{"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/cosine-annealing/papers/32","list_of":"/method/cosine-annealing","method":"Cosine Annealing","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":32,"pages_in_order":40,"rows_per_page":100,"rows":[3101,3200],"of":3965,"counts":{"archive_papers_tagged":3965,"with_a_code_link":1734,"where_syntology_ran_a_sample":627,"not_listed_spam_title":0,"listed":3965,"listed_where_code_ran":627,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":513,"every_run_a_failure_of_syntologys_instrument":114,"listed_with_a_run_with_no_instrument_failure":513,"listed_every_run_a_failure_of_syntologys_instrument":114,"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/cosine-annealing","prev":"/method/cosine-annealing/papers/31","next":"/method/cosine-annealing/papers/33","papers":[{"paper":"/paper/measuring-and-narrowing-the-compositionality","slug":"measuring-and-narrowing-the-compositionality","title":"Measuring and Narrowing the Compositionality Gap in Language Models","date":"2022-10-07","arxiv_id":"2210.03350","n_code_links":1,"syntology":null},{"paper":"/paper/binding-language-models-in-symbolic-languages","slug":"binding-language-models-in-symbolic-languages","title":"Binding Language Models in Symbolic Languages","date":"2022-10-06","arxiv_id":"2210.02875","n_code_links":4,"syntology":{"ran":2,"of":3,"n_ran_checked":1,"n_instrument":1,"unverified":1,"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) · 1 unverified","official":{"repos":["hkunlp/binder"],"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":"generalization-properties-of-retrieval-based","title":"Generalization Properties of Retrieval-based Models","date":"2022-10-06","arxiv_id":"2210.02617","n_code_links":0,"syntology":null},{"paper":"/paper/guess-the-instruction-making-language-models","slug":"guess-the-instruction-making-language-models","title":"Guess the Instruction! Flipped Learning Makes Language Models Stronger Zero-Shot Learners","date":"2022-10-06","arxiv_id":"2210.02969","n_code_links":1,"syntology":null},{"paper":"/paper/rainier-reinforced-knowledge-introspector-for","slug":"rainier-reinforced-knowledge-introspector-for","title":"Rainier: Reinforced Knowledge Introspector for Commonsense Question Answering","date":"2022-10-06","arxiv_id":"2210.03078","n_code_links":1,"syntology":{"ran":7,"of":13,"n_ran_checked":4,"n_instrument":3,"unverified":6,"pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 4 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 6 unverified","official":{"repos":["liujch1998/rainier"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":6,"ran_from_kinds":["official"]}}},{"paper":"/paper/glm-130b-an-open-bilingual-pre-trained-model","slug":"glm-130b-an-open-bilingual-pre-trained-model","title":"GLM-130B: An Open Bilingual Pre-trained Model","date":"2022-10-05","arxiv_id":"2210.02414","n_code_links":9,"syntology":{"ran":15,"of":21,"n_ran_checked":14,"n_instrument":1,"unverified":6,"pointer_only":0,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 1 where Syntology's instrument failed) · 6 unverified","official":{"repos":["thudm/glm-130b"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/explaining-patterns-in-data-with-language","slug":"explaining-patterns-in-data-with-language","title":"Explaining Patterns in Data with Language Models via Interpretable Autoprompting","date":"2022-10-04","arxiv_id":"2210.01848","n_code_links":2,"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":["csinva/imodelsX"],"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":"complexity-based-prompting-for-multi-step","title":"Complexity-Based Prompting for Multi-Step Reasoning","date":"2022-10-03","arxiv_id":"2210.00720","n_code_links":0,"syntology":null},{"paper":"/paper/language-models-are-greedy-reasoners-a","slug":"language-models-are-greedy-reasoners-a","title":"Language Models Are Greedy Reasoners: A Systematic Formal Analysis of Chain-of-Thought","date":"2022-10-03","arxiv_id":"2210.01240","n_code_links":2,"syntology":{"ran":4,"of":5,"n_ran_checked":2,"n_instrument":2,"unverified":1,"pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["asaparov/prontoqa"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/exploiting-selection-bias-on-underspecified","slug":"exploiting-selection-bias-on-underspecified","title":"Underspecification