{"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/label-smoothing/papers/67","list_of":"/method/label-smoothing","method":"Label Smoothing","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":67,"pages_in_order":144,"rows_per_page":100,"rows":[6601,6700],"of":14327,"counts":{"archive_papers_tagged":14327,"with_a_code_link":6651,"where_syntology_ran_a_sample":2259,"not_listed_spam_title":0,"listed":14327,"listed_where_code_ran":2259,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1920,"every_run_a_failure_of_syntologys_instrument":339,"listed_with_a_run_with_no_instrument_failure":1920,"listed_every_run_a_failure_of_syntologys_instrument":339,"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/label-smoothing","prev":"/method/label-smoothing/papers/66","next":"/method/label-smoothing/papers/68","papers":[{"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/benchmark-generation-framework-with","slug":"benchmark-generation-framework-with","title":"Benchmark Generation Framework with Customizable Distortions for Image Classifier Robustness","date":"2023-10-28","arxiv_id":"2310.18626","n_code_links":1,"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},{"paper":null,"slug":"a-comprehensive-evaluation-of-constrained","title":"Evaluating, Understanding, and Improving Constrained Text Generation for Large Language Models","date":"2023-10-25","arxiv_id":"2310.16343","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-no-reference-quality-assessment-method-for","title":"A No-Reference Quality Assessment Method for Digital Human Head","date":"2023-10-25","arxiv_id":"2310.16732","n_code_links":0,"syntology":null},{"paper":"/paper/an-early-evaluation-of-gpt-4v-ision","slug":"an-early-evaluation-of-gpt-4v-ision","title":"An Early Evaluation of GPT-4V(ision)","date":"2023-10-25","arxiv_id":"2310.16534","n_code_links":1,"syntology":null},{"paper":null,"slug":"can-gpt-models-follow-human-summarization","title":"Can GPT models Follow Human Summarization Guidelines? Evaluating ChatGPT and GPT-4 for Dialogue Summarization","date":"2023-10-25","arxiv_id":"2310.16810","n_code_links":0,"syntology":null},{"paper":"/paper/clex-continuous-length-extrapolation-for","slug":"clex-continuous-length-extrapolation-for","title":"CLEX: Continuous Length Extrapolation for Large Language Models","date":"2023-10-25","arxiv_id":"2310.16450","n_code_links":1,"syntology":{"ran":9,"of":10,"n_ran_checked":6,"n_instrument":3,"unverified":1,"pointer_only":1,"phrase":"9 ran (of which 2 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","official":{"repos":["damo-nlp-sg/clex"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":2,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"graft-gradual-fusion-transformer-for","title":"GraFT: Gradual Fusion Transformer for Multimodal Re-Identification","date":"2023-10-25","arxiv_id":"2310.16856","n_code_links":0,"syntology":null},{"paper":"/paper/is-chatgpt-a-good-multi-party-conversation","slug":"is-chatgpt-a-good-multi-party-conversation","title":"Is ChatGPT a Good Multi-Party Conversation Solver?","date":"2023-10-25","arxiv_id":"2310.16301","n_code_links":1,"syntology":null},{"paper":"/paper/llm-fp4-4-bit-floating-point-quantized","slug":"llm-fp4-4-bit-floating-point-quantized","title":"LLM-FP4: 4-Bit Floating-Point Quantized Transformers","date":"2023-10-25","arxiv_id":"2310.16836","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"3 ran (of which 3 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) · 0 unverified; every one of the 3 samples that ran constructed an object rather than computing a result","official":{"repos":["nbasyl/llm-fp4"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/llm-performance-predictors-are-good","slug":"llm-performance-predictors-are-good","title":"LLM Performance Predictors are good initializers for Architecture Search","date":"2023-10-25","arxiv_id":"2310.16712","n_code_links":1,"syntology":{"ran":4,"of":6,"n_ran_checked":4,"n_instrument":0,"unverified":2,"pointer_only":6,"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":["ubc-nlp/llmas"],"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":"/paper/modality-agnostic-self-supervised-learning","slug":"modality-agnostic-self-supervised-learning","title":"Modality-Agnostic