{"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/residual-connection/papers/158","list_of":"/method/residual-connection","method":"Residual Connection","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":158,"pages_in_order":285,"rows_per_page":100,"rows":[15701,15800],"of":28401,"counts":{"archive_papers_tagged":28401,"with_a_code_link":12847,"where_syntology_ran_a_sample":3897,"not_listed_spam_title":0,"listed":28401,"listed_where_code_ran":3897,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":3291,"every_run_a_failure_of_syntologys_instrument":606,"listed_with_a_run_with_no_instrument_failure":3291,"listed_every_run_a_failure_of_syntologys_instrument":606,"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/residual-connection","prev":"/method/residual-connection/papers/157","next":"/method/residual-connection/papers/159","papers":[{"paper":null,"slug":"offline-clustering-approach-to-self","title":"Offline Clustering Approach to Self-supervised Learning for Class-imbalanced Image Data","date":"2022-12-22","arxiv_id":"2212.11444","n_code_links":0,"syntology":null},{"paper":"/paper/supergb-d-zero-shot-instance-segmentation-in","slug":"supergb-d-zero-shot-instance-segmentation-in","title":"SupeRGB-D: Zero-shot Instance Segmentation in Cluttered Indoor Environments","date":"2022-12-22","arxiv_id":"2212.11922","n_code_links":1,"syntology":null},{"paper":null,"slug":"understanding-and-improving-the-role-of","title":"Understanding and Improving the Role of Projection Head in Self-Supervised Learning","date":"2022-12-22","arxiv_id":"2212.11491","n_code_links":0,"syntology":null},{"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/cross-linguistic-syntactic-difference-in","slug":"cross-linguistic-syntactic-difference-in","title":"Cross-Linguistic Syntactic Difference in Multilingual BERT: How Good is It and How Does It Affect Transfer?","date":"2022-12-21","arxiv_id":"2212.10879","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":"/paper/exploring-content-relationships-for","slug":"exploring-content-relationships-for","title":"Exploring Content Relationships for Distilling Efficient GANs","date":"2022-12-21","arxiv_id":"2212.11091","n_code_links":1,"syntology":null},{"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/lifelong-reinforcement-learning-with","slug":"lifelong-reinforcement-learning-with","title":"Lifelong Reinforcement Learning with Modulating Masks","date":"2022-12-21","arxiv_id":"2212.11110","n_code_links":4,"syntology":null},{"paper":null,"slug":"moquad-motion-focused-quadruple-construction","title":"MoQuad: Motion-focused Quadruple Construction for Video Contrastive Learning","date":"2022-12-21","arxiv_id":"2212.10870","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":null,"slug":"towards-efficient-visual-simplification-of","title":"Towards Efficient Visual Simplification of Computational Graphs in Deep Neural Networks","date":"2022-12-21","arxiv_id":"2212.10774","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":null,"slug":"a-twitter-bert-approach-for-offensive","title":"A Twitter BERT Approach for Offensive Language Detection in Marathi","date":"2022-12-20","arxiv_id":"2212.10039","n_code_links":0,"syntology":null},{"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":"conditioned-generative-transformers-for","title":"Unified Framework for Histopathology Image Augmentation and Classification via Generative Models","date":"2022-12-20","arxiv_id":"2212.09977","n_code_links":0,"syntology":null},{"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":null,"slug":"hybrid-rule-neural-coreference-resolution","title":"Hybrid Rule-Neural Coreference Resolution System based on Actor-Critic Learning","date":"2022-12-20","arxiv_id":"2212.10087","n_code_links":0,"syntology":null},{"paper":null,"slug":"identifying-and-manipulating-the-personality","title":"Identifying and Manipulating the Personality Traits of Language Models","date":"2022-12-20","arxiv_id":"2212.10276","n_code_links":0,"syntology":null},{"paper":null,"slug":"in-and-out-of-domain-text-adversarial","title":"In and Out-of-Domain Text Adversarial Robustness via Label Smoothing","date":"2022-12-20","arxiv_id":"2212.10258","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":"/paper/on-the-applicability-of-synthetic-data-for-re","slug":"on-the-applicability-of-synthetic-data-for-re","title":"On the Applicability of Synthetic Data for Re-Identification","date":"2022-12-20","arxiv_id":"2212.10105","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":null,"slug":"parameter-efficient-zero-shot-transfer-for","title":"Parameter-efficient Zero-shot Transfer for Cross-Language Dense Retrieval with Adapters","date":"2022-12-20","arxiv_id":"2212.10448","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":"/paper/pretraining-without-attention","slug":"pretraining-without-attention","title":"Pretraining Without Attention","date":"2022-12-20","arxiv_id":"2212.10544","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: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["jxiw/bigs"],"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":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":null,"slug":"covid-19-detection-based-on-self-supervised","title":"COVID-19 Detection Based on Self-Supervised Transfer Learning Using Chest X-Ray Images","date":"2022-12-19","arxiv_id":"2212.09276","n_code_links":0,"syntology":null},{"paper":null,"slug":"denoising-instrumented-mouthguard","title":"Denoising instrumented mouthguard measurements of head impact kinematics with a convolutional neural network","date":"2022-12-19","arxiv_id":"2212.09832","n_code_links":0,"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":null,"slug":"enriching-relation-extraction-with-openie","title":"Enriching Relation Extraction with