{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/method/cosine-annealing/papers/3","list_of":"/method/cosine-annealing","method":"Cosine Annealing","archive":{"snapshot":"2025-07-28"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"date (newest first), then slug","page":3,"pages_in_order":40,"rows_per_page":100,"rows":[201,300],"of":3965,"counts":{"archive_papers_tagged":3965,"with_a_code_link":1734,"where_syntology_ran_a_sample":627,"not_listed_spam_title":0,"listed":3965,"listed_where_code_ran":627,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":513,"every_run_a_failure_of_syntologys_instrument":114,"listed_with_a_run_with_no_instrument_failure":513,"listed_every_run_a_failure_of_syntologys_instrument":114,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/method/cosine-annealing","prev":"/method/cosine-annealing/papers/2","next":"/method/cosine-annealing/papers/4","papers":[{"paper":null,"slug":"text-compression-for-efficient-language","title":"Text Compression for Efficient Language Generation","date":"2025-03-14","arxiv_id":"2503.11426","n_code_links":0,"syntology":null},{"paper":null,"slug":"compositional-subspace-representation-fine","title":"Compositional Subspace Representation Fine-tuning for Adaptive Large Language Models","date":"2025-03-13","arxiv_id":"2503.10617","n_code_links":0,"syntology":null},{"paper":null,"slug":"it-is-too-many-options-pitfalls-of-multiple","title":"It is Too Many Options: Pitfalls of Multiple-Choice Questions in Generative AI and Medical Education","date":"2025-03-13","arxiv_id":"2503.13508","n_code_links":0,"syntology":null},{"paper":null,"slug":"siege-autonomous-multi-turn-jailbreaking-of","title":"Tempest: Autonomous Multi-Turn Jailbreaking of Large Language Models with Tree Search","date":"2025-03-13","arxiv_id":"2503.10619","n_code_links":0,"syntology":null},{"paper":null,"slug":"rethinking-prompt-based-debiasing-in-large","title":"Rethinking Prompt-based Debiasing in Large Language Models","date":"2025-03-12","arxiv_id":"2503.09219","n_code_links":0,"syntology":null},{"paper":null,"slug":"vaxguard-a-multi-generator-multi-type-and","title":"VaxGuard: A Multi-Generator, Multi-Type, and Multi-Role Dataset for Detecting LLM-Generated Vaccine Misinformation","date":"2025-03-12","arxiv_id":"2503.09103","n_code_links":0,"syntology":null},{"paper":"/paper/vlog-video-language-models-by-generative","slug":"vlog-video-language-models-by-generative","title":"VLog: Video-Language Models by Generative Retrieval of Narration Vocabulary","date":"2025-03-12","arxiv_id":"2503.09402","n_code_links":1,"syntology":{"ran":7,"of":10,"n_ran_checked":5,"n_instrument":2,"unverified":3,"pointer_only":10,"phrase":"7 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; 2 where Syntology's instrument failed) · 3 unverified","official":{"repos":["showlab/vlog"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/context-aware-biases-for-length-extrapolation","slug":"context-aware-biases-for-length-extrapolation","title":"Context-aware Biases for Length Extrapolation","date":"2025-03-11","arxiv_id":"2503.08067","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 1 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; the one sample that ran constructed an object rather than computing a result","official":{"repos":["axiomlab/Cable"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["found_in_text"]}}},{"paper":null,"slug":"gpt-ppg-a-gpt-based-foundation-model-for","title":"GPT-PPG: A GPT-based Foundation Model for Photoplethysmography Signals","date":"2025-03-11","arxiv_id":"2503.08015","n_code_links":0,"syntology":null},{"paper":null,"slug":"interpretable-and-robust-dialogue-state","title":"Interpretable and Robust Dialogue State Tracking via Natural Language Summarization with