{"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/87","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":87,"pages_in_order":244,"rows_per_page":100,"rows":[8601,8700],"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/86","next":"/method/adam/papers/88","papers":[{"paper":"/paper/is-mamba-capable-of-in-context-learning","slug":"is-mamba-capable-of-in-context-learning","title":"Is Mamba Capable of In-Context Learning?","date":"2024-02-05","arxiv_id":"2402.03170","n_code_links":1,"syntology":{"ran":7,"of":8,"n_ran_checked":6,"n_instrument":1,"unverified":1,"pointer_only":8,"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":["automl/is_mamba_capable_of_icl"],"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":null,"slug":"lb-kbqa-large-language-model-and-bert-based","title":"LB-KBQA: Large-language-model and BERT based Knowledge-Based Question and Answering System","date":"2024-02-05","arxiv_id":"2402.05130","n_code_links":0,"syntology":null},{"paper":"/paper/llm-agents-in-interaction-measuring","slug":"llm-agents-in-interaction-measuring","title":"LLM Agents in Interaction: Measuring Personality Consistency and Linguistic Alignment in Interacting Populations of Large Language Models","date":"2024-02-05","arxiv_id":"2402.02896","n_code_links":1,"syntology":null},{"paper":null,"slug":"mobilitygpt-enhanced-human-mobility-modeling","title":"MobilityGPT: Enhanced Human Mobility Modeling with a GPT model","date":"2024-02-05","arxiv_id":"2402.03264","n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-lingual-malaysian-embedding-leveraging","title":"Multi-Lingual Malaysian Embedding: Leveraging Large Language Models for Semantic Representations","date":"2024-02-05","arxiv_id":"2402.03053","n_code_links":0,"syntology":null},{"paper":"/paper/swag-storytelling-with-action-guidance","slug":"swag-storytelling-with-action-guidance","title":"SWAG: Storytelling With Action Guidance","date":"2024-02-05","arxiv_id":"2402.03483","n_code_links":1,"syntology":null},{"paper":null,"slug":"toward-human-ai-alignment-in-large-scale","title":"Toward Human-AI Alignment in Large-Scale Multi-Player Games","date":"2024-02-05","arxiv_id":"2402.03575","n_code_links":0,"syntology":null},{"paper":"/paper/unimem-towards-a-unified-view-of-long-context","slug":"unimem-towards-a-unified-view-of-long-context","title":"UniMem: Towards a Unified View of Long-Context Large Language Models","date":"2024-02-05","arxiv_id":"2402.03009","n_code_links":1,"syntology":null},{"paper":"/paper/a-flexible-bayesian-g-formula-for-causal","slug":"a-flexible-bayesian-g-formula-for-causal","title":"A flexible Bayesian g-formula for causal survival analyses with time-dependent confounding","date":"2024-02-04","arxiv_id":"2402.02306","n_code_links":1,"syntology":null},{"paper":"/paper/a-graph-is-worth-k-words-euclideanizing-graph","slug":"a-graph-is-worth-k-words-euclideanizing-graph","title":"A Graph is Worth $K$ Words: Euclideanizing Graph using Pure Transformer","date":"2024-02-04","arxiv_id":"2402.02464","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: 1 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["A4Bio/GraphsGPT"],"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":"aligner-achieving-efficient-alignment-through","title":"Aligner: Efficient Alignment by Learning to Correct","date":"2024-02-04","arxiv_id":"2402.02416","n_code_links":0,"syntology":null},{"paper":"/paper/autotimes-autoregressive-time-series","slug":"autotimes-autoregressive-time-series","title":"AutoTimes: Autoregressive Time Series Forecasters via Large Language Models","date":"2024-02-04","arxiv_id":"2402.02370","n_code_links":1,"syntology":null},{"paper":null,"slug":"breaking-mlperf-training-a-case-study-on","title":"Breaking MLPerf Training: A Case Study on Optimizing BERT","date":"2024-02-04","arxiv_id":"2402.02447","n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluating-large-language-models-in-analysing","title":"Evaluating Large Language Models in Analysing Classroom Dialogue","date":"2024-02-04","arxiv_id":"2402.02380","n_code_links":0,"syntology":null},{"paper":"/paper/gerea-question-aware-prompt-captions-for","slug":"gerea-question-aware-prompt-captions-for","title":"GeReA: