{"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":"/task/language-modelling/papers/116","list_of":"/task/language-modelling","task":"Language Modelling","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":116,"pages_in_order":177,"rows_per_page":100,"rows":[11501,11600],"of":17610,"counts":{"archive_papers_tagged":17610,"with_a_code_link":7012,"where_syntology_ran_a_sample":2428,"not_listed_spam_title":0,"listed":17610,"listed_where_code_ran":2428,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":2027,"every_run_a_failure_of_syntologys_instrument":401,"listed_with_a_run_with_no_instrument_failure":2027,"listed_every_run_a_failure_of_syntologys_instrument":401,"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":"/task/language-modelling","prev":"/task/language-modelling/papers/115","next":"/task/language-modelling/papers/117","papers":[{"url":null,"slug":"persianmind-a-cross-lingual-persian-english","title":"PersianMind: A Cross-Lingual Persian-English Large Language Model","date":"2024-01-12","arxiv_id":"2401.06466","repositories_listed":0,"syntology":null},{"url":null,"slug":"xls-r-deep-learning-model-for-multilingual","title":"XLS-R Deep Learning Model for Multilingual ASR on Low- Resource Languages: Indonesian, Javanese, and Sundanese","date":"2024-01-12","arxiv_id":"2401.06832","repositories_listed":0,"syntology":null},{"url":null,"slug":"distilling-vision-language-models-on-millions","title":"Distilling Vision-Language Models on Millions of Videos","date":"2024-01-11","arxiv_id":"2401.06129","repositories_listed":0,"syntology":null},{"url":null,"slug":"epilepsyllm-domain-specific-large-language","title":"EpilepsyLLM: Domain-Specific Large Language Model Fine-tuned with Epilepsy Medical Knowledge","date":"2024-01-11","arxiv_id":"2401.05908","repositories_listed":0,"syntology":null},{"url":null,"slug":"how-teachers-can-use-large-language-models","title":"How Teachers Can Use Large Language Models and Bloom's Taxonomy to Create Educational Quizzes","date":"2024-01-11","arxiv_id":"2401.05914","repositories_listed":0,"syntology":null},{"url":null,"slug":"investigating-data-contamination-for-pre","title":"Investigating Data Contamination for Pre-training Language Models","date":"2024-01-11","arxiv_id":"2401.06059","repositories_listed":0,"syntology":null},{"url":null,"slug":"lingualchemy-fusing-typological-and","title":"LinguAlchemy: Fusing Typological and Geographical Elements for Unseen Language Generalization","date":"2024-01-11","arxiv_id":"2401.06034","repositories_listed":0,"syntology":null},{"url":null,"slug":"risk-taxonomy-mitigation-and-assessment","title":"Risk Taxonomy, Mitigation, and Assessment Benchmarks of Large Language Model Systems","date":"2024-01-11","arxiv_id":"2401.05778","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-conversational-diagnostic-ai","title":"Towards Conversational Diagnostic AI","date":"2024-01-11","arxiv_id":"2401.05654","repositories_listed":0,"syntology":null},{"url":null,"slug":"xtrimopglm-unified-100b-scale-pre-trained","title":"xTrimoPGLM: Unified 100B-Scale Pre-trained Transformer for Deciphering the Language of Protein","date":"2024-01-11","arxiv_id":"2401.06199","repositories_listed":0,"syntology":null},{"url":null,"slug":"chatgpt-let-us-chat-sign-language-experiments","title":"ChatGPT, Let us Chat Sign Language: Experiments, Architectural Elements, Challenges and Research Directions","date":"2024-01-10","arxiv_id":"2401.06804","repositories_listed":0,"syntology":null},{"url":null,"slug":"hierarchical-classification-of-transversal","title":"Hierarchical Classification of Transversal Skills in Job Ads Based on Sentence Embeddings","date":"2024-01-10","arxiv_id":"2401.05073","repositories_listed":0,"syntology":null},{"url":null,"slug":"knowledge-sharing-in-manufacturing-using","title":"Knowledge Sharing in Manufacturing using Large Language Models: User Evaluation and Model Benchmarking","date":"2024-01-10","arxiv_id":"2401.05200","repositories_listed":0,"syntology":null},{"url":null,"slug":"less-is-more-a-closer-look-at-multi-modal-few","title":"Less