{"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/adam/papers/104","list_of":"/method/adam","method":"Adam","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":104,"pages_in_order":244,"rows_per_page":100,"rows":[10301,10400],"of":24390,"counts":{"archive_papers_tagged":24390,"with_a_code_link":10944,"where_syntology_ran_a_sample":3424,"not_listed_spam_title":0,"listed":24390,"listed_where_code_ran":3424,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":2899,"every_run_a_failure_of_syntologys_instrument":525,"listed_with_a_run_with_no_instrument_failure":2899,"listed_every_run_a_failure_of_syntologys_instrument":525,"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/adam","prev":"/method/adam/papers/103","next":"/method/adam/papers/105","papers":[{"paper":"/paper/botchat-evaluating-llms-capabilities-of","slug":"botchat-evaluating-llms-capabilities-of","title":"BotChat: Evaluating LLMs' Capabilities of Having Multi-Turn Dialogues","date":"2023-10-20","arxiv_id":"2310.13650","n_code_links":1,"syntology":{"ran":1,"of":3,"n_ran_checked":0,"n_instrument":1,"unverified":2,"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) · 2 unverified","official":{"repos":["open-compass/botchat"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/bridging-the-gap-between-synthetic-and","slug":"bridging-the-gap-between-synthetic-and","title":"Bridging the Gap between Synthetic and Authentic Images for Multimodal Machine Translation","date":"2023-10-20","arxiv_id":"2310.13361","n_code_links":1,"syntology":null},{"paper":"/paper/cache-me-if-you-can-an-online-cost-aware","slug":"cache-me-if-you-can-an-online-cost-aware","title":"Cache me if you Can: an Online Cost-aware Teacher-Student framework to Reduce the Calls to Large Language Models","date":"2023-10-20","arxiv_id":"2310.13395","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["stoyian/OCaTS"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"challenges-and-contributing-factors-in-the","title":"Challenges and Contributing Factors in the Utilization of Large Language Models (LLMs)","date":"2023-10-20","arxiv_id":"2310.13343","n_code_links":0,"syntology":null},{"paper":null,"slug":"design-inclusive-language-models-for","title":"She had Cobalt Blue Eyes: Prompt Testing to Create Aligned and Sustainable Language Models","date":"2023-10-20","arxiv_id":"2310.18333","n_code_links":0,"syntology":null},{"paper":null,"slug":"equivariant-transformer-is-all-you-need","title":"Equivariant Transformer is all you need","date":"2023-10-20","arxiv_id":"2310.13222","n_code_links":0,"syntology":null},{"paper":"/paper/evaluation-metrics-in-the-era-of-gpt-4","slug":"evaluation-metrics-in-the-era-of-gpt-4","title":"Evaluation Metrics in the Era of GPT-4: Reliably Evaluating Large Language Models on Sequence to Sequence Tasks","date":"2023-10-20","arxiv_id":"2310.13800","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":["protagolabs/seq2seq_llm_evaluation"],"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":"/paper/exploring-the-impact-of-corpus-diversity-on","slug":"exploring-the-impact-of-corpus-diversity-on","title":"Exploring the Impact of Corpus Diversity on Financial Pretrained Language Models","date":"2023-10-20","arxiv_id":"2310.13312","n_code_links":1,"syntology":null},{"paper":null,"slug":"fabula-intelligence-report-generation-using","title":"FABULA: Intelligence Report Generation Using Retrieval-Augmented Narrative Construction","date":"2023-10-20","arxiv_id":"2310.13848","n_code_links":0,"syntology":null},{"paper":null,"slug":"fmrt-learning-accurate-feature-matching-with","title":"FMRT: Learning Accurate Feature Matching with Reconciliatory Transformer","date":"2023-10-20","arxiv_id":"2310.13605","n_code_links":0,"syntology":null},{"paper":null,"slug":"foundation-model-s-embedded-representations","title":"Foundation Model's Embedded Representations May Detect Distribution