Self-Supervised Learning with Meta-Learned Masked Auto-Encoder","date":"2023-10-25","arxiv_id":"2310.16318","n_code_links":1,"syntology":{"ran":3,"of":8,"n_ran_checked":3,"n_instrument":0,"unverified":5,"pointer_only":8,"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":null}},{"paper":"/paper/netfound-foundation-model-for-network","slug":"netfound-foundation-model-for-network","title":"netFound: Foundation Model for Network Security","date":"2023-10-25","arxiv_id":"2310.17025","n_code_links":1,"syntology":null},{"paper":"/paper/occuquest-mitigating-occupational-bias-for","slug":"occuquest-mitigating-occupational-bias-for","title":"OccuQuest: Mitigating Occupational Bias for Inclusive Large Language Models","date":"2023-10-25","arxiv_id":"2310.16517","n_code_links":1,"syntology":null},{"paper":null,"slug":"rebuild-city-buildings-from-off-nadir-aerial","title":"Prompt-Driven Building Footprint Extraction in Aerial Images with Offset-Building Model","date":"2023-10-25","arxiv_id":"2310.16717","n_code_links":0,"syntology":null},{"paper":"/paper/smurf-thp-score-matching-based-uncertainty","slug":"smurf-thp-score-matching-based-uncertainty","title":"SMURF-THP: Score Matching-based UnceRtainty quantiFication for Transformer Hawkes Process","date":"2023-10-25","arxiv_id":"2310.16336","n_code_links":1,"syntology":null},{"paper":"/paper/superhf-supervised-iterative-learning-from","slug":"superhf-supervised-iterative-learning-from","title":"SuperHF: Supervised Iterative Learning from Human Feedback","date":"2023-10-25","arxiv_id":"2310.16763","n_code_links":1,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"0 ran · 1 unverified","official":{"repos":["openfeedback/superhf"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"paper":null,"slug":"transpose-6d-object-pose-estimation-with","title":"TransPose: 6D Object Pose Estimation with Geometry-Aware Transformer","date":"2023-10-25","arxiv_id":"2310.16279","n_code_links":0,"syntology":null},{"paper":null,"slug":"using-gpt-4-to-augment-unbalanced-data-for","title":"Using GPT-4 to Augment Unbalanced Data for Automatic Scoring","date":"2023-10-25","arxiv_id":"2310.18365","n_code_links":0,"syntology":null},{"paper":null,"slug":"confounder-balancing-in-adversarial-domain","title":"Confounder Balancing in Adversarial Domain Adaptation for Pre-Trained Large Models Fine-Tuning","date":"2023-10-24","arxiv_id":"2310.16062","n_code_links":0,"syntology":null},{"paper":null,"slug":"decoupled-detr-spatially-disentangling-1","title":"Decoupled DETR: Spatially Disentangling Localization and Classification for Improved End-to-End Object Detection","date":"2023-10-24","arxiv_id":"2310.15955","n_code_links":0,"syntology":null},{"paper":"/paper/dynamic-convolutional-neural-networks-as","slug":"dynamic-convolutional-neural-networks-as","title":"Dynamic Convolutional Neural Networks as Efficient Pre-trained Audio Models","date":"2023-10-24","arxiv_id":"2310.15648","n_code_links":1,"syntology":null},{"paper":"/paper/mixture-of-tokens-efficient-llms-through","slug":"mixture-of-tokens-efficient-llms-through","title":"Mixture of Tokens: Continuous MoE through Cross-Example Aggregation","date":"2023-10-24","arxiv_id":"2310.15961","n_code_links":1,"syntology":null},{"paper":"/paper/musr-testing-the-limits-of-chain-of-thought","slug":"musr-testing-the-limits-of-chain-of-thought","title":"MuSR: Testing the Limits of Chain-of-thought with Multistep Soft Reasoning","date":"2023-10-24","arxiv_id":"2310.16049","n_code_links":3,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"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) · 0 unverified","official":{"repos":["zayne-sprague/musr"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/notechat-a-dataset-of-synthetic-doctor","slug":"notechat-a-dataset-of-synthetic-doctor","title":"NoteChat: A Dataset of Synthetic Doctor-Patient Conversations Conditioned on Clinical Notes","date":"2023-10-24","arxiv_id":"2310.15959","n_code_links":1,"syntology":null},{"paper":null,"slug":"octopus-a-multitask-model-and-toolkit-for","title":"Octopus: A Multitask Model and Toolkit for Arabic Natural Language