Question-Aware Prompt Captions for Knowledge-based Visual Question Answering","date":"2024-02-04","arxiv_id":"2402.02503","n_code_links":1,"syntology":{"ran":13,"of":18,"n_ran_checked":13,"n_instrument":0,"unverified":5,"pointer_only":18,"phrase":"13 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; 0 where Syntology's instrument failed) · 5 unverified","official":{"repos":["upper9527/gerea"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":13,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"improving-assessment-of-tutoring-practices","title":"Improving Assessment of Tutoring Practices using Retrieval-Augmented Generation","date":"2024-02-04","arxiv_id":"2402.14594","n_code_links":0,"syntology":null},{"paper":"/paper/invit-a-generalizable-routing-problem-solver","slug":"invit-a-generalizable-routing-problem-solver","title":"INViT: A Generalizable Routing Problem Solver with Invariant Nested View Transformer","date":"2024-02-04","arxiv_id":"2402.02317","n_code_links":1,"syntology":{"ran":8,"of":12,"n_ran_checked":6,"n_instrument":2,"unverified":4,"pointer_only":12,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified","official":{"repos":["kasumigaoka-utaha/invit"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"key-graph-transformer-for-image-restoration","title":"Key-Graph Transformer for Image Restoration","date":"2024-02-04","arxiv_id":"2402.02634","n_code_links":0,"syntology":null},{"paper":"/paper/minusformer-improving-time-series-forecasting","slug":"minusformer-improving-time-series-forecasting","title":"Minusformer: Improving Time Series Forecasting by Progressively Learning Residuals","date":"2024-02-04","arxiv_id":"2402.02332","n_code_links":1,"syntology":null},{"paper":"/paper/pathformer-multi-scale-transformers-with","slug":"pathformer-multi-scale-transformers-with","title":"Pathformer: Multi-scale Transformers with Adaptive Pathways for Time Series Forecasting","date":"2024-02-04","arxiv_id":"2402.05956","n_code_links":1,"syntology":{"ran":6,"of":11,"n_ran_checked":6,"n_instrument":0,"unverified":5,"pointer_only":11,"phrase":"6 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; 0 where Syntology's instrument failed) · 5 unverified","official":{"repos":["decisionintelligence/pathformer"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"prosac-provably-safe-certification-for","title":"PROSAC: Provably Safe Certification for Machine Learning Models under Adversarial Attacks","date":"2024-02-04","arxiv_id":"2402.02629","n_code_links":0,"syntology":null},{"paper":null,"slug":"spctnet-a-series-parallel-cnn-and-transformer","title":"SPCTNet: A Series-Parallel CNN and Transformer Network for 3D Medical Image Segmentation","date":"2024-02-04","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"spin-an-efficient-secure-computation","title":"Spin: An Efficient Secure Computation Framework with GPU Acceleration","date":"2024-02-04","arxiv_id":"2402.02320","n_code_links":0,"syntology":null},{"paper":"/paper/timer-transformers-for-time-series-analysis","slug":"timer-transformers-for-time-series-analysis","title":"Timer: Generative Pre-trained Transformers Are Large Time Series Models","date":"2024-02-04","arxiv_id":"2402.02368","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["thuml/Large-Time-Series-Model"],"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/unified-training-of-universal-time-series","slug":"unified-training-of-universal-time-series","title":"Unified Training of Universal Time Series Forecasting Transformers","date":"2024-02-04","arxiv_id":"2402.02592","n_code_links":1,"syntology":null},{"paper":null,"slug":"betterv-controlled-verilog-generation-with","title":"BetterV: Controlled Verilog Generation with Discriminative Guidance","date":"2024-02-03","arxiv_id":"2402.03375","n_code_links":0,"syntology":null},{"paper":null,"slug":"data-quality-matters-suicide-intention","title":"Data Quality Matters: Suicide Intention Detection on Social Media Posts Using