{"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/bpe/papers/130","list_of":"/method/bpe","method":"BPE","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":130,"pages_in_order":190,"rows_per_page":100,"rows":[12901,13000],"of":18975,"counts":{"archive_papers_tagged":18975,"with_a_code_link":8675,"where_syntology_ran_a_sample":2895,"not_listed_spam_title":0,"listed":18975,"listed_where_code_ran":2895,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":2443,"every_run_a_failure_of_syntologys_instrument":452,"listed_with_a_run_with_no_instrument_failure":2443,"listed_every_run_a_failure_of_syntologys_instrument":452,"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/bpe","prev":"/method/bpe/papers/129","next":"/method/bpe/papers/131","papers":[{"paper":"/paper/rethinking-with-retrieval-faithful-large","slug":"rethinking-with-retrieval-faithful-large","title":"Rethinking with Retrieval: Faithful Large Language Model Inference","date":"2022-12-31","arxiv_id":"2301.00303","n_code_links":1,"syntology":null},{"paper":"/paper/transifc-invariant-cues-aware-feature","slug":"transifc-invariant-cues-aware-feature","title":"TransIFC: Invariant Cues-aware Feature Concentration Learning for Efficient Fine-grained Bird Image Classification","date":"2022-12-31","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"memory-augmented-lookup-dictionary-based","title":"Memory Augmented Lookup Dictionary based Language Modeling for Automatic Speech Recognition","date":"2022-12-30","arxiv_id":"2301.00066","n_code_links":0,"syntology":null},{"paper":"/paper/on-the-inconsistencies-of-conditionals","slug":"on-the-inconsistencies-of-conditionals","title":"Inconsistencies in Masked Language Models","date":"2022-12-30","arxiv_id":"2301.00068","n_code_links":1,"syntology":null},{"paper":null,"slug":"targeted-phishing-campaigns-using-large-scale","title":"Targeted Phishing Campaigns using Large Scale Language Models","date":"2022-12-30","arxiv_id":"2301.00665","n_code_links":0,"syntology":null},{"paper":"/paper/transformer-in-transformer-as-backbone-for","slug":"transformer-in-transformer-as-backbone-for","title":"Transformer in Transformer as Backbone for Deep Reinforcement Learning","date":"2022-12-30","arxiv_id":"2212.14538","n_code_links":1,"syntology":null},{"paper":"/paper/efficient-image-super-resolution-with-feature","slug":"efficient-image-super-resolution-with-feature","title":"Efficient Image Super-Resolution with Feature Interaction Weighted Hybrid Network","date":"2022-12-29","arxiv_id":"2212.14181","n_code_links":1,"syntology":null},{"paper":"/paper/efficient-movie-scene-detection-using-state","slug":"efficient-movie-scene-detection-using-state","title":"Efficient Movie Scene Detection using State-Space Transformers","date":"2022-12-29","arxiv_id":"2212.14427","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["md-mohaiminul/trans4mer"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"error-syntax-aware-augmentation-of-feedback","title":"Error syntax aware augmentation of feedback comment generation dataset","date":"2022-12-29","arxiv_id":"2212.14293","n_code_links":0,"syntology":null},{"paper":null,"slug":"exploring-depth-information-for-face","title":"Exploring Depth Information for Face Manipulation Detection","date":"2022-12-29","arxiv_id":"2212.14230","n_code_links":0,"syntology":null},{"paper":"/paper/gpt-takes-the-bar-exam","slug":"gpt-takes-the-bar-exam","title":"GPT Takes the Bar Exam","date":"2022-12-29","arxiv_id":"2212.14402","n_code_links":5,"syntology":null},{"paper":null,"slug":"maximizing-use-case-specificity-through","title":"Maximizing Use-Case Specificity through Precision Model Tuning","date":"2022-12-29","arxiv_id":"2212.14206","n_code_links":0,"syntology":null},{"paper":"/paper/unsupervised-construction-of-representations","slug":"unsupervised-construction-of-representations","title":"Robust representations of oil wells' intervals via sparse attention