{"total":31,"rows":[{"id":"2512.23808","title":"MiMo-Audio: Audio Language Models are Few-