RoBERTa-CNN","date":"2024-02-03","arxiv_id":"2402.02262","n_code_links":0,"syntology":null},{"paper":null,"slug":"de-3-bert-distance-enhanced-early-exiting-for","title":"DE$^3$-BERT: Distance-Enhanced Early Exiting for BERT based on Prototypical Networks","date":"2024-02-03","arxiv_id":"2402.05948","n_code_links":0,"syntology":null},{"paper":null,"slug":"diffvein-a-unified-diffusion-network-for","title":"DiffVein: A Unified Diffusion Network for Finger Vein Segmentation and Authentication","date":"2024-02-03","arxiv_id":"2402.02060","n_code_links":0,"syntology":null},{"paper":null,"slug":"do-moral-judgment-and-reasoning-capability-of","title":"Do Moral Judgment and Reasoning Capability of LLMs Change with Language? A Study using the Multilingual Defining Issues Test","date":"2024-02-03","arxiv_id":"2402.02135","n_code_links":0,"syntology":null},{"paper":"/paper/effibench-benchmarking-the-efficiency-of","slug":"effibench-benchmarking-the-efficiency-of","title":"EffiBench: Benchmarking the Efficiency of Automatically Generated Code","date":"2024-02-03","arxiv_id":"2402.02037","n_code_links":1,"syntology":{"ran":3,"of":5,"n_ran_checked":1,"n_instrument":2,"unverified":2,"pointer_only":5,"phrase":"3 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; 2 where Syntology's instrument failed) · 2 unverified","official":{"repos":["huangd1999/EffiBench"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/how-well-do-llms-cite-relevant-medical","slug":"how-well-do-llms-cite-relevant-medical","title":"How well do LLMs cite relevant medical references? An evaluation framework and analyses","date":"2024-02-03","arxiv_id":"2402.02008","n_code_links":1,"syntology":null},{"paper":null,"slug":"imusic-imu-based-facial-expression-capture","title":"IMUSE: IMU-based Facial Expression Capture","date":"2024-02-03","arxiv_id":"2402.03944","n_code_links":0,"syntology":null},{"paper":"/paper/parzc-parametric-zero-cost-proxies-for","slug":"parzc-parametric-zero-cost-proxies-for","title":"ParZC: Parametric Zero-Cost Proxies for Efficient NAS","date":"2024-02-03","arxiv_id":"2402.02105","n_code_links":0,"syntology":null},{"paper":"/paper/scribformer-transformer-makes-cnn-work-better","slug":"scribformer-transformer-makes-cnn-work-better","title":"ScribFormer: Transformer Makes CNN Work Better for Scribble-based Medical Image Segmentation","date":"2024-02-03","arxiv_id":"2402.02029","n_code_links":1,"syntology":null},{"paper":null,"slug":"tci-former-thermal-conduction-inspired","title":"TCI-Former: Thermal Conduction-Inspired Transformer for Infrared Small Target Detection","date":"2024-02-03","arxiv_id":"2402.02046","n_code_links":0,"syntology":null},{"paper":null,"slug":"textit-minmaxmin-q-learning","title":"MinMaxMin $Q$-learning","date":"2024-02-03","arxiv_id":"2402.05951","n_code_links":0,"syntology":null},{"paper":null,"slug":"textit-sqt-textit-std-q-target","title":"SQT -- std $Q$-target","date":"2024-02-03","arxiv_id":"2402.05950","n_code_links":0,"syntology":null},{"paper":"/paper/topology-informed-graph-transformer","slug":"topology-informed-graph-transformer","title":"Topology-Informed Graph Transformer","date":"2024-02-03","arxiv_id":"2402.02005","n_code_links":2,"syntology":{"ran":17,"of":21,"n_ran_checked":17,"n_instrument":0,"unverified":4,"pointer_only":21,"phrase":"17 ran (of which 0 constructed an object rather than computing a result; 17 with no instrument failure: 0 honoured, 2 violated, 15 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","official":{"repos":["leemingo/tigt"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":3,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/tsis-a-supplementary-algorithm-to-t-smiles","slug":"tsis-a-supplementary-algorithm-to-t-smiles","title":"Hierarchical Structure Enhances the Convergence and Generalizability of Linear Molecular Representation","date":"2024-02-03","arxiv_id":"2402.02164","n_code_links":1,"syntology":null},{"paper":"/paper/a-data-driven-analysis-of-robust-automatic","slug":"a-data-driven-analysis-of-robust-automatic","title":"A Data-Driven Analysis of Robust Automatic Piano