{"total":335,"rows":[{"id":"2503.20783","title":"Understanding R1-Zero-Like Training: A Critical Perspective","created":"2025-03-26","cited_by_count":1345,"area":"lr"},{"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":"2506.01844","title":"SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics","created":"2025-06-02","cited_by_count":530,"area":"mllm"},{"id":"2510.25741","title":"Scaling Latent Reasoning via Looped Language Models","created":"2025-10-29","cited_by_count":165,"area":"lr"},{"id":"2506.20512","title":"OctoThinker: Mid-training Incentivizes Reinforcement Learning Scaling","created":"2025-06-25","cited_by_count":113,"area":"lr"},{"id":"2504.03624","title":"Nemotron-H: A Family of Accurate and Efficient Hybrid Mamba-Transformer Models","created":"2025-04-04","cited_by_count":100,"area":"lr"},{"id":"2510.07077","title":"Vision-Language-Action Models for Robotics: A Review Towards Real-World Applications","created":"2025-10-08","cited_by_count":84,"area":"mllm"},{"id":"2507.10532","title":"Reasoning or Memorization? Unreliable Results of Reinforcement Learning Due to Data Contamination","created":"2025-07-14","cited_by_count":82,"area":"lr"},{"id":"2504.01017","title":"Scaling Language-Free Visual Representation Learning","created":"2025-04-01","cited_by_count":66,"area":null},{"id":"2512.13607","title":"Nemotron-Cascade: Scaling Cascaded Reinforcement Learning for General-Purpose Reasoning Models","created":"2025-12-15","cited_by_count":48,"area":"lr"},{"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":"2511.08923","title":"TiDAR: Think in Diffusion, Talk in Autoregression","created":"2025-11-12","cited_by_count":37,"area":"lr"},{"id":"2512.10858","title":"Scaling Behavior of Discrete Diffusion Language Models","created":"2025-12-11","cited_by_count":35,"area":"diffusion"},{"id":"2601.22153","title":"DynamicVLA: A Vision-Language-Action Model for Dynamic Object Manipulation","created":"2026-01-29","cited_by_count":34,"area":"vla"},{"id":"2511.05963","title":"Next-Latent Prediction Transformers Learn Compact World Models","created":"2025-11-08","cited_by_count":31,"area":"wm"},{"id":"2505.10475","title":"Parallel Scaling Law for Language Models","created":"2025-05-15","cited_by_count":30,"area":"lr"},{"id":"2503.15621","title":"LLaVA-MORE: A Comparative Study of LLMs and Visual Backbones for Enhanced Visual Instruction Tuning","created":"2025-03-19","cited_by_count":28,"area":"mllm"},{"id":"2503.08540","title":"Mellow: a small audio language model for reasoning","created":"2025-03-11","cited_by_count":27,"area":"lr"},{"id":"2502.07864","title":"TransMLA: Multi-Head Latent Attention Is All You Need","created":"2025-02-11","cited_by_count":23,"area":"inference"},{"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":"2509.11963","title":"ToolRM: Outcome Reward Models for Tool-Calling Large Language Models","created":"2025-09-15","cited_by_count":17,"area":"lr"},{"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":"2510.17206","title":"Soft-Masked Diffusion Language Models","created":"2025-10-20","cited_by_count":16,"area":"diffusion"},{"id":"2505.12781","title":"A Token is Worth over 1,000 Tokens: Efficient Knowledge Distillation through Low-Rank Clone","created":"2025-05-19","cited_by_count":15,"area":"distill"},{"id":"2507.10616","title":"Scalpel vs. Hammer: GRPO Amplifies Existing Capabilities, SFT Replaces Them","created":"2025-07-13","cited_by_count":15,"area":"lr"},{"id":"2502.15654","title":"Machine-generated text detection prevents language model collapse","created":"2025-02-21","cited_by_count":14,"area":"synth"},{"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":"2602.22661","title":"dLLM: Simple Diffusion Language Modeling","created":"2026-02-26","cited_by_count":14,"area":"diffusion"},{"id":"2504.04718","title":"T1: Tool-integrated Verification for Test-time Compute Scaling in Small Language Models","created":"2025-04-07","cited_by_count":13,"area":"lr"},{"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":"2504.07825","title":"Who Benchmarks the Benchmarks? Towards Comprehensive Evaluation of Commonsense Reasoning Benchmarks","created":"2025-04-10","cited_by_count":11,"area":"lr"},{"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":"2507.08799","title":"KV Cache Steering for Controlling Frozen LLMs","created":"2025-07-11","cited_by_count":11,"area":"inference"},{"id":"2602.17004","title":"Arcee Trinity Large Technical Report","created":"2026-02-19","cited_by_count":11,"area":"moe"},{"id":"2602.23225","title":"Why Diffusion Language Models Struggle with Truly Parallel (Non-Autoregressive) Decoding?","created":"2026-02-26","cited_by_count":11,"area":"lr"},{"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":"2505.13111","title":"Why