{"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-modeling/papers/86","list_of":"/task/language-modeling","task":"Language Modeling","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":86,"pages_in_order":142,"rows_per_page":100,"rows":[8501,8600],"of":14182,"counts":{"archive_papers_tagged":14182,"with_a_code_link":5620,"where_syntology_ran_a_sample":1894,"not_listed_spam_title":0,"listed":14182,"listed_where_code_ran":1894,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1580,"every_run_a_failure_of_syntologys_instrument":314,"listed_with_a_run_with_no_instrument_failure":1580,"listed_every_run_a_failure_of_syntologys_instrument":314,"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-modeling","prev":"/task/language-modeling/papers/85","next":"/task/language-modeling/papers/87","papers":[{"url":null,"slug":"does-cross-cultural-alignment-change-the","title":"Does Cross-Cultural Alignment Change the Commonsense Morality of Language Models?","date":"2024-06-24","arxiv_id":"2406.16316","repositories_listed":0,"syntology":null},{"url":null,"slug":"gpt-4v-explorations-mining-autonomous-driving","title":"GPT-4V Explorations: Mining Autonomous Driving","date":"2024-06-24","arxiv_id":"2406.16817","repositories_listed":0,"syntology":null},{"url":null,"slug":"guardrails-for-avoiding-harmful-medical","title":"Guardrails for avoiding harmful medical product recommendations and off-label promotion in generative AI models","date":"2024-06-24","arxiv_id":"2406.16455","repositories_listed":0,"syntology":null},{"url":null,"slug":"inducing-group-fairness-in-llm-based","title":"Inducing Group Fairness in Prompt-Based Language Model Decisions","date":"2024-06-24","arxiv_id":"2406.16738","repositories_listed":0,"syntology":null},{"url":null,"slug":"large-vocabulary-size-improves-large-language","title":"Large Vocabulary Size Improves Large Language Models","date":"2024-06-24","arxiv_id":"2406.16508","repositories_listed":0,"syntology":null},{"url":null,"slug":"modulating-language-model-experiences-through","title":"Modulating Language Model Experiences through Frictions","date":"2024-06-24","arxiv_id":"2407.12804","repositories_listed":0,"syntology":null},{"url":null,"slug":"resmaster-mastering-high-resolution-image","title":"ResMaster: Mastering High-Resolution Image Generation via Structural and Fine-Grained Guidance","date":"2024-06-24","arxiv_id":"2406.16476","repositories_listed":0,"syntology":null},{"url":null,"slug":"sparser-is-faster-and-less-is-more-efficient","title":"Sparser is Faster and Less is More: Efficient Sparse Attention for Long-Range Transformers","date":"2024-06-24","arxiv_id":"2406.16747","repositories_listed":0,"syntology":null},{"url":null,"slug":"understanding-and-mitigating-tokenization","title":"Understanding and Mitigating Tokenization Bias in Language Models","date":"2024-06-24","arxiv_id":"2406.16829","repositories_listed":0,"syntology":null},{"url":null,"slug":"unicoder-scaling-code-large-language-model","title":"UniCoder: Scaling Code Large Language Model via Universal Code","date":"2024-06-24","arxiv_id":"2406.16441","repositories_listed":0,"syntology":null},{"url":null,"slug":"recall-membership-inference-via-relative","title":"ReCaLL: Membership Inference via Relative Conditional Log-Likelihoods","date":"2024-06-23","arxiv_id":"2406.15968","repositories_listed":0,"syntology":null},{"url":null,"slug":"cat-bench-benchmarking-language-model","title":"CaT-BENCH: Benchmarking Language Model Understanding of Causal and Temporal Dependencies in Plans","date":"2024-06-22","arxiv_id":"2406.15823","repositories_listed":0,"syntology":null},{"url":null,"slug":"language-alignment-via-nash-learning-and","title":"Language Alignment via Nash-learning and Adaptive feedback","date":"2024-06-22","arxiv_id":"2406.15890","repositories_listed":0,"syntology":null},{"url":null,"slug":"mossbench-is-your-multimodal-language-model","title":"MOSSBench: Is Your Multimodal Language Model Oversensitive to Safe Queries?","date":"2024-06-22","arxiv_id":"2406.17806","repositories_listed":0,"syntology":null},{"url":null,"slug":"reading-is-believing-revisiting-language","title":"Reading