{"paper":null,"slug":"improving-robustness-for-vision-transformer","title":"Improving Robustness for Vision Transformer with a Simple Dynamic Scanning Augmentation","date":"2023-11-01","arxiv_id":"2311.00441","n_code_links":0,"syntology":null},{"paper":null,"slug":"rethinking-decision-transformer-via","title":"Rethinking Decision Transformer via Hierarchical Reinforcement Learning","date":"2023-11-01","arxiv_id":"2311.00267","n_code_links":0,"syntology":null},{"paper":"/paper/the-development-of-llms-for-embodied","slug":"the-development-of-llms-for-embodied","title":"Advances in Embodied Navigation Using Large Language Models: A Survey","date":"2023-11-01","arxiv_id":"2311.00530","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-systematic-review-for-transformer-based","title":"A Systematic Review for Transformer-based Long-term Series Forecasting","date":"2023-10-31","arxiv_id":"2310.20218","n_code_links":0,"syntology":null},{"paper":null,"slug":"breathing-life-into-faces-speech-driven-3d","title":"Breathing Life into Faces: Speech-driven 3D Facial Animation with Natural Head Pose and Detailed Shape","date":"2023-10-31","arxiv_id":"2310.20240","n_code_links":0,"syntology":null},{"paper":"/paper/causal-interpretation-of-self-attention-in","slug":"causal-interpretation-of-self-attention-in","title":"Causal Interpretation of Self-Attention in Pre-Trained Transformers","date":"2023-10-31","arxiv_id":"2310.20307","n_code_links":1,"syntology":null},{"paper":null,"slug":"chipnemo-domain-adapted-llms-for-chip-design","title":"ChipNeMo: Domain-Adapted LLMs for Chip Design","date":"2023-10-31","arxiv_id":"2311.00176","n_code_links":0,"syntology":null},{"paper":null,"slug":"diversified-node-sampling-based-hierarchical","title":"Diversified Node Sampling based Hierarchical Transformer Pooling for Graph Representation Learning","date":"2023-10-31","arxiv_id":"2310.20250","n_code_links":0,"syntology":null},{"paper":null,"slug":"does-gpt-4-pass-the-turing-test","title":"Does GPT-4 pass the Turing test?","date":"2023-10-31","arxiv_id":"2310.20216","n_code_links":0,"syntology":null},{"paper":null,"slug":"efficient-classification-of-student-help","title":"Efficient Classification of Student Help Requests in Programming Courses Using Large Language Models","date":"2023-10-31","arxiv_id":"2310.20105","n_code_links":0,"syntology":null},{"paper":"/paper/generate-what-you-prefer-reshaping-sequential","slug":"generate-what-you-prefer-reshaping-sequential","title":"Generate What You Prefer: Reshaping Sequential Recommendation via Guided Diffusion","date":"2023-10-31","arxiv_id":"2310.20453","n_code_links":1,"syntology":null},{"paper":null,"slug":"global-transformer-architecture-for-indoor","title":"Global Transformer Architecture for Indoor Room Temperature Forecasting","date":"2023-10-31","arxiv_id":"2310.20476","n_code_links":0,"syntology":null},{"paper":null,"slug":"graphtransformers-for-geospatial-forecasting","title":"GraphTransformers for Geospatial Forecasting of Hurricane Trajectories","date":"2023-10-31","arxiv_id":"2310.20174","n_code_links":0,"syntology":null},{"paper":"/paper/in-search-of-lost-online-test-time-adaptation","slug":"in-search-of-lost-online-test-time-adaptation","title":"In Search of Lost Online Test-time Adaptation: A Survey","date":"2023-10-31","arxiv_id":"2310.20199","n_code_links":1,"syntology":{"ran":14,"of":17,"n_ran_checked":9,"n_instrument":5,"unverified":3,"pointer_only":7,"phrase":"14 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; 5 where Syntology's instrument failed) · 3 unverified","official":{"repos":["jo-wang/otta_vit_survey"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/learning-from-mistakes-makes-llm-better","slug":"learning-from-mistakes-makes-llm-better","title":"Learning From Mistakes Makes LLM Better Reasoner","date":"2023-10-31","arxiv_id":"2310.20689","n_code_links":1,"syntology":{"ran":3,"of":4,"n_ran_checked":2,"n_instrument":1,"unverified":1,"pointer_only":0,"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) · 1 unverified","official":{"repos":["microsoft/lema"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"what-a-whole-slide-image-can-tell-subtype","title":"What a Whole Slide Image