{"total":194,"rows":[{"id":"2503.14734","title":"GR00T N1: An Open Foundation Model for Generalist Humanoid Robots","created":"2025-03-18","cited_by_count":1225,"area":null},{"id":"2504.01017","title":"Scaling Language-Free Visual Representation Learning","created":"2025-04-01","cited_by_count":66,"area":null},{"id":"2508.15884","title":"Jet-Nemotron: Efficient Language Model with Post Neural Architecture Search","created":"2025-08-21","cited_by_count":41,"area":null},{"id":"2504.12285","title":"BitNet b1.58 2B4T Technical Report","created":"2025-04-16","cited_by_count":38,"area":null},{"id":"2507.11412","title":"Seq vs Seq: An Open Suite of Paired Encoders and Decoders","created":"2025-07-15","cited_by_count":38,"area":null},{"id":"2502.19249","title":"Between Circuits and Chomsky: Pre-pretraining on Formal Languages Imparts Linguistic Biases","created":"2025-02-26","cited_by_count":37,"area":null},{"id":"2504.14693","title":"Video-MMLU: A Massive Multi-Discipline Lecture Understanding Benchmark","created":"2025-04-20","cited_by_count":37,"area":null},{"id":"2510.06826","title":"Mid-Training of Large Language Models: A Survey","created":"2025-10-08","cited_by_count":21,"area":null},{"id":"2601.22813","title":"Quartet II: Accurate LLM Pre-Training in NVFP4 by Improved Unbiased Gradient Estimation","created":"2026-01-30","cited_by_count":21,"area":null},{"id":"2605.02087","title":"Model Spec Midtraining: Improving How Alignment Training Generalizes","created":"2026-05-03","cited_by_count":20,"area":null},{"id":"2505.04601","title":"OpenVision: A Fully-Open, Cost-Effective Family of Advanced Vision Encoders for Multimodal Learning","created":"2025-05-07","cited_by_count":16,"area":null},{"id":"2504.02398","title":"Scaling Analysis of Interleaved Speech-Text Language Models","created":"2025-04-03","cited_by_count":14,"area":null},{"id":"2505.13772","title":"Krikri: Advancing Open Large Language Models for Greek","created":"2025-05-19","cited_by_count":14,"area":null},{"id":"2511.18903","title":"How Learning Rate Decay Wastes Your Best Data in Curriculum-Based LLM Pretraining","created":"2025-11-24","cited_by_count":14,"area":null},{"id":"2505.18383","title":"NileChat: Towards Linguistically Diverse and Culturally Aware LLMs for Local Communities","created":"2025-05-23","cited_by_count":13,"area":null},{"id":"2506.19697","title":"Outlier-Safe Pre-Training for Robust 4-Bit Quantization of Large Language Models","created":"2025-06-24","cited_by_count":13,"area":null},{"id":"2601.21571","title":"Shaping capabilities with token-level data filtering","created":"2026-01-29","cited_by_count":13,"area":null},{"id":"2502.15814","title":"Slamming: Training a Speech Language Model on One GPU in a Day","created":"2025-02-19","cited_by_count":12,"area":null},{"id":"2506.02961","title":"FlowerTune: A Cross-Domain Benchmark for Federated Fine-Tuning of Large Language Models","created":"2025-06-03","cited_by_count":11,"area":null},{"id":"2510.03680","title":"Rainbow Padding: Mitigating Early Termination in Instruction-Tuned Diffusion LLMs","created":"2025-10-04","cited_by_count":10,"area":null},{"id":"2502.11187","title":"TituLLMs: A Family of Bangla LLMs with Comprehensive Benchmarking","created":"2025-02-16","cited_by_count":9,"area":null},{"id":"2505.12534","title":"ChemPile: A 250GB Diverse and Curated Dataset for Chemical Foundation Models","created":"2025-05-18","cited_by_count":9,"area":null},{"id":"2505.16602","title":"MEgoHand: Multimodal Egocentric Hand-Object Interaction Motion Generation","created":"2025-05-22","cited_by_count":9,"area":null},{"id":"2506.17611","title":"OpusLM: A Family of Open Unified Speech Language Models","created":"2025-06-21","cited_by_count":9,"area":null},{"id":"2509.16989","title":"PTQTP: Post-Training Quantization to Trit-Planes for Large Language Models","created":"2025-09-21","cited_by_count":9,"area":null},{"id":"2509.25087","title":"Scaling with Collapse: Efficient and Predictable Training of LLM Families","created":"2025-09-29","cited_by_count":9,"area":null},{"id":"2603.10145","title":"Lost in Backpropagation: The LM Head is a Gradient Bottleneck","created":"2026-03-10","cited_by_count":9,"area":null},{"id":"2505.22785","title":"Navigating the Latent Space Dynamics of Neural Models","created":"2025-05-28","cited_by_count":8,"area":null},{"id":"2601.15793","title":"HumanLLM: Towards Personalized Understanding and Simulation of Human Nature","created":"2026-01-22","cited_by_count":8,"area":null},{"id":"2506.14123","title":"Sampling from Your Language Model One Byte at a Time","created":"2025-06-17","cited_by_count":7,"area":null},{"id":"2507.08567","title":"AbbIE: Autoregressive Block-Based Iterative Encoder for Efficient Sequence Modeling","created":"2025-07-11","cited_by_count":7,"area":null},{"id":"2510.21909","title":"Explaining and Mitigating Crosslingual Tokenizer Inequities","created":"2025-10-24","cited_by_count":7,"area":null},{"id":"2511.06086","title":"MuonAll: Muon Variant for Efficient Finetuning of Large Language Models","created":"2025-11-08","cited_by_count":7,"area":null},{"id":"2602.07824","title":"Data Darwinism Part I: Unlocking the Value of Scientific Data for Pre-training","created":"2026-02-08","cited_by_count":7,"area":null},{"id":"2602.09823","title":"Covo-Audio Technical Report","created":"2026-02-10","cited_by_count":7,"area":null},{"id":"2602.16490","title":"From Growing to Looping: A Unified View of Iterative Computation in LLMs","created":"2026-02-18","cited_by_count":7,"area":null},{"id":"2603.11021","title":"Leech Lattice Vector Quantization for Efficient LLM Compression","created":"2026-03-11","cited_by_count":7,"area":null},{"id":"2502.18886","title":"On Pruning State-Space LLMs","created":"2025-02-26","cited_by_count":6,"area":null},{"id":"2510.02768","title":"A Granular Study of Safety Pretraining under Model Abliteration","created":"2025-10-03","cited_by_count":6,"area":null},{"id":"2509.07370","title":"PersonaFuse: A Personality Activation-Driven Framework for Enhancing Human-LLM Interactions","created":"2025-09-09","cited_by_count":5,"area":null},{"id":"2509.14275","title":"FedMentor: Domain-Aware Differential Privacy for Heterogeneous Federated LLMs in Mental Health","created":"2025-09-16","cited_by_count":5,"area":null},{"id":"2510.06126","title":"lm-Meter: Unveiling Runtime Inference Latency for On-Device Language Models","created":"2025-10-07","cited_by_count":5,"area":null},{"id":"2604.07569","title":"Learning is Forgetting: LLM Training As Lossy Compression","created":"2026-04-08","cited_by_count":5,"area":null},{"id":"2505.22549","title":"DES-LOC: Desynced Low Communication Adaptive Optimizers for Training Foundation Models","created":"2025-05-28","cited_by_count":4,"area":null},{"id":"2508.02076","title":"Everyone Contributes! Incentivizing Strategic Cooperation in Multi-LLM Systems via Sequential Public Goods Games","created":"2025-08-04","cited_by_count":4,"area":null},{"id":"2509.22935","title":"Compute-Optimal Quantization-Aware Training","created":"2025-09-26","cited_by_count":4,"area":null},{"id":"2602.09003","title":"Data Science and Technology Towards AGI Part I: Tiered Data Management","created":"2026-02-09","cited_by_count":4,"area":null},{"id":"2602.14696","title":"A Critical Look at Targeted Instruction Selection: Disentangling What Matters (and What Doesn't)","created":"2026-02-16","cited_by_count":4,"area":null},{"id":"2605.12705","title":"Early Data Exposure Improves Robustness to Subsequent Fine-Tuning","created":"2026-05-12","cited_by_count":4,"area":null},{"id":"2605.23158","title":"What Does the Server See? Understanding Privacy Leakage from Large Language Models in Split Inference","created":"2026-05-22","cited_by_count":4,"area":null},{"id":"2605.31371","title":"Softsign: Smooth Sign in Your Optimizer For Better Parameter Heterogeneity