Is Believing: Revisiting Language Bottleneck Models for Image Classification","date":"2024-06-22","arxiv_id":"2406.15816","repositories_listed":0,"syntology":null},{"url":null,"slug":"rethinking-entity-level-unlearning-for-large","title":"Unveiling Entity-Level Unlearning for Large Language Models: A Comprehensive Analysis","date":"2024-06-22","arxiv_id":"2406.15796","repositories_listed":0,"syntology":null},{"url":null,"slug":"video-salmonn-speech-enhanced-audio-visual","title":"video-SALMONN: Speech-Enhanced Audio-Visual Large Language Models","date":"2024-06-22","arxiv_id":"2406.15704","repositories_listed":0,"syntology":null},{"url":null,"slug":"domain-adaptation-of-llama3-70b-instruct","title":"Domain Adaptation of Llama3-70B-Instruct through Continual Pre-Training and Model Merging: A Comprehensive Evaluation","date":"2024-06-21","arxiv_id":"2406.14971","repositories_listed":0,"syntology":null},{"url":null,"slug":"giusberto-a-legal-language-model-for-personal","title":"GiusBERTo: A Legal Language Model for Personal Data De-identification in Italian Court of Auditors Decisions","date":"2024-06-21","arxiv_id":"2406.15032","repositories_listed":0,"syntology":null},{"url":null,"slug":"inferring-pluggable-types-with-machine","title":"Inferring Pluggable Types with Machine Learning","date":"2024-06-21","arxiv_id":"2406.15676","repositories_listed":0,"syntology":null},{"url":null,"slug":"temprompt-multi-task-prompt-learning-for","title":"TemPrompt: Multi-Task Prompt Learning for Temporal Relation Extraction in RAG-based Crowdsourcing Systems","date":"2024-06-21","arxiv_id":"2406.14825","repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-morphological-tree-tokenizer","title":"Unsupervised Morphological Tree Tokenizer","date":"2024-06-21","arxiv_id":"2406.15245","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-large-language-model-outperforms-other","title":"A Large Language Model Outperforms Other Computational Approaches to the High-Throughput Phenotyping of Physician Notes","date":"2024-06-20","arxiv_id":"2406.14757","repositories_listed":0,"syntology":null},{"url":null,"slug":"advantage-alignment-algorithms","title":"Advantage Alignment Algorithms","date":"2024-06-20","arxiv_id":"2406.14662","repositories_listed":0,"syntology":null},{"url":null,"slug":"apeer-automatic-prompt-engineering-enhances","title":"APEER: Automatic Prompt Engineering Enhances Large Language Model Reranking","date":"2024-06-20","arxiv_id":"2406.14449","repositories_listed":0,"syntology":null},{"url":null,"slug":"cebench-a-benchmarking-toolkit-for-the-cost","title":"CEBench: A Benchmarking Toolkit for the Cost-Effectiveness of LLM Pipelines","date":"2024-06-20","arxiv_id":"2407.12797","repositories_listed":0,"syntology":null},{"url":null,"slug":"communication-efficient-adaptive-batch-size","title":"Communication-Efficient Adaptive Batch Size Strategies for Distributed Local Gradient Methods","date":"2024-06-20","arxiv_id":"2406.13936","repositories_listed":0,"syntology":null},{"url":null,"slug":"demystifying-forgetting-in-language-model","title":"Demystifying Language Model Forgetting with Low-rank Example Associations","date":"2024-06-20","arxiv_id":"2406.14026","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-the-llm-based-robot-manipulation","title":"Enhancing the LLM-Based Robot Manipulation Through Human-Robot Collaboration","date":"2024-06-20","arxiv_id":"2406.14097","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-spatial-representations-in-the","title":"Exploring Spatial Representations in the Historical Lake District Texts with LLM-based Relation Extraction","date":"2024-06-20","arxiv_id":"2406.14336","repositories_listed":0,"syntology":null},{"url":null,"slug":"factual-dialogue-summarization-via-learning","title":"Factual Dialogue Summarization via Learning from Large Language Models","date":"2024-06-20","arxiv_id":"2406.14709","repositories_listed":0,"syntology":null},{"url":null,"slug":"healing-powers-of-bert-how-task-specific-fine","title":"Healing Powers of BERT: How Task-Specific Fine-Tuning Recovers Corrupted Language