Shift","date":"2023-10-20","arxiv_id":"2310.13836","n_code_links":0,"syntology":null},{"paper":"/paper/moqagpt-zero-shot-multi-modal-open-domain","slug":"moqagpt-zero-shot-multi-modal-open-domain","title":"MoqaGPT : Zero-Shot Multi-modal Open-domain Question Answering with Large Language Model","date":"2023-10-20","arxiv_id":"2310.13265","n_code_links":1,"syntology":null},{"paper":"/paper/plausibility-processing-in-transformer","slug":"plausibility-processing-in-transformer","title":"Plausibility Processing in Transformer Language Models: Focusing on the Role of Attention Heads in GPT","date":"2023-10-20","arxiv_id":"2310.13824","n_code_links":1,"syntology":null},{"paper":null,"slug":"potloc-pseudo-label-oriented-transformer-for","title":"POTLoc: Pseudo-Label Oriented Transformer for Point-Supervised Temporal Action Localization","date":"2023-10-20","arxiv_id":"2310.13585","n_code_links":0,"syntology":null},{"paper":null,"slug":"robust-training-for-conversational-question","title":"Robust Training for Conversational Question Answering Models with Reinforced Reformulation Generation","date":"2023-10-20","arxiv_id":"2310.13505","n_code_links":0,"syntology":null},{"paper":"/paper/skin-lesion-segmentation-improved-by","slug":"skin-lesion-segmentation-improved-by","title":"Skin Lesion Segmentation Improved by Transformer-based Networks with Inter-scale Dependency Modeling","date":"2023-10-20","arxiv_id":"2310.13604","n_code_links":1,"syntology":null},{"paper":null,"slug":"the-impact-of-performance-expectancy-workload","title":"The Impact of Performance Expectancy, Workload, Risk, and Satisfaction on Trust in ChatGPT: Cross-sectional Survey Analysis","date":"2023-10-20","arxiv_id":"2311.05632","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-perils-promises-of-fact-checking-with","title":"The Perils & Promises of Fact-checking with Large Language Models","date":"2023-10-20","arxiv_id":"2310.13549","n_code_links":0,"syntology":null},{"paper":"/paper/tuna-instruction-tuning-using-feedback-from","slug":"tuna-instruction-tuning-using-feedback-from","title":"Tuna: Instruction Tuning using Feedback from Large Language Models","date":"2023-10-20","arxiv_id":"2310.13385","n_code_links":1,"syntology":null},{"paper":null,"slug":"wordart-designer-user-driven-artistic","title":"WordArt Designer: User-Driven Artistic Typography Synthesis using Large Language Models","date":"2023-10-20","arxiv_id":"2310.18332","n_code_links":0,"syntology":null},{"paper":null,"slug":"2d-3d-interlaced-transformer-for-point-cloud-1","title":"2D-3D Interlaced Transformer for Point Cloud Segmentation with Scene-Level Supervision","date":"2023-10-19","arxiv_id":"2310.12817","n_code_links":0,"syntology":null},{"paper":"/paper/agenttuning-enabling-generalized-agent","slug":"agenttuning-enabling-generalized-agent","title":"AgentTuning: Enabling Generalized Agent Abilities for LLMs","date":"2023-10-19","arxiv_id":"2310.12823","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":["thudm/agenttuning"],"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":"an-exploration-of-in-context-learning-for","title":"Exploring In-Context Learning of Textless Speech Language Model for Speech Classification Tasks","date":"2023-10-19","arxiv_id":"2310.12477","n_code_links":0,"syntology":null},{"paper":null,"slug":"automatic-hallucination-assessment-for","title":"ReEval: Automatic Hallucination Evaluation for Retrieval-Augmented Large Language Models via Transferable Adversarial Attacks","date":"2023-10-19","arxiv_id":"2310.12516","n_code_links":0,"syntology":null},{"paper":"/paper/automix-automatically-mixing-language-models","slug":"automix-automatically-mixing-language-models","title":"AutoMix: Automatically Mixing Language Models","date":"2023-10-19","arxiv_id":"2310.12963","n_code_links":1,"syntology":{"ran":2,"of":4,"n_ran_checked":0,"n_instrument":2,"unverified":2,"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) · 