{"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/38","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":38,"pages_in_order":244,"rows_per_page":100,"rows":[3701,3800],"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/37","next":"/method/adam/papers/39","papers":[{"paper":null,"slug":"supervised-chain-of-thought","title":"Supervised Chain of Thought","date":"2024-10-18","arxiv_id":"2410.14198","n_code_links":0,"syntology":null},{"paper":"/paper/timeseriesexam-a-time-series-understanding","slug":"timeseriesexam-a-time-series-understanding","title":"TimeSeriesExam: A time series understanding exam","date":"2024-10-18","arxiv_id":"2410.14752","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":1,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":null,"slug":"transfer-learning-on-transformers-for","title":"Transfer Learning on Transformers for Building Energy Consumption Forecasting -- A Comparative Study","date":"2024-10-18","arxiv_id":"2410.14107","n_code_links":0,"syntology":null},{"paper":"/paper/xpert-extended-persistence-transformer","slug":"xpert-extended-persistence-transformer","title":"xPerT: Extended Persistence Transformer","date":"2024-10-18","arxiv_id":"2410.14193","n_code_links":2,"syntology":null},{"paper":null,"slug":"a-systematic-investigation-of-knowledge","title":"How Does Knowledge Selection Help Retrieval Augmented Generation?","date":"2024-10-17","arxiv_id":"2410.13258","n_code_links":0,"syntology":null},{"paper":"/paper/active-dormant-attention-heads","slug":"active-dormant-attention-heads","title":"Active-Dormant Attention Heads: Mechanistically Demystifying Extreme-Token Phenomena in LLMs","date":"2024-10-17","arxiv_id":"2410.13835","n_code_links":1,"syntology":{"ran":1,"of":6,"n_ran_checked":1,"n_instrument":0,"unverified":5,"pointer_only":6,"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) · 5 unverified","official":{"repos":["guotianyu2000/active-dormant-attention"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"adversarial-testing-as-a-tool-for","title":"Adversarial Testing as a Tool for Interpretability: Length-based Overfitting of Elementary Functions in Transformers","date":"2024-10-17","arxiv_id":"2410.13802","n_code_links":0,"syntology":null},{"paper":null,"slug":"better-to-ask-in-english-evaluation-of-large","title":"Better to Ask in English: Evaluation of Large Language Models on English, Low-resource and Cross-Lingual Settings","date":"2024-10-17","arxiv_id":"2410.13153","n_code_links":0,"syntology":null},{"paper":null,"slug":"co-segmentation-without-any-pixel-level","title":"Co-Segmentation without any Pixel-level Supervision with Application to Large-Scale Sketch Classification","date":"2024-10-17","arxiv_id":"2410.13582","n_code_links":0,"syntology":null},{"paper":"/paper/d-fine-redefine-regression-task-in-detrs-as","slug":"d-fine-redefine-regression-task-in-detrs-as","title":"D-FINE: Redefine Regression Task in DETRs as Fine-grained Distribution Refinement","date":"2024-10-17","arxiv_id":"2410.13842","n_code_links":5,"syntology":{"ran":10,"of":14,"n_ran_checked":10,"n_instrument":0,"unverified":4,"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) · 4 unverified","official":{"repos":["Peterande/D-FINE"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/detecting-ai-generated-texts-in-cross-domains","slug":"detecting-ai-generated-texts-in-cross-domains","title":"Detecting AI-Generated Texts in Cross-Domains","date":"2024-10-17","arxiv_id":"2410.13966","n_code_links":1,"syntology":null},{"paper":null,"slug":"durian-e-2-duration-informed-attention","title":"DurIAN-E 2: Duration Informed Attention Network with Adaptive Variational Autoencoder and Adversarial Learning for Expressive Text-to-Speech