Models","date":"2024-06-20","arxiv_id":"2406.14459","repositories_listed":0,"syntology":null},{"url":null,"slug":"how-many-parameters-does-it-take-to-change-a","title":"How Many Parameters Does it Take to Change a Light Bulb? Evaluating Performance in Self-Play of Conversational Games as a Function of Model Characteristics","date":"2024-06-20","arxiv_id":"2406.14051","repositories_listed":0,"syntology":null},{"url":null,"slug":"measuring-sample-importance-in-data-pruning","title":"Measuring Sample Importance in Data Pruning for Language Models based on Information Entropy","date":"2024-06-20","arxiv_id":"2406.14124","repositories_listed":0,"syntology":null},{"url":null,"slug":"mind-the-privacy-unit-user-level-differential","title":"Mind the Privacy Unit! User-Level Differential Privacy for Language Model Fine-Tuning","date":"2024-06-20","arxiv_id":"2406.14322","repositories_listed":0,"syntology":null},{"url":null,"slug":"multiagent-collaboration-attack-investigating","title":"MultiAgent Collaboration Attack: Investigating Adversarial Attacks in Large Language Model Collaborations via Debate","date":"2024-06-20","arxiv_id":"2406.14711","repositories_listed":0,"syntology":null},{"url":null,"slug":"ranking-llms-by-compression","title":"Ranking LLMs by compression","date":"2024-06-20","arxiv_id":"2406.14171","repositories_listed":0,"syntology":null},{"url":null,"slug":"spl-a-socratic-playground-for-learning","title":"SPL: A Socratic Playground for Learning Powered by Large Language Model","date":"2024-06-20","arxiv_id":"2406.13919","repositories_listed":0,"syntology":null},{"url":null,"slug":"block-level-text-spotting-with-llms","title":"Block-level Text Spotting with LLMs","date":"2024-06-19","arxiv_id":"2406.13208","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-collaborative-semantics-of-language","title":"Enhancing Collaborative Semantics of Language Model-Driven Recommendations via Graph-Aware Learning","date":"2024-06-19","arxiv_id":"2406.13235","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-distractor-generation-for-multiple","title":"Enhancing Distractor Generation for Multiple-Choice Questions with Retrieval Augmented Pretraining and Knowledge Graph Integration","date":"2024-06-19","arxiv_id":"2406.13578","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-travel-choice-modeling-with-large","title":"Enhancing Travel Choice Modeling with Large Language Models: A Prompt-Learning Approach","date":"2024-06-19","arxiv_id":"2406.13558","repositories_listed":0,"syntology":null},{"url":null,"slug":"from-single-agent-to-multi-agent-improving","title":"From Single Agent to Multi-Agent: Improving Traffic Signal Control","date":"2024-06-19","arxiv_id":"2406.13693","repositories_listed":0,"syntology":null},{"url":null,"slug":"in-context-former-lightning-fast-compressing","title":"In-Context Former: Lightning-fast Compressing Context for Large Language Model","date":"2024-06-19","arxiv_id":"2406.13618","repositories_listed":0,"syntology":null},{"url":null,"slug":"investigating-low-cost-llm-annotation-for","title":"Investigating Low-Cost LLM Annotation for~Spoken Dialogue Understanding Datasets","date":"2024-06-19","arxiv_id":"2406.13269","repositories_listed":0,"syntology":null},{"url":null,"slug":"large-language-models-are-biased-because-they","title":"Large Language Models are Biased Because They Are Large Language Models","date":"2024-06-19","arxiv_id":"2406.13138","repositories_listed":0,"syntology":null},{"url":null,"slug":"lit-large-language-model-driven-intention","title":"LIT: Large Language Model Driven Intention Tracking for Proactive Human-Robot Collaboration -- A Robot Sous-Chef Application","date":"2024-06-19","arxiv_id":"2406.13787","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-impact-of-auxiliary-patient-data-on","title":"The Impact of Auxiliary Patient Data on Automated Chest X-Ray Report Generation and How to Incorporate It","date":"2024-06-19","arxiv_id":"2406.13181","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-holistic-language-video","title":"Towards Holistic Language-video Representation: the language model-enhanced MSR-Video to Text