Can Tell? Subtype-guided Masked Transformer for Pathological Image Captioning","date":"2023-10-31","arxiv_id":"2310.20607","n_code_links":0,"syntology":null},{"paper":null,"slug":"bioinstruct-instruction-tuning-of-large","title":"BioInstruct: Instruction Tuning of Large Language Models for Biomedical Natural Language Processing","date":"2023-10-30","arxiv_id":"2310.19975","n_code_links":0,"syntology":null},{"paper":null,"slug":"building-real-world-meeting-summarization","title":"Building Real-World Meeting Summarization Systems using Large Language Models: A Practical Perspective","date":"2023-10-30","arxiv_id":"2310.19233","n_code_links":0,"syntology":null},{"paper":null,"slug":"constituency-parsing-using-llms","title":"Constituency Parsing using LLMs","date":"2023-10-30","arxiv_id":"2310.19462","n_code_links":0,"syntology":null},{"paper":"/paper/dynamics-of-instruction-tuning-each-ability","slug":"dynamics-of-instruction-tuning-each-ability","title":"Dynamics of Instruction Tuning: Each Ability of Large Language Models Has Its Own Growth Pace","date":"2023-10-30","arxiv_id":"2310.19651","n_code_links":1,"syntology":null},{"paper":"/paper/exploiting-image-related-inductive-biases-in","slug":"exploiting-image-related-inductive-biases-in","title":"AViTMP: A Tracking-Specific Transformer for Single-Branch Visual Tracking","date":"2023-10-30","arxiv_id":"2310.19542","n_code_links":1,"syntology":null},{"paper":null,"slug":"fusing-temporal-graphs-into-transformers-for","title":"Fusing Temporal Graphs into Transformers for Time-Sensitive Question Answering","date":"2023-10-30","arxiv_id":"2310.19292","n_code_links":0,"syntology":null},{"paper":"/paper/grokking-tickets-lottery-tickets-accelerate","slug":"grokking-tickets-lottery-tickets-accelerate","title":"Bridging Lottery Ticket and Grokking: Understanding Grokking from Inner Structure of Networks","date":"2023-10-30","arxiv_id":"2310.19470","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":["gouki510/grokking-tickets"],"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/interpretable-by-design-text-classification","slug":"interpretable-by-design-text-classification","title":"Interpretable-by-Design Text Understanding with Iteratively Generated Concept Bottleneck","date":"2023-10-30","arxiv_id":"2310.19660","n_code_links":1,"syntology":null},{"paper":"/paper/large-trajectory-models-are-scalable-motion","slug":"large-trajectory-models-are-scalable-motion","title":"Large Trajectory Models are Scalable Motion Predictors and Planners","date":"2023-10-30","arxiv_id":"2310.19620","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":["tsinghua-mars-lab/statetransformer"],"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/mist-medical-image-segmentation-transformer","slug":"mist-medical-image-segmentation-transformer","title":"MIST: Medical Image Segmentation Transformer with Convolutional Attention Mixing (CAM) Decoder","date":"2023-10-30","arxiv_id":"2310.19898","n_code_links":1,"syntology":null},{"paper":"/paper/one-for-all-bridge-the-gap-between-1","slug":"one-for-all-bridge-the-gap-between-1","title":"One-for-All: Bridge the Gap Between Heterogeneous Architectures in Knowledge Distillation","date":"2023-10-30","arxiv_id":"2310.19444","n_code_links":1,"syntology":{"ran":0,"of":3,"n_ran_checked":0,"n_instrument":0,"unverified":3,"pointer_only":3,"phrase":"0 ran · 3 unverified","official":{"repos":["hao840/ofakd"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":[]}}},{"paper":null,"slug":"solarformer-multi-scale-transformer-for-solar","title":"SolarFormer: Multi-scale Transformer for Solar PV Profiling","date":"2023-10-30","arxiv_id":"2310.20057","n_code_links":0,"syntology":null},{"paper":"/paper/towards-few-annotation-learning-for-object","slug":"towards-few-annotation-learning-for-object","title":"Towards Few-Annotation Learning for Object Detection: Are Transformer-based Models More Efficient ?","date":"2023-10-30","arxiv_id":"2310.19936","n_code_links":1,"syntology":null},{"paper":"/paper/multimodal-chatgpt-for-medical-applications","slug":"multimodal-chatgpt-for-medical-applications","title":"Multimodal ChatGPT for Medical Applications: an Experimental Study of