Synthesis","date":"2024-10-17","arxiv_id":"2410.13288","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancing-generalization-in-sparse-mixture-of","title":"Enhancing Generalization in Sparse Mixture of Experts Models: The Case for Increased Expert Activation in Compositional Tasks","date":"2024-10-17","arxiv_id":"2410.13964","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancing-text-generation-in-joint-nlg-nlu","title":"Enhancing Text Generation in Joint NLG/NLU Learning Through Curriculum Learning, Semi-Supervised Training, and Advanced Optimization Techniques","date":"2024-10-17","arxiv_id":"2410.13498","n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluating-self-generated-documents-for","title":"Evaluating Self-Generated Documents for Enhancing Retrieval-Augmented Generation with Large Language Models","date":"2024-10-17","arxiv_id":"2410.13192","n_code_links":0,"syntology":null},{"paper":"/paper/faithbench-a-diverse-hallucination-benchmark","slug":"faithbench-a-diverse-hallucination-benchmark","title":"FaithBench: A Diverse Hallucination Benchmark for Summarization by Modern LLMs","date":"2024-10-17","arxiv_id":"2410.13210","n_code_links":2,"syntology":null},{"paper":"/paper/help-me-identify-is-an-llm-vqa-system-all-we","slug":"help-me-identify-is-an-llm-vqa-system-all-we","title":"Help Me Identify: Is an LLM+VQA System All We Need to Identify Visual Concepts?","date":"2024-10-17","arxiv_id":"2410.13651","n_code_links":1,"syntology":null},{"paper":"/paper/hiformer-hybrid-frequency-feature-enhancement","slug":"hiformer-hybrid-frequency-feature-enhancement","title":"Hiformer: Hybrid Frequency Feature Enhancement Inverted Transformer for Long-Term Wind Power Prediction","date":"2024-10-17","arxiv_id":"2410.13303","n_code_links":1,"syntology":null},{"paper":null,"slug":"integrating-temporal-representations-for","title":"Integrating Temporal Representations for Dynamic Memory Retrieval and Management in Large Language Models","date":"2024-10-17","arxiv_id":"2410.13553","n_code_links":0,"syntology":null},{"paper":null,"slug":"iterselecttune-an-iterative-training","title":"IterSelectTune: An Iterative Training Framework for Efficient Instruction-Tuning Data Selection","date":"2024-10-17","arxiv_id":"2410.13464","n_code_links":0,"syntology":null},{"paper":null,"slug":"jailbreaking-llm-controlled-robots","title":"Jailbreaking LLM-Controlled Robots","date":"2024-10-17","arxiv_id":"2410.13691","n_code_links":0,"syntology":null},{"paper":"/paper/learning-graph-quantized-tokenizers-for","slug":"learning-graph-quantized-tokenizers-for","title":"Learning Graph Quantized Tokenizers","date":"2024-10-17","arxiv_id":"2410.13798","n_code_links":1,"syntology":{"ran":11,"of":13,"n_ran_checked":7,"n_instrument":4,"unverified":2,"pointer_only":3,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified","official":{"repos":["limei0307/GQT"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"linguistically-grounded-analysis-of-language","title":"Linguistically Grounded Analysis of Language Models using Shapley Head Values","date":"2024-10-17","arxiv_id":"2410.13396","n_code_links":0,"syntology":null},{"paper":"/paper/loldu-low-rank-adaptation-via-lower-diag","slug":"loldu-low-rank-adaptation-via-lower-diag","title":"LoLDU: Low-Rank Adaptation via Lower-Diag-Upper Decomposition for Parameter-Efficient Fine-Tuning","date":"2024-10-17","arxiv_id":"2410.13618","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":3,"n_instrument":1,"unverified":0,"pointer_only":4,"phrase":"4 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; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["skddj/loldu"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/looking-inward-language-models-can-learn","slug":"looking-inward-language-models-can-learn","title":"Looking