Dataset","date":"2024-06-19","arxiv_id":"2406.13809","repositories_listed":0,"syntology":null},{"url":null,"slug":"transferable-speech-to-text-large-language","title":"Transferable speech-to-text large language model alignment module","date":"2024-06-19","arxiv_id":"2406.13357","repositories_listed":0,"syntology":null},{"url":null,"slug":"applying-ensemble-methods-to-model-agnostic","title":"Applying Ensemble Methods to Model-Agnostic Machine-Generated Text Detection","date":"2024-06-18","arxiv_id":"2406.12570","repositories_listed":0,"syntology":null},{"url":null,"slug":"gpt-czech-poet-generation-of-czech-poetic","title":"GPT Czech Poet: Generation of Czech Poetic Strophes with Language Models","date":"2024-06-18","arxiv_id":"2407.12790","repositories_listed":0,"syntology":null},{"url":null,"slug":"in-context-learning-of-energy-functions","title":"In-Context Learning of Energy Functions","date":"2024-06-18","arxiv_id":"2406.12785","repositories_listed":0,"syntology":null},{"url":null,"slug":"interpretable-catastrophic-forgetting-of","title":"Refine Large Language Model Fine-tuning via Instruction Vector","date":"2024-06-18","arxiv_id":"2406.12227","repositories_listed":0,"syntology":null},{"url":null,"slug":"large-language-model-as-a-universal-clinical","title":"Large Language Model as a Universal Clinical Multi-task Decoder","date":"2024-06-18","arxiv_id":"2406.12738","repositories_listed":0,"syntology":null},{"url":null,"slug":"mcsd-an-efficient-language-model-with-diverse","title":"MCSD: An Efficient Language Model with Diverse Fusion","date":"2024-06-18","arxiv_id":"2406.12230","repositories_listed":0,"syntology":null},{"url":null,"slug":"pdss-a-privacy-preserving-framework-for-step","title":"PDSS: A Privacy-Preserving Framework for Step-by-Step Distillation of Large Language Models","date":"2024-06-18","arxiv_id":"2406.12403","repositories_listed":0,"syntology":null},{"url":null,"slug":"qog-question-and-options-generation-based-on","title":"QOG:Question and Options Generation based on Language Model","date":"2024-06-18","arxiv_id":"2406.12381","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-distillation-for-model-stacking-unlocks","title":"Self-Distillation for Model Stacking Unlocks Cross-Lingual NLU in 200+ Languages","date":"2024-06-18","arxiv_id":"2406.12739","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-solution-for-cvpr2024-foundational-few","title":"The Solution for CVPR2024 Foundational Few-Shot Object Detection Challenge","date":"2024-06-18","arxiv_id":"2406.12225","repositories_listed":0,"syntology":null},{"url":null,"slug":"urbanllm-autonomous-urban-activity-planning","title":"UrbanLLM: Autonomous Urban Activity Planning and Management with Large Language Models","date":"2024-06-18","arxiv_id":"2406.12360","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-collaborative-data-analytics-system-with","title":"SLEGO: A Collaborative Data Analytics System with LLM Recommender for Diverse Users","date":"2024-06-17","arxiv_id":"2406.11232","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-personalised-learning-tool-for-physics","title":"A Personalised Learning Tool for Physics Undergraduate Students Built On a Large Language Model for Symbolic Regression","date":"2024-06-17","arxiv_id":"2407.00065","repositories_listed":0,"syntology":null},{"url":null,"slug":"hare-human-priors-a-key-to-small-language","title":"HARE: HumAn pRiors, a key to small language model Efficiency","date":"2024-06-17","arxiv_id":"2406.11410","repositories_listed":0,"syntology":null},{"url":null,"slug":"large-language-models-and-knowledge-graphs-1","title":"Large Language Models and Knowledge Graphs for Astronomical Entity Disambiguation","date":"2024-06-17","arxiv_id":"2406.11400","repositories_listed":0,"syntology":null},{"url":null,"slug":"lfplm-a-general-and-flexible-load-forecasting","title":"A General Framework for Load Forecasting based on Pre-trained Large Language Model","date":"2024-06-17","arxiv_id":"2406.11336","repositories_listed":0,"syntology":null},{"url":null,"slug":"lilium-ebay-s-large-language-models-for-e","title":"LiLiuM: eBay's Large Language Models for