in Language Modeling Tasks: A Causality-Informed Study of Gendered Pronoun Resolution","date":"2022-09-30","arxiv_id":"2210.00131","n_code_links":2,"syntology":null},{"paper":"/paper/smallcap-lightweight-image-captioning","slug":"smallcap-lightweight-image-captioning","title":"SmallCap: Lightweight Image Captioning Prompted with Retrieval Augmentation","date":"2022-09-30","arxiv_id":"2209.15323","n_code_links":1,"syntology":null},{"paper":null,"slug":"bidirectional-language-models-are-also-few","title":"Bidirectional Language Models Are Also Few-shot Learners","date":"2022-09-29","arxiv_id":"2209.14500","n_code_links":0,"syntology":null},{"paper":"/paper/dynamic-prompt-learning-via-policy-gradient","slug":"dynamic-prompt-learning-via-policy-gradient","title":"Dynamic Prompt Learning via Policy Gradient for Semi-structured Mathematical Reasoning","date":"2022-09-29","arxiv_id":"2209.14610","n_code_links":2,"syntology":{"ran":3,"of":7,"n_ran_checked":1,"n_instrument":2,"unverified":4,"pointer_only":0,"phrase":"3 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; 2 where Syntology's instrument failed) · 4 unverified","official":null}},{"paper":null,"slug":"medical-image-captioning-via-generative","title":"Medical Image Captioning via Generative Pretrained Transformers","date":"2022-09-28","arxiv_id":"2209.13983","n_code_links":0,"syntology":null},{"paper":"/paper/who-is-gpt-3-an-exploration-of-personality","slug":"who-is-gpt-3-an-exploration-of-personality","title":"Who is GPT-3? An Exploration of Personality, Values and Demographics","date":"2022-09-28","arxiv_id":"2209.14338","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-critical-appraisal-of-equity-in","title":"How GPT-3 responds to different publics on climate change and Black Lives Matter: A critical appraisal of equity in conversational AI","date":"2022-09-27","arxiv_id":"2209.13627","n_code_links":0,"syntology":null},{"paper":null,"slug":"do-ever-larger-octopi-still-amplify-reporting","title":"Do ever larger octopi still amplify reporting biases? Evidence from judgments of typical colour","date":"2022-09-26","arxiv_id":"2209.12786","n_code_links":0,"syntology":null},{"paper":"/paper/news-summarization-and-evaluation-in-the-era","slug":"news-summarization-and-evaluation-in-the-era","title":"News Summarization and Evaluation in the Era of GPT-3","date":"2022-09-26","arxiv_id":"2209.12356","n_code_links":1,"syntology":null},{"paper":null,"slug":"moral-mimicry-large-language-models-produce","title":"Moral Mimicry: Large Language Models Produce Moral Rationalizations Tailored to Political Identity","date":"2022-09-24","arxiv_id":"2209.12106","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-case-report-on-the-a-i-locked-in-problem","title":"A Case Report On The \"A.I. Locked-In Problem\": social concerns with modern NLP","date":"2022-09-22","arxiv_id":"2209.12687","n_code_links":0,"syntology":null},{"paper":null,"slug":"dfx-a-low-latency-multi-fpga-appliance-for","title":"DFX: A Low-latency Multi-FPGA Appliance for Accelerating Transformer-based Text Generation","date":"2022-09-22","arxiv_id":"2209.10797","n_code_links":0,"syntology":null},{"paper":null,"slug":"text-revealer-private-text-reconstruction-via","title":"Text Revealer: Private Text Reconstruction via Model Inversion Attacks against Transformers","date":"2022-09-21","arxiv_id":"2209.10505","n_code_links":0,"syntology":null},{"paper":"/paper/learn-to-explain-multimodal-reasoning-via","slug":"learn-to-explain-multimodal-reasoning-via","title":"Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering","date":"2022-09-20","arxiv_id":"2209.09513","n_code_links":1,"syntology":{"ran":4,"of":5,"n_ran_checked":0,"n_instrument":4,"unverified":1,"pointer_only":2,"phrase":"4 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; 4 where Syntology's instrument failed) · 1 unverified","official":{"repos":["lupantech/ScienceQA"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official","unlocated"]}}},{"paper":"/paper/meta-adapters-parameter-efficient-few-shot","slug":"meta-adapters-parameter-efficient-few-shot","title":"Meta-Adapters: Parameter Efficient Few-shot Fine-tuning through