Transcription","date":"2024-02-02","arxiv_id":"2402.01424","n_code_links":0,"syntology":null},{"paper":"/paper/alert-transformer-bridging-asynchronous-and","slug":"alert-transformer-bridging-asynchronous-and","title":"ALERT-Transformer: Bridging Asynchronous and Synchronous Machine Learning for Real-Time Event-based Spatio-Temporal Data","date":"2024-02-02","arxiv_id":"2402.01393","n_code_links":0,"syntology":null},{"paper":null,"slug":"an-introduction-to-graphical-tensor-notation","title":"An introduction to graphical tensor notation for mechanistic interpretability","date":"2024-02-02","arxiv_id":"2402.01790","n_code_links":0,"syntology":null},{"paper":null,"slug":"bat-learning-to-reason-about-spatial-sounds","title":"BAT: Learning to Reason about Spatial Sounds with Large Language Models","date":"2024-02-02","arxiv_id":"2402.01591","n_code_links":0,"syntology":null},{"paper":"/paper/challenges-in-training-pinns-a-loss-landscape","slug":"challenges-in-training-pinns-a-loss-landscape","title":"Challenges in Training PINNs: A Loss Landscape Perspective","date":"2024-02-02","arxiv_id":"2402.01868","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":2,"n_instrument":2,"unverified":0,"pointer_only":4,"phrase":"4 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["pratikrathore8/opt_for_pinns"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/clarifying-the-path-to-user-satisfaction-an","slug":"clarifying-the-path-to-user-satisfaction-an","title":"Clarifying the Path to User Satisfaction: An Investigation into Clarification Usefulness","date":"2024-02-02","arxiv_id":"2402.01934","n_code_links":1,"syntology":null},{"paper":null,"slug":"comet-generating-commit-messages-using-delta","title":"COMET: Generating Commit Messages using Delta Graph Context Representation","date":"2024-02-02","arxiv_id":"2402.01841","n_code_links":0,"syntology":null},{"paper":"/paper/cross-view-masked-diffusion-transformers-for","slug":"cross-view-masked-diffusion-transformers-for","title":"Cross-view Masked Diffusion Transformers for Person Image Synthesis","date":"2024-02-02","arxiv_id":"2402.01516","n_code_links":1,"syntology":{"ran":2,"of":5,"n_ran_checked":2,"n_instrument":0,"unverified":3,"pointer_only":0,"phrase":"2 ran (of which 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) · 3 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","official":{"repos":["trungpx/xmdpt"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"enhancing-stochastic-gradient-descent-a","title":"Enhancing Stochastic Gradient Descent: A Unified Framework and Novel Acceleration Methods for Faster Convergence","date":"2024-02-02","arxiv_id":"2402.01515","n_code_links":0,"syntology":null},{"paper":"/paper/exploring-the-limitations-of-graph-reasoning","slug":"exploring-the-limitations-of-graph-reasoning","title":"Can LLMs perform structured graph reasoning?","date":"2024-02-02","arxiv_id":"2402.01805","n_code_links":1,"syntology":null},{"paper":null,"slug":"faster-inference-of-integer-swin-transformer","title":"Faster Inference of Integer SWIN Transformer by Removing the GELU Activation","date":"2024-02-02","arxiv_id":"2402.01169","n_code_links":0,"syntology":null},{"paper":null,"slug":"how-can-generative-ai-enhance-the-well-being","title":"How Can Generative AI Enhance the Well-being of Blind?","date":"2024-02-02","arxiv_id":"2402.07919","n_code_links":0,"syntology":null},{"paper":"/paper/improving-sequential-recommendations-with","slug":"improving-sequential-recommendations-with","title":"Improving Sequential Recommendations with LLMs","date":"2024-02-02","arxiv_id":"2402.01339","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: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["dh-r/llm-sequential-recommendation"],"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":"/paper/integrating-large-language-models-in-causal","slug":"integrating-large-language-models-in-causal","title":"Integrating Large Language Models in Causal Discovery: A Statistical Causal Approach","date":"2024-02-02","arxiv_id":"2402.01454","n_code_links":2,"syntology":null},{"paper":"/paper/llm-detector-improving-ai-generated-chinese","slug":"llm-detector-improving-ai-generated-chinese","title":"LLM-Detector: Improving