e-commerce","date":"2024-06-17","arxiv_id":"2406.12023","repositories_listed":0,"syntology":null},{"url":null,"slug":"mitigating-large-language-model-hallucination","title":"Mitigating Large Language Model Hallucination with Faithful Finetuning","date":"2024-06-17","arxiv_id":"2406.11267","repositories_listed":0,"syntology":null},{"url":null,"slug":"preserving-knowledge-in-large-language-model","title":"Preserving Knowledge in Large Language Model with Model-Agnostic Self-Decompression","date":"2024-06-17","arxiv_id":"2406.11354","repositories_listed":0,"syntology":null},{"url":null,"slug":"promises-outlooks-and-challenges-of-diffusion","title":"Promises, Outlooks and Challenges of Diffusion Language Modeling","date":"2024-06-17","arxiv_id":"2406.11473","repositories_listed":0,"syntology":null},{"url":null,"slug":"prompts-as-auto-optimized-training","title":"Prompts as Auto-Optimized Training Hyperparameters: Training Best-in-Class IR Models from Scratch with 10 Gold Labels","date":"2024-06-17","arxiv_id":"2406.11706","repositories_listed":0,"syntology":null},{"url":null,"slug":"skip-layer-attention-bridging-abstract-and","title":"Skip-Layer Attention: Bridging Abstract and Detailed Dependencies in Transformers","date":"2024-06-17","arxiv_id":"2406.11274","repositories_listed":0,"syntology":null},{"url":null,"slug":"steve-series-step-by-step-construction-of","title":"STEVE Series: Step-by-Step Construction of Agent Systems in Minecraft","date":"2024-06-17","arxiv_id":"2406.11247","repositories_listed":0,"syntology":null},{"url":null,"slug":"tifg-text-informed-feature-generation-with","title":"Retrieval-Augmented Feature Generation for Domain-Specific Classification","date":"2024-06-17","arxiv_id":"2406.11177","repositories_listed":0,"syntology":null},{"url":"/paper/videollm-online-online-video-large-language-1","slug":"videollm-online-online-video-large-language-1","title":"VideoLLM-online: Online Video Large Language Model for Streaming Video","date":"2024-06-17","arxiv_id":"2406.11816","repositories_listed":0,"syntology":null},{"url":null,"slug":"what-kinds-of-tokens-benefit-from-distant","title":"What Kinds of Tokens Benefit from Distant Text? An Analysis on Long Context Language Modeling","date":"2024-06-17","arxiv_id":"2406.11238","repositories_listed":0,"syntology":null},{"url":null,"slug":"large-language-models-for-dysfluency","title":"Large Language Models for Dysfluency Detection in Stuttered Speech","date":"2024-06-16","arxiv_id":"2406.11025","repositories_listed":0,"syntology":null},{"url":null,"slug":"taking-a-deep-breath-enhancing-language","title":"Taking a Deep Breath: Enhancing Language Modeling of Large Language Models with Sentinel Tokens","date":"2024-06-16","arxiv_id":"2406.10985","repositories_listed":0,"syntology":null},{"url":null,"slug":"cancerllm-a-large-language-model-in-cancer","title":"CancerLLM: A Large Language Model in Cancer Domain","date":"2024-06-15","arxiv_id":"2406.10459","repositories_listed":0,"syntology":null},{"url":null,"slug":"large-language-model-enhanced-clustering-for","title":"Large Language Model Enhanced Clustering for News Event Detection","date":"2024-06-15","arxiv_id":"2406.10552","repositories_listed":0,"syntology":null},{"url":null,"slug":"mallm-gan-multi-agent-large-language-model-as","title":"MALLM-GAN: Multi-Agent Large Language Model as Generative Adversarial Network for Synthesizing Tabular Data","date":"2024-06-15","arxiv_id":"2406.10521","repositories_listed":0,"syntology":null},{"url":null,"slug":"reactor-mk-1-performances-mmlu-humaneval-and","title":"Reactor Mk.1 performances: MMLU, HumanEval and BBH test results","date":"2024-06-15","arxiv_id":"2406.10515","repositories_listed":0,"syntology":null},{"url":"/paper/robopoint-a-vision-language-model-for-spatial","slug":"robopoint-a-vision-language-model-for-spatial","title":"RoboPoint: A Vision-Language Model for Spatial Affordance Prediction for Robotics","date":"2024-06-15","arxiv_id":"2406.10721","repositories_listed":0,"syntology":null},{"url":null,"slug":"vceval-rethinking-what-is-a-good-educational","title":"VCEval: Rethinking What is a Good Educational Video and How to Automatically Evaluate