Meta-Learning","date":"2022-09-19","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"will-it-blend-mixing-training-paradigms","title":"Will It Blend? Mixing Training Paradigms & Prompting for Argument Quality Prediction","date":"2022-09-19","arxiv_id":"2209.08966","n_code_links":0,"syntology":null},{"paper":"/paper/psychologically-informed-chain-of-thought","slug":"psychologically-informed-chain-of-thought","title":"Psychologically-informed chain-of-thought prompts for metaphor understanding in large language models","date":"2022-09-16","arxiv_id":"2209.08141","n_code_links":1,"syntology":{"ran":5,"of":5,"n_ran_checked":5,"n_instrument":0,"unverified":0,"pointer_only":0,"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":["benpry/chain-of-thought-metaphor"],"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":null,"slug":"text-and-patterns-for-effective-chain-of","title":"Text and Patterns: For Effective Chain of Thought, It Takes Two to Tango","date":"2022-09-16","arxiv_id":"2209.07686","n_code_links":0,"syntology":null},{"paper":"/paper/efficient-quantized-sparse-matrix-operations","slug":"efficient-quantized-sparse-matrix-operations","title":"Efficient Quantized Sparse Matrix Operations on Tensor Cores","date":"2022-09-14","arxiv_id":"2209.06979","n_code_links":1,"syntology":null},{"paper":null,"slug":"out-of-one-many-using-language-models-to","title":"Out of One, Many: Using Language Models to Simulate Human Samples","date":"2022-09-14","arxiv_id":"2209.06899","n_code_links":0,"syntology":null},{"paper":null,"slug":"chain-of-explanation-new-prompting-method-to","title":"Chain of Explanation: New Prompting Method to Generate Higher Quality Natural Language Explanation for Implicit Hate Speech","date":"2022-09-11","arxiv_id":"2209.04889","n_code_links":0,"syntology":null},{"paper":null,"slug":"why-so-toxic-measuring-and-triggering-toxic","title":"Why So Toxic? Measuring and Triggering Toxic Behavior in Open-Domain Chatbots","date":"2022-09-07","arxiv_id":"2209.03463","n_code_links":0,"syntology":null},{"paper":"/paper/macab-model-agnostic-clean-annotation","slug":"macab-model-agnostic-clean-annotation","title":"TransCAB: Transferable Clean-Annotation Backdoor to Object Detection with Natural Trigger in Real-World","date":"2022-09-06","arxiv_id":"2209.02339","n_code_links":1,"syntology":null},{"paper":"/paper/chemberta-2-towards-chemical-foundation","slug":"chemberta-2-towards-chemical-foundation","title":"ChemBERTa-2: Towards Chemical Foundation Models","date":"2022-09-05","arxiv_id":"2209.01712","n_code_links":2,"syntology":null},{"paper":null,"slug":"evaluating-the-susceptibility-of-pre-trained","title":"Evaluating the Susceptibility of Pre-Trained Language Models via Handcrafted Adversarial Examples","date":"2022-09-05","arxiv_id":"2209.02128","n_code_links":0,"syntology":null},{"paper":"/paper/do-large-language-models-know-what-humans","slug":"do-large-language-models-know-what-humans","title":"Do Large Language Models know what humans know?","date":"2022-09-04","arxiv_id":"2209.01515","n_code_links":1,"syntology":null},{"paper":null,"slug":"every-picture-tells-a-story-image-grounded","title":"Every picture tells a story: Image-grounded controllable stylistic story generation","date":"2022-09-04","arxiv_id":"2209.01638","n_code_links":0,"syntology":null},{"paper":"/paper/elaboration-generating-commonsense-question","slug":"elaboration-generating-commonsense-question","title":"Elaboration-Generating Commonsense Question Answering at Scale","date":"2022-09-02","arxiv_id":"2209.01232","n_code_links":1,"syntology":null},{"paper":"/paper/folio-natural-language-reasoning-with-first","slug":"folio-natural-language-reasoning-with-first","title":"FOLIO: Natural Language Reasoning with First-Order Logic","date":"2022-09-02","arxiv_id":"2209.00840","n_code_links":1,"syntology":null},{"paper":null,"slug":"efficient-sparsely-activated-transformers","title":"Efficient Sparsely Activated Transformers","date":"2022-08-31","arxiv_id":"2208.14580","n_code_links":0,"syntology":null},{"paper":null,"slug":"swin-transformer-yolov5-for-real-time-wine","title":"Swin-transformer-yolov5 For Real-time Wine Grape Bunch