LLMs","date":"2025-03-11","arxiv_id":"2503.08857","n_code_links":0,"syntology":null},{"paper":null,"slug":"llms-virtual-users-and-bias-predicting-any","title":"Llms, Virtual Users, and Bias: Predicting Any Survey Question Without Human Data","date":"2025-03-11","arxiv_id":"2503.16498","n_code_links":0,"syntology":null},{"paper":null,"slug":"exploring-multimodal-perception-in-large","title":"Exploring Multimodal Perception in Large Language Models Through Perceptual Strength Ratings","date":"2025-03-10","arxiv_id":"2503.06980","n_code_links":0,"syntology":null},{"paper":null,"slug":"filter-images-first-generate-instructions","title":"Filter Images First, Generate Instructions Later: Pre-Instruction Data Selection for Visual Instruction Tuning","date":"2025-03-10","arxiv_id":"2503.07591","n_code_links":0,"syntology":null},{"paper":null,"slug":"fully-autonomous-programming-using-iterative","title":"Fully Autonomous Programming using Iterative Multi-Agent Debugging with Large Language Models","date":"2025-03-10","arxiv_id":"2503.07693","n_code_links":0,"syntology":null},{"paper":"/paper/implicit-reasoning-in-transformers-is","slug":"implicit-reasoning-in-transformers-is","title":"Implicit Reasoning in Transformers is Reasoning through Shortcuts","date":"2025-03-10","arxiv_id":"2503.07604","n_code_links":1,"syntology":{"ran":7,"of":7,"n_ran_checked":6,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["TianheL/LM-Implicit-Reasoning"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"improving-cognitive-diagnostics-in-pathology","title":"Improving cognitive diagnostics in pathology: a deep learning approach for augmenting perceptional understanding of histopathology images","date":"2025-03-10","arxiv_id":"2503.06894","n_code_links":0,"syntology":null},{"paper":null,"slug":"mapqa-open-domain-geospatial-question","title":"MapQA: Open-domain Geospatial Question Answering on Map Data","date":"2025-03-10","arxiv_id":"2503.07871","n_code_links":0,"syntology":null},{"paper":null,"slug":"taking-notes-brings-focus-towards-multi-turn","title":"Taking Notes Brings Focus? Towards Multi-Turn Multimodal Dialogue Learning","date":"2025-03-10","arxiv_id":"2503.07002","n_code_links":0,"syntology":null},{"paper":null,"slug":"effectiveness-of-zero-shot-cot-in-japanese","title":"Effectiveness of Zero-shot-CoT in Japanese Prompts","date":"2025-03-09","arxiv_id":"2503.06765","n_code_links":0,"syntology":null},{"paper":null,"slug":"unigenx-unified-generation-of-sequence-and","title":"UniGenX: Unified Generation of Sequence and Structure with Autoregressive Diffusion","date":"2025-03-09","arxiv_id":"2503.06687","n_code_links":0,"syntology":null},{"paper":"/paper/limtopic-llm-based-topic-modeling-and-text","slug":"limtopic-llm-based-topic-modeling-and-text","title":"LimTopic: LLM-based Topic Modeling and Text Summarization for Analyzing Scientific Articles limitations","date":"2025-03-08","arxiv_id":"2503.10658","n_code_links":1,"syntology":null},{"paper":null,"slug":"evaluating-large-language-models-in-code","title":"Evaluating Large Language Models in Code Generation: INFINITE Methodology for Defining the Inference Index","date":"2025-03-07","arxiv_id":"2503.05852","n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluating-local-and-cloud-based-large","title":"Simulating and Analysing Human Survey Responses with Large Language Models: A Case Study in Energy Stated Preference","date":"2025-03-07","arxiv_id":"2503.10652","n_code_links":0,"syntology":null},{"paper":null,"slug":"idea-prune-an-integrated-enlarge-and-prune","title":"IDEA Prune: An Integrated Enlarge-and-Prune Pipeline in Generative Language Model Pretraining","date":"2025-03-07","arxiv_id":"2503.05920","n_code_links":0,"syntology":null},{"paper":null,"slug":"zero-shot-medical-event-prediction-using-a","title":"Zero-shot Medical Event Prediction Using a Generative Pre-trained Transformer on Electronic Health