2 unverified","official":{"repos":["automix-llm/automix"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/avtenet-audio-visual-transformer-based","slug":"avtenet-audio-visual-transformer-based","title":"AVTENet: Audio-Visual Transformer-based Ensemble Network Exploiting Multiple Experts for Video Deepfake Detection","date":"2023-10-19","arxiv_id":"2310.13103","n_code_links":0,"syntology":null},{"paper":"/paper/character-level-chinese-backpack-language","slug":"character-level-chinese-backpack-language","title":"Character-level Chinese Backpack Language Models","date":"2023-10-19","arxiv_id":"2310.12751","n_code_links":1,"syntology":null},{"paper":"/paper/da-transunet-integrating-spatial-and-channel","slug":"da-transunet-integrating-spatial-and-channel","title":"DA-TransUNet: Integrating Spatial and Channel Dual Attention with Transformer U-Net for Medical Image Segmentation","date":"2023-10-19","arxiv_id":"2310.12570","n_code_links":1,"syntology":null},{"paper":"/paper/eureka-human-level-reward-design-via-coding","slug":"eureka-human-level-reward-design-via-coding","title":"Eureka: Human-Level Reward Design via Coding Large Language Models","date":"2023-10-19","arxiv_id":"2310.12931","n_code_links":1,"syntology":{"ran":11,"of":12,"n_ran_checked":9,"n_instrument":2,"unverified":1,"pointer_only":1,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 1 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["eureka-research/Eureka"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":1,"ran_from_kinds":["community","official"]}}},{"paper":null,"slug":"experimental-narratives-a-comparison-of-human","title":"Experimental Narratives: A Comparison of Human Crowdsourced Storytelling and AI Storytelling","date":"2023-10-19","arxiv_id":"2310.12902","n_code_links":0,"syntology":null},{"paper":null,"slug":"exploring-graph-neural-networks-for-indian","title":"Exploring Graph Neural Networks for Indian Legal Judgment Prediction","date":"2023-10-19","arxiv_id":"2310.12800","n_code_links":0,"syntology":null},{"paper":"/paper/identifying-and-adapting-transformer","slug":"identifying-and-adapting-transformer","title":"Identifying and Adapting Transformer-Components Responsible for Gender Bias in an English Language Model","date":"2023-10-19","arxiv_id":"2310.12611","n_code_links":1,"syntology":{"ran":4,"of":5,"n_ran_checked":4,"n_instrument":0,"unverified":1,"pointer_only":5,"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":["iabhijith/bias-causal-analysis"],"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":"laser-linear-compression-in-wireless","title":"LASER: Linear Compression in Wireless Distributed Optimization","date":"2023-10-19","arxiv_id":"2310.13033","n_code_links":0,"syntology":null},{"paper":"/paper/letfuser-light-weight-end-to-end-transformer","slug":"letfuser-light-weight-end-to-end-transformer","title":"LeTFuser: Light-weight End-to-end Transformer-Based Sensor Fusion for Autonomous Driving with Multi-Task Learning","date":"2023-10-19","arxiv_id":"2310.13135","n_code_links":1,"syntology":null},{"paper":null,"slug":"medai-dialog-corpus-medic-zero-shot","title":"MedAI Dialog Corpus (MEDIC): Zero-Shot Classification of Doctor and AI Responses in Health Consultations","date":"2023-10-19","arxiv_id":"2310.12489","n_code_links":0,"syntology":null},{"paper":"/paper/minimalist-and-high-performance-semantic","slug":"minimalist-and-high-performance-semantic","title":"Minimalist and High-Performance Semantic Segmentation with Plain Vision Transformers","date":"2023-10-19","arxiv_id":"2310.12755","n_code_links":1,"syntology":null},{"paper":null,"slug":"multi-granularity-backprojection-transformer","title":"Multi-granularity Backprojection Transformer for Remote Sensing Image Super-Resolution","date":"2023-10-19","arxiv_id":"2310.12507","n_code_links":0,"syntology":null},{"paper":"/paper/non-autoregressive-sentence-ordering","slug":"non-autoregressive-sentence-ordering","title":"Non-Autoregressive