Detection","date":"2022-08-30","arxiv_id":"2208.14508","n_code_links":0,"syntology":null},{"paper":"/paper/ammunition-component-classification-using","slug":"ammunition-component-classification-using","title":"Ammunition Component Classification Using Deep Learning","date":"2022-08-26","arxiv_id":"2208.12863","n_code_links":1,"syntology":null},{"paper":null,"slug":"on-reality-and-the-limits-of-language-data","title":"On Reality and the Limits of Language Data: Aligning LLMs with Human Norms","date":"2022-08-25","arxiv_id":"2208.11981","n_code_links":0,"syntology":null},{"paper":null,"slug":"comparison-of-object-detection-algorithms-for","title":"Comparison of Object Detection Algorithms for Street-level Objects","date":"2022-08-24","arxiv_id":"2208.11315","n_code_links":0,"syntology":null},{"paper":null,"slug":"research-on-mask-wearing-detection-of-natural","title":"A New Method on Mask-Wearing Detection for Natural Population Based on Improved YOLOv4","date":"2022-08-24","arxiv_id":"2208.11353","n_code_links":0,"syntology":null},{"paper":"/paper/prompting-as-probing-using-language-models","slug":"prompting-as-probing-using-language-models","title":"Prompting as Probing: Using Language Models for Knowledge Base Construction","date":"2022-08-23","arxiv_id":"2208.11057","n_code_links":1,"syntology":{"ran":6,"of":6,"n_ran_checked":2,"n_instrument":4,"unverified":0,"pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 2 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","official":{"repos":["hemile/iswc-challenge"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/mulzdg-multilingual-code-switching-framework","slug":"mulzdg-multilingual-code-switching-framework","title":"MulZDG: Multilingual Code-Switching Framework for Zero-shot Dialogue Generation","date":"2022-08-18","arxiv_id":"2208.08629","n_code_links":1,"syntology":null},{"paper":"/paper/using-large-language-models-to-simulate","slug":"using-large-language-models-to-simulate","title":"Using Large Language Models to Simulate Multiple Humans and Replicate Human Subject Studies","date":"2022-08-18","arxiv_id":"2208.10264","n_code_links":2,"syntology":{"ran":2,"of":4,"n_ran_checked":2,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","official":{"repos":["gatiaher/using-large-language-models-to-replicate-human-subject-studies"],"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/neural-embeddings-for-text","slug":"neural-embeddings-for-text","title":"Neural Embeddings for Text","date":"2022-08-17","arxiv_id":"2208.08386","n_code_links":1,"syntology":null},{"paper":"/paper/mocapact-a-multi-task-dataset-for-simulated","slug":"mocapact-a-multi-task-dataset-for-simulated","title":"MoCapAct: A Multi-Task Dataset for Simulated Humanoid Control","date":"2022-08-15","arxiv_id":"2208.07363","n_code_links":1,"syntology":{"ran":4,"of":5,"n_ran_checked":4,"n_instrument":0,"unverified":1,"pointer_only":0,"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) · 1 unverified","official":{"repos":["microsoft/MoCapAct"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"targeted-honeyword-generation-with-language","title":"Targeted Honeyword Generation with Language Models","date":"2022-08-15","arxiv_id":"2208.06946","n_code_links":0,"syntology":null},{"paper":null,"slug":"teacher-guided-training-an-efficient","title":"Teacher Guided Training: An Efficient Framework for Knowledge Transfer","date":"2022-08-14","arxiv_id":"2208.06825","n_code_links":0,"syntology":null},{"paper":"/paper/adan-adaptive-nesterov-momentum-algorithm-for","slug":"adan-adaptive-nesterov-momentum-algorithm-for","title":"Adan: Adaptive Nesterov Momentum Algorithm for Faster Optimizing Deep Models","date":"2022-08-13","arxiv_id":"2208.06677","n_code_links":9,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["sail-sg/adan"],"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/real-time-accident-detection-in-traffic","slug":"real-time-accident-detection-in-traffic","title":"Real-Time Accident Detection in Traffic Surveillance Using Deep Learning","date":"2022-08-12","arxiv_id":"2208.06461","n_code_links":1,"syntology":null},{"paper":null,"slug":"debiased-large-language-models-still","title":"Debiased Large Language Models Still Associate Muslims with Uniquely Violent