GPT-4V","date":"2023-10-29","arxiv_id":"2310.19061","n_code_links":1,"syntology":null},{"paper":"/paper/pushdown-layers-encoding-recursive-structure","slug":"pushdown-layers-encoding-recursive-structure","title":"Pushdown Layers: Encoding Recursive Structure in Transformer Language Models","date":"2023-10-29","arxiv_id":"2310.19089","n_code_links":1,"syntology":{"ran":14,"of":23,"n_ran_checked":14,"n_instrument":0,"unverified":9,"pointer_only":23,"phrase":"14 ran (of which 8 constructed an object rather than computing a result; 14 with no instrument failure: 1 honoured, 0 violated, 13 with no contract checked; 0 where Syntology's instrument failed) · 9 unverified","official":{"repos":["murtyshikhar/pushdown-layers"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":8,"n_ran_no_instrument_failure":14,"n_unverified":9,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"astormer-an-ast-structure-aware-transformer","title":"ASTormer: An AST Structure-aware Transformer Decoder for Text-to-SQL","date":"2023-10-28","arxiv_id":"2310.18662","n_code_links":0,"syntology":null},{"paper":"/paper/integration-of-persistent-laplacian-and-pre","slug":"integration-of-persistent-laplacian-and-pre","title":"Integration of persistent Laplacian and pre-trained transformer for protein solubility changes upon mutation","date":"2023-10-28","arxiv_id":"2310.18760","n_code_links":1,"syntology":null},{"paper":"/paper/local-global-self-supervised-visual","slug":"local-global-self-supervised-visual","title":"Patch-Wise Self-Supervised Visual Representation Learning: A Fine-Grained Approach","date":"2023-10-28","arxiv_id":"2310.18651","n_code_links":1,"syntology":null},{"paper":null,"slug":"multiscale-spectral-spatial-convolutional","title":"MultiScale Spectral-Spatial Convolutional Transformer for Hyperspectral Image Classification","date":"2023-10-28","arxiv_id":"2310.18550","n_code_links":0,"syntology":null},{"paper":null,"slug":"using-large-language-models-to-support","title":"Using Large Language Models to Support Thematic Analysis in Empirical Legal Studies","date":"2023-10-28","arxiv_id":"2310.18729","n_code_links":0,"syntology":null},{"paper":"/paper/boosting-data-analytics-with-synthetic-volume","slug":"boosting-data-analytics-with-synthetic-volume","title":"Boosting Data Analytics With Synthetic Volume Expansion","date":"2023-10-27","arxiv_id":"2310.17848","n_code_links":1,"syntology":null},{"paper":"/paper/can-llms-keep-a-secret-testing-privacy","slug":"can-llms-keep-a-secret-testing-privacy","title":"Can LLMs Keep a Secret? Testing Privacy Implications of Language Models via Contextual Integrity Theory","date":"2023-10-27","arxiv_id":"2310.17884","n_code_links":1,"syntology":null},{"paper":null,"slug":"faultseg-swin-unetr-transformer-based-self","title":"FaultSeg Swin-UNETR: Transformer-Based Self-Supervised Pretraining Model for Fault Recognition","date":"2023-10-27","arxiv_id":"2310.17974","n_code_links":0,"syntology":null},{"paper":"/paper/fp8-lm-training-fp8-large-language-models","slug":"fp8-lm-training-fp8-large-language-models","title":"FP8-LM: Training FP8 Large Language Models","date":"2023-10-27","arxiv_id":"2310.18313","n_code_links":1,"syntology":null},{"paper":null,"slug":"gpt-4-vision-on-medical-image-classification","title":"GPT-4 Vision on Medical Image Classification -- A Case Study on COVID-19 Dataset","date":"2023-10-27","arxiv_id":"2310.18498","n_code_links":0,"syntology":null},{"paper":null,"slug":"knowing-what-llms-do-not-know-a-simple-yet","title":"Knowing What LLMs DO NOT Know: A Simple Yet Effective Self-Detection Method","date":"2023-10-27","arxiv_id":"2310.17918","n_code_links":0,"syntology":null},{"paper":"/paper/large-language-models-for-aspect-based","slug":"large-language-models-for-aspect-based","title":"Large language models for aspect-based sentiment analysis","date":"2023-10-27","arxiv_id":"2310.18025","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":["qagentur/absa_llm"],"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/multi-label-emotion-analysis-in-conversation","slug":"multi-label-emotion-analysis-in-conversation","title":"Multi-label Emotion Analysis in Conversation via Multimodal Knowledge