{"total":97,"rows":[{"id":"2402.00838","title":"OLMo: Accelerating the Science of Language Models","created":"2024-02-01","cited_by_count":613,"area":null},{"id":"2402.07827","title":"Aya Model: An Instruction Finetuned Open-Access Multilingual Language Model","created":"2024-02-12","cited_by_count":295,"area":null},{"id":"2305.13169","title":"A Pretrainer's Guide to Training Data: Measuring the Effects of Data Age, Domain Coverage, Quality, & Toxicity","created":"2023-05-22","cited_by_count":182,"area":null},{"id":"2309.04662","title":"MADLAD-400: A Multilingual And Document-Level Large Audited Dataset","created":"2023-09-09","cited_by_count":181,"area":null},{"id":"2504.14899","title":"Uni3C: Unifying Precisely 3D-Enhanced Camera and Human Motion Controls for Video Generation","created":"2025-04-21","cited_by_count":77,"area":null},{"id":"2512.15840","title":"Large Video Planner Enables Generalizable Robot Control","created":"2025-12-17","cited_by_count":70,"area":null},{"id":"2509.06155","title":"UniVerse-1: Unified Audio-Video Generation via Stitching of Experts","created":"2025-09-07","cited_by_count":61,"area":null},{"id":"2312.10523","title":"Paloma: A Benchmark for Evaluating Language Model Fit","created":"2023-12-16","cited_by_count":54,"area":null},{"id":"2507.09404","title":"Scaling Laws for Optimal Data Mixtures","created":"2025-07-12","cited_by_count":52,"area":null},{"id":"2309.02706","title":"HAE-RAE Bench: Evaluation of Korean Knowledge in Language Models","created":"2023-09-06","cited_by_count":47,"area":null},{"id":"2509.08519","title":"HuMo: Human-Centric Video Generation via Collaborative Multi-Modal Conditioning","created":"2025-09-10","cited_by_count":47,"area":null},{"id":"2512.08765","title":"Wan-Move: Motion-controllable Video Generation via Latent Trajectory Guidance","created":"2025-12-09","cited_by_count":45,"area":null},{"id":"2403.10691","title":"MYTE: Morphology-Driven Byte Encoding for Better and Fairer Multilingual Language Modeling","created":"2024-03-15","cited_by_count":40,"area":null},{"id":"2401.10440","title":"Breaking the Curse of Multilinguality with Cross-lingual Expert Language Models","created":"2024-01-19","cited_by_count":38,"area":null},{"id":"2511.03334","title":"UniAVGen: Unified Audio and Video Generation with Asymmetric Cross-Modal Interactions","created":"2025-11-05","cited_by_count":38,"area":null},{"id":"2603.25746","title":"ShotStream: Streaming Multi-Shot Video Generation for Interactive Storytelling","created":"2026-03-26","cited_by_count":28,"area":null},{"id":"2602.19163","title":"JavisDiT++: Unified Modeling and Optimization for Joint Audio-Video Generation","created":"2026-02-22","cited_by_count":25,"area":null},{"id":"2403.03894","title":"IRCoder: Intermediate Representations Make Language Models Robust Multilingual Code Generators","created":"2024-03-06","cited_by_count":23,"area":null},{"id":"2401.04531","title":"MERA: A Comprehensive LLM Evaluation in Russian","created":"2024-01-09","cited_by_count":22,"area":null},{"id":"2510.22037","title":"ATLAS: Adaptive Transfer Scaling Laws for Multilingual Pretraining, Finetuning, and Decoding the Curse of Multilinguality","created":"2025-10-24","cited_by_count":22,"area":null},{"id":"2406.14969","title":"Uni-Mol2: Exploring Molecular Pretraining Model at Scale","created":"2024-06-21","cited_by_count":20,"area":null},{"id":"2504.14194","title":"Meta-rater: A Multi-dimensional Data Selection Method for Pre-training Language Models","created":"2025-04-19","cited_by_count":19,"area":null},{"id":"2508.08601","title":"Yan: Foundational Interactive Video Generation","created":"2025-08-12","cited_by_count":15,"area":null},{"id":"2312.15713","title":"PersianLLaMA: Towards Building First Persian Large Language Model","created":"2023-12-25","cited_by_count":14,"area":null},{"id":"2407.04822","title":"YourMT3+: Multi-instrument Music Transcription with Enhanced Transformer Architectures and