Sentence Ordering","date":"2023-10-19","arxiv_id":"2310.12640","n_code_links":1,"syntology":null},{"paper":null,"slug":"not-all-countries-celebrate-thanksgiving-on","title":"Not All Countries Celebrate Thanksgiving: On the Cultural Dominance in Large Language Models","date":"2023-10-19","arxiv_id":"2310.12481","n_code_links":0,"syntology":null},{"paper":"/paper/predicting-ovarian-cancer-treatment-response","slug":"predicting-ovarian-cancer-treatment-response","title":"Predicting Ovarian Cancer Treatment Response in Histopathology using Hierarchical Vision Transformers and Multiple Instance Learning","date":"2023-10-19","arxiv_id":"2310.12866","n_code_links":1,"syntology":null},{"paper":"/paper/product-attribute-value-extraction-using","slug":"product-attribute-value-extraction-using","title":"ExtractGPT: Exploring the Potential of Large Language Models for Product Attribute Value Extraction","date":"2023-10-19","arxiv_id":"2310.12537","n_code_links":1,"syntology":null},{"paper":"/paper/real-time-motion-prediction-via-heterogeneous-1","slug":"real-time-motion-prediction-via-heterogeneous-1","title":"Real-Time Motion Prediction via Heterogeneous Polyline Transformer with Relative Pose Encoding","date":"2023-10-19","arxiv_id":"2310.12970","n_code_links":2,"syntology":{"ran":3,"of":5,"n_ran_checked":3,"n_instrument":0,"unverified":2,"pointer_only":5,"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) · 2 unverified","official":{"repos":["zhejz/hptr"],"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":["listed","official"]}}},{"paper":"/paper/sdgym-low-code-reinforcement-learning","slug":"sdgym-low-code-reinforcement-learning","title":"SDGym: Low-Code Reinforcement Learning Environments using System Dynamics Models","date":"2023-10-19","arxiv_id":"2310.12494","n_code_links":1,"syntology":null},{"paper":"/paper/sequence-length-independent-norm-based","slug":"sequence-length-independent-norm-based","title":"Sequence Length Independent Norm-Based Generalization Bounds for Transformers","date":"2023-10-19","arxiv_id":"2310.13088","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["traugerjacob/transformer-gen-bounds"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/the-foundation-model-transparency-index","slug":"the-foundation-model-transparency-index","title":"The Foundation Model Transparency Index","date":"2023-10-19","arxiv_id":"2310.12941","n_code_links":1,"syntology":null},{"paper":"/paper/the-shifted-and-the-overlooked-a-task","slug":"the-shifted-and-the-overlooked-a-task","title":"The Shifted and The Overlooked: A Task-oriented Investigation of User-GPT Interactions","date":"2023-10-19","arxiv_id":"2310.12418","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":2,"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":["ozyyshr/sharegpt_investigation"],"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":"/paper/to-grok-or-not-to-grok-disentangling","slug":"to-grok-or-not-to-grok-disentangling","title":"To grok or not to grok: Disentangling generalization and memorization on corrupted algorithmic datasets","date":"2023-10-19","arxiv_id":"2310.13061","n_code_links":1,"syntology":{"ran":10,"of":10,"n_ran_checked":10,"n_instrument":0,"unverified":0,"pointer_only":10,"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":["d-doshi/Grokking"],"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":null,"slug":"towards-robust-pruning-an-adaptive-knowledge","title":"Towards Robust Pruning: An Adaptive Knowledge-Retention Pruning Strategy for Language Models","date":"2023-10-19","arxiv_id":"2310.13191","n_code_links":0,"syntology":null},{"paper":"/paper/transformer-based-entity-legal-form","slug":"transformer-based-entity-legal-form","title":"Transformer-based Entity Legal Form