is More: A Closer Look at Semantic-based Few-Shot Learning","date":"2024-01-10","arxiv_id":"2401.05010","repositories_listed":0,"syntology":null},{"url":null,"slug":"theory-of-mind-abilities-of-large-language","title":"Theory of Mind abilities of Large Language Models in Human-Robot Interaction : An Illusion?","date":"2024-01-10","arxiv_id":"2401.05302","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-prompt-based-methods-for-zero-shot","title":"Exploring Prompt-Based Methods for Zero-Shot Hypernym Prediction with Large Language Models","date":"2024-01-09","arxiv_id":"2401.04515","repositories_listed":0,"syntology":null},{"url":null,"slug":"how-predictable-is-language-model-benchmark","title":"How predictable is language model benchmark performance?","date":"2024-01-09","arxiv_id":"2401.04757","repositories_listed":0,"syntology":null},{"url":null,"slug":"chain-of-lora-efficient-fine-tuning-of","title":"Chain of LoRA: Efficient Fine-tuning of Language Models via Residual Learning","date":"2024-01-08","arxiv_id":"2401.04151","repositories_listed":0,"syntology":null},{"url":null,"slug":"dme-driver-integrating-human-decision-logic","title":"DME-Driver: Integrating Human Decision Logic and 3D Scene Perception in Autonomous Driving","date":"2024-01-08","arxiv_id":"2401.03641","repositories_listed":0,"syntology":null},{"url":null,"slug":"ffsplit-split-feed-forward-network-for","title":"FFSplit: Split Feed-Forward Network For Optimizing Accuracy-Efficiency Trade-off in Language Model Inference","date":"2024-01-08","arxiv_id":"2401.04044","repositories_listed":0,"syntology":null},{"url":null,"slug":"flightllm-efficient-large-language-model","title":"FlightLLM: Efficient Large Language Model Inference with a Complete Mapping Flow on FPGAs","date":"2024-01-08","arxiv_id":"2401.03868","repositories_listed":0,"syntology":null},{"url":null,"slug":"idofew-intermediate-training-using-dual","title":"IDoFew: Intermediate Training Using Dual-Clustering in Language Models for Few Labels Text Classification","date":"2024-01-08","arxiv_id":"2401.04025","repositories_listed":0,"syntology":null},{"url":null,"slug":"language-conditioned-robotic-manipulation","title":"Language-Conditioned Robotic Manipulation with Fast and Slow Thinking","date":"2024-01-08","arxiv_id":"2401.04181","repositories_listed":0,"syntology":null},{"url":null,"slug":"sparse-meets-dense-a-hybrid-approach-to","title":"Sparse Meets Dense: A Hybrid Approach to Enhance Scientific Document Retrieval","date":"2024-01-08","arxiv_id":"2401.04055","repositories_listed":0,"syntology":null},{"url":null,"slug":"why-solving-multi-agent-path-finding-with","title":"Why Solving Multi-agent Path Finding with Large Language Model has not Succeeded Yet","date":"2024-01-08","arxiv_id":"2401.03630","repositories_listed":0,"syntology":null},{"url":null,"slug":"llm-powered-code-vulnerability-repair-with","title":"LLM-Powered Code Vulnerability Repair with Reinforcement Learning and Semantic Reward","date":"2024-01-07","arxiv_id":"2401.03374","repositories_listed":0,"syntology":null},{"url":null,"slug":"maintaining-journalistic-integrity-in-the","title":"Maintaining Journalistic Integrity in the Digital Age: A Comprehensive NLP Framework for Evaluating Online News Content","date":"2024-01-07","arxiv_id":"2401.03467","repositories_listed":0,"syntology":null},{"url":null,"slug":"setformer-is-what-you-need-for-vision-and","title":"SeTformer is What You Need for Vision and Language","date":"2024-01-07","arxiv_id":"2401.03540","repositories_listed":0,"syntology":null},{"url":null,"slug":"token-free-llms-can-generate-chinese","title":"CharPoet: A Chinese Classical Poetry Generation System Based on Token-free LLM","date":"2024-01-07","arxiv_id":"2401.03512","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-context-through-contrast","title":"Enhancing Context Through Contrast","date":"2024-01-06","arxiv_id":"2401.03314","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-essay-scoring-with-adversarial","title":"Enhancing