Acts","date":"2022-08-08","arxiv_id":"2208.04417","n_code_links":0,"syntology":null},{"paper":null,"slug":"object-detection-using-sim2real-domain","title":"Object Detection Using Sim2Real Domain Randomization for Robotic Applications","date":"2022-08-08","arxiv_id":"2208.04171","n_code_links":0,"syntology":null},{"paper":null,"slug":"studying-writer-suggestion-interaction-a","title":"Interacting with next-phrase suggestions: How suggestion systems aid and influence the cognitive processes of writing","date":"2022-08-01","arxiv_id":"2208.00636","n_code_links":0,"syntology":null},{"paper":"/paper/what-can-transformers-learn-in-context-a-case","slug":"what-can-transformers-learn-in-context-a-case","title":"What Can Transformers Learn In-Context? A Case Study of Simple Function Classes","date":"2022-08-01","arxiv_id":"2208.01066","n_code_links":2,"syntology":null},{"paper":null,"slug":"lad-language-models-as-data-for-zero-shot","title":"LAD: Language Models as Data for Zero-Shot Dialog","date":"2022-07-28","arxiv_id":"2207.14393","n_code_links":0,"syntology":null},{"paper":null,"slug":"large-language-models-and-the-reverse-turing","title":"Large Language Models and the Reverse Turing Test","date":"2022-07-28","arxiv_id":"2207.14382","n_code_links":0,"syntology":null},{"paper":null,"slug":"traffic-sign-detection-with-event-cameras-and","title":"Traffic Sign Detection With Event Cameras and DCNN","date":"2022-07-27","arxiv_id":"2207.13345","n_code_links":0,"syntology":null},{"paper":null,"slug":"is-gpt-3-all-you-need-for-visual-question","title":"Is GPT-3 all you need for Visual Question Answering in Cultural Heritage?","date":"2022-07-25","arxiv_id":"2207.12101","n_code_links":0,"syntology":null},{"paper":"/paper/zero-shot-video-captioning-with-evolving","slug":"zero-shot-video-captioning-with-evolving","title":"Zero-Shot Video Captioning with Evolving Pseudo-Tokens","date":"2022-07-22","arxiv_id":"2207.11100","n_code_links":1,"syntology":null},{"paper":null,"slug":"bigissue-a-realistic-bug-localization","title":"BigIssue: A Realistic Bug Localization Benchmark","date":"2022-07-21","arxiv_id":"2207.10739","n_code_links":0,"syntology":null},{"paper":null,"slug":"word-play-for-playing-othello-reverses","title":"Word Play for Playing Othello (Reverses)","date":"2022-07-18","arxiv_id":"2207.08766","n_code_links":0,"syntology":null},{"paper":"/paper/can-large-language-models-reason-about","slug":"can-large-language-models-reason-about","title":"Can large language models reason about medical questions?","date":"2022-07-17","arxiv_id":"2207.08143","n_code_links":1,"syntology":{"ran":10,"of":10,"n_ran_checked":10,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["vlievin/medical-reasoning"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/electra-is-a-zero-shot-learner-too","slug":"electra-is-a-zero-shot-learner-too","title":"ELECTRA is a Zero-Shot Learner, Too","date":"2022-07-17","arxiv_id":"2207.08141","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["nishiwen1214/rtd-electra"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"active-data-pattern-extraction-attacks-on","title":"Combing for Credentials: Active Pattern Extraction from Smart Reply","date":"2022-07-14","arxiv_id":"2207.10802","n_code_links":0,"syntology":null},{"paper":"/paper/recurrent-memory-transformer","slug":"recurrent-memory-transformer","title":"Recurrent Memory Transformer","date":"2022-07-14","arxiv_id":"2207.06881","n_code_links":3,"syntology":{"ran":6,"of":13,"n_ran_checked":5,"n_instrument":1,"unverified":7,"pointer_only":2,"phrase":"6 ran (of which 3 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 1 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 7 unverified","official":{"repos":["booydar/lm-rmt","booydar/transformer-xl"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":6,"ran_from_kinds":["community","official","unlocated"]}}},{"paper":"/paper/dynast-dynamic-sparse-transformer-for","slug":"dynast-dynamic-sparse-transformer-for","title":"DynaST: Dynamic Sparse Transformer for Exemplar-Guided Image Generation","date":"2022-07-13","arxiv_id":"2207.06124","n_code_links":1,"syntology":{"ran":5,"of":8,"n_ran_checked":3,"n_instrument":2,"unverified":3,"pointer_only":0,"phrase":"5 