Knowledge Distillation Works in Generative Models: A Minimal Working Explanation","created":"2025-05-19","cited_by_count":9,"area":"distill"},{"id":"2505.16602","title":"MEgoHand: Multimodal Egocentric Hand-Object Interaction Motion Generation","created":"2025-05-22","cited_by_count":9,"area":null},{"id":"2505.24550","title":"A*-Thought: Efficient Reasoning via Bidirectional Compression for Low-Resource Settings","created":"2025-05-30","cited_by_count":9,"area":"lr"},{"id":"2506.13331","title":"Mixture of Cognitive Reasoners: Modular Reasoning with Brain-Like Specialization","created":"2025-06-16","cited_by_count":9,"area":"lr"},{"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":"2509.23873","title":"Winning the Pruning Gamble: A Unified Approach to Joint Sample and Token Pruning for Efficient Supervised Fine-Tuning","created":"2025-09-28","cited_by_count":8,"area":"alignment"},{"id":"2601.15793","title":"HumanLLM: Towards Personalized Understanding and Simulation of Human Nature","created":"2026-01-22","cited_by_count":8,"area":null},{"id":"2602.20330","title":"Circuit Tracing in Vision-Language Models: Understanding the Internal Mechanisms of Multimodal Thinking","created":"2026-02-23","cited_by_count":8,"area":"lr"},{"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":"2509.24945","title":"MobileLLM-R1: Exploring the Limits of Sub-Billion Language Model Reasoners with Open Training Recipes","created":"2025-09-29","cited_by_count":7,"area":"lr"},{"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":"2603.01469","title":"Mean-Flow based One-Step Vision-Language-Action","created":"2026-03-02","cited_by_count":7,"area":"vla"},{"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":"2506.09967","title":"Resa: Transparent Reasoning Models via SAEs","created":"2025-06-11","cited_by_count":6,"area":"lr"},{"id":"2509.14769","title":"Frame Sampling Strategies Matter: A Benchmark for small vision language models","created":"2025-09-18","cited_by_count":6,"area":"mllm"},{"id":"2510.02768","title":"A Granular Study of Safety Pretraining under Model Abliteration","created":"2025-10-03","cited_by_count":6,"area":null},{"id":"2510.05077","title":"Slm-mux: Orchestrating small language models for reasoning","created":"2025-10-06","cited_by_count":6,"area":"lr"},{"id":"2510.23642","title":"VisCoder2: Building Multi-Language Visualization Coding Agents","created":"2025-10-24","cited_by_count":6,"area":"agents"},{"id":"2512.16602","title":"Refusal Steering: Fine-grained Control over LLM Refusal Behaviour for Sensitive Topics","created":"2025-12-18","cited_by_count":6,"area":"safety"},{"id":"2502.12974","title":"Learning Refined Document Representations for Dense Retrieval via Deliberate Thinking","created":"2025-02-18","cited_by_count":5,"area":"lr"},{"id":"2505.07293","title":"AttentionInfluence: Adopting Attention Head Influence for Weak-to-Strong Pretraining Data Selection","created":"2025-05-12","cited_by_count":5,"area":"lr"},{"id":"2507.08473","title":"Evaluating SAE interpretability without explanations","created":"2025-07-11","cited_by_count":5,"area":"mechinterp"},{"id":"2507.20984","title":"SmallThinker: A Family of Efficient Large Language Models Natively Trained for Local Deployment","created":"2025-07-28","cited_by_count":5,"area":"lr"},{"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":"2509.21499","title":"On Code-Induced Reasoning in LLMs","created":"2025-09-25","cited_by_count":5,"area":"lr"},{"id":"2510.02066","title":"Chain-of-Thought Reasoning in Streaming Full-Duplex End-to-End Spoken Dialogue Systems","created":"2025-10-02","cited_by_count":5,"area":"lr"},{"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":"2502.11284","title":"Balancing the Budget: Understanding Trade-offs Between Supervised and Preference-Based Finetuning","created":"2025-02-16","cited_by_count":4,"area":"alignment"},{"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":"2510.00219","title":"Thoughtbubbles: an Unsupervised Method for Parallel Thinking in Latent Space","created":"2025-09-30","cited_by_count":4,"area":"lr"},{"id":"2601.16046","title":"DextER: Language-driven Dexterous Grasp Generation with Embodied Reasoning","created":"2026-01-22","cited_by_count":4,"area":"lr"},{"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":"2602.19548","title":"Beyond a Single Extractor: Re-thinking HTML-to-Text Extraction for LLM Pretraining","created":"2026-02-23","cited_by_count":4,"area":"lr"},{"id":"2603.00054","title":"Expert Divergence Learning for MoE-based Language Models","created":"2026-02-10","cited_by_count":4,"area":"moe"},{"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}],"next_cursor":"100"}