Generation","date":"2023-10-24","arxiv_id":"2310.16127","n_code_links":0,"syntology":null},{"paper":"/paper/practical-computational-power-of-linear","slug":"practical-computational-power-of-linear","title":"Practical Computational Power of Linear Transformers and Their Recurrent and Self-Referential Extensions","date":"2023-10-24","arxiv_id":"2310.16076","n_code_links":1,"syntology":{"ran":3,"of":4,"n_ran_checked":1,"n_instrument":2,"unverified":1,"pointer_only":4,"phrase":"3 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; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["idsia/fwp-formal-lang"],"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/trams-training-free-memory-selection-for-long","slug":"trams-training-free-memory-selection-for-long","title":"TRAMS: Training-free Memory Selection for Long-range Language Modeling","date":"2023-10-24","arxiv_id":"2310.15494","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":["lwaekfjlk/trams"],"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":"ui-layout-generation-with-llms-guided-by-ui","title":"UI Layout Generation with LLMs Guided by UI Grammar","date":"2023-10-24","arxiv_id":"2310.15455","n_code_links":0,"syntology":null},{"paper":null,"slug":"what-algorithms-can-transformers-learn-a","title":"What Algorithms can Transformers Learn? A Study in Length Generalization","date":"2023-10-24","arxiv_id":"2310.16028","n_code_links":0,"syntology":null},{"paper":"/paper/alpacare-instruction-tuned-large-language","slug":"alpacare-instruction-tuned-large-language","title":"AlpaCare:Instruction-tuned Large Language Models for Medical Application","date":"2023-10-23","arxiv_id":"2310.14558","n_code_links":1,"syntology":{"ran":7,"of":7,"n_ran_checked":7,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["xzhang97666/alpacare"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"analyzing-multilingual-competency-of-llms-in","title":"Analyzing Multilingual Competency of LLMs in Multi-Turn Instruction Following: A Case Study of Arabic","date":"2023-10-23","arxiv_id":"2310.14819","n_code_links":0,"syntology":null},{"paper":null,"slug":"branch-solve-merge-improves-large-language","title":"Branch-Solve-Merge Improves Large Language Model Evaluation and Generation","date":"2023-10-23","arxiv_id":"2310.15123","n_code_links":0,"syntology":null},{"paper":"/paper/calibration-of-time-series-forecasting","slug":"calibration-of-time-series-forecasting","title":"Calibration of Time-Series Forecasting: Detecting and Adapting Context-Driven Distribution Shift","date":"2023-10-23","arxiv_id":"2310.14838","n_code_links":2,"syntology":{"ran":7,"of":8,"n_ran_checked":4,"n_instrument":3,"unverified":1,"pointer_only":2,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","official":{"repos":["half111/calibration_cds"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"causal-inference-using-llm-guided-discovery","title":"Causal Inference Using LLM-Guided Discovery","date":"2023-10-23","arxiv_id":"2310.15117","n_code_links":0,"syntology":null},{"paper":"/paper/evaluating-spatial-understanding-of-large","slug":"evaluating-spatial-understanding-of-large","title":"Evaluating Spatial Understanding of Large Language Models","date":"2023-10-23","arxiv_id":"2310.14540","n_code_links":1,"syntology":{"ran":3,"of":6,"n_ran_checked":3,"n_instrument":0,"unverified":3,"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) · 3 unverified","official":{"repos":["runopti/spatialevalllm"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"evaluating-the-knowledge-base-completion","title":"Evaluating the Knowledge Base Completion Potential of GPT","date":"2023-10-23","arxiv_id":"2310.14771","n_code_links":0,"syntology":null},{"paper":null,"slug":"exploring-the-boundaries-of-gpt-4-in","title":"Exploring the Boundaries of GPT-4 in Radiology","date":"2023-10-23","arxiv_id":"2310.14573","n_code_links":0,"syntology":null},{"paper":null,"slug":"generative-pre-trained-transformer-for-1","title":"Generative Pre-trained Transformer for Vietnamese Community-based COVID-19 Question Answering","date":"2023-10-23","arxiv_id":"2310.14602","n_code_links":0,"syntology":null},{"paper":null,"slug":"gpt-4-as-an-effective-zero-shot-evaluator-for","title":"GPT-4 as an Effective Zero-Shot Evaluator for Scientific Figure