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","official":{"repos":["huage001/dynast"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":2,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/re2g-retrieve-rerank-generate-2","slug":"re2g-retrieve-rerank-generate-2","title":"Re2G: Retrieve, Rerank, Generate","date":"2022-07-13","arxiv_id":"2207.06300","n_code_links":1,"syntology":{"ran":7,"of":8,"n_ran_checked":6,"n_instrument":1,"unverified":1,"pointer_only":1,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["ibm/kgi-slot-filling"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/sparsetir-composable-abstractions-for-sparse","slug":"sparsetir-composable-abstractions-for-sparse","title":"SparseTIR: Composable Abstractions for Sparse Compilation in Deep Learning","date":"2022-07-11","arxiv_id":"2207.04606","n_code_links":2,"syntology":{"ran":6,"of":6,"n_ran_checked":5,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 2 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["uwsampl/sparsetir","uwsampl/sparsetir-artifact"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"few-shot-training-llms-for-project-specific","title":"Few-shot training LLMs for project-specific code-summarization","date":"2022-07-09","arxiv_id":"2207.04237","n_code_links":0,"syntology":null},{"paper":null,"slug":"hidden-schema-networks","title":"Hidden Schema Networks","date":"2022-07-08","arxiv_id":"2207.03777","n_code_links":0,"syntology":null},{"paper":null,"slug":"neural-language-models-are-not-born-equal-to","title":"Neural Language Models are not Born Equal to Fit Brain Data, but Training Helps","date":"2022-07-07","arxiv_id":"2207.03380","n_code_links":0,"syntology":null},{"paper":null,"slug":"sensitivity-analysis-on-transferred-neural","title":"Sensitivity Analysis on Transferred Neural Architectures of BERT and GPT-2 for Financial Sentiment Analysis","date":"2022-07-07","arxiv_id":"2207.03037","n_code_links":0,"syntology":null},{"paper":null,"slug":"ask-me-what-you-need-product-retrieval-using","title":"Ask Me What You Need: Product Retrieval using Knowledge from GPT-3","date":"2022-07-06","arxiv_id":"2207.02516","n_code_links":0,"syntology":null},{"paper":null,"slug":"machine-learning-model-sizes-and-the","title":"Machine Learning Model Sizes and the Parameter Gap","date":"2022-07-05","arxiv_id":"2207.02852","n_code_links":0,"syntology":null},{"paper":"/paper/deepspeed-inference-enabling-efficient","slug":"deepspeed-inference-enabling-efficient","title":"DeepSpeed Inference: Enabling Efficient Inference of Transformer Models at Unprecedented Scale","date":"2022-06-30","arxiv_id":"2207.00032","n_code_links":2,"syntology":null},{"paper":"/paper/gaitforemer-self-supervised-pre-training-of","slug":"gaitforemer-self-supervised-pre-training-of","title":"GaitForeMer: Self-Supervised Pre-Training of Transformers via Human Motion Forecasting for Few-Shot Gait Impairment Severity Estimation","date":"2022-06-30","arxiv_id":"2207.00106","n_code_links":1,"syntology":null},{"paper":"/paper/materials-transformers-language-models-for","slug":"materials-transformers-language-models-for","title":"Materials Transformers Language Models for Generative Materials Design: a benchmark study","date":"2022-06-27","arxiv_id":"2206.13578","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-test-for-evaluating-performance-in-human","title":"A Test for Evaluating Performance in Human-Computer Systems","date":"2022-06-24","arxiv_id":"2206.12390","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-disability-lens-towards-biases-in-gpt-3","title":"A Disability Lens towards Biases in GPT-3 Generated Open-Ended Languages","date":"2022-06-23","arxiv_id":"2206.11993","n_code_links":0,"syntology":null},{"paper":null,"slug":"cocopie-xgen-a-full-stack-ai-oriented","title":"CoCoPIE XGen: A Full-Stack AI-Oriented Optimizing Framework","date":"2022-06-21","arxiv_id":"2206.10620","n_code_links":0,"syntology":null},{"paper":null,"slug":"using-cognitive-psychology-to-understand-gpt","title":"Using cognitive psychology to understand GPT-3","date":"2022-06-21","arxiv_id":"2206.14576","n_code_links":0,"syntology":null},{"paper":"/paper/nuqmm-quantized-matmul-for-efficient","slug":"nuqmm-quantized-matmul-for-efficient","title":"LUT-GEMM: Quantized Matrix Multiplication based on LUTs for Efficient Inference in Large-Scale Generative