Inward: Language Models Can Learn About Themselves by Introspection","date":"2024-10-17","arxiv_id":"2410.13787","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":["felixbinder/introspection_self_prediction"],"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":"marineformer-a-transformer-based-navigation","title":"MarineFormer: A Spatio-Temporal Attention Model for USV Navigation in Dynamic Marine Environments","date":"2024-10-17","arxiv_id":"2410.13973","n_code_links":0,"syntology":null},{"paper":"/paper/mcqg-srefine-multiple-choice-question","slug":"mcqg-srefine-multiple-choice-question","title":"MCQG-SRefine: Multiple Choice Question Generation and Evaluation with Iterative Self-Critique, Correction, and Comparison Feedback","date":"2024-10-17","arxiv_id":"2410.13191","n_code_links":1,"syntology":null},{"paper":"/paper/measuring-and-modifying-the-readability-of","slug":"measuring-and-modifying-the-readability-of","title":"Measuring and Modifying the Readability of English Texts with GPT-4","date":"2024-10-17","arxiv_id":"2410.14028","n_code_links":1,"syntology":null},{"paper":null,"slug":"metacognitive-monitoring-a-human-ability","title":"Judgment of Learning: A Human Ability Beyond Generative Artificial Intelligence","date":"2024-10-17","arxiv_id":"2410.13392","n_code_links":0,"syntology":null},{"paper":"/paper/mirage-bench-automatic-multilingual-benchmark","slug":"mirage-bench-automatic-multilingual-benchmark","title":"MIRAGE-Bench: Automatic Multilingual Benchmark Arena for Retrieval-Augmented Generation Systems","date":"2024-10-17","arxiv_id":"2410.13716","n_code_links":1,"syntology":null},{"paper":null,"slug":"on-the-learn-to-optimize-capabilities-of","title":"On the Learn-to-Optimize Capabilities of Transformers in In-Context Sparse Recovery","date":"2024-10-17","arxiv_id":"2410.13981","n_code_links":0,"syntology":null},{"paper":null,"slug":"personalized-adaptation-via-in-context","title":"Personalized Adaptation via In-Context Preference Learning","date":"2024-10-17","arxiv_id":"2410.14001","n_code_links":0,"syntology":null},{"paper":null,"slug":"precipitation-nowcasting-using-diffusion","title":"Precipitation Nowcasting Using Diffusion Transformer with Causal Attention","date":"2024-10-17","arxiv_id":"2410.13314","n_code_links":0,"syntology":null},{"paper":"/paper/rag-ddr-optimizing-retrieval-augmented","slug":"rag-ddr-optimizing-retrieval-augmented","title":"RAG-DDR: Optimizing Retrieval-Augmented Generation Using Differentiable Data Rewards","date":"2024-10-17","arxiv_id":"2410.13509","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":["openmatch/rag-ddr"],"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":"rgb-to-hyperspectral-spectral-reconstruction","title":"RGB to Hyperspectral: Spectral Reconstruction for Enhanced Surgical Imaging","date":"2024-10-17","arxiv_id":"2410.13570","n_code_links":0,"syntology":null},{"paper":"/paper/sbi-rag-enhancing-math-word-problem-solving","slug":"sbi-rag-enhancing-math-word-problem-solving","title":"SBI-RAG: Enhancing Math Word Problem Solving for Students through Schema-Based Instruction and Retrieval-Augmented Generation","date":"2024-10-17","arxiv_id":"2410.13293","n_code_links":1,"syntology":null},{"paper":null,"slug":"soullmate-an-application-enhancing-diverse","title":"SouLLMate: An Application Enhancing Diverse Mental Health Support with Adaptive LLMs, Prompt Engineering, and RAG Techniques","date":"2024-10-17","arxiv_id":"2410.16322","n_code_links":0,"syntology":null},{"paper":null,"slug":"temporal-enhanced-multimodal-transformer-for","title":"Temporal-Enhanced Multimodal Transformer for Referring