Handling","created":"2026-05-29","cited_by_count":4,"area":null},{"id":"2502.19790","title":"Mixtera: A Data Plane for Foundation Model Training","created":"2025-02-27","cited_by_count":3,"area":null},{"id":"2506.16552","title":"Revela: Dense Retriever Learning via Language Modeling","created":"2025-06-19","cited_by_count":3,"area":null},{"id":"2508.19228","title":"Predicting the Order of Upcoming Tokens Improves Language Modeling","created":"2025-08-26","cited_by_count":3,"area":null},{"id":"2510.20860","title":"Data-Centric Lessons To Improve Speech-Language Pretraining","created":"2025-10-22","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":"2602.03484","title":"Preferences for Idiomatic Language are Acquired Slowly -- and Forgotten Quickly: A Case Study on Swedish","created":"2026-02-03","cited_by_count":3,"area":null},{"id":"2604.08764","title":"Revisiting Anisotropy in Language Transformers: The Geometry of Learning Dynamics","created":"2026-04-09","cited_by_count":3,"area":null},{"id":"2606.04115","title":"dMX: Differentiable Mixed-Precision Assignment for Low-Precision Floating-Point Formats","created":"2026-06-02","cited_by_count":3,"area":null},{"id":"2502.05159","title":"A Lightweight Method to Disrupt Memorized Sequences in LLM","created":"2025-02-07","cited_by_count":2,"area":null},{"id":"2505.12592","title":"PromptPrism: A Linguistically-Inspired Taxonomy for Prompts","created":"2025-05-19","cited_by_count":2,"area":null},{"id":"2505.16661","title":"A Japanese Language Model and Three New Evaluation Benchmarks for Pharmaceutical NLP","created":"2025-05-22","cited_by_count":2,"area":null},{"id":"2507.00999","title":"La Leaderboard: A Large Language Model Leaderboard for Spanish Varieties and Languages of Spain and Latin America","created":"2025-07-01","cited_by_count":2,"area":null},{"id":"2509.25664","title":"QFrBLiMP: a Quebec-French Benchmark of Linguistic Minimal Pairs","created":"2025-09-30","cited_by_count":2,"area":null},{"id":"2510.05026","title":"Idiom Understanding as a Tool to Measure the Dialect Gap","created":"2025-10-06","cited_by_count":2,"area":null},{"id":"2510.05046","title":"COLE: a Comprehensive Benchmark for French Language Understanding Evaluation","created":"2025-10-06","cited_by_count":2,"area":null},{"id":"2510.05361","title":"MT-DAO: Multi-Timescale Distributed Adaptive Optimizers with Local Updates","created":"2025-10-06","cited_by_count":2,"area":null},{"id":"2512.07612","title":"PCMind-2.1-Kaiyuan-2B Technical Report","created":"2025-12-08","cited_by_count":2,"area":null},{"id":"2602.00747","title":"Decouple Searching from Training: Scaling Data Mixing via Model Merging for Large Language Model Pre-training","created":"2026-01-31","cited_by_count":2,"area":null},{"id":"2602.05164","title":"Position: Capability Control Should be a Separate Goal From Alignment","created":"2026-02-05","cited_by_count":2,"area":null},{"id":"2602.10300","title":"Configuration-to-Performance Scaling Law with Neural Ansatz","created":"2026-02-10","cited_by_count":2,"area":null},{"id":"2602.14896","title":"Algorithmic Simplification of Neural Networks with Mosaic-of-Motifs","created":"2026-02-16","cited_by_count":2,"area":null},{"id":"2603.26539","title":"How Open Must Language Models be to Enable Reliable Scientific Inference?","created":"2026-03-27","cited_by_count":2,"area":null},{"id":"2605.06546","title":"Efficient Pre-Training with Token Superposition","created":"2026-05-07","cited_by_count":2,"area":null},{"id":"2605.09635","title":"K12-KGraph: A Curriculum-Aligned Knowledge Graph for Benchmarking and Training Educational LLMs","created":"2026-05-10","cited_by_count":2,"area":null},{"id":"2605.20706","title":"Llamas on the Web: Memory-Efficient, Performance-Portable, and Multi-Precision LLM Inference with WebGPU","created":"2026-05-20","cited_by_count":2,"area":null},{"id":"2607.01538","title":"Can Language Models Actually Retrieve In-Context? Drowning in Documents at