Records","date":"2025-03-07","arxiv_id":"2503.05893","n_code_links":0,"syntology":null},{"paper":null,"slug":"compositional-causal-reasoning-evaluation-in","title":"Compositional Causal Reasoning Evaluation in Language Models","date":"2025-03-06","arxiv_id":"2503.04556","n_code_links":0,"syntology":null},{"paper":null,"slug":"hilgen-hierarchically-informed-data","title":"HILGEN: Hierarchically-Informed Data Generation for Biomedical NER Using Knowledgebases and Large Language Models","date":"2025-03-06","arxiv_id":"2503.04930","n_code_links":0,"syntology":null},{"paper":"/paper/the-box-is-in-the-pen-evaluating-commonsense-1","slug":"the-box-is-in-the-pen-evaluating-commonsense-1","title":"The Box is in the Pen: Evaluating Commonsense Reasoning in Neural Machine Translation","date":"2025-03-05","arxiv_id":"2503.03308","n_code_links":1,"syntology":null},{"paper":null,"slug":"beyond-cosine-decay-on-the-effectiveness-of","title":"Beyond Cosine Decay: On the effectiveness of Infinite Learning Rate Schedule for Continual Pre-training","date":"2025-03-04","arxiv_id":"2503.02844","n_code_links":0,"syntology":null},{"paper":null,"slug":"effectively-steer-llm-to-follow-preference","title":"Effectively Steer LLM To Follow Preference via Building Confident Directions","date":"2025-03-04","arxiv_id":"2503.02989","n_code_links":0,"syntology":null},{"paper":null,"slug":"interpretable-few-shot-retinal-disease","title":"Interpretable Few-Shot Retinal Disease Diagnosis with Concept-Guided Prompting of Vision-Language Models","date":"2025-03-04","arxiv_id":"2503.02917","n_code_links":0,"syntology":null},{"paper":null,"slug":"use-me-wisely-ai-driven-assessment-for-llm","title":"Use Me Wisely: AI-Driven Assessment for LLM Prompting Skills Development","date":"2025-03-04","arxiv_id":"2503.02532","n_code_links":0,"syntology":null},{"paper":null,"slug":"weak-to-strong-generalization-even-in-random","title":"Weak-to-Strong Generalization Even in Random Feature Networks, Provably","date":"2025-03-04","arxiv_id":"2503.02877","n_code_links":0,"syntology":null},{"paper":null,"slug":"zero-shot-multi-label-classification-of","title":"Zero-Shot Multi-Label Classification of Bangla Documents: Large Decoders Vs. Classic Encoders","date":"2025-03-04","arxiv_id":"2503.02993","n_code_links":0,"syntology":null},{"paper":null,"slug":"2503-01630","title":"Machine Learners Should Acknowledge the Legal Implications of Large Language Models as Personal Data","date":"2025-03-03","arxiv_id":"2503.01630","n_code_links":0,"syntology":null},{"paper":null,"slug":"2503-01814","title":"LLMInit: A Free Lunch from Large Language Models for Selective Initialization of Recommendation","date":"2025-03-03","arxiv_id":"2503.01814","n_code_links":0,"syntology":null},{"paper":null,"slug":"attention-condensation-via-sparsity-induced","title":"Attention Condensation via Sparsity Induced Regularized Training","date":"2025-03-03","arxiv_id":"2503.01564","n_code_links":0,"syntology":null},{"paper":"/paper/cancer-type-stage-and-prognosis-assessment","slug":"cancer-type-stage-and-prognosis-assessment","title":"Cancer Type, Stage and Prognosis Assessment from Pathology Reports using LLMs","date":"2025-03-03","arxiv_id":"2503.01194","n_code_links":1,"syntology":null},{"paper":"/paper/label-ranker-self-aware-preference-for","slug":"label-ranker-self-aware-preference-for","title":"Label Ranker: Self-Aware Preference for Classification Label Position in Visual Masked Self-Supervised Pre-Trained Model","date":"2025-03-03","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"using-not-so-large-language-models-for","title":"Using (Not so) Large Language Models for Generating Simulation Models in a Formal DSL -- A Study on Reaction Networks","date":"2025-03-03","arxiv_id":"2503.01675","n_code_links":0,"syntology":null},{"paper":"/paper/2503-00955","slug":"2503-00955","title":"SemViQA: A Semantic Question Answering System for Vietnamese Information Fact-Checking","date":"2025-03-02","arxiv_id":"2503.00955","n_code_links":1,"syntology":null},{"paper":null,"slug":"psychological-counseling-ability-of-large","title":"Psychological Counseling Ability of Large Language Models","date":"2025-03-01","arxiv_id":"2503.07627","n_code_links":0,"syntology":null},{"paper":null,"slug":"beyond-words-a-latent-memory-approach-to","title":"Beyond Words: A Latent Memory Approach to Internal Reasoning in LLMs","date":"2025-02-28","arxiv_id":"2502.21030","n_code_links":0,"syntology":null},{"paper":"/paper/codi-compressing-chain-of-thought-into","slug":"codi-compressing-chain-of-thought-into","title":"CODI: Compressing Chain-of-Thought into Continuous Space via Self-Distillation","date":"2025-02-28","arxiv_id":"2502.21074","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":null}},{"paper":"/paper/nutrigen-personalized-meal-plan-generator","slug":"nutrigen-personalized-meal-plan-generator","title":"NutriGen: Personalized Meal Plan Generator Leveraging Large Language Models to Enhance Dietary and Nutritional Adherence","date":"2025-02-28","arxiv_id":"2502.20601","n_code_links":1,"syntology":null},{"paper":"/paper/seismollm-advancing-seismic-monitoring-via","slug":"seismollm-advancing-seismic-monitoring-via","title":"SeisMoLLM: Advancing Seismic Monitoring via Cross-modal Transfer with Pre-trained Large Language Model","date":"2025-02-27","arxiv_id":"2502.19960","n_code_links":1,"syntology":{"ran":3,"of":6,"n_ran_checked":3,"n_instrument":0,"unverified":3,"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) · 3 unverified","official":{"repos":["StarMoonWang/SeisMoLLM"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/walnutdata-a-uav-remote-sensing-dataset-of","slug":"walnutdata-a-uav-remote-sensing-dataset-of","title":"WalnutData: A UAV Remote Sensing Dataset of Green Walnuts and Model Evaluation","date":"2025-02-27","arxiv_id":"2502.20092","n_code_links":1,"syntology":null},{"paper":null,"slug":"cognitive-networks-highlight-differences-and","title":"Cognitive networks highlight differences and similarities in the STEM mindsets of human and LLM-simulated trainees, experts and academics","date":"2025-02-26","arxiv_id":"2502.19529","n_code_links":0,"syntology":null},{"paper":null,"slug":"deep-bench-deep-learning-benchmark-dataset","title":"Deep-Bench: Deep Learning Benchmark Dataset for Code Generation","date":"2025-02-26","arxiv_id":"2502.18726","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-sharpness-disparity-principle-in","title":"The Sharpness Disparity Principle in Transformers for Accelerating Language Model Pre-Training","date":"2025-02-26","arxiv_id":"2502.19002","n_code_links":0,"syntology":null},{"paper":null,"slug":"assessing-large-language-models-in-agentic","title":"Assessing Large Language Models in Agentic Multilingual National Bias","date":"2025-02-25","arxiv_id":"2502.17945","n_code_links":0,"syntology":null},{"paper":null,"slug":"independent-mobility-gpt-idm-gpt-a-self","title":"Independent Mobility GPT (IDM-GPT): A Self-Supervised Multi-Agent Large Language Model Framework for Customized Traffic Mobility Analysis Using Machine Learning Models","date":"2025-02-25","arxiv_id":"2502.18652","n_code_links":0,"syntology":null},{"paper":null,"slug":"scaling-llm-pre-training-with-vocabulary","title":"Scaling LLM Pre-training with Vocabulary Curriculum","date":"2025-02-25","arxiv_id":"2502.17910","n_code_links":0,"syntology":null},{"paper":null,"slug":"applying-llms-to-active-learning-towards-cost","title":"Applying LLMs to Active Learning: Towards Cost-Efficient Cross-Task Text Classification without Manually Labeled Data","date":"2025-02-24","arxiv_id":"2502.16892","n_code_links":0,"syntology":null},{"paper":null,"slug":"are-large-language-models-good-data","title":"Are