Multi-Object Tracking and Segmentation","date":"2024-10-17","arxiv_id":"2410.13437","n_code_links":0,"syntology":null},{"paper":"/paper/towards-cross-cultural-machine-translation","slug":"towards-cross-cultural-machine-translation","title":"Towards Cross-Cultural Machine Translation with Retrieval-Augmented Generation from Multilingual Knowledge Graphs","date":"2024-10-17","arxiv_id":"2410.14057","n_code_links":0,"syntology":{"ran":5,"of":5,"n_ran_checked":5,"n_instrument":0,"unverified":0,"pointer_only":5,"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":null}},{"paper":null,"slug":"training-compute-optimal-vision-transformers","title":"Training Compute-Optimal Vision Transformers for Brain Encoding","date":"2024-10-17","arxiv_id":"2410.19810","n_code_links":0,"syntology":null},{"paper":"/paper/unig-modelling-unitary-3d-gaussians-for-view","slug":"unig-modelling-unitary-3d-gaussians-for-view","title":"UniGS: Modeling Unitary 3D Gaussians for Novel View Synthesis from Sparse-view Images","date":"2024-10-17","arxiv_id":"2410.13195","n_code_links":2,"syntology":null},{"paper":null,"slug":"advancing-fairness-in-natural-language","title":"Advancing Fairness in Natural Language Processing: From Traditional Methods to Explainability","date":"2024-10-16","arxiv_id":"2410.12511","n_code_links":0,"syntology":null},{"paper":"/paper/agent-skill-acquisition-for-large-language","slug":"agent-skill-acquisition-for-large-language","title":"Agent Skill Acquisition for Large Language Models via CycleQD","date":"2024-10-16","arxiv_id":"2410.14735","n_code_links":1,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"0 ran · 1 unverified","official":{"repos":["SakanaAI/CycleQD"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"paper":"/paper/at-rag-an-adaptive-rag-model-enhancing-query","slug":"at-rag-an-adaptive-rag-model-enhancing-query","title":"AT-RAG: An Adaptive RAG Model Enhancing Query Efficiency with Topic Filtering and Iterative Reasoning","date":"2024-10-16","arxiv_id":"2410.12886","n_code_links":1,"syntology":null},{"paper":null,"slug":"ccsbench-evaluating-compositional","title":"CCSBench: Evaluating Compositional Controllability in LLMs for Scientific Document Summarization","date":"2024-10-16","arxiv_id":"2410.12601","n_code_links":0,"syntology":null},{"paper":"/paper/cofe-rag-a-comprehensive-full-chain","slug":"cofe-rag-a-comprehensive-full-chain","title":"CoFE-RAG: A Comprehensive Full-chain Evaluation Framework for Retrieval-Augmented Generation with Enhanced Data Diversity","date":"2024-10-16","arxiv_id":"2410.12248","n_code_links":1,"syntology":null},{"paper":null,"slug":"communication-efficient-and-tensorized","title":"Communication-Efficient and Tensorized Federated Fine-Tuning of Large Language Models","date":"2024-10-16","arxiv_id":"2410.13097","n_code_links":0,"syntology":null},{"paper":null,"slug":"context-scaling-versus-task-scaling-in-in","title":"Context-Scaling versus Task-Scaling in In-Context Learning","date":"2024-10-16","arxiv_id":"2410.12783","n_code_links":0,"syntology":null},{"paper":"/paper/evaluating-morphological-compositional","slug":"evaluating-morphological-compositional","title":"Evaluating Morphological Compositional Generalization in Large Language Models","date":"2024-10-16","arxiv_id":"2410.12656","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":["selimfirat/bilkent-turkish-writings-dataset"],"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":"evaluation-of-attribution-bias-in-retrieval","title":"Evaluation of Attribution Bias in Retrieval-Augmented Large Language Models","date":"2024-10-16","arxiv_id":"2410.12380","n_code_links":0,"syntology":null},{"paper":null,"slug":"exploring-large-language-models-for-hate","title":"Exploring