Classification","date":"2023-10-19","arxiv_id":"2310.12766","n_code_links":1,"syntology":null},{"paper":"/paper/understanding-addition-in-transformers","slug":"understanding-addition-in-transformers","title":"Understanding Addition in Transformers","date":"2023-10-19","arxiv_id":"2310.13121","n_code_links":4,"syntology":{"ran":12,"of":16,"n_ran_checked":12,"n_instrument":0,"unverified":4,"pointer_only":0,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","official":{"repos":["apartresearch/conceptual-interp","apartresearch/integer_addition","apartresearch/interger_addition"],"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/amr-parsing-with-causal-hierarchical","slug":"amr-parsing-with-causal-hierarchical","title":"AMR Parsing with Causal Hierarchical Attention and Pointers","date":"2023-10-18","arxiv_id":"2310.11964","n_code_links":1,"syntology":{"ran":5,"of":5,"n_ran_checked":3,"n_instrument":2,"unverified":0,"pointer_only":2,"phrase":"5 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; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["louchao98/chap_amr_parser"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"deep-learning-based-on-transformer","title":"Deep learning based on Transformer architecture for power system short-term voltage stability assessment with class imbalance","date":"2023-10-18","arxiv_id":"2310.11690","n_code_links":0,"syntology":null},{"paper":null,"slug":"direct-neural-machine-translation-with-task","title":"Direct Neural Machine Translation with Task-level Mixture of Experts models","date":"2023-10-18","arxiv_id":"2310.12236","n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluating-the-symbol-binding-ability-of","title":"Evaluating the Symbol Binding Ability of Large Language Models for Multiple-Choice Questions in Vietnamese General Education","date":"2023-10-18","arxiv_id":"2310.12059","n_code_links":0,"syntology":null},{"paper":"/paper/fast-multipole-attention-a-divide-and-conquer","slug":"fast-multipole-attention-a-divide-and-conquer","title":"Fast Multipole Attention: A Divide-and-Conquer Attention Mechanism for Long Sequences","date":"2023-10-18","arxiv_id":"2310.11960","n_code_links":1,"syntology":null},{"paper":null,"slug":"field-testing-items-using-artificial","title":"Field-testing items using artificial intelligence: Natural language processing with transformers","date":"2023-10-18","arxiv_id":"2310.11655","n_code_links":0,"syntology":null},{"paper":"/paper/harnessing-dataset-cartography-for-improved","slug":"harnessing-dataset-cartography-for-improved","title":"Harnessing Dataset Cartography for Improved Compositional Generalization in Transformers","date":"2023-10-18","arxiv_id":"2310.12118","n_code_links":1,"syntology":null},{"paper":"/paper/lacma-language-aligning-contrastive-learning","slug":"lacma-language-aligning-contrastive-learning","title":"LACMA: Language-Aligning Contrastive Learning with Meta-Actions for Embodied Instruction Following","date":"2023-10-18","arxiv_id":"2310.12344","n_code_links":1,"syntology":{"ran":1,"of":5,"n_ran_checked":1,"n_instrument":0,"unverified":4,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","official":{"repos":["joeyy5588/lacma"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/monarch-mixer-a-simple-sub-quadratic-gemm-1","slug":"monarch-mixer-a-simple-sub-quadratic-gemm-1","title":"Monarch Mixer: A Simple Sub-Quadratic GEMM-Based Architecture","date":"2023-10-18","arxiv_id":"2310.12109","n_code_links":1,"syntology":{"ran":4,"of":7,"n_ran_checked":4,"n_instrument":0,"unverified":3,"pointer_only":0,"phrase":"4 ran (of which 4 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) · 3 unverified; every one of the 4 samples that ran constructed an object rather than computing a result","official":null}},{"paper":"/paper/quantify-health-related-atomic-knowledge-in","slug":"quantify-health-related-atomic-knowledge-in","title":"Quantifying Self-diagnostic Atomic Knowledge in Chinese Medical Foundation Model: A