Essay Scoring with Adversarial Weights Perturbation and Metric-specific AttentionPooling","date":"2024-01-06","arxiv_id":"2401.05433","repositories_listed":0,"syntology":null},{"url":null,"slug":"part-of-speech-tagger-for-bodo-language-using","title":"Part-of-Speech Tagger for Bodo Language using Deep Learning approach","date":"2024-01-06","arxiv_id":"2401.03175","repositories_listed":0,"syntology":null},{"url":null,"slug":"pixar-auto-regressive-language-modeling-in","title":"PIXAR: Auto-Regressive Language Modeling in Pixel Space","date":"2024-01-06","arxiv_id":"2401.03321","repositories_listed":0,"syntology":null},{"url":null,"slug":"docgraphlm-documental-graph-language-model","title":"DocGraphLM: Documental Graph Language Model for Information Extraction","date":"2024-01-05","arxiv_id":"2401.02823","repositories_listed":0,"syntology":null},{"url":null,"slug":"introducing-bode-a-fine-tuned-large-language","title":"Introducing Bode: A Fine-Tuned Large Language Model for Portuguese Prompt-Based Task","date":"2024-01-05","arxiv_id":"2401.02909","repositories_listed":0,"syntology":null},{"url":null,"slug":"object-centric-instruction-augmentation-for","title":"Object-Centric Instruction Augmentation for Robotic Manipulation","date":"2024-01-05","arxiv_id":"2401.02814","repositories_listed":0,"syntology":null},{"url":null,"slug":"thousands-of-ai-authors-on-the-future-of-ai","title":"Thousands of AI Authors on the Future of AI","date":"2024-01-05","arxiv_id":"2401.02843","repositories_listed":0,"syntology":null},{"url":null,"slug":"voronav-voronoi-based-zero-shot-object","title":"VoroNav: Voronoi-based Zero-shot Object Navigation with Large Language Model","date":"2024-01-05","arxiv_id":"2401.02695","repositories_listed":0,"syntology":null},{"url":null,"slug":"xuat-copilot-multi-agent-collaborative-system","title":"XUAT-Copilot: Multi-Agent Collaborative System for Automated User Acceptance Testing with Large Language Model","date":"2024-01-05","arxiv_id":"2401.02705","repositories_listed":0,"syntology":null},{"url":null,"slug":"beyond-extraction-contextualising-tabular","title":"Beyond Extraction: Contextualising Tabular Data for Efficient Summarisation by Language Models","date":"2024-01-04","arxiv_id":"2401.02333","repositories_listed":0,"syntology":null},{"url":null,"slug":"memory-consciousness-and-large-language-model","title":"Memory, Consciousness and Large Language Model","date":"2024-01-04","arxiv_id":"2401.02509","repositories_listed":0,"syntology":null},{"url":null,"slug":"pokergpt-an-end-to-end-lightweight-solver-for","title":"PokerGPT: An End-to-End Lightweight Solver for Multi-Player Texas Hold'em via Large Language Model","date":"2024-01-04","arxiv_id":"2401.06781","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-contrast-better-reflection-through","title":"Self-Contrast: Better Reflection Through Inconsistent Solving Perspectives","date":"2024-01-04","arxiv_id":"2401.02009","repositories_listed":0,"syntology":null},{"url":"/paper/sycoca-symmetrizing-contrastive-captioners","slug":"sycoca-symmetrizing-contrastive-captioners","title":"SyCoCa: Symmetrizing Contrastive Captioners with Attentive Masking for Multimodal Alignment","date":"2024-01-04","arxiv_id":"2401.02137","repositories_listed":0,"syntology":null},{"url":null,"slug":"understanding-llms-a-comprehensive-overview","title":"Understanding LLMs: A Comprehensive Overview from Training to Inference","date":"2024-01-04","arxiv_id":"2401.02038","repositories_listed":0,"syntology":null},{"url":null,"slug":"cross-target-stance-detection-by-exploiting","title":"Cross-target Stance Detection by Exploiting Target Analytical Perspectives","date":"2024-01-03","arxiv_id":"2401.01761","repositories_listed":0,"syntology":null},{"url":null,"slug":"incorporating-geo-diverse-knowledge-into","title":"Incorporating Geo-Diverse Knowledge into Prompting for Increased Geographical Robustness in Object Recognition","date":"2024-01-03","arxiv_id":"2401.01482","repositories_listed":0,"syntology":null},{"url":null,"slug":"iterative-mask-filling-an-effective-text","title":"Iterative