It","date":"2024-06-15","arxiv_id":"2407.12005","repositories_listed":0,"syntology":null},{"url":null,"slug":"3d-rpe-enhancing-long-context-modeling","title":"3D-RPE: Enhancing Long-Context Modeling Through 3D Rotary Position Encoding","date":"2024-06-14","arxiv_id":"2406.09897","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-fundamental-trade-off-in-aligned-language","title":"A Probability--Quality Trade-off in Aligned Language Models and its Relation to Sampling Adaptors","date":"2024-06-14","arxiv_id":"2406.10203","repositories_listed":0,"syntology":null},{"url":null,"slug":"datasets-for-multilingual-answer-sentence","title":"Datasets for Multilingual Answer Sentence Selection","date":"2024-06-14","arxiv_id":"2406.10172","repositories_listed":0,"syntology":null},{"url":null,"slug":"geb-1-3b-open-lightweight-large-language","title":"GEB-1.3B: Open Lightweight Large Language Model","date":"2024-06-14","arxiv_id":"2406.09900","repositories_listed":0,"syntology":null},{"url":null,"slug":"openecad-an-efficient-visual-language-model","title":"OpenECAD: An Efficient Visual Language Model for Editable 3D-CAD Design","date":"2024-06-14","arxiv_id":"2406.09913","repositories_listed":0,"syntology":null},{"url":null,"slug":"ospc-detecting-harmful-memes-with-large","title":"OSPC: Detecting Harmful Memes with Large Language Model as a Catalyst","date":"2024-06-14","arxiv_id":"2406.09779","repositories_listed":0,"syntology":null},{"url":null,"slug":"parse-ego4d-personal-action-recommendation","title":"PARSE-Ego4D: Personal Action Recommendation Suggestions for Egocentric Videos","date":"2024-06-14","arxiv_id":"2407.09503","repositories_listed":0,"syntology":null},{"url":null,"slug":"robogolf-mastering-real-world-minigolf-with-a","title":"RoboGolf: Mastering Real-World Minigolf with a Reflective Multi-Modality Vision-Language Model","date":"2024-06-14","arxiv_id":"2406.10157","repositories_listed":0,"syntology":null},{"url":null,"slug":"trip-pal-travel-planning-with-guarantees-by","title":"TRIP-PAL: Travel Planning with Guarantees by Combining Large Language Models and Automated Planners","date":"2024-06-14","arxiv_id":"2406.10196","repositories_listed":0,"syntology":null},{"url":"/paper/vision-language-modeling-of-content","slug":"vision-language-modeling-of-content","title":"Vision Language Modeling of Content, Distortion and Appearance for Image Quality Assessment","date":"2024-06-14","arxiv_id":"2406.09858","repositories_listed":0,"syntology":null},{"url":null,"slug":"chain-of-though-cot-prompting-strategies-for","title":"Chain-of-Though (CoT) prompting strategies for medical error detection and correction","date":"2024-06-13","arxiv_id":"2406.09103","repositories_listed":0,"syntology":null},{"url":null,"slug":"clst-cold-start-mitigation-in-knowledge","title":"CLST: Cold-Start Mitigation in Knowledge Tracing by Aligning a Generative Language Model as a Students' Knowledge Tracer","date":"2024-06-13","arxiv_id":"2406.10296","repositories_listed":0,"syntology":null},{"url":null,"slug":"discreteslu-a-large-language-model-with-self","title":"DiscreteSLU: A Large Language Model with Self-Supervised Discrete Speech Units for Spoken Language Understanding","date":"2024-06-13","arxiv_id":"2406.09345","repositories_listed":0,"syntology":null},{"url":null,"slug":"dubwise-video-guided-speech-duration-control","title":"DubWise: Video-Guided Speech Duration Control in Multimodal LLM-based Text-to-Speech for Dubbing","date":"2024-06-13","arxiv_id":"2406.08802","repositories_listed":0,"syntology":null},{"url":null,"slug":"elicitationgpt-text-elicitation-mechanisms","title":"ElicitationGPT: Text Elicitation Mechanisms via Language Models","date":"2024-06-13","arxiv_id":"2406.09363","repositories_listed":0,"syntology":null},{"url":null,"slug":"generative-ai-based-prompt-evolution","title":"Generative AI-based Prompt Evolution Engineering Design Optimization With Vision-Language Model","date":"2024-06-13","arxiv_id":"2406.09143","repositories_listed":0,"syntology":null}],"record_sha256":"9e6cc61d850d2e306f6f7d6b7803af9cbe68c62934fd202e64b88f3a0885bf6a","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}