Large Language Models for Hate Speech Detection in Rioplatense Spanish","date":"2024-10-16","arxiv_id":"2410.12174","n_code_links":0,"syntology":null},{"paper":null,"slug":"fusionllm-a-decentralized-llm-training-system","title":"FusionLLM: A Decentralized LLM Training System on Geo-distributed GPUs with Adaptive Compression","date":"2024-10-16","arxiv_id":"2410.12707","n_code_links":0,"syntology":null},{"paper":"/paper/hypothesis-testing-the-circuit-hypothesis-in","slug":"hypothesis-testing-the-circuit-hypothesis-in","title":"Hypothesis Testing the Circuit Hypothesis in LLMs","date":"2024-10-16","arxiv_id":"2410.13032","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":["blei-lab/circuitry"],"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":null,"slug":"identifying-task-groupings-for-multi-task","title":"Identifying Task Groupings for Multi-Task Learning Using Pointwise V-Usable Information","date":"2024-10-16","arxiv_id":"2410.12774","n_code_links":0,"syntology":null},{"paper":null,"slug":"is-semantic-chunking-worth-the-computational","title":"Is Semantic Chunking Worth the Computational Cost?","date":"2024-10-16","arxiv_id":"2410.13070","n_code_links":0,"syntology":null},{"paper":null,"slug":"kallini-et-al-2024-do-not-compare-impossible","title":"Kallini et al. (2024) do not compare impossible languages with constituency-based ones","date":"2024-10-16","arxiv_id":"2410.12271","n_code_links":0,"syntology":null},{"paper":null,"slug":"mambabev-an-efficient-3d-detection-model-with","title":"MambaBEV: An efficient 3D detection model with Mamba2","date":"2024-10-16","arxiv_id":"2410.12673","n_code_links":0,"syntology":null},{"paper":"/paper/meta-chunking-learning-efficient-text","slug":"meta-chunking-learning-efficient-text","title":"Meta-Chunking: Learning Text Segmentation and Semantic Completion via Logical Perception","date":"2024-10-16","arxiv_id":"2410.12788","n_code_links":1,"syntology":{"ran":5,"of":5,"n_ran_checked":4,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"5 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; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["IAAR-Shanghai/Meta-Chunking"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"mirror-a-novel-approach-for-the-automated","title":"MIRROR: A Novel Approach for the Automated Evaluation of Open-Ended Question Generation","date":"2024-10-16","arxiv_id":"2410.12893","n_code_links":0,"syntology":null},{"paper":"/paper/mmed-rag-versatile-multimodal-rag-system-for","slug":"mmed-rag-versatile-multimodal-rag-system-for","title":"MMed-RAG: Versatile Multimodal RAG System for Medical Vision Language Models","date":"2024-10-16","arxiv_id":"2410.13085","n_code_links":1,"syntology":{"ran":7,"of":10,"n_ran_checked":3,"n_instrument":4,"unverified":3,"pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 3 unverified","official":{"repos":["richard-peng-xia/mmed-rag"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/msc-sql-multi-sample-critiquing-small","slug":"msc-sql-multi-sample-critiquing-small","title":"MSc-SQL: Multi-Sample Critiquing Small Language Models For Text-To-SQL Translation","date":"2024-10-16","arxiv_id":"2410.12916","n_code_links":1,"syntology":{"ran":9,"of":9,"n_ran_checked":9,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["layer6ai-labs/msc-sql"],"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":["official"]}}},{"paper":null,"slug":"on-a-scale-from-1-to-5-quantifying","title":"On A Scale From 1 to 5: Quantifying Hallucination in Faithfulness Evaluation","date":"2024-10-16","arxiv_id":"2410.12222","n_code_links":0,"syntology":null},{"paper":null,"slug":"shapefilegpt-a-multi-agent-large-language","title":"ShapefileGPT: A Multi-Agent Large