Computational Analysis","date":"2023-10-18","arxiv_id":"2310.11722","n_code_links":1,"syntology":null},{"paper":null,"slug":"solving-the-multiplication-problem-of-a-large","title":"Solving the multiplication problem of a large language model system using a graph-based method","date":"2023-10-18","arxiv_id":"2310.13016","n_code_links":0,"syntology":null},{"paper":"/paper/sotopia-interactive-evaluation-for-social","slug":"sotopia-interactive-evaluation-for-social","title":"SOTOPIA: Interactive Evaluation for Social Intelligence in Language Agents","date":"2023-10-18","arxiv_id":"2310.11667","n_code_links":2,"syntology":null},{"paper":null,"slug":"speed-speculative-pipelined-execution-for","title":"SPEED: Speculative Pipelined Execution for Efficient Decoding","date":"2023-10-18","arxiv_id":"2310.12072","n_code_links":0,"syntology":null},{"paper":null,"slug":"tailoring-adversarial-attacks-on-deep-neural","title":"Tailoring Adversarial Attacks on Deep Neural Networks for Targeted Class Manipulation Using DeepFool Algorithm","date":"2023-10-18","arxiv_id":"2310.13019","n_code_links":0,"syntology":null},{"paper":null,"slug":"vst-efficient-and-stronger-visual-saliency","title":"VST++: Efficient and Stronger Visual Saliency Transformer","date":"2023-10-18","arxiv_id":"2310.11725","n_code_links":0,"syntology":null},{"paper":null,"slug":"an-automatic-learning-rate-schedule-algorithm","title":"An Automatic Learning Rate Schedule Algorithm for Achieving Faster Convergence and Steeper Descent","date":"2023-10-17","arxiv_id":"2310.11291","n_code_links":0,"syntology":null},{"paper":"/paper/bitnet-scaling-1-bit-transformers-for-large","slug":"bitnet-scaling-1-bit-transformers-for-large","title":"BitNet: Scaling 1-bit Transformers for Large Language Models","date":"2023-10-17","arxiv_id":"2310.11453","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":null}},{"paper":"/paper/compatible-transformer-for-irregularly","slug":"compatible-transformer-for-irregularly","title":"Compatible Transformer for Irregularly Sampled Multivariate Time Series","date":"2023-10-17","arxiv_id":"2310.11022","n_code_links":1,"syntology":null},{"paper":"/paper/compost-characterizing-and-evaluating","slug":"compost-characterizing-and-evaluating","title":"CoMPosT: Characterizing and Evaluating Caricature in LLM Simulations","date":"2023-10-17","arxiv_id":"2310.11501","n_code_links":1,"syntology":{"ran":3,"of":4,"n_ran_checked":3,"n_instrument":0,"unverified":1,"pointer_only":4,"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) · 1 unverified","official":{"repos":["myracheng/lm_caricature"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"disentangling-the-linguistic-competence-of","title":"Disentangling the Linguistic Competence of Privacy-Preserving BERT","date":"2023-10-17","arxiv_id":"2310.11363","n_code_links":0,"syntology":null},{"paper":null,"slug":"emergent-ai-assisted-discourse-case-study-of","title":"Emergent AI-Assisted Discourse: Case Study of a Second Language Writer Authoring with ChatGPT","date":"2023-10-17","arxiv_id":"2310.10903","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhanced-transformer-architecture-for-natural","title":"Enhanced Transformer Architecture for Natural Language Processing","date":"2023-10-17","arxiv_id":"2310.10930","n_code_links":0,"syntology":null},{"paper":"/paper/evaluating-llms-for-privilege-escalation","slug":"evaluating-llms-for-privilege-escalation","title":"LLMs as Hackers: Autonomous Linux Privilege Escalation Attacks","date":"2023-10-17","arxiv_id":"2310.11409","n_code_links":1,"syntology":null},{"paper":null,"slug":"experimenting-ai-technologies-for","title":"Experimenting AI Technologies for Disinformation Combat: the IDMO Project","date":"2023-10-17","arxiv_id":"2310.11097","n_code_links":0,"syntology":null},{"paper":null,"slug":"focdepthformer-transformer-with-lstm-for","title":"FocDepthFormer: Transformer with latent