mechanism","date":"2022-12-29","arxiv_id":"2212.14246","n_code_links":2,"syntology":null},{"paper":"/paper/part-guided-relational-transformers-for-fine","slug":"part-guided-relational-transformers-for-fine","title":"Part-guided Relational Transformers for Fine-grained Visual Recognition","date":"2022-12-28","arxiv_id":"2212.13685","n_code_links":1,"syntology":null},{"paper":null,"slug":"revealed-uncovering-pro-eating-disorder","title":"RevealED: Uncovering Pro-Eating Disorder Content on Twitter Using Deep Learning","date":"2022-12-28","arxiv_id":"2212.13949","n_code_links":0,"syntology":null},{"paper":"/paper/swin-mae-masked-autoencoders-for-small","slug":"swin-mae-masked-autoencoders-for-small","title":"Swin MAE: Masked Autoencoders for Small Datasets","date":"2022-12-28","arxiv_id":"2212.13805","n_code_links":1,"syntology":null},{"paper":null,"slug":"thermal-heating-in-reram-crossbar-arrays","title":"Thermal Heating in ReRAM Crossbar Arrays: Challenges and Solutions","date":"2022-12-28","arxiv_id":"2212.13707","n_code_links":0,"syntology":null},{"paper":"/paper/1st-place-solution-for-youtubevos-challenge-1","slug":"1st-place-solution-for-youtubevos-challenge-1","title":"1st Place Solution for YouTubeVOS Challenge 2022: Referring Video Object Segmentation","date":"2022-12-27","arxiv_id":"2212.14679","n_code_links":1,"syntology":null},{"paper":"/paper/a-generalization-of-vit-mlp-mixer-to-graphs","slug":"a-generalization-of-vit-mlp-mixer-to-graphs","title":"A Generalization of ViT/MLP-Mixer to Graphs","date":"2022-12-27","arxiv_id":"2212.13350","n_code_links":3,"syntology":{"ran":2,"of":3,"n_ran_checked":2,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["XiaoxinHe/Graph-ViT-MLPMixer"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":"/paper/bart-it-an-efficient-sequence-to-sequence","slug":"bart-it-an-efficient-sequence-to-sequence","title":"BART-IT: An Efficient Sequence-to-Sequence Model for Italian Text Summarization","date":"2022-12-27","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/countering-malicious-content-moderation","slug":"countering-malicious-content-moderation","title":"Countering Malicious Content Moderation Evasion in Online Social Networks: Simulation and Detection of Word Camouflage","date":"2022-12-27","arxiv_id":"2212.14727","n_code_links":1,"syntology":null},{"paper":"/paper/dae-former-dual-attention-guided-efficient","slug":"dae-former-dual-attention-guided-efficient","title":"DAE-Former: Dual Attention-guided Efficient Transformer for Medical Image Segmentation","date":"2022-12-27","arxiv_id":"2212.13504","n_code_links":1,"syntology":null},{"paper":"/paper/deepcuts-single-shot-interpretability-based","slug":"deepcuts-single-shot-interpretability-based","title":"DeepCuts: Single-Shot Interpretability based Pruning for BERT","date":"2022-12-27","arxiv_id":"2212.13392","n_code_links":1,"syntology":null},{"paper":null,"slug":"exploring-transformer-backbones-for-image","title":"Exploring Transformer Backbones for Image Diffusion Models","date":"2022-12-27","arxiv_id":"2212.14678","n_code_links":0,"syntology":null},{"paper":null,"slug":"tegformer-topic-to-essay-generation-with-good","title":"TegFormer: Topic-to-Essay Generation with Good Topic Coverage and High Text Coherence","date":"2022-12-27","arxiv_id":"2212.13456","n_code_links":0,"syntology":null},{"paper":null,"slug":"using-large-language-models-to-generate","title":"Using Large Language Models to Generate Engaging Captions for Data Visualizations","date":"2022-12-27","arxiv_id":"2212.14047","n_code_links":0,"syntology":null},{"paper":null,"slug":"biologically-inspired-design-concept","title":"Biologically Inspired Design Concept Generation Using Generative Pre-Trained Transformers","date":"2022-12-26","arxiv_id":"2212.13196","n_code_links":0,"syntology":null},{"paper":null,"slug":"transformer-and-gan-based-super-resolution","title":"Transformer and GAN Based Super-Resolution Reconstruction Network for Medical Images","date":"2022-12-26","arxiv_id":"2212.13068","n_code_links":0,"syntology":null},{"paper":"/paper/typeformer-transformers-for-mobile-keystroke","slug":"typeformer-transformers-for-mobile-keystroke","title":"TypeFormer: Transformers for Mobile Keystroke Biometrics","date":"2022-12-26","arxiv_id":"2212.13075","n_code_links":1,"syntology":null},{"paper":null,"slug":"boosting-urban-traffic-speed-prediction-via","title":"Boosting Urban Traffic Speed Prediction via Integrating Implicit Spatial Correlations","date":"2022-12-25","arxiv_id":"2212.12932","n_code_links":0,"syntology":null},{"paper":"/paper/hybrid-representation-learning-for-cognitive","slug":"hybrid-representation-learning-for-cognitive","title":"Hybrid Representation Learning for Cognitive Diagnosis in Late-Life Depression Over 5 Years with Structural MRI","date":"2022-12-24","arxiv_id":"2212.12810","n_code_links":1,"syntology":null},{"paper":"/paper/on-realization-of-intelligent-decision-making","slug":"on-realization-of-intelligent-decision-making","title":"On Realization of Intelligent Decision-Making in the Real World: A Foundation Decision Model Perspective","date":"2022-12-24","arxiv_id":"2212.12669","n_code_links":1,"syntology":null},{"paper":null,"slug":"optimizing-deep-transformers-for-chinese-thai","title":"Optimizing Deep Transformers for Chinese-Thai Low-Resource Translation","date":"2022-12-24","arxiv_id":"2212.12662","n_code_links":0,"syntology":null},{"paper":"/paper/a-close-look-at-spatial-modeling-from","slug":"a-close-look-at-spatial-modeling-from","title":"A Close Look at Spatial Modeling: From Attention to Convolution","date":"2022-12-23","arxiv_id":"2212.12552","n_code_links":1,"syntology":null},{"paper":null,"slug":"amdet-attention-based-multiple-dimensions-eeg","title":"AMDET: Attention based Multiple Dimensions EEG Transformer for Emotion Recognition","date":"2022-12-23","arxiv_id":"2212.12134","n_code_links":0,"syntology":null},{"paper":"/paper/benchmark-for-uncertainty-robustness-in-self","slug":"benchmark-for-uncertainty-robustness-in-self","title":"Benchmark for Uncertainty & Robustness in Self-Supervised Learning","date":"2022-12-23","arxiv_id":"2212.12411","n_code_links":1,"syntology":null},{"paper":null,"slug":"detecting-objects-with-graph-priors-and-graph","title":"Detecting Objects with Context-Likelihood Graphs and Graph Refinement","date":"2022-12-23","arxiv_id":"2212.12395","n_code_links":0,"syntology":null},{"paper":null,"slug":"why-does-surprisal-from-larger-transformer","title":"Why Does Surprisal From Larger Transformer-Based Language Models Provide a Poorer Fit to Human Reading Times?","date":"2022-12-23","arxiv_id":"2212.12131","n_code_links":0,"syntology":null},{"paper":"/paper/genie-large-scale-pre-training-for-text","slug":"genie-large-scale-pre-training-for-text","title":"Text Generation with Diffusion Language Models: A Pre-training Approach with Continuous Paragraph Denoise","date":"2022-12-22","arxiv_id":"2212.11685","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["microsoft/ProphetNet"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"when-are-lemons-purple-the-concept","title":"When are Lemons Purple? The Concept Association Bias of Vision-Language Models","date":"2022-12-22","arxiv_id":"2212.12043","n_code_links":0,"syntology":null},{"paper":"/paper/analyzing-semantic-faithfulness-of-language","slug":"analyzing-semantic-faithfulness-of-language","title":"Analyzing Semantic Faithfulness of Language Models via Input Intervention on Question Answering","date":"2022-12-21","arxiv_id":"2212.10696","n_code_links":1,"syntology":null},{"paper":"/paper/automatic-emotion-modelling-in-written","slug":"automatic-emotion-modelling-in-written","title":"Automatic Emotion Modelling in Written Stories","date":"2022-12-21","arxiv_id":"2212.11382","n_code_links":1,"syntology":null},{"paper":"/paper/beyond-contrastive-learning-a-variational","slug":"beyond-contrastive-learning-a-variational","title":"Beyond Contrastive Learning: A Variational Generative Model for Multilingual Retrieval","date":"2022-12-21","arxiv_id":"2212.10726","n_code_links":1,"syntology":null},{"paper":"/paper/duat-dual-aggregation-transformer-network-for","slug":"duat-dual-aggregation-transformer-network-for","title":"DuAT: Dual-Aggregation Transformer Network for Medical Image Segmentation","date":"2022-12-21","arxiv_id":"2212.11677","n_code_links":1,"syntology":null},{"paper":"/paper/entropy-and-distance-based-predictors-from","slug":"entropy-and-distance-based-predictors-from","title":"Entropy- and Distance-Based Predictors From GPT-2 Attention Patterns Predict Reading Times Over and Above GPT-2 Surprisal","date":"2022-12-21","arxiv_id":"2212.11185","n_code_links":1,"syntology":{"ran":7,"of":11,"n_ran_checked":7,"n_instrument":0,"unverified":4,"pointer_only":8,"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) · 4 unverified","official":{"repos":["byungdoh/attn_dist"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"investigation-of-network-architecture-for","title":"Investigation of Network Architecture for Multimodal Head-and-Neck Tumor Segmentation","date":"2022-12-21","arxiv_id":"2212.10724","n_code_links":0,"syntology":null},{"paper":null,"slug":"jasmine-arabic-gpt-models-for-few-shot","title":"JASMINE: Arabic GPT Models for Few-Shot Learning","date":"2022-12-21","arxiv_id":"2212.10755","n_code_links":0,"syntology":null},{"paper":null,"slug":"kl-regularized-normalization-framework-for","title":"KL Regularized Normalization Framework for Low Resource Tasks","date":"2022-12-21","arxiv_id":"2212.11275","n_code_links":0,"syntology":null},{"paper":"/paper/slgtformer-an-attention-based-approach-to","slug":"slgtformer-an-attention-based-approach-to","title":"SLGTformer: An Attention-Based Approach to Sign Language Recognition","date":"2022-12-21","arxiv_id":"2212.10746","n_code_links":1,"syntology":null},{"paper":null,"slug":"spoken-language-understanding-for","title":"Spoken Language Understanding for Conversational AI: Recent Advances and Future Direction","date":"2022-12-21","arxiv_id":"2212.10728","n_code_links":0,"syntology":null},{"paper":null,"slug":"text-classification-in-shipping-industry","title":"Text classification in shipping industry using unsupervised models and Transformer based supervised models","date":"2022-12-21","arxiv_id":"2212.12407","n_code_links":0,"syntology":null},{"paper":"/paper/uncontrolled-lexical-exposure-leads-to","slug":"uncontrolled-lexical-exposure-leads-to","title":"Uncontrolled Lexical Exposure Leads to Overestimation of Compositional Generalization in Pretrained Models","date":"2022-12-21","arxiv_id":"2212.10769","n_code_links":1,"syntology":null},{"paper":"/paper/a-length-extrapolatable-transformer","slug":"a-length-extrapolatable-transformer","title":"A Length-Extrapolatable Transformer","date":"2022-12-20","arxiv_id":"2212.10554","n_code_links":5,"syntology":{"ran":4,"of":6,"n_ran_checked":4,"n_instrument":0,"unverified":2,"pointer_only":2,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 2 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["microsoft/torchscale"],"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":["listed","unlocated"]}}},{"paper":"/paper/bygpt5-end-to-end-style-conditioned-poetry","slug":"bygpt5-end-to-end-style-conditioned-poetry","title":"ByGPT5: End-to-End Style-conditioned Poetry Generation with Token-free Language Models","date":"2022-12-20","arxiv_id":"2212.10474","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["potamides/uniformers"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"controllable-text-generation-with-language","title":"Controllable Text Generation with Language Constraints","date":"2022-12-20","arxiv_id":"2212.10466","n_code_links":0,"syntology":null},{"paper":null,"slug":"diff-glat-diffusion-glancing-transformer-for","title":"Diffusion Glancing Transformer for Parallel Sequence to Sequence Learning","date":"2022-12-20","arxiv_id":"2212.10240","n_code_links":0,"syntology":null},{"paper":"/paper/do-language-models-have-coherent-mental","slug":"do-language-models-have-coherent-mental","title":"Do language models have coherent mental models of everyday