Large Language Models Good Data Preprocessors?","date":"2025-02-24","arxiv_id":"2502.16790","n_code_links":0,"syntology":null},{"paper":null,"slug":"reasoning-about-affordances-causal-and","title":"Reasoning about Affordances: Causal and Compositional Reasoning in LLMs","date":"2025-02-23","arxiv_id":"2502.16606","n_code_links":0,"syntology":null},{"paper":"/paper/a-close-look-at-decomposition-based-xai","slug":"a-close-look-at-decomposition-based-xai","title":"A Close Look at Decomposition-based XAI-Methods for Transformer Language Models","date":"2025-02-21","arxiv_id":"2502.15886","n_code_links":2,"syntology":null},{"paper":"/paper/bp-gpt-auditory-neural-decoding-using-fmri","slug":"bp-gpt-auditory-neural-decoding-using-fmri","title":"BP-GPT: Auditory Neural Decoding Using fMRI-prompted LLM","date":"2025-02-21","arxiv_id":"2502.15172","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["1994cxy/bp-gpt"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"single-pass-detection-of-jailbreaking-input","title":"Single-pass Detection of Jailbreaking Input in Large Language Models","date":"2025-02-21","arxiv_id":"2502.15435","n_code_links":0,"syntology":null},{"paper":null,"slug":"deeprtl-bridging-verilog-understanding-and","title":"DeepRTL: Bridging Verilog Understanding and Generation with a Unified Representation Model","date":"2025-02-20","arxiv_id":"2502.15832","n_code_links":0,"syntology":null},{"paper":null,"slug":"entropy-uid-a-method-for-optimizing","title":"Entropy-UID: A Method for Optimizing Information Density","date":"2025-02-20","arxiv_id":"2502.14366","n_code_links":0,"syntology":null},{"paper":null,"slug":"hallucination-detection-in-large-language","title":"Hallucination Detection in Large Language Models with Metamorphic Relations","date":"2025-02-20","arxiv_id":"2502.15844","n_code_links":0,"syntology":null},{"paper":null,"slug":"an-enhancement-of-cuckoo-search-algorithm-for","title":"An Enhancement of Cuckoo Search Algorithm for Optimal Earthquake Evacuation Space Allocation in Intramuros, Manila City","date":"2025-02-19","arxiv_id":"2502.13477","n_code_links":0,"syntology":null},{"paper":null,"slug":"giving-ai-personalities-leads-to-more-human","title":"Giving AI Personalities Leads to More Human-Like Reasoning","date":"2025-02-19","arxiv_id":"2502.14155","n_code_links":0,"syntology":null},{"paper":null,"slug":"hidden-darkness-in-llm-generated-designs","title":"Hidden Darkness in LLM-Generated Designs: Exploring Dark Patterns in Ecommerce Web Components Generated by LLMs","date":"2025-02-19","arxiv_id":"2502.13499","n_code_links":0,"syntology":null},{"paper":"/paper/pitvqa-vector-matrix-low-rank-adaptation-for","slug":"pitvqa-vector-matrix-low-rank-adaptation-for","title":"PitVQA++: Vector Matrix-Low-Rank Adaptation for Open-Ended Visual Question Answering in Pituitary Surgery","date":"2025-02-19","arxiv_id":"2502.14149","n_code_links":1,"syntology":null},{"paper":null,"slug":"rgar-recurrence-generation-augmented","title":"RGAR: Recurrence Generation-augmented Retrieval for Factual-aware Medical Question Answering","date":"2025-02-19","arxiv_id":"2502.13361","n_code_links":0,"syntology":null},{"paper":null,"slug":"an-llm-powered-agent-for-physiological-data","title":"An LLM-Powered Agent for Physiological Data Analysis: A Case Study on PPG-based Heart Rate Estimation","date":"2025-02-18","arxiv_id":"2502.12836","n_code_links":0,"syntology":null},{"paper":null,"slug":"lmn-a-tool-for-generating-machine-enforceable","title":"LMN: A Tool for Generating Machine Enforceable Policies from Natural Language Access Control Rules using LLMs","date":"2025-02-18","arxiv_id":"2502.12460","n_code_links":0,"syntology":null},{"paper":"/paper/adasplash-adaptive-sparse-flash-attention","slug":"adasplash-adaptive-sparse-flash-attention","title":"AdaSplash: Adaptive Sparse Flash Attention","date":"2025-02-17","arxiv_id":"2502.12082","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":0,"n_instrument":2,"unverified":1,"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) · 1 unverified","official":{"repos":["deep-spin/adasplash"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"ai-generated-text-detection-with-a-gltr-based","title":"AI-generated Text Detection with a GLTR-based Approach","date":"2025-02-17","arxiv_id":"2502.12064","n_code_links":0,"syntology":null},{"paper":null,"slug":"biases-in-edge-language-models-detection","title":"Biases in Edge Language Models: Detection, Analysis, and Mitigation","date":"2025-02-17","arxiv_id":"2502.11349","n_code_links":0,"syntology":null},{"paper":null,"slug":"disco-device-server-collaborative-llm-based","title":"DiSCo: Device-Server Collaborative LLM-Based Text Streaming Services","date":"2025-02-17","arxiv_id":"2502.11417","n_code_links":0,"syntology":null},{"paper":null,"slug":"smartllm-smart-contract-auditing-using-custom","title":"SmartLLM: Smart Contract Auditing using Custom Generative AI","date":"2025-02-17","arxiv_id":"2502.13167","n_code_links":0,"syntology":null},{"paper":null,"slug":"performance-review-on-llm-for-solving","title":"Performance Review on LLM for solving leetcode problems","date":"2025-02-16","arxiv_id":"2502.15770","n_code_links":0,"syntology":null},{"paper":"/paper/tumlu-a-unified-and-native-language","slug":"tumlu-a-unified-and-native-language","title":"TUMLU: A Unified and Native Language Understanding Benchmark for Turkic Languages","date":"2025-02-16","arxiv_id":"2502.11020","n_code_links":1,"syntology":null},{"paper":null,"slug":"vendi-rag-adaptively-trading-off-diversity","title":"Vendi-RAG: Adaptively Trading-Off Diversity And Quality Significantly Improves Retrieval Augmented Generation With LLMs","date":"2025-02-16","arxiv_id":"2502.11228","n_code_links":0,"syntology":null},{"paper":null,"slug":"controllablegpt-a-ground-up-designed","title":"ControllableGPT: A Ground-Up Designed Controllable GPT for Molecule Optimization","date":"2025-02-15","arxiv_id":"2502.10631","n_code_links":0,"syntology":null},{"paper":"/paper/the-underlying-structures-of-self-attention","slug":"the-underlying-structures-of-self-attention","title":"The underlying structures of self-attention: symmetry, directionality, and emergent dynamics in Transformer training","date":"2025-02-15","arxiv_id":"2502.10927","n_code_links":1,"syntology":null},{"paper":null,"slug":"do-large-language-models-reason-causally-like","title":"Do Large Language Models Reason Causally Like Us? Even Better?","date":"2025-02-14","arxiv_id":"2502.10215","n_code_links":0,"syntology":null},{"paper":null,"slug":"mechanistic-unveiling-of-transformer-circuits","title":"Mechanistic Unveiling of Transformer Circuits: Self-Influence as a Key to Model Reasoning","date":"2025-02-13","arxiv_id":"2502.09022","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-influence-of-visual-and-linguistic-cues","title":"Can Vision-Language Models Infer Speaker's Ignorance? The Role of Visual and Linguistic Cues","date":"2025-02-13","arxiv_id":"2502.09120","n_code_links":0,"syntology":null},{"paper":"/paper/intar-inter-task-auto-reconfigurable","slug":"intar-inter-task-auto-reconfigurable","title":"InTAR: Inter-Task Auto-Reconfigurable Accelerator Design for High Data Volume Variation in DNNs","date":"2025-02-12","arxiv_id":"2502.08807","n_code_links":1,"syntology":null},{"paper":null,"slug":"ynote-a-novel-music-notation-for-fine-tuning","title":"YNote: A Novel Music Notation for Fine-Tuning LLMs in Music Generation","date":"2025-02-12","arxiv_id":"2502.10467","n_code_links":0,"syntology":null},{"paper":"/paper/automated-capability-discovery-via-model-self","slug":"automated-capability-discovery-via-model-self","title":"Automated