AI-Generated Chinese Text Detection with Open-Source LLM Instruction Tuning","date":"2024-02-02","arxiv_id":"2402.01158","n_code_links":1,"syntology":null},{"paper":null,"slug":"lotr-low-tensor-rank-weight-adaptation","title":"LoTR: Low Tensor Rank Weight Adaptation","date":"2024-02-02","arxiv_id":"2402.01376","n_code_links":0,"syntology":null},{"paper":null,"slug":"predicting-atp-binding-sites-in-protein","title":"Predicting ATP binding sites in protein sequences using Deep Learning and Natural Language Processing","date":"2024-02-02","arxiv_id":"2402.01829","n_code_links":0,"syntology":null},{"paper":null,"slug":"retrieval-augmented-end-to-end-spoken-dialog","title":"Retrieval Augmented End-to-End Spoken Dialog Models","date":"2024-02-02","arxiv_id":"2402.01828","n_code_links":0,"syntology":null},{"paper":null,"slug":"todyformer-towards-holistic-dynamic-graph","title":"Todyformer: Towards Holistic Dynamic Graph Transformers with Structure-Aware Tokenization","date":"2024-02-02","arxiv_id":"2402.05944","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-a-unified-language-model-for","title":"CorpusLM: Towards a Unified Language Model on Corpus for Knowledge-Intensive Tasks","date":"2024-02-02","arxiv_id":"2402.01176","n_code_links":0,"syntology":null},{"paper":null,"slug":"transformers-learn-nonlinear-features-in","title":"Transformers Learn Nonlinear Features In Context: Nonconvex Mean-field Dynamics on the Attention Landscape","date":"2024-02-02","arxiv_id":"2402.01258","n_code_links":0,"syntology":null},{"paper":"/paper/travelplanner-a-benchmark-for-real-world","slug":"travelplanner-a-benchmark-for-real-world","title":"TravelPlanner: A Benchmark for Real-World Planning with Language Agents","date":"2024-02-02","arxiv_id":"2402.01622","n_code_links":2,"syntology":{"ran":17,"of":17,"n_ran_checked":13,"n_instrument":4,"unverified":0,"pointer_only":4,"phrase":"17 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 1 honoured, 0 violated, 12 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","official":{"repos":["OSU-NLP-Group/TravelPlanner"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"paper":null,"slug":"understanding-adam-optimizer-via-online","title":"Understanding Adam Optimizer via Online Learning of Updates: Adam is FTRL in Disguise","date":"2024-02-02","arxiv_id":"2402.01567","n_code_links":0,"syntology":null},{"paper":null,"slug":"what-will-my-model-forget-forecasting","title":"What Will My Model Forget? Forecasting Forgotten Examples in Language Model Refinement","date":"2024-02-02","arxiv_id":"2402.01865","n_code_links":0,"syntology":null},{"paper":"/paper/dendritic-learning-incorporated-vision","slug":"dendritic-learning-incorporated-vision","title":"Dendritic Learning-incorporated Vision Transformer for Image Recognition","date":"2024-02-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"fuseformer-a-transformer-for-visual-and","title":"FuseFormer: A Transformer for Visual and Thermal Image Fusion","date":"2024-02-01","arxiv_id":"2402.00971","n_code_links":0,"syntology":null},{"paper":null,"slug":"generation-distillation-and-evaluation-of","title":"Generation, Distillation and Evaluation of Motivational Interviewing-Style Reflections with a Foundational Language Model","date":"2024-02-01","arxiv_id":"2402.01051","n_code_links":0,"syntology":null},{"paper":null,"slug":"hierarchical-multi-label-classification-of-2","title":"Hierarchical Multi-Label Classification of Online Vaccine Concerns","date":"2024-02-01","arxiv_id":"2402.01783","n_code_links":0,"syntology":null},{"paper":null,"slug":"hiqa-a-hierarchical-contextual-augmentation","title":"HiQA: A Hierarchical Contextual Augmentation RAG for Multi-Documents QA","date":"2024-02-01","arxiv_id":"2402.01767","n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-planning-based-reasoning-by","title":"Learning Planning-based Reasoning by Trajectories Collection and Process Reward Synthesizing","date":"2024-02-01","arxiv_id":"2402.00658","n_code_links":0,"syntology":null},{"paper":"/paper/merging-multi-task-models-via-weight","slug":"merging-multi-task-models-via-weight","title":"Merging