Cross-dataset Stem Augmentation","created":"2024-07-05","cited_by_count":13,"area":null},{"id":"2510.24963","title":"Language Model Behavioral Phases are Consistent Across Architecture, Training Data, and Scale","created":"2025-10-28","cited_by_count":13,"area":null},{"id":"2601.06395","title":"AfriqueLLM: How Data Mixing and Model Architecture Impact Continued Pre-training for African Languages","created":"2026-01-10","cited_by_count":12,"area":null},{"id":"2404.05829","title":"SambaLingo: Teaching Large Language Models New Languages","created":"2024-04-08","cited_by_count":11,"area":null},{"id":"2407.06380","title":"Data, Data Everywhere: A Guide for Pretraining Dataset Construction","created":"2024-07-08","cited_by_count":11,"area":null},{"id":"2510.03117","title":"Taming Text-to-Sounding Video Generation via Advanced Modality Condition and Interaction","created":"2025-10-03","cited_by_count":11,"area":null},{"id":"2601.07220","title":"The Roots of Performance Disparity in Multilingual Language Models: Intrinsic Modeling Difficulty or Design Choices?","created":"2026-01-12","cited_by_count":11,"area":null},{"id":"2305.11129","title":"mLongT5: A Multilingual and Efficient Text-To-Text Transformer for Longer Sequences","created":"2023-05-18","cited_by_count":10,"area":null},{"id":"2504.06011","title":"Llama-3-Nanda-10B-Chat: An Open Generative Large Language Model for Hindi","created":"2025-04-08","cited_by_count":10,"area":null},{"id":"2506.22724","title":"The Translation Barrier Hypothesis: Multilingual Generation with Large Language Models Suffers from Implicit Translation Failure","created":"2025-06-28","cited_by_count":10,"area":null},{"id":"2510.25947","title":"Revisiting Multilingual Data Mixtures in Language Model Pretraining","created":"2025-10-29","cited_by_count":10,"area":null},{"id":"2602.05827","title":"Sparse Video Generation Propels Real-World Beyond-the-View Vision-Language Navigation","created":"2026-02-05","cited_by_count":10,"area":null},{"id":"2604.03723","title":"SymphoMotion: Joint Control of Camera Motion and Object Dynamics for Coherent Video Generation","created":"2026-04-04","cited_by_count":10,"area":null},{"id":"2512.06905","title":"Scaling Zero-Shot Reference-to-Video Generation","created":"2025-12-07","cited_by_count":9,"area":null},{"id":"2312.06134","title":"Order Matters in the Presence of Dataset Imbalance for Multilingual Learning","created":"2023-12-11","cited_by_count":7,"area":null},{"id":"2407.07630","title":"A Review of the Challenges with Massive Web-mined Corpora Used in Large Language Models Pre-Training","created":"2024-07-10","cited_by_count":7,"area":null},{"id":"2509.24979","title":"Video Generation with Stable Transparency via Shiftable RGB-A Distribution Learner","created":"2025-09-29","cited_by_count":7,"area":null},{"id":"2410.04579","title":"Upsample or Upweight? Balanced Training on Heavily Imbalanced Datasets","created":"2024-10-06","cited_by_count":6,"area":null},{"id":"2507.07202","title":"A Survey on Long-Video Storytelling Generation: Architectures, Consistency, and Cinematic Quality","created":"2025-07-09","cited_by_count":6,"area":null},{"id":"2312.10171","title":"Pipeline and Dataset Generation for Automated Fact-checking in Almost Any Language","created":"2023-12-15","cited_by_count":4,"area":null},{"id":"2408.15491","title":"Enhancing and Accelerating Large Language Models via Instruction-Aware Contextual Compression","created":"2024-08-28","cited_by_count":4,"area":null},{"id":"2412.20218","title":"YAD: Leveraging T5 for Improved Automatic Diacritization of Yor\\`ub\\'a Text","created":"2024-12-28","cited_by_count":4,"area":null},{"id":"2502.12476","title":"CoCo-CoLa: Evaluating and Improving Language Adherence in Multilingual LLMs","created":"2025-02-18","cited_by_count":4,"area":null},{"id":"2503.01493","title":"Sherkala-Chat: Building a State-of-the-Art LLM for Kazakh in a Moderately Resourced