Language Model Framework for Automated Shapefile Processing","date":"2024-10-16","arxiv_id":"2410.12376","n_code_links":0,"syntology":null},{"paper":"/paper/stabilize-the-latent-space-for-image","slug":"stabilize-the-latent-space-for-image","title":"Stabilize the Latent Space for Image Autoregressive Modeling: A Unified Perspective","date":"2024-10-16","arxiv_id":"2410.12490","n_code_links":1,"syntology":{"ran":3,"of":5,"n_ran_checked":3,"n_instrument":0,"unverified":2,"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) · 2 unverified","official":{"repos":["DAMO-NLP-SG/DiGIT"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"swim-an-attention-only-model-for-speech","title":"AttentiveMOS: A Lightweight Attention-Only Model for Speech Quality Prediction","date":"2024-10-16","arxiv_id":"2410.12675","n_code_links":0,"syntology":null},{"paper":null,"slug":"table-llm-specialist-language-model","title":"Table-LLM-Specialist: Language Model Specialists for Tables using Iterative Generator-Validator Fine-tuning","date":"2024-10-16","arxiv_id":"2410.12164","n_code_links":0,"syntology":null},{"paper":null,"slug":"tracking-universal-features-through-fine","title":"Tracking Universal Features Through Fine-Tuning and Model Merging","date":"2024-10-16","arxiv_id":"2410.12391","n_code_links":0,"syntology":null},{"paper":null,"slug":"unifying-economic-and-language-models-for","title":"Unifying Economic and Language Models for Enhanced Sentiment Analysis of the Oil Market","date":"2024-10-16","arxiv_id":"2410.12473","n_code_links":0,"syntology":null},{"paper":"/paper/unitary-multi-margin-bert-for-robust-natural","slug":"unitary-multi-margin-bert-for-robust-natural","title":"Unitary Multi-Margin BERT for Robust Natural Language Processing","date":"2024-10-16","arxiv_id":"2410.12759","n_code_links":1,"syntology":null},{"paper":null,"slug":"when-not-to-answer-evaluating-prompts-on-gpt","title":"When Not to Answer: Evaluating Prompts on GPT Models for Effective Abstention in Unanswerable Math Word Problems","date":"2024-10-16","arxiv_id":"2410.13029","n_code_links":0,"syntology":null},{"paper":null,"slug":"athena-retrieval-augmented-legal-judgment","title":"Athena: Retrieval-augmented Legal Judgment Prediction with Large Language Models","date":"2024-10-15","arxiv_id":"2410.11195","n_code_links":0,"syntology":null},{"paper":null,"slug":"bypassing-the-exponential-dependency-looped","title":"Bypassing the Exponential Dependency: Looped Transformers Efficiently Learn In-context by Multi-step Gradient Descent","date":"2024-10-15","arxiv_id":"2410.11268","n_code_links":0,"syntology":null},{"paper":"/paper/cognitive-overload-attack-prompt-injection","slug":"cognitive-overload-attack-prompt-injection","title":"Cognitive Overload Attack:Prompt Injection for Long Context","date":"2024-10-15","arxiv_id":"2410.11272","n_code_links":1,"syntology":null},{"paper":"/paper/de-jargonizing-science-for-journalists-with","slug":"de-jargonizing-science-for-journalists-with","title":"De-jargonizing Science for Journalists with GPT-4: A Pilot Study","date":"2024-10-15","arxiv_id":"2410.12069","n_code_links":1,"syntology":null},{"paper":"/paper/deciphering-the-chaos-enhancing-jailbreak","slug":"deciphering-the-chaos-enhancing-jailbreak","title":"Deciphering the Chaos: Enhancing Jailbreak Attacks via Adversarial Prompt Translation","date":"2024-10-15","arxiv_id":"2410.11317","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":["qizhangli/adversarial-prompt-translator"],"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":"dodt-enhanced-online-decision-transformer","title":"DODT: Enhanced Online Decision Transformer Learning through Dreamer's Actor-Critic Trajectory