Million Token Scale","created":"2026-07-01","cited_by_count":2,"area":null},{"id":"2607.14427","title":"Per-Token Fixed-Point Convergence in Depth-Recurrent Transformers","created":"2026-07-15","cited_by_count":2,"area":null},{"id":"2608.01672","title":"Learning What to Remember: Test-Time Training via Context Distillation","created":"2026-08-03","cited_by_count":2,"area":null},{"id":"2608.11981","title":"Benchmarking Trustworthiness of SLMs: Pre-trained vs. Compressed","created":"2026-08-12","cited_by_count":2,"area":null},{"id":"2609.25081","title":"ufakzeka-1: Building and Evaluating a 151M-Parameter Turkish Language Model from Scratch","created":"2026-09-18","cited_by_count":2,"area":null},{"id":"2504.02521","title":"UNDO: Understanding Distillation as Optimization","created":"2025-04-03","cited_by_count":1,"area":null},{"id":"2505.09851","title":"ZENN: A Thermodynamics-Inspired Computational Framework for Heterogeneous Data-Driven Modeling","created":"2025-05-14","cited_by_count":1,"area":null},{"id":"2505.10083","title":"ChronoSteer: Bridging Large Language Model and Time Series Foundation Model via Synthetic Cross-Modal Alignment Dataset","created":"2025-05-15","cited_by_count":1,"area":null},{"id":"2506.07424","title":"Plug-in and Fine-tuning: Bridging the Gap between Small Language Models and Large Language Models","created":"2025-06-09","cited_by_count":1,"area":null},{"id":"2507.16922","title":"A Unifying Scheme for Extractive Content Selection Tasks","created":"2025-07-22","cited_by_count":1,"area":null},{"id":"2510.06235","title":"Stacked Regression using Off-the-shelf, Stimulus-tuned and Fine-tuned Neural Networks for Predicting fMRI Brain Responses to Movies (Algonauts 2025 Report)","created":"2025-10-02","cited_by_count":1,"area":null},{"id":"2510.07227","title":"Where to Begin: Efficient Pretraining via Subnetwork Selection and Distillation","created":"2025-10-08","cited_by_count":1,"area":null},{"id":"2510.25784","title":"zFLoRA: Zero-Latency Fused Low-Rank Adapters","created":"2025-10-28","cited_by_count":1,"area":null},{"id":"2511.10618","title":"Know Your Limits: Entropy Estimation Modeling for Compression and Generalization","created":"2025-11-13","cited_by_count":1,"area":null},{"id":"2512.04847","title":"Language Models as Semantic Teachers: Post-Training Alignment for Medical Audio Understanding","created":"2025-12-04","cited_by_count":1,"area":null},{"id":"2512.11192","title":"SciLaD: A Large-Scale, Transparent, Reproducible Dataset for Natural Scientific Language Processing","created":"2025-12-12","cited_by_count":1,"area":null},{"id":"2602.04396","title":"LoRDO: Distributed Low-Rank Optimization with Infrequent Communication","created":"2026-02-04","cited_by_count":1,"area":null},{"id":"2602.05393","title":"Late-to-Early Training: LET LLMs Learn Earlier, So Faster and Better","created":"2026-02-05","cited_by_count":1,"area":null},{"id":"2602.15563","title":"1-Bit Wonder: Improving QAT Performance in the Low-Bit Regime through K-Means Quantization","created":"2026-02-17","cited_by_count":1,"area":null},{"id":"2603.16430","title":"EngGPT2: Sovereign, Efficient and Open Intelligence","created":"2026-03-17","cited_by_count":1,"area":null},{"id":"2603.24929","title":"LogitScope: A Framework for Analyzing LLM Uncertainty Through Information Metrics","created":"2026-03-26","cited_by_count":1,"area":null},{"id":"2604.11050","title":"Shared Emotion Geometry Across Small Language Models: A Cross-Architecture Study of Representation, Behavior, and Methodological Confounds","created":"2026-04-13","cited_by_count":1,"area":null},{"id":"2605.02038","title":"What Single-Prompt Accuracy Misses: A Multi-Variant Reliability Audit of Language Models","created":"2026-05-03","cited_by_count":1,"area":null},{"id":"2605.17842","title":"SNLP: Layer-Parallel Inference via Structured Newton Corrections","created":"2026-05-18","cited_by_count":1,"area":null}],"next_cursor":"100"}