Multi-Task Models via Weight-Ensembling Mixture of Experts","date":"2024-02-01","arxiv_id":"2402.00433","n_code_links":1,"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: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["tanganke/weight-ensembling_moe"],"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/multivariate-probabilistic-time-series","slug":"multivariate-probabilistic-time-series","title":"Multivariate Probabilistic Time Series Forecasting with Correlated Errors","date":"2024-02-01","arxiv_id":"2402.01000","n_code_links":1,"syntology":{"ran":3,"of":4,"n_ran_checked":0,"n_instrument":3,"unverified":1,"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) · 1 unverified","official":{"repos":["rottenivy/mv_pts_correlatederr"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"neural-style-transfer-with-twin-delayed-ddpg","title":"Neural Style Transfer with Twin-Delayed DDPG for Shared Control of Robotic Manipulators","date":"2024-02-01","arxiv_id":"2402.00722","n_code_links":0,"syntology":null},{"paper":null,"slug":"ocassionally-secure-a-comparative-analysis-of","title":"Ocassionally Secure: A Comparative Analysis of Code Generation Assistants","date":"2024-02-01","arxiv_id":"2402.00689","n_code_links":0,"syntology":null},{"paper":null,"slug":"on-the-psychology-of-gpt-4-moderately-anxious","title":"On the Psychology of GPT-4: Moderately anxious, slightly masculine, honest, and humble","date":"2024-02-01","arxiv_id":"2402.01777","n_code_links":0,"syntology":null},{"paper":"/paper/reagent-towards-a-model-agnostic-feature","slug":"reagent-towards-a-model-agnostic-feature","title":"ReAGent: A Model-agnostic Feature Attribution Method for Generative Language Models","date":"2024-02-01","arxiv_id":"2402.00794","n_code_links":1,"syntology":null},{"paper":"/paper/recurrent-transformers-with-dynamic-halt","slug":"recurrent-transformers-with-dynamic-halt","title":"Investigating Recurrent Transformers with Dynamic Halt","date":"2024-02-01","arxiv_id":"2402.00976","n_code_links":1,"syntology":null},{"paper":null,"slug":"self-supervised-contrastive-pre-training-for-1","title":"Self-Supervised Contrastive Pre-Training for Multivariate Point Processes","date":"2024-02-01","arxiv_id":"2402.00987","n_code_links":0,"syntology":null},{"paper":"/paper/sparql-generation-with-entity-pre-trained-gpt","slug":"sparql-generation-with-entity-pre-trained-gpt","title":"SPARQL Generation with Entity Pre-trained GPT for KG Question Answering","date":"2024-02-01","arxiv_id":"2402.00969","n_code_links":1,"syntology":null},{"paper":null,"slug":"tiny-titans-can-smaller-large-language-models","title":"Tiny Titans: Can Smaller Large Language Models Punch Above Their Weight in the Real World for Meeting Summarization?","date":"2024-02-01","arxiv_id":"2402.00841","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-scalable-robotic-intervention-of","title":"Human-mediated Large Language Models for Robotic Intervention in Children with Autism Spectrum Disorders","date":"2024-02-01","arxiv_id":"2402.00260","n_code_links":0,"syntology":null},{"paper":null,"slug":"understanding-the-expressive-power-and","title":"Understanding the Expressive Power and Mechanisms of Transformer for Sequence Modeling","date":"2024-02-01","arxiv_id":"2402.00522","n_code_links":0,"syntology":null},{"paper":null,"slug":"code-aware-prompting-a-study-of-coverage","title":"Code-Aware Prompting: A study of Coverage Guided Test Generation in Regression Setting using LLM","date":"2024-01-31","arxiv_id":"2402.00097","n_code_links":0,"syntology":null},{"paper":null,"slug":"computation-and-parameter-efficient-multi","title":"Computation and Parameter Efficient Multi-Modal Fusion Transformer for Cued Speech Recognition","date":"2024-01-31","arxiv_id":"2401.17604","n_code_links":0,"syntology":null},{"paper":"/paper/consmax-hardware-friendly-alternative-softmax","slug":"consmax-hardware-friendly-alternative-softmax","title":"ConSmax: Hardware-Friendly Alternative Softmax with Learnable Parameters","date":"2024-01-31","arxiv_id":"2402.10930","n_code_links":1,"syntology":null},{"paper":null,"slug":"document-structure-in-long-document","title":"Document