Distillation","date":"2023-10-27","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/qilin-med-vl-towards-chinese-large-vision","slug":"qilin-med-vl-towards-chinese-large-vision","title":"Qilin-Med-VL: Towards Chinese Large Vision-Language Model for General Healthcare","date":"2023-10-27","arxiv_id":"2310.17956","n_code_links":1,"syntology":{"ran":4,"of":5,"n_ran_checked":3,"n_instrument":1,"unverified":1,"pointer_only":5,"phrase":"4 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; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["williamliujl/qilin-med-vl"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/revising-with-a-backward-glance-regressions","slug":"revising-with-a-backward-glance-regressions","title":"Revising with a Backward Glance: Regressions and Skips during Reading as Cognitive Signals for Revision Policies in Incremental Processing","date":"2023-10-27","arxiv_id":"2310.18229","n_code_links":1,"syntology":null},{"paper":"/paper/siamese-detr-for-generic-multi-object","slug":"siamese-detr-for-generic-multi-object","title":"Siamese-DETR for Generic Multi-Object Tracking","date":"2023-10-27","arxiv_id":"2310.17875","n_code_links":1,"syntology":null},{"paper":"/paper/soul-towards-sentiment-and-opinion","slug":"soul-towards-sentiment-and-opinion","title":"SOUL: Towards Sentiment and Opinion Understanding of Language","date":"2023-10-27","arxiv_id":"2310.17924","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 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) · 3 unverified","official":{"repos":["damo-nlp-sg/soul"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/sqlformer-deep-auto-regressive-query-graph","slug":"sqlformer-deep-auto-regressive-query-graph","title":"SQLformer: Deep Auto-Regressive Query Graph Generation for Text-to-SQL Translation","date":"2023-10-27","arxiv_id":"2310.18376","n_code_links":1,"syntology":null},{"paper":"/paper/transformers-as-graph-to-graph-models","slug":"transformers-as-graph-to-graph-models","title":"Transformers as Graph-to-Graph Models","date":"2023-10-27","arxiv_id":"2310.17936","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":2,"n_instrument":0,"unverified":1,"pointer_only":3,"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":["idiap/g2g-transformer"],"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":"/paper/what-you-see-is-what-you-detect-towards","slug":"what-you-see-is-what-you-detect-towards","title":"What You See Is What You Detect: Towards better Object Densification in 3D detection","date":"2023-10-27","arxiv_id":"2310.17842","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-framework-for-automated-measurement-of","title":"A Framework for Automated Measurement of Responsible AI Harms in Generative AI Applications","date":"2023-10-26","arxiv_id":"2310.17750","n_code_links":0,"syntology":null},{"paper":null,"slug":"bert-pin-a-bert-based-framework-for","title":"BERT-PIN: A BERT-based Framework for Recovering Missing Data Segments in Time-series Load Profiles","date":"2023-10-26","arxiv_id":"2310.17742","n_code_links":0,"syntology":null},{"paper":null,"slug":"can-large-language-models-replace-humans-in","title":"Can large language models replace humans in the systematic review process? Evaluating GPT-4's efficacy in screening and extracting data from peer-reviewed and grey literature in multiple languages","date":"2023-10-26","arxiv_id":"2310.17526","n_code_links":0,"syntology":null},{"paper":null,"slug":"can-llms-grade-short-answer-reading","title":"Can LLMs Grade Short-Answer Reading Comprehension Questions : An Empirical Study with a Novel Dataset","date":"2023-10-26","arxiv_id":"2310.18373","n_code_links":0,"syntology":null},{"paper":"/paper/codebook-features-sparse-and-discrete","slug":"codebook-features-sparse-and-discrete","title":"Codebook Features: Sparse and Discrete Interpretability for Neural Networks","date":"2023-10-26","arxiv_id":"2310.17230","n_code_links":1,"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: 1 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["taufeeque9/codebook-features"],"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/competeai-understanding-the-competition","slug":"competeai-understanding-the-competition","title":"CompeteAI: Understanding the Competition Dynamics in Large Language Model-based Agents","date":"2023-10-26","arxiv_id":"2310.17512","n_code_links":1,"syntology":{"ran":1,"of":5,"n_ran_checked":1,"n_instrument":0,"unverified":4,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","official":{"repos":["microsoft/competeai"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"cultural-adaptation-of-recipes","title":"Cultural Adaptation of Recipes","date":"2023-10-26","arxiv_id":"2310.17353","n_code_links":0,"syntology":null},{"paper":null,"slug":"is-explanation-the-cure-misinformation","title":"Is Explanation the Cure? Misinformation Mitigation in the Short Term and Long Term","date":"2023-10-26","arxiv_id":"2310.17711","n_code_links":0,"syntology":null},{"paper":"/paper/learning-to-abstract-with-nonparametric","slug":"learning-to-abstract-with-nonparametric","title":"Learning to Abstract with Nonparametric Variational Information Bottleneck","date":"2023-10-26","arxiv_id":"2310.17284","n_code_links":2,"syntology":{"ran":10,"of":15,"n_ran_checked":8,"n_instrument":2,"unverified":5,"pointer_only":15,"phrase":"10 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; 2 where Syntology's instrument failed) · 5 unverified","official":{"repos":["idiap/nvib","idiap/nvib_selfattention"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":"/paper/lightlm-a-lightweight-deep-and-narrow","slug":"lightlm-a-lightweight-deep-and-narrow","title":"LightLM: A Lightweight Deep and Narrow Language Model for Generative Recommendation","date":"2023-10-26","arxiv_id":"2310.17488","n_code_links":1,"syntology":{"ran":11,"of":12,"n_ran_checked":11,"n_instrument":0,"unverified":1,"pointer_only":12,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 1 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["dongyuanjushi/lightlm"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"mo-yolo-end-to-end-multiple-object-tracking","title":"DecoderTracker: Decoder-Only Method for Multiple-Object Tracking","date":"2023-10-26","arxiv_id":"2310.17170","n_code_links":0,"syntology":null},{"paper":null,"slug":"privacy-preserving-representation-learning-1","title":"Privacy-preserving Representation Learning for Speech Understanding","date":"2023-10-26","arxiv_id":"2310.17194","n_code_links":0,"syntology":null},{"paper":null,"slug":"skill-mix-a-flexible-and-expandable-family-of","title":"Skill-Mix: a Flexible and Expandable Family of Evaluations for AI models","date":"2023-10-26","arxiv_id":"2310.17567","n_code_links":0,"syntology":null},{"paper":"/paper/sliceformer-make-multi-head-attention-as","slug":"sliceformer-make-multi-head-attention-as","title":"Sliceformer: Make Multi-head Attention as Simple as Sorting in Discriminative Tasks","date":"2023-10-26","arxiv_id":"2310.17683","n_code_links":1,"syntology":null},{"paper":"/paper/the-expressive-power-of-low-rank-adaptation","slug":"the-expressive-power-of-low-rank-adaptation","title":"The Expressive Power of Low-Rank Adaptation","date":"2023-10-26","arxiv_id":"2310.17513","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":["uw-madison-lee-lab/expressive_power_of_lora"],"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/transformers-learn-higher-order-optimization","slug":"transformers-learn-higher-order-optimization","title":"Transformers Learn to Achieve Second-Order Convergence Rates for In-Context Linear Regression","date":"2023-10-26","arxiv_id":"2310.17086","n_code_links":1,"syntology":{"ran":8,"of":10,"n_ran_checked":6,"n_instrument":2,"unverified":2,"pointer_only":10,"phrase":"8 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; 2 where Syntology's instrument failed) · 2 unverified","official":{"repos":["deqingfu/transformers-icl-higher-order"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["found_in_text"]}}},{"paper":null,"slug":"you-are-an-expert-linguistic-annotator-limits","title":"\"You Are An Expert Linguistic Annotator\": Limits of LLMs as Analyzers of Abstract Meaning Representation","date":"2023-10-26","arxiv_id":"2310.17793","n_code_links":0,"syntology":null}],"record_sha256":"ede6945d40649fdb50290ba8cd393afd482f3c7a986de533397904ea79049e3f","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}