LSTM for Depth Estimation from Focal Stack","date":"2023-10-17","arxiv_id":"2310.11178","n_code_links":0,"syntology":null},{"paper":"/paper/intent-detection-and-slot-filling-for-home","slug":"intent-detection-and-slot-filling-for-home","title":"Intent Detection and Slot Filling for Home Assistants: Dataset and Analysis for Bangla and Sylheti","date":"2023-10-17","arxiv_id":"2310.10935","n_code_links":1,"syntology":null},{"paper":null,"slug":"large-language-model-prediction-capabilities","title":"Large Language Model Prediction Capabilities: Evidence from a Real-World Forecasting Tournament","date":"2023-10-17","arxiv_id":"2310.13014","n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-from-red-teaming-gender-bias","title":"Learning from Red Teaming: Gender Bias Provocation and Mitigation in Large Language Models","date":"2023-10-17","arxiv_id":"2310.11079","n_code_links":0,"syntology":null},{"paper":null,"slug":"mason-nlp-at-erisk-2023-deep-learning-based","title":"MASON-NLP at eRisk 2023: Deep Learning-Based Detection of Depression Symptoms from Social Media Texts","date":"2023-10-17","arxiv_id":"2310.10941","n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-omics-sampling-based-graph-transformer","title":"Multi-omics Sampling-based Graph Transformer for Synthetic Lethality Prediction","date":"2023-10-17","arxiv_id":"2310.11082","n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-self-supervised-pre-fine-tuned","title":"Multi Self-supervised Pre-fine-tuned Transformer Fusion for Better Intelligent Transportation Detection","date":"2023-10-17","arxiv_id":"2310.11307","n_code_links":0,"syntology":null},{"paper":"/paper/neural-attention-enhancing-qkv-calculation-in","slug":"neural-attention-enhancing-qkv-calculation-in","title":"Neural Attention: Enhancing QKV Calculation in Self-Attention Mechanism with Neural Networks","date":"2023-10-17","arxiv_id":"2310.11398","n_code_links":1,"syntology":null},{"paper":"/paper/probing-the-creativity-of-large-language","slug":"probing-the-creativity-of-large-language","title":"Probing the Creativity of Large Language Models: Can models produce divergent semantic association?","date":"2023-10-17","arxiv_id":"2310.11158","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":0,"n_instrument":1,"unverified":1,"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) · 1 unverified","official":{"repos":["dingnlab/probing_creativity"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/signgt-signed-attention-based-graph","slug":"signgt-signed-attention-based-graph","title":"SignGT: Signed Attention-based Graph Transformer for Graph Representation Learning","date":"2023-10-17","arxiv_id":"2310.11025","n_code_links":0,"syntology":null},{"paper":"/paper/understanding-writing-style-in-social-media","slug":"understanding-writing-style-in-social-media","title":"Understanding writing style in social media with a supervised contrastively pre-trained transformer","date":"2023-10-17","arxiv_id":"2310.11081","n_code_links":1,"syntology":null},{"paper":null,"slug":"utilising-a-large-language-model-to-annotate","title":"Utilising a Large Language Model to Annotate Subject Metadata: A Case Study in an Australian National Research Data Catalogue","date":"2023-10-17","arxiv_id":"2310.11318","n_code_links":0,"syntology":null},{"paper":"/paper/vct-visual-change-transformer-for-remote","slug":"vct-visual-change-transformer-for-remote","title":"VcT: Visual change Transformer for Remote Sensing Image Change Detection","date":"2023-10-17","arxiv_id":"2310.11417","n_code_links":1,"syntology":null},{"paper":null,"slug":"what-is-a-good-question-task-oriented-asking","title":"Alexpaca: Learning Factual Clarification Question Generation Without Examples","date":"2023-10-17","arxiv_id":"2310.11571","n_code_links":0,"syntology":null},{"paper":"/paper/zipformer-a-faster-and-better-encoder-for","slug":"zipformer-a-faster-and-better-encoder-for","title":"Zipformer: A faster and better encoder for automatic speech recognition","date":"2023-10-17","arxiv_id":"2310.11230","n_code_links":1,"syntology":null},{"paper":"/paper/a-cross-transformer-for-image-denoising","slug":"a-cross-transformer-for-image-denoising","title":"A cross Transformer for image denoising","date":"2023-10-16","arxiv_id":"2310.10408","n_code_links":1,"syntology":null},{"paper":"/paper/adalomo-low-memory-optimization-with-adaptive","slug":"adalomo-low-memory-optimization-with-adaptive","title":"AdaLomo: Low-memory Optimization with Adaptive Learning Rate","date":"2023-10-16","arxiv_id":"2310.10195","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":2,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["openlmlab/lomo"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/approximating-two-layer-feedforward-networks","slug":"approximating-two-layer-feedforward-networks","title":"Approximating Two-Layer Feedforward Networks for Efficient Transformers","date":"2023-10-16","arxiv_id":"2310.10837","n_code_links":2,"syntology":{"ran":3,"of":4,"n_ran_checked":1,"n_instrument":2,"unverified":1,"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) · 1 unverified","official":{"repos":["robertcsordas/moe","robertcsordas/moe_layer"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"battle-of-the-large-language-models-dolly-vs","title":"Battle of the Large Language Models: Dolly vs LLaMA vs Vicuna vs Guanaco vs Bard vs ChatGPT -- A Text-to-SQL Parsing Comparison","date":"2023-10-16","arxiv_id":"2310.10190","n_code_links":0,"syntology":null},{"paper":null,"slug":"biomedjourney-counterfactual-biomedical-image","title":"BiomedJourney: Counterfactual Biomedical Image Generation by Instruction-Learning from Multimodal Patient Journeys","date":"2023-10-16","arxiv_id":"2310.10765","n_code_links":0,"syntology":null},{"paper":"/paper/bioplanner-automatic-evaluation-of-llms-on","slug":"bioplanner-automatic-evaluation-of-llms-on","title":"BioPlanner: Automatic Evaluation of LLMs on Protocol Planning in Biology","date":"2023-10-16","arxiv_id":"2310.10632","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":2,"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":["bioplanner/bioplanner"],"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":"/paper/data-contamination-through-the-lens-of-time","slug":"data-contamination-through-the-lens-of-time","title":"Data Contamination Through the Lens of Time","date":"2023-10-16","arxiv_id":"2310.10628","n_code_links":1,"syntology":{"ran":2,"of":4,"n_ran_checked":2,"n_instrument":0,"unverified":2,"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) · 2 unverified","official":{"repos":["abacusai/to-the-cutoff"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/factored-verification-detecting-and-reducing","slug":"factored-verification-detecting-and-reducing","title":"Factored Verification: Detecting and Reducing Hallucination in Summaries of Academic Papers","date":"2023-10-16","arxiv_id":"2310.10627","n_code_links":1,"syntology":null},{"paper":null,"slug":"few-shot-action-recognition-with-captioning","title":"Few-shot Action Recognition with Captioning Foundation Models","date":"2023-10-16","arxiv_id":"2310.10125","n_code_links":0,"syntology":null},{"paper":null,"slug":"fine-tuning-chatgpt-for-automatic-scoring","title":"Fine-tuning ChatGPT for Automatic Scoring","date":"2023-10-16","arxiv_id":"2310.10072","n_code_links":0,"syntology":null},{"paper":"/paper/investigating-bias-in-multilingual-language","slug":"investigating-bias-in-multilingual-language","title":"Investigating Bias in Multilingual Language Models: Cross-Lingual Transfer of Debiasing Techniques","date":"2023-10-16","arxiv_id":"2310.10310","n_code_links":1,"syntology":null}],"record_sha256":"01162aad01ee8d7200e6ce650e64058d11ef2f56b67c00b888cd9b464fdd3bdb","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}