Forecasting","date":"2024-10-15","arxiv_id":"2410.11359","n_code_links":0,"syntology":null},{"paper":"/paper/dynamicer-resolving-emerging-mentions-to","slug":"dynamicer-resolving-emerging-mentions-to","title":"DynamicER: Resolving Emerging Mentions to Dynamic Entities for RAG","date":"2024-10-15","arxiv_id":"2410.11494","n_code_links":1,"syntology":null},{"paper":null,"slug":"ed-vit-splitting-vision-transformer-for","title":"Efficient Partitioning Vision Transformer on Edge Devices for Distributed Inference","date":"2024-10-15","arxiv_id":"2410.11650","n_code_links":0,"syntology":null},{"paper":null,"slug":"efiln-the-electric-field-inversion","title":"EFILN: The Electric Field Inversion-Localization Network for High-Precision Underwater Positioning","date":"2024-10-15","arxiv_id":"2410.11223","n_code_links":0,"syntology":null},{"paper":null,"slug":"evidence-of-cognitive-deficits","title":"Evidence of Cognitive Deficits andDevelopmental Advances in Generative AI: A Clock Drawing Test Analysis","date":"2024-10-15","arxiv_id":"2410.11756","n_code_links":0,"syntology":null},{"paper":"/paper/from-promise-to-practice-realizing-high","slug":"from-promise-to-practice-realizing-high","title":"From promise to practice: realizing high-performance decentralized training","date":"2024-10-15","arxiv_id":"2410.11998","n_code_links":2,"syntology":null},{"paper":null,"slug":"holistic-reasoning-with-long-context-lms-a","title":"Holistic Reasoning with Long-Context LMs: A Benchmark for Database Operations on Massive Textual Data","date":"2024-10-15","arxiv_id":"2410.11996","n_code_links":0,"syntology":null},{"paper":null,"slug":"is-hate-lost-in-translation-evaluation-of","title":"\"Is Hate Lost in Translation?\": Evaluation of Multilingual LGBTQIA+ Hate Speech Detection","date":"2024-10-15","arxiv_id":"2410.11230","n_code_links":0,"syntology":null},{"paper":"/paper/jigsaw-puzzles-splitting-harmful-questions-to","slug":"jigsaw-puzzles-splitting-harmful-questions-to","title":"Jigsaw Puzzles: Splitting Harmful Questions to Jailbreak Large Language Models","date":"2024-10-15","arxiv_id":"2410.11459","n_code_links":1,"syntology":null},{"paper":"/paper/meta-dt-offline-meta-rl-as-conditional","slug":"meta-dt-offline-meta-rl-as-conditional","title":"Meta-DT: Offline Meta-RL as Conditional Sequence Modeling with World Model Disentanglement","date":"2024-10-15","arxiv_id":"2410.11448","n_code_links":1,"syntology":{"ran":3,"of":5,"n_ran_checked":2,"n_instrument":1,"unverified":2,"pointer_only":5,"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) · 2 unverified","official":{"repos":["nju-rl/meta-dt"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"mitigating-suboptimality-of-deterministic","title":"Mitigating Suboptimality of Deterministic Policy Gradients in Complex Q-functions","date":"2024-10-15","arxiv_id":"2410.11833","n_code_links":0,"syntology":null},{"paper":"/paper/moh-multi-head-attention-as-mixture-of-head","slug":"moh-multi-head-attention-as-mixture-of-head","title":"MoH: Multi-Head Attention as Mixture-of-Head Attention","date":"2024-10-15","arxiv_id":"2410.11842","n_code_links":3,"syntology":{"ran":14,"of":18,"n_ran_checked":6,"n_instrument":8,"unverified":4,"pointer_only":3,"phrase":"14 ran (of which 5 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 8 where Syntology's instrument failed) · 4 unverified","official":{"repos":["skyworkai/moh"],"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":["listed","official","unlocated"]}}},{"paper":"/paper/mtu-bench-a-multi-granularity-tool-use","slug":"mtu-bench-a-multi-granularity-tool-use","title":"MTU-Bench: A Multi-granularity Tool-Use Benchmark for Large Language Models","date":"2024-10-15","arxiv_id":"2410.11710","n_code_links":1,"syntology":null},{"paper":"/paper/multiview-scene-graph","slug":"multiview-scene-graph","title":"Multiview