Setting","created":"2025-03-03","cited_by_count":4,"area":null},{"id":"2606.13676","title":"Modality Forcing for Scalable Spatial Generation","created":"2026-06-11","cited_by_count":4,"area":null},{"id":"2607.17097","title":"HarmoHOI: Harmonizing Appearance and 3D Motion for Multi-view Hand-Object Interaction Synthesis","created":"2026-07-19","cited_by_count":4,"area":null},{"id":"2405.17261","title":"Does Diffusion Beat GAN in Image Super Resolution?","created":"2024-05-27","cited_by_count":3,"area":null},{"id":"2410.17532","title":"Responsible Multilingual Large Language Models: A Survey of Development, Applications, and Societal Impact","created":"2024-10-23","cited_by_count":3,"area":null},{"id":"2410.18902","title":"LLMs for Extremely Low-Resource Finno-Ugric Languages","created":"2024-10-24","cited_by_count":3,"area":null},{"id":"2509.17858","title":"CorPipe at CRAC 2025: Evaluating Multilingual Encoders for Multilingual Coreference Resolution","created":"2025-09-22","cited_by_count":3,"area":null},{"id":"2510.14949","title":"DialectGen: Benchmarking and Improving Dialect Robustness in Multimodal Generation","created":"2025-10-16","cited_by_count":3,"area":null},{"id":"2512.10772","title":"Grow Up and Merge: Scaling Strategies for Efficient Language Adaptation","created":"2025-12-11","cited_by_count":3,"area":null},{"id":"2602.15210","title":"\\\"UberWeb: Insights from Multilingual Curation for a 20-Trillion-Token Dataset","created":"2026-02-16","cited_by_count":3,"area":null},{"id":"2603.23906","title":"GenMask: Adapting DiT for Segmentation via Direct Mask Generation","created":"2026-03-25","cited_by_count":3,"area":null},{"id":"2311.07767","title":"GreekT5: A Series of Greek Sequence-to-Sequence Models for News Summarization","created":"2023-11-13","cited_by_count":2,"area":null},{"id":"2403.17407","title":"Transcribing Bengali Text with Regional Dialects to IPA using District Guided Tokens","created":"2024-03-26","cited_by_count":2,"area":null},{"id":"2601.01778","title":"BanglaIPA: Towards Robust Text-to-IPA Transcription with Contextual Rewriting in Bengali","created":"2026-01-05","cited_by_count":2,"area":null},{"id":"2601.22306","title":"Sylber 2.0: A Universal Syllable Embedding","created":"2026-01-29","cited_by_count":2,"area":null},{"id":"2603.01418","title":"UniTalking: A Unified Audio-Video Framework for Talking Portrait Generation","created":"2026-03-02","cited_by_count":2,"area":null},{"id":"2603.17651","title":"Anchoring and Rescaling Attention for Semantically Coherent Inbetweening","created":"2026-03-18","cited_by_count":2,"area":null},{"id":"2605.17488","title":"Omni-Customizer: End-to-End MultiModal Customization for Joint Audio-Video Generation","created":"2026-05-17","cited_by_count":2,"area":null},{"id":"2606.05290","title":"Do Models Share Safety Representations? Cross-Model Steering for Safe Visual Generation","created":"2026-06-03","cited_by_count":2,"area":null},{"id":"2407.09861","title":"A Systematic Survey of Natural Language Processing for the Greek Language","created":"2024-07-13","cited_by_count":1,"area":null},{"id":"2411.01030","title":"Birdie: Advancing State Space Models with Reward-Driven Objectives and Curricula","created":"2024-11-01","cited_by_count":1,"area":null},{"id":"2511.19319","title":"SyncMV4D: Synchronized Multi-view Joint Diffusion of Appearance and Motion for Hand-Object Interaction Synthesis","created":"2025-11-24","cited_by_count":1,"area":null},{"id":"2512.10545","title":"XDoGE: Multilingual Data Reweighting to Enhance Language Inclusivity in LLMs","created":"2025-12-11","cited_by_count":1,"area":null},{"id":"2606.26058","title":"DomainShuttle: Freeform Open Domain Subject-driven Text-to-video Generation","created":"2026-06-24","cited_by_count":1,"area":null},{"id":"2607.18217","title":"HOMIE: Human-object Centric Video Personalization via Multimodal Intelligent Enhancement","created":"2026-07-20","cited_by_count":1,"area":null},{"id":"2607.28351","title":"Teffic-Audio: Tell Fact from Fiction","created":"2026-07-30","cited_by_count":1,"area":null},{"id":"2305.08800","title":"Measuring Cross-Lingual Transferability of Multilingual Transformers on Sentence Classification","created":"2023-05-15","cited_by_count":0,"area":null},{"id":"2411.03644","title":"Deploying Multi-task Online Server with Large Language Model","created":"2024-11-06","cited_by_count":0,"area":null},{"id":"2503.07066","title":"You Only Debias Once: Towards Flexible Accuracy-Fairness Trade-offs at Inference Time","created":"2025-03-10","cited_by_count":0,"area":null},{"id":"2503.17963","title":"Won: Establishing Best Practices for Korean Financial NLP","created":"2025-03-23","cited_by_count":0,"area":null},{"id":"2509.11496","title":"AKCIT-FN at CheckThat! 2025: Switching Fine-Tuned SLMs and LLM Prompting for Multilingual Claim Normalization","created":"2025-09-15","cited_by_count":0,"area":null},{"id":"2509.15556","title":"Exploring Polyglot Harmony: On Multilingual Data Allocation for Large Language Models Pretraining","created":"2025-09-19","cited_by_count":0,"area":null},{"id":"2512.21580","title":"Gamayun's Path to Multilingual Mastery: Cost-Efficient Training of a 1.5B-Parameter LLM","created":"2025-12-25","cited_by_count":0,"area":null},{"id":"2601.10804","title":"BYOL: Bring Your Own Language Into LLMs","created":"2026-01-15","cited_by_count":0,"area":null},{"id":"2601.21759","title":"Influence Guided Sampling for Domain Adaptation of Text Retrievers","created":"2026-01-29","cited_by_count":0,"area":null},{"id":"2603.05506","title":"FaceCam: Portrait Video Camera Control via Scale-Aware Conditioning","created":"2026-03-05","cited_by_count":0,"area":null},{"id":"2603.27915","title":"FlashSign: Pose-Free Guidance for Efficient Sign Language Video Generation","created":"2026-03-30","cited_by_count":0,"area":null},{"id":"2604.20549","title":"Toward Cross-Lingual Quality Classifiers for Multilingual Pretraining Data Selection","created":"2026-04-22","cited_by_count":0,"area":null},{"id":"2604.27918","title":"Generate Your Talking Avatar from Video Reference","created":"2026-04-30","cited_by_count":0,"area":null},{"id":"2605.06859","title":"Knowledge Transfer Scaling Laws for 3D Medical Imaging","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2605.27767","title":"UniMaia: Steering Chess Policies with Language for Human-like Play","created":"2026-05-26","cited_by_count":0,"area":null},{"id":"2605.30133","title":"CorPipe at CRAC 2026: Empty Nodes and Cross-Lingual Transfer in Multilingual Coreference Resolution","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2606.21657","title":"Chehre: An Emoji-Prompted Dataset to Explore Perceptual Flexibility in Video Language Models","created":"2026-06-19","cited_by_count":0,"area":null},{"id":"2606.30514","title":"3D Scene-Adaptive Trajectory-Controllable Human Image Animation with Camera Movement","created":"2026-06-29","cited_by_count":0,"area":null},{"id":"2608.09355","title":"Alpha as an Efficiency Signal: Visibility-Routed RGBA Image-to-Video Generation","created":"2026-08-10","cited_by_count":0,"area":null},{"id":"2608.29890","title":"En-ViMedNER: An English-Vietnamese Parallel Biomedical Corpus with UMLS Semantic Type Annotations","created":"2026-08-30","cited_by_count":0,"area":null},{"id":"2609.33167","title":"FloodDiffusion 2: Efficient and Path Controllable Streaming Motion Generation","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2609.36503","title":"AVIO: Learning to Add and Remove Sounding Objects in Audiovisual Scenes","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.02180","title":"Generative Cinematographer: Composing Camera and Object Motion in 3D","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.05587","title":"Generating the Wild: Individual-Consistent Image-to-Video Generation for Wildlife","created":"2026-10-04","cited_by_count":0,"area":null}],"next_cursor":null}