Mask Filling: An Effective Text Augmentation Method Using Masked Language Modeling","date":"2024-01-03","arxiv_id":"2401.01830","repositories_listed":0,"syntology":null},{"url":null,"slug":"predicting-challenge-moments-from-students","title":"Predicting challenge moments from students' discourse: A comparison of GPT-4 to two traditional natural language processing approaches","date":"2024-01-03","arxiv_id":"2401.01692","repositories_listed":0,"syntology":null},{"url":null,"slug":"bev-clip-multi-modal-bev-retrieval","title":"BEV-TSR: Text-Scene Retrieval in BEV Space for Autonomous Driving","date":"2024-01-02","arxiv_id":"2401.01065","repositories_listed":0,"syntology":null},{"url":null,"slug":"dialclip-empowering-clip-as-multi-modal","title":"DialCLIP: Empowering CLIP as Multi-Modal Dialog Retriever","date":"2024-01-02","arxiv_id":"2401.01076","repositories_listed":0,"syntology":null},{"url":null,"slug":"discovering-significant-topics-from-legal","title":"Discovering Significant Topics from Legal Decisions with Selective Inference","date":"2024-01-02","arxiv_id":"2401.01068","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-parallel-audio-generation-using","title":"Efficient Parallel Audio Generation using Group Masked Language Modeling","date":"2024-01-02","arxiv_id":"2401.01099","repositories_listed":0,"syntology":null},{"url":null,"slug":"imperio-language-guided-backdoor-attacks-for","title":"Imperio: Language-Guided Backdoor Attacks for Arbitrary Model Control","date":"2024-01-02","arxiv_id":"2401.01085","repositories_listed":0,"syntology":null},{"url":null,"slug":"assistgui-task-oriented-pc-graphical-user","title":"AssistGUI: Task-Oriented PC Graphical User Interface Automation","date":"2024-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"codi-2-in-context-interleaved-and-interactive-1","title":"CoDi-2: In-Context Interleaved and Interactive Any-to-Any Generation","date":"2024-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"cosmo-contrastive-streamlined-multimodal","title":"COSMO: COntrastive Streamlined MultimOdal Model with Interleaved Pre-Training","date":"2024-01-01","arxiv_id":"2401.00849","repositories_listed":0,"syntology":null},{"url":null,"slug":"digger-detecting-copyright-content-mis-usage","title":"Digger: Detecting Copyright Content Mis-usage in Large Language Model Training","date":"2024-01-01","arxiv_id":"2401.00676","repositories_listed":0,"syntology":null},{"url":null,"slug":"discovering-syntactic-interaction-clues-for","title":"Discovering Syntactic Interaction Clues for Human-Object Interaction Detection","date":"2024-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"disentangled-prompt-representation-for-domain","title":"Disentangled Prompt Representation for Domain Generalization","date":"2024-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":"/paper/edge-aware-3d-instance-segmentation-network","slug":"edge-aware-3d-instance-segmentation-network","title":"Edge-Aware 3D Instance Segmentation Network with Intelligent Semantic Prior","date":"2024-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"few-shot-object-detection-with-foundation","title":"Few-Shot Object Detection with Foundation Models","date":"2024-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"jack-of-all-tasks-master-of-many-designing-1","title":"Jack of All Tasks Master of Many: Designing General-Purpose Coarse-to-Fine Vision-Language Model","date":"2024-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"large-language-models-aren-t-all-that-you","title":"Large Language Models aren't all that you need","date":"2024-01-01","arxiv_id":"2401.00698","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-scaling-up-a-multilingual-vision-and","title":"On Scaling Up a Multilingual Vision and Language Model","date":"2024-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"pevl-pose-enhanced-vision-language-model-for","title":"PeVL: Pose-Enhanced Vision-Language Model for Fine-Grained Human Action