Scene Graph","date":"2024-10-15","arxiv_id":"2410.11187","n_code_links":1,"syntology":{"ran":17,"of":37,"n_ran_checked":11,"n_instrument":6,"unverified":20,"pointer_only":37,"phrase":"17 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 0 violated, 10 with no contract checked; 6 where Syntology's instrument failed) · 20 unverified","official":{"repos":["ai4ce/MSG"],"state":"official (archive's flag): 17 ran","n_ran":17,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":20,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"nonlinear-gaussian-process-tomography-with","title":"Nonlinear Gaussian process tomography with imposed non-negativity constraints on physical quantities for plasma diagnostics","date":"2024-10-15","arxiv_id":"2410.11454","n_code_links":0,"syntology":null},{"paper":null,"slug":"on-the-capacity-of-citation-generation-by","title":"On the Capacity of Citation Generation by Large Language Models","date":"2024-10-15","arxiv_id":"2410.11217","n_code_links":0,"syntology":null},{"paper":"/paper/pixology-probing-the-linguistic-and-visual","slug":"pixology-probing-the-linguistic-and-visual","title":"Pixology: Probing the Linguistic and Visual Capabilities of Pixel-based Language Models","date":"2024-10-15","arxiv_id":"2410.12011","n_code_links":1,"syntology":{"ran":8,"of":8,"n_ran_checked":8,"n_instrument":0,"unverified":0,"pointer_only":8,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["kushaltatariya/Pixology"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"redeep-detecting-hallucination-in-retrieval","title":"ReDeEP: Detecting Hallucination in Retrieval-Augmented Generation via Mechanistic Interpretability","date":"2024-10-15","arxiv_id":"2410.11414","n_code_links":0,"syntology":null},{"paper":null,"slug":"rethinking-graph-transformer-architecture","title":"Rethinking Graph Transformer Architecture Design for Node Classification","date":"2024-10-15","arxiv_id":"2410.11189","n_code_links":0,"syntology":null},{"paper":null,"slug":"retrieval-augmented-spelling-correction-for-e","title":"Retrieval Augmented Spelling Correction for E-Commerce Applications","date":"2024-10-15","arxiv_id":"2410.11655","n_code_links":0,"syntology":null},{"paper":"/paper/rulerag-rule-guided-retrieval-augmented","slug":"rulerag-rule-guided-retrieval-augmented","title":"RuleRAG: Rule-guided retrieval-augmented generation with language models for question answering","date":"2024-10-15","arxiv_id":"2410.22353","n_code_links":1,"syntology":null},{"paper":null,"slug":"seadate-remedy-dual-attention-transformer","title":"SeaDATE: Remedy Dual-Attention Transformer with Semantic Alignment via Contrast Learning for Multimodal Object Detection","date":"2024-10-15","arxiv_id":"2410.11358","n_code_links":0,"syntology":null},{"paper":null,"slug":"seer-self-aligned-evidence-extraction-for","title":"SEER: Self-Aligned Evidence Extraction for Retrieval-Augmented Generation","date":"2024-10-15","arxiv_id":"2410.11315","n_code_links":0,"syntology":null},{"paper":null,"slug":"selection-p-self-supervised-task-agnostic","title":"Selection-p: Self-Supervised Task-Agnostic Prompt Compression for Faithfulness and Transferability","date":"2024-10-15","arxiv_id":"2410.11786","n_code_links":0,"syntology":null},{"paper":"/paper/self-adaptive-multimodal-retrieval-augmented","slug":"self-adaptive-multimodal-retrieval-augmented","title":"Self-adaptive Multimodal Retrieval-Augmented Generation","date":"2024-10-15","arxiv_id":"2410.11321","n_code_links":1,"syntology":null}],"record_sha256":"60acb412ad22734f0e4fe0073a96bad9d99cb88a02c059b2ef8f9695859f47f8","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}