Structure in Long Document Transformers","date":"2024-01-31","arxiv_id":"2401.17658","n_code_links":0,"syntology":null},{"paper":"/paper/enclap-combining-neural-audio-codec-and-audio","slug":"enclap-combining-neural-audio-codec-and-audio","title":"EnCLAP: Combining Neural Audio Codec and Audio-Text Joint Embedding for Automated Audio Captioning","date":"2024-01-31","arxiv_id":"2401.17690","n_code_links":1,"syntology":null},{"paper":null,"slug":"exploring-the-limits-of-decoder-only-models","title":"Exploring the limits of decoder-only models trained on public speech recognition corpora","date":"2024-01-31","arxiv_id":"2402.00235","n_code_links":0,"syntology":null},{"paper":null,"slug":"global-liar-factuality-of-llms-over-time-and","title":"Global-Liar: Factuality of LLMs over Time and Geographic Regions","date":"2024-01-31","arxiv_id":"2401.17839","n_code_links":0,"syntology":null},{"paper":"/paper/graph-transformers-without-positional","slug":"graph-transformers-without-positional","title":"Graph Transformers without Positional Encodings","date":"2024-01-31","arxiv_id":"2401.17791","n_code_links":0,"syntology":null},{"paper":null,"slug":"head-and-neck-tumor-segmentation-from-18f-f","title":"Head and Neck Tumor Segmentation from [18F]F-FDG PET/CT Images Based on 3D Diffusion Model","date":"2024-01-31","arxiv_id":"2401.17593","n_code_links":0,"syntology":null},{"paper":"/paper/leveraging-swin-transformer-for-local-to","slug":"leveraging-swin-transformer-for-local-to","title":"Leveraging Swin Transformer for Local-to-Global Weakly Supervised Semantic Segmentation","date":"2024-01-31","arxiv_id":"2401.17828","n_code_links":1,"syntology":null},{"paper":"/paper/llm-voting-human-choices-and-ai-collective","slug":"llm-voting-human-choices-and-ai-collective","title":"LLM Voting: Human Choices and AI Collective Decision Making","date":"2024-01-31","arxiv_id":"2402.01766","n_code_links":1,"syntology":{"ran":0,"of":2,"n_ran_checked":0,"n_instrument":0,"unverified":2,"pointer_only":2,"phrase":"0 ran · 2 unverified","official":{"repos":["ethz-coss/LLM_voting"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":[]}}},{"paper":"/paper/local-feature-matching-using-deep-learning-a","slug":"local-feature-matching-using-deep-learning-a","title":"Local Feature Matching Using Deep Learning: A Survey","date":"2024-01-31","arxiv_id":"2401.17592","n_code_links":1,"syntology":null},{"paper":null,"slug":"making-a-long-story-short-in-conversation","title":"Making a Long Story Short in Conversation Modeling","date":"2024-01-31","arxiv_id":"2402.00143","n_code_links":0,"syntology":null},{"paper":null,"slug":"mitigating-the-problem-of-strong-priors-in","title":"Mitigating the Influence of Distractor Tasks in LMs with Prior-Aware Decoding","date":"2024-01-31","arxiv_id":"2401.17692","n_code_links":0,"syntology":null},{"paper":null,"slug":"paramanu-a-family-of-novel-efficient-indic","title":"Paramanu: A Family of Novel Efficient Generative Foundation Language Models for Indian Languages","date":"2024-01-31","arxiv_id":"2401.18034","n_code_links":0,"syntology":null},{"paper":"/paper/positional-encoding-helps-recurrent-neural","slug":"positional-encoding-helps-recurrent-neural","title":"Positional Encoding Helps Recurrent Neural Networks Handle a Large Vocabulary","date":"2024-01-31","arxiv_id":"2402.00236","n_code_links":1,"syntology":null},{"paper":null,"slug":"rag-fusion-a-new-take-on-retrieval-augmented","title":"RAG-Fusion: a New Take on Retrieval-Augmented Generation","date":"2024-01-31","arxiv_id":"2402.03367","n_code_links":0,"syntology":null},{"paper":"/paper/raptor-recursive-abstractive-processing-for","slug":"raptor-recursive-abstractive-processing-for","title":"RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval","date":"2024-01-31","arxiv_id":"2401.18059","n_code_links":3,"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":["parthsarthi03/RAPTOR"],"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"]}}}],"record_sha256":"4b4fc466bf9d0b756e1233754063881dc0bbddb320763a5777d2e26671d761fc","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}