Captions","date":"2023-10-23","arxiv_id":"2310.15405","n_code_links":0,"syntology":null},{"paper":null,"slug":"hallucination-detection-for-grounded","title":"Hallucination Detection for Grounded Instruction Generation","date":"2023-10-23","arxiv_id":"2310.15319","n_code_links":0,"syntology":null},{"paper":null,"slug":"instructexcel-a-benchmark-for-natural","title":"InstructExcel: A Benchmark for Natural Language Instruction in Excel","date":"2023-10-23","arxiv_id":"2310.14495","n_code_links":0,"syntology":null},{"paper":"/paper/large-language-models-can-share-images-too","slug":"large-language-models-can-share-images-too","title":"Large Language Models can Share Images, Too!","date":"2023-10-23","arxiv_id":"2310.14804","n_code_links":2,"syntology":null},{"paper":"/paper/linc-a-neurosymbolic-approach-for-logical","slug":"linc-a-neurosymbolic-approach-for-logical","title":"LINC: A Neurosymbolic Approach for Logical Reasoning by Combining Language Models with First-Order Logic Provers","date":"2023-10-23","arxiv_id":"2310.15164","n_code_links":1,"syntology":{"ran":1,"of":7,"n_ran_checked":0,"n_instrument":1,"unverified":6,"pointer_only":7,"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) · 6 unverified","official":{"repos":["benlipkin/linc"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":6,"ran_from_kinds":["official"]}}},{"paper":"/paper/location-aware-visual-question-generation","slug":"location-aware-visual-question-generation","title":"Location-Aware Visual Question Generation with Lightweight Models","date":"2023-10-23","arxiv_id":"2310.15129","n_code_links":1,"syntology":null},{"paper":"/paper/non-autoregressive-streaming-transformer-for","slug":"non-autoregressive-streaming-transformer-for","title":"Non-autoregressive Streaming Transformer for Simultaneous Translation","date":"2023-10-23","arxiv_id":"2310.14883","n_code_links":1,"syntology":{"ran":5,"of":5,"n_ran_checked":4,"n_instrument":1,"unverified":0,"pointer_only":5,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["ictnlp/nast"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/p2at-pyramid-pooling-axial-transformer-for","slug":"p2at-pyramid-pooling-axial-transformer-for","title":"P2AT: Pyramid Pooling Axial Transformer for Real-time Semantic Segmentation","date":"2023-10-23","arxiv_id":"2310.15025","n_code_links":1,"syntology":null},{"paper":"/paper/partialformer-modeling-part-instead-of-whole","slug":"partialformer-modeling-part-instead-of-whole","title":"PartialFormer: Modeling Part Instead of Whole for Machine Translation","date":"2023-10-23","arxiv_id":"2310.14921","n_code_links":1,"syntology":null},{"paper":"/paper/slog-a-structural-generalization-benchmark","slug":"slog-a-structural-generalization-benchmark","title":"SLOG: A Structural Generalization Benchmark for Semantic Parsing","date":"2023-10-23","arxiv_id":"2310.15040","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":1,"n_instrument":1,"unverified":0,"pointer_only":0,"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":["bingzhilee/slog"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/teleqna-a-benchmark-dataset-to-assess-large","slug":"teleqna-a-benchmark-dataset-to-assess-large","title":"TeleQnA: A Benchmark Dataset to Assess Large Language Models Telecommunications Knowledge","date":"2023-10-23","arxiv_id":"2310.15051","n_code_links":1,"syntology":null},{"paper":"/paper/text2topic-multi-label-text-classification","slug":"text2topic-multi-label-text-classification","title":"Text2Topic: Multi-Label Text Classification System for Efficient Topic Detection in User Generated Content with Zero-Shot Capabilities","date":"2023-10-23","arxiv_id":"2310.14817","n_code_links":1,"syntology":null},{"paper":null,"slug":"unleashing-the-potential-of-prompt","title":"Unleashing the potential of prompt engineering for large language models","date":"2023-10-23","arxiv_id":"2310.14735","n_code_links":0,"syntology":null},{"paper":"/paper/a-pytorch-reproduction-of-masked-generative","slug":"a-pytorch-reproduction-of-masked-generative","title":"A Pytorch Reproduction of Masked Generative Image Transformer","date":"2023-10-22","arxiv_id":"2310.14400","n_code_links":1,"syntology":null}],"record_sha256":"1b8e12115e7e64dc217c2238eb782d794929addaac097a96a759dfdf026ad992","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}