OpenIE","date":"2022-12-19","arxiv_id":"2212.09376","n_code_links":0,"syntology":null},{"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":"less-is-more-parameter-free-text","title":"Less is More: Parameter-Free Text Classification with Gzip","date":"2022-12-19","arxiv_id":"2212.09410","n_code_links":0,"syntology":null},{"paper":null,"slug":"mantis-at-tsar-2022-shared-task-improved","title":"MANTIS at TSAR-2022 Shared Task: Improved Unsupervised Lexical Simplification with Pretrained Encoders","date":"2022-12-19","arxiv_id":"2212.09855","n_code_links":0,"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/beats-audio-pre-training-with-acoustic","slug":"beats-audio-pre-training-with-acoustic","title":"BEATs: Audio Pre-Training with Acoustic Tokenizers","date":"2022-12-18","arxiv_id":"2212.09058","n_code_links":4,"syntology":{"ran":16,"of":18,"n_ran_checked":13,"n_instrument":3,"unverified":2,"pointer_only":4,"phrase":"16 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; 3 where Syntology's instrument failed) · 2 unverified","official":{"repos":["microsoft/unilm"],"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/bort-towards-explainable-neural-networks-with","slug":"bort-towards-explainable-neural-networks-with","title":"Bort: Towards Explainable Neural Networks with Bounded Orthogonal Constraint","date":"2022-12-18","arxiv_id":"2212.09062","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":["zbr17/bort"],"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/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":null,"slug":"neural-coreference-resolution-based-on","title":"Neural Coreference Resolution based on Reinforcement Learning","date":"2022-12-18","arxiv_id":"2212.09028","n_code_links":0,"syntology":null},{"paper":null,"slug":"neural-rankers-for-effective-screening","title":"Neural Rankers for Effective Screening Prioritisation in Medical Systematic Review Literature Search","date":"2022-12-18","arxiv_id":"2212.09017","n_code_links":0,"syntology":null},{"paper":null,"slug":"performance-analysis-of-yolo-based","title":"Performance Analysis of YOLO-based Architectures for Vehicle Detection from Traffic Images in Bangladesh","date":"2022-12-18","arxiv_id":"2212.09144","n_code_links":0,"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":null,"slug":"exploiting-rich-textual-user-product-context","title":"Exploiting Rich Textual User-Product Context for Improving Sentiment Analysis","date":"2022-12-17","arxiv_id":"2212.08888","n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-unsupervised-video-object","title":"Improving Unsupervised Video Object Segmentation with Motion-Appearance Synergy","date":"2022-12-17","arxiv_id":"2212.08816","n_code_links":0,"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":null,"slug":"pre-trained-image-encoder-for-generalizable","title":"Pre-Trained Image Encoder for Generalizable Visual Reinforcement Learning","date":"2022-12-17","arxiv_id":"2212.08860","n_code_links":0,"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":null,"slug":"dqnet-cross-model-detail-querying-for","title":"DQnet: Cross-Model Detail Querying for Camouflaged Object Detection","date":"2022-12-16","arxiv_id":"2212.08296","n_code_links":0,"syntology":null},{"paper":"/paper/from-xception-to-nexception-new-design","slug":"from-xception-to-nexception-new-design","title":"From Xception to NEXcepTion: New Design Decisions and Neural Architecture Search","date":"2022-12-16","arxiv_id":"2212.08448","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":null,"slug":"investigation-of-japanese-png-bert-language","title":"Investigation of Japanese PnG BERT language model in text-to-speech synthesis for pitch accent language","date":"2022-12-16","arxiv_id":"2212.08321","n_code_links":0,"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":"plansformer-generating-symbolic-plans-using","title":"Plansformer: Generating Symbolic Plans using Transformers","date":"2022-12-16","arxiv_id":"2212.08681","n_code_links":0,"syntology":null},{"paper":null,"slug":"poibert-a-transformer-based-model-for-the","title":"POIBERT: A Transformer-based Model for the Tour Recommendation Problem","date":"2022-12-16","arxiv_id":"2212.13900","n_code_links":0,"syntology":null},{"paper":"/paper/reco-reliable-causal-chain-reasoning-via","slug":"reco-reliable-causal-chain-reasoning-via","title":"ReCo: Reliable Causal Chain Reasoning via Structural Causal Recurrent Neural Networks","date":"2022-12-16","arxiv_id":"2212.08322","n_code_links":1,"syntology":{"ran":4,"of":6,"n_ran_checked":3,"n_instrument":1,"unverified":2,"pointer_only":6,"phrase":"4 ran (of which 2 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) · 2 unverified","official":{"repos":["waste-wood/reco"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":2,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"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},{"paper":null,"slug":"teaching-small-language-models-to-reason","title":"Teaching Small Language Models to Reason","date":"2022-12-16","arxiv_id":"2212.08410","n_code_links":0,"syntology":null},{"paper":null,"slug":"traffic-sign-detection-and-recognition-using","title":"Traffic sign detection and recognition using event camera image reconstruction","date":"2022-12-16","arxiv_id":"2212.08387","n_code_links":0,"syntology":null},{"paper":null,"slug":"utilizing-distilbert-transformer-model-for","title":"Utilizing distilBert transformer model for sentiment classification of COVID-19's Persian open-text responses","date":"2022-12-16","arxiv_id":"2212.08407","n_code_links":0,"syntology":null},{"paper":null,"slug":"combating-uncertainty-and-class-imbalance-in","title":"Combating Uncertainty and Class Imbalance in Facial Expression Recognition","date":"2022-12-15","arxiv_id":"2212.07751","n_code_links":0,"syntology":null}],"record_sha256":"823f34f328e6646515d3f3b1ce6dc64272dd78f54c53de4442c31d2b2e8670cf","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}