Capability Discovery via Model Self-Exploration","date":"2025-02-11","arxiv_id":"2502.07577","n_code_links":2,"syntology":null},{"paper":"/paper/grammar-control-in-dialogue-response","slug":"grammar-control-in-dialogue-response","title":"Grammar Control in Dialogue Response Generation for Language Learning Chatbots","date":"2025-02-11","arxiv_id":"2502.07544","n_code_links":1,"syntology":null},{"paper":null,"slug":"tractable-transformers-for-flexible","title":"Tractable Transformers for Flexible Conditional Generation","date":"2025-02-11","arxiv_id":"2502.07616","n_code_links":0,"syntology":null},{"paper":null,"slug":"debatebench-a-challenging-long-context","title":"DebateBench: A Challenging Long Context Reasoning Benchmark For Large Language Models","date":"2025-02-10","arxiv_id":"2502.06279","n_code_links":0,"syntology":null},{"paper":null,"slug":"find-central-dogma-again","title":"Find Central Dogma Again: Leveraging Multilingual Transfer in Large Language Models","date":"2025-02-10","arxiv_id":"2502.06253","n_code_links":0,"syntology":null},{"paper":null,"slug":"large-language-models-in-software-security-a","title":"LLMs in Software Security: A Survey of Vulnerability Detection Techniques and Insights","date":"2025-02-10","arxiv_id":"2502.07049","n_code_links":0,"syntology":null},{"paper":null,"slug":"leveraging-gpt-4o-efficiency-for-detecting","title":"Leveraging GPT-4o Efficiency for Detecting Rework Anomaly in Business Processes","date":"2025-02-10","arxiv_id":"2502.06918","n_code_links":0,"syntology":null},{"paper":null,"slug":"benchmarking-prompt-engineering-techniques","title":"Benchmarking Prompt Engineering Techniques for Secure Code Generation with GPT Models","date":"2025-02-09","arxiv_id":"2502.06039","n_code_links":0,"syntology":null},{"paper":null,"slug":"emergence-of-episodic-memory-in-transformers","title":"Emergence of Episodic Memory in Transformers: Characterizing Changes in Temporal Structure of Attention Scores During Training","date":"2025-02-09","arxiv_id":"2502.06902","n_code_links":0,"syntology":null},{"paper":null,"slug":"large-language-models-for-in-file","title":"Large Language Models for In-File Vulnerability Localization Can Be \"Lost in the End\"","date":"2025-02-09","arxiv_id":"2502.06898","n_code_links":0,"syntology":null},{"paper":null,"slug":"scaffoldgpt-a-scaffold-based-large-language","title":"ScaffoldGPT: A Scaffold-based GPT Model for Drug Optimization","date":"2025-02-09","arxiv_id":"2502.06891","n_code_links":0,"syntology":null},{"paper":null,"slug":"forbidden-science-dual-use-ai-challenge","title":"Forbidden Science: Dual-Use AI Challenge Benchmark and Scientific Refusal Tests","date":"2025-02-08","arxiv_id":"2502.06867","n_code_links":0,"syntology":null},{"paper":"/paper/the-odyssey-of-the-fittest-can-agents-survive","slug":"the-odyssey-of-the-fittest-can-agents-survive","title":"The Odyssey of the Fittest: Can Agents Survive and Still Be Good?","date":"2025-02-08","arxiv_id":"2502.05442","n_code_links":1,"syntology":null},{"paper":null,"slug":"can-large-language-models-understand-1","title":"Can Large Language Models Understand Intermediate Representations?","date":"2025-02-07","arxiv_id":"2502.06854","n_code_links":0,"syntology":null},{"paper":null,"slug":"detection-of-llm-generated-java-code-using","title":"Detection of LLM-Generated Java Code Using Discretized Nested Bigrams","date":"2025-02-07","arxiv_id":"2502.15740","n_code_links":0,"syntology":null},{"paper":null,"slug":"eap-gp-mitigating-saturation-effect-in","title":"EAP-GP: Mitigating Saturation Effect in Gradient-based Automated Circuit Identification","date":"2025-02-07","arxiv_id":"2502.06852","n_code_links":0,"syntology":null}],"record_sha256":"545d9edc921319273187ec7247fb4117a96559e5faf489a47ad5802c08da26bf","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}