things?","date":"2022-12-20","arxiv_id":"2212.10029","n_code_links":1,"syntology":{"ran":0,"of":5,"n_ran_checked":0,"n_instrument":0,"unverified":5,"pointer_only":0,"phrase":"0 ran · 5 unverified","official":{"repos":["allenai/everyday-things"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":5,"ran_from_kinds":[]}}},{"paper":"/paper/docasref-a-pilot-empirical-study-on","slug":"docasref-a-pilot-empirical-study-on","title":"DocAsRef: An Empirical Study on Repurposing Reference-Based Summary Quality Metrics Reference-Freely","date":"2022-12-20","arxiv_id":"2212.10013","n_code_links":1,"syntology":null},{"paper":"/paper/eit-enhanced-interactive-transformer","slug":"eit-enhanced-interactive-transformer","title":"EIT: Enhanced Interactive Transformer","date":"2022-12-20","arxiv_id":"2212.10197","n_code_links":2,"syntology":null},{"paper":null,"slug":"future-sight-dynamic-story-generation-with","title":"Future Sight: Dynamic Story Generation with Large Pretrained Language Models","date":"2022-12-20","arxiv_id":"2212.09947","n_code_links":0,"syntology":null},{"paper":null,"slug":"generic-temporal-reasoning-with-differential","title":"Generic Temporal Reasoning with Differential Analysis and Explanation","date":"2022-12-20","arxiv_id":"2212.10467","n_code_links":0,"syntology":null},{"paper":null,"slug":"go-tuning-improving-zero-shot-learning","title":"Go-tuning: Improving Zero-shot Learning Abilities of Smaller Language Models","date":"2022-12-20","arxiv_id":"2212.10461","n_code_links":0,"syntology":null},{"paper":"/paper/is-gpt-3-a-good-data-annotator","slug":"is-gpt-3-a-good-data-annotator","title":"Is GPT-3 a Good Data Annotator?","date":"2022-12-20","arxiv_id":"2212.10450","n_code_links":1,"syntology":null},{"paper":null,"slug":"is-gpt-3-a-psychopath-evaluating-large","title":"Evaluating Psychological Safety of Large Language Models","date":"2022-12-20","arxiv_id":"2212.10529","n_code_links":0,"syntology":null},{"paper":null,"slug":"krona-parameter-efficient-tuning-with","title":"KronA: Parameter Efficient Tuning with Kronecker Adapter","date":"2022-12-20","arxiv_id":"2212.10650","n_code_links":0,"syntology":null},{"paper":"/paper/large-language-models-are-reasoning-teachers","slug":"large-language-models-are-reasoning-teachers","title":"Large Language Models Are Reasoning Teachers","date":"2022-12-20","arxiv_id":"2212.10071","n_code_links":1,"syntology":{"ran":7,"of":9,"n_ran_checked":7,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["itsnamgyu/reasoning-teacher"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/meteor-guided-divergence-for-video-captioning","slug":"meteor-guided-divergence-for-video-captioning","title":"METEOR Guided Divergence for Video Captioning","date":"2022-12-20","arxiv_id":"2212.10690","n_code_links":1,"syntology":null},{"paper":null,"slug":"pairreranker-pairwise-reranking-for-natural","title":"PairReranker: Pairwise Reranking for Natural Language Generation","date":"2022-12-20","arxiv_id":"2212.10555","n_code_links":0,"syntology":null},{"paper":"/paper/pay-attention-to-your-tone-introducing-a-new","slug":"pay-attention-to-your-tone-introducing-a-new","title":"Pay Attention to Your Tone: Introducing a New Dataset for Polite Language Rewrite","date":"2022-12-20","arxiv_id":"2212.10190","n_code_links":1,"syntology":null},{"paper":null,"slug":"receptive-field-alignment-enables-transformer","title":"Dissecting Transformer Length Extrapolation via the Lens of Receptive Field Analysis","date":"2022-12-20","arxiv_id":"2212.10356","n_code_links":0,"syntology":null},{"paper":"/paper/t-projection-high-quality-annotation","slug":"t-projection-high-quality-annotation","title":"T-Projection: High Quality Annotation Projection for Sequence Labeling Tasks","date":"2022-12-20","arxiv_id":"2212.10548","n_code_links":2,"syntology":null},{"paper":null,"slug":"true-detective-a-challenging-benchmark-for","title":"True Detective: A Deep Abductive Reasoning Benchmark Undoable for GPT-3 and Challenging for