Recognition","date":"2024-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"pixel-aligned-language-model","title":"Pixel-Aligned Language Model","date":"2024-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"predicting-anti-microbial-resistance-using","title":"Predicting Anti-microbial Resistance using Large Language Models","date":"2024-01-01","arxiv_id":"2401.00642","repositories_listed":0,"syntology":null},{"url":null,"slug":"querying-as-prompt-parameter-efficient","title":"Querying as Prompt: Parameter-Efficient Learning for Multimodal Language Model","date":"2024-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"searching-fast-and-slow-through-product","title":"Searching, fast and slow, through product catalogs","date":"2024-01-01","arxiv_id":"2401.00737","repositories_listed":0,"syntology":null},{"url":null,"slug":"taking-the-next-step-with-generative","title":"Taking the Next Step with Generative Artificial Intelligence: The Transformative Role of Multimodal Large Language Models in Science Education","date":"2024-01-01","arxiv_id":"2401.00832","repositories_listed":0,"syntology":null},{"url":null,"slug":"beyond-chinchilla-optimal-accounting-for","title":"Beyond Chinchilla-Optimal: Accounting for Inference in Language Model Scaling Laws","date":"2023-12-31","arxiv_id":"2401.00448","repositories_listed":0,"syntology":null},{"url":null,"slug":"bidirectional-trained-tree-structured-decoder","title":"Bidirectional Trained Tree-Structured Decoder for Handwritten Mathematical Expression Recognition","date":"2023-12-31","arxiv_id":"2401.00435","repositories_listed":0,"syntology":null},{"url":null,"slug":"docllm-a-layout-aware-generative-language","title":"DocLLM: A layout-aware generative language model for multimodal document understanding","date":"2023-12-31","arxiv_id":"2401.00908","repositories_listed":0,"syntology":null},{"url":null,"slug":"hsc-gpt-a-large-language-model-for-human","title":"HSC-GPT: A Large Language Model for Human Settlements Construction","date":"2023-12-31","arxiv_id":"2401.00504","repositories_listed":0,"syntology":null},{"url":null,"slug":"boosting-large-language-model-for-speech","title":"Boosting Large Language Model for Speech Synthesis: An Empirical Study","date":"2023-12-30","arxiv_id":"2401.00246","repositories_listed":0,"syntology":null},{"url":null,"slug":"reasoninglm-enabling-structural-subgraph","title":"ReasoningLM: Enabling Structural Subgraph Reasoning in Pre-trained Language Models for Question Answering over Knowledge Graph","date":"2023-12-30","arxiv_id":"2401.00158","repositories_listed":0,"syntology":null},{"url":null,"slug":"trace-and-edit-relation-associations-in-gpt","title":"Trace and Edit Relation Associations in GPT","date":"2023-12-30","arxiv_id":"2401.02976","repositories_listed":0,"syntology":null},{"url":null,"slug":"principled-gradient-based-markov-chain-monte","title":"Principled Gradient-based Markov Chain Monte Carlo for Text Generation","date":"2023-12-29","arxiv_id":"2312.17710","repositories_listed":0,"syntology":null},{"url":null,"slug":"smot-think-in-state-machine","title":"State Machine of Thoughts: Leveraging Past Reasoning Trajectories for Enhancing Problem Solving","date":"2023-12-29","arxiv_id":"2312.17445","repositories_listed":0,"syntology":null},{"url":null,"slug":"do-androids-know-they-re-only-dreaming-of","title":"Do Androids Know They're Only Dreaming of Electric Sheep?","date":"2023-12-28","arxiv_id":"2312.17249","repositories_listed":0,"syntology":null},{"url":null,"slug":"language-model-as-an-annotator-unsupervised","title":"Language Model as an Annotator: Unsupervised Context-aware Quality Phrase Generation","date":"2023-12-28","arxiv_id":"2312.17349","repositories_listed":0,"syntology":null},{"url":null,"slug":"large-language-model-for-causal-decision","title":"LLM4Causal: Democratized Causal Tools for Everyone via Large Language Model","date":"2023-12-28","arxiv_id":"2312.17122","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-generate-text-in-arbitrary","title":"Learning to Generate Text in Arbitrary Writing