Language Models","date":"2022-06-20","arxiv_id":"2206.09557","n_code_links":2,"syntology":null},{"paper":"/paper/argumentative-text-generation-in-economic","slug":"argumentative-text-generation-in-economic","title":"Argumentative Text Generation in Economic Domain","date":"2022-06-18","arxiv_id":"2206.09251","n_code_links":1,"syntology":null},{"paper":null,"slug":"automatic-summarization-of-russian-texts","title":"Automatic Summarization of Russian Texts: Comparison of Extractive and Abstractive Methods","date":"2022-06-18","arxiv_id":"2206.09253","n_code_links":0,"syntology":null},{"paper":"/paper/video-sparse-transformer-with-attention","slug":"video-sparse-transformer-with-attention","title":"Video Sparse Transformer With Attention-Guided Memory for Video Object Detection","date":"2022-06-17","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"automatic-detection-of-rice-disease-in-images","title":"Automatic Detection of Rice Disease in Images of Various Leaf Sizes","date":"2022-06-15","arxiv_id":"2206.07344","n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluating-object-detector-ensembles-for","title":"Evaluating object detector ensembles for improving the robustness of artifact detection in endoscopic video streams","date":"2022-06-15","arxiv_id":"2206.07580","n_code_links":0,"syntology":null},{"paper":"/paper/making-sense-of-dependence-efficient-black","slug":"making-sense-of-dependence-efficient-black","title":"Making Sense of Dependence: Efficient Black-box Explanations Using Dependence Measure","date":"2022-06-13","arxiv_id":"2206.06219","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":["paulnovello/hsic-attribution-method"],"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":"a-dataset-and-benchmark-for-automatically","title":"From Human Days to Machine Seconds: Automatically Answering and Generating Machine Learning Final Exams","date":"2022-06-11","arxiv_id":"2206.05442","n_code_links":0,"syntology":null},{"paper":"/paper/putting-gpt-3-s-creativity-to-the-alternative","slug":"putting-gpt-3-s-creativity-to-the-alternative","title":"Putting GPT-3's Creativity to the (Alternative Uses) Test","date":"2022-06-10","arxiv_id":"2206.08932","n_code_links":1,"syntology":null},{"paper":"/paper/beyond-the-imitation-game-quantifying-and","slug":"beyond-the-imitation-game-quantifying-and","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","date":"2022-06-09","arxiv_id":"2206.04615","n_code_links":6,"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":["google/BIG-bench"],"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":"dynamar-dynamic-prompt-with-mask-token","title":"DynaMaR: Dynamic Prompt with Mask Token Representation","date":"2022-06-07","arxiv_id":"2206.02982","n_code_links":0,"syntology":null},{"paper":"/paper/on-the-advance-of-making-language-models","slug":"on-the-advance-of-making-language-models","title":"Making Large Language Models Better Reasoners with Step-Aware Verifier","date":"2022-06-06","arxiv_id":"2206.02336","n_code_links":0,"syntology":null},{"paper":null,"slug":"automatic-generation-of-programming-exercises-1","title":"Automatic Generation of Programming Exercises and Code Explanations using Large Language Models","date":"2022-06-03","arxiv_id":"2206.11861","n_code_links":0,"syntology":null},{"paper":null,"slug":"differentially-private-model-compression","title":"Differentially Private Model Compression","date":"2022-06-03","arxiv_id":"2206.01838","n_code_links":0,"syntology":null},{"paper":"/paper/decentralized-training-of-foundation-models","slug":"decentralized-training-of-foundation-models","title":"Decentralized Training of Foundation Models in Heterogeneous Environments","date":"2022-06-02","arxiv_id":"2206.01288","n_code_links":1,"syntology":{"ran":1,"of":3,"n_ran_checked":1,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["DS3Lab/DT-FM"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"research-on-smoking-behavior-detection-system","title":"Research on Smoking Behavior Detection System Based on Deep Learning","date":"2022-06-01","arxiv_id":null,"n_code_links":0,"syntology":null}],"record_sha256":"ff1e45987198d008a5b523fe84138c317a7d96fe27cfc0910dcd3d000df15849","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}