GPT-4","date":"2022-12-20","arxiv_id":"2212.10114","n_code_links":0,"syntology":null},{"paper":"/paper/why-can-gpt-learn-in-context-language-models","slug":"why-can-gpt-learn-in-context-language-models","title":"Why Can GPT Learn In-Context? Language Models Implicitly Perform Gradient Descent as Meta-Optimizers","date":"2022-12-20","arxiv_id":"2212.10559","n_code_links":1,"syntology":null},{"paper":"/paper/difformer-empowering-diffusion-model-on","slug":"difformer-empowering-diffusion-model-on","title":"Empowering Diffusion Models on the Embedding Space for Text Generation","date":"2022-12-19","arxiv_id":"2212.09412","n_code_links":1,"syntology":{"ran":10,"of":11,"n_ran_checked":8,"n_instrument":2,"unverified":1,"pointer_only":9,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 3 honoured, 0 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["zhjgao/difformer"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/do-conll-2003-named-entity-taggers-still-work","slug":"do-conll-2003-named-entity-taggers-still-work","title":"Do CoNLL-2003 Named Entity Taggers Still Work Well in 2023?","date":"2022-12-19","arxiv_id":"2212.09747","n_code_links":1,"syntology":null},{"paper":"/paper/emergent-analogical-reasoning-in-large","slug":"emergent-analogical-reasoning-in-large","title":"Emergent Analogical Reasoning in Large Language Models","date":"2022-12-19","arxiv_id":"2212.09196","n_code_links":2,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["taylorwwebb/emergent_analogies_llm"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":"/paper/evaluating-human-language-model-interaction","slug":"evaluating-human-language-model-interaction","title":"Evaluating Human-Language Model Interaction","date":"2022-12-19","arxiv_id":"2212.09746","n_code_links":1,"syntology":null},{"paper":"/paper/large-language-models-are-reasoners-with-self","slug":"large-language-models-are-reasoners-with-self","title":"Large Language Models are Better Reasoners with Self-Verification","date":"2022-12-19","arxiv_id":"2212.09561","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":["WENGSYX/Self-Verification"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"paper":"/paper/lens-a-learnable-evaluation-metric-for-text","slug":"lens-a-learnable-evaluation-metric-for-text","title":"LENS: A Learnable Evaluation Metric for Text Simplification","date":"2022-12-19","arxiv_id":"2212.09739","n_code_links":1,"syntology":null},{"paper":null,"slug":"miga-a-unified-multi-task-generation","title":"MIGA: A Unified Multi-task Generation Framework for Conversational Text-to-SQL","date":"2022-12-19","arxiv_id":"2212.09278","n_code_links":0,"syntology":null},{"paper":"/paper/mist-multi-modal-iterative-spatial-temporal","slug":"mist-multi-modal-iterative-spatial-temporal","title":"MIST: Multi-modal Iterative Spatial-Temporal Transformer for Long-form Video Question Answering","date":"2022-12-19","arxiv_id":"2212.09522","n_code_links":1,"syntology":null},{"paper":null,"slug":"mu-2-slam-multitask-multilingual-speech-and","title":"Mu$^{2}$SLAM: Multitask, Multilingual Speech and Language Models","date":"2022-12-19","arxiv_id":"2212.09553","n_code_links":0,"syntology":null},{"paper":null,"slug":"multilingual-sequence-to-sequence-models-for","title":"Multilingual Sequence-to-Sequence Models for Hebrew NLP","date":"2022-12-19","arxiv_id":"2212.09682","n_code_links":0,"syntology":null},{"paper":"/paper/reasoning-with-language-model-prompting-a","slug":"reasoning-with-language-model-prompting-a","title":"Reasoning with Language Model Prompting: A Survey","date":"2022-12-19","arxiv_id":"2212.09597","n_code_links":2,"syntology":null},{"paper":null,"slug":"srtr-self-reasoning-transformer-with-visual","title":"SrTR: Self-reasoning Transformer with Visual-linguistic Knowledge for Scene Graph Generation","date":"2022-12-19","arxiv_id":"2212.09329","n_code_links":0,"syntology":null},{"paper":"/paper/the-case-for-4-bit-precision-k-bit-inference","slug":"the-case-for-4-bit-precision-k-bit-inference","title":"The case for 4-bit precision: k-bit Inference Scaling