Styles","date":"2023-12-28","arxiv_id":"2312.17242","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-rate-of-convergence-of-an-over","title":"On the rate of convergence of an over-parametrized Transformer classifier learned by gradient descent","date":"2023-12-28","arxiv_id":"2312.17007","repositories_listed":0,"syntology":null},{"url":null,"slug":"spike-no-more-stabilizing-the-pre-training-of","title":"Spike No More: Stabilizing the Pre-training of Large Language Models","date":"2023-12-28","arxiv_id":"2312.16903","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-auto-modeling-of-formal-verification","title":"Towards Auto-Modeling of Formal Verification for NextG Protocols: A Multimodal cross- and self-attention Large Language Model Approach","date":"2023-12-28","arxiv_id":"2312.17353","repositories_listed":0,"syntology":null},{"url":null,"slug":"virtual-scientific-companion-for-synchrotron","title":"Virtual Scientific Companion for Synchrotron Beamlines: A Prototype","date":"2023-12-28","arxiv_id":"2312.17180","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-large-language-model-based-computational","title":"A Large Language Model-based Computational Approach to Improve Identity-Related Write-Ups","date":"2023-12-27","arxiv_id":"2312.16659","repositories_listed":0,"syntology":null},{"url":null,"slug":"automating-knowledge-acquisition-for-content","title":"Automating Knowledge Acquisition for Content-Centric Cognitive Agents Using LLMs","date":"2023-12-27","arxiv_id":"2312.16378","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-intra-task-relations-to-improve","title":"Exploring intra-task relations to improve meta-learning algorithms","date":"2023-12-27","arxiv_id":"2312.16612","repositories_listed":0,"syntology":null},{"url":null,"slug":"pangu-p-enhancing-language-model","title":"PanGu-$π$: Enhancing Language Model Architectures via Nonlinearity Compensation","date":"2023-12-27","arxiv_id":"2312.17276","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-bi-objective-e-constrained-framework-for","title":"A bi-objective $ε$-constrained framework for quality-cost optimization in language model ensembles","date":"2023-12-26","arxiv_id":"2312.16119","repositories_listed":0,"syntology":null},{"url":null,"slug":"knowledgenavigator-leveraging-large-language","title":"KnowledgeNavigator: Leveraging Large Language Models for Enhanced Reasoning over Knowledge Graph","date":"2023-12-26","arxiv_id":"2312.15880","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-split-and-privatize-framework-for-large","title":"A Split-and-Privatize Framework for Large Language Model Fine-Tuning","date":"2023-12-25","arxiv_id":"2312.15603","repositories_listed":0,"syntology":null},{"url":null,"slug":"aham-adapt-help-ask-model-harvesting-llms-for","title":"AHAM: Adapt, Help, Ask, Model -- Harvesting LLMs for literature mining","date":"2023-12-25","arxiv_id":"2312.15784","repositories_listed":0,"syntology":null},{"url":null,"slug":"persianllama-towards-building-first-persian","title":"PersianLLaMA: Towards Building First Persian Large Language Model","date":"2023-12-25","arxiv_id":"2312.15713","repositories_listed":0,"syntology":null},{"url":null,"slug":"manipllm-embodied-multimodal-large-language","title":"ManipLLM: Embodied Multimodal Large Language Model for Object-Centric Robotic Manipulation","date":"2023-12-24","arxiv_id":"2312.16217","repositories_listed":0,"syntology":null},{"url":null,"slug":"multimodal-classification-of-teaching","title":"Multimodal Classification of Teaching Activities from University Lecture Recordings","date":"2023-12-24","arxiv_id":"2312.17262","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-explainable-ai-approach-to-large-language","title":"An Explainable AI Approach to Large Language Model Assisted Causal Model Auditing and Development","date":"2023-12-23","arxiv_id":"2312.16211","repositories_listed":0,"syntology":null}],"record_sha256":"22da89b1a1e118bd39ca29360dd4944c552a9ef76cb2069f32950cbfde146edb","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}