Laws","date":"2022-12-19","arxiv_id":"2212.09720","n_code_links":1,"syntology":null},{"paper":"/paper/tokenization-consistency-matters-for","slug":"tokenization-consistency-matters-for","title":"Tokenization Consistency Matters for Generative Models on Extractive NLP Tasks","date":"2022-12-19","arxiv_id":"2212.09912","n_code_links":1,"syntology":null},{"paper":"/paper/can-retriever-augmented-language-models","slug":"can-retriever-augmented-language-models","title":"Can Retriever-Augmented Language Models Reason? The Blame Game Between the Retriever and the Language Model","date":"2022-12-18","arxiv_id":"2212.09146","n_code_links":1,"syntology":null},{"paper":"/paper/style-hallucinated-dual-consistency-learning-1","slug":"style-hallucinated-dual-consistency-learning-1","title":"Style-Hallucinated Dual Consistency Learning: A Unified Framework for Visual Domain Generalization","date":"2022-12-18","arxiv_id":"2212.09068","n_code_links":1,"syntology":null},{"paper":"/paper/claim-optimization-in-computational","slug":"claim-optimization-in-computational","title":"Claim Optimization in Computational Argumentation","date":"2022-12-17","arxiv_id":"2212.08913","n_code_links":1,"syntology":null},{"paper":"/paper/leveraging-wastewater-monitoring-for-covid-19","slug":"leveraging-wastewater-monitoring-for-covid-19","title":"Leveraging Wastewater Monitoring for COVID-19 Forecasting in the US: a Deep Learning study","date":"2022-12-17","arxiv_id":"2212.08798","n_code_links":1,"syntology":null},{"paper":"/paper/autoencoders-as-cross-modal-teachers-can","slug":"autoencoders-as-cross-modal-teachers-can","title":"Autoencoders as Cross-Modal Teachers: Can Pretrained 2D Image Transformers Help 3D Representation Learning?","date":"2022-12-16","arxiv_id":"2212.08320","n_code_links":4,"syntology":null},{"paper":"/paper/convolution-enhanced-evolving-attention","slug":"convolution-enhanced-evolving-attention","title":"Convolution-enhanced Evolving Attention Networks","date":"2022-12-16","arxiv_id":"2212.08330","n_code_links":1,"syntology":null},{"paper":"/paper/homonymy-information-for-english-wordnet-1","slug":"homonymy-information-for-english-wordnet-1","title":"Homonymy Information for English WordNet","date":"2022-12-16","arxiv_id":"2212.08388","n_code_links":1,"syntology":null},{"paper":"/paper/ledcnet-a-lightweight-and-efficient-semantic","slug":"ledcnet-a-lightweight-and-efficient-semantic","title":"LOANet: A Lightweight Network Using Object Attention for Extracting Buildings and Roads from UAV Aerial Remote Sensing Images","date":"2022-12-16","arxiv_id":"2212.08490","n_code_links":1,"syntology":null},{"paper":null,"slug":"legalrelectra-mixed-domain-language-modeling","title":"LegalRelectra: Mixed-domain Language Modeling for Long-range Legal Text Comprehension","date":"2022-12-16","arxiv_id":"2212.08204","n_code_links":0,"syntology":null},{"paper":null,"slug":"murmur-modular-multi-step-reasoning-for-semi","title":"MURMUR: Modular Multi-Step Reasoning for Semi-Structured Data-to-Text Generation","date":"2022-12-16","arxiv_id":"2212.08607","n_code_links":0,"syntology":null},{"paper":null,"slug":"reducing-sequence-length-learning-impacts-on","title":"Assessing the Impact of Sequence Length Learning on Classification Tasks for Transformer Encoder Models","date":"2022-12-16","arxiv_id":"2212.08399","n_code_links":0,"syntology":null},{"paper":"/paper/rethinking-cooking-state-recognition-with","slug":"rethinking-cooking-state-recognition-with","title":"Rethinking Cooking State Recognition with Vision Transformers","date":"2022-12-16","arxiv_id":"2212.08586","n_code_links":1,"syntology":null},{"paper":"/paper/self-prompting-large-language-models-for-open","slug":"self-prompting-large-language-models-for-open","title":"Self-Prompting Large Language Models for Zero-Shot Open-Domain QA","date":"2022-12-16","arxiv_id":"2212.08635","n_code_links":1,"syntology":null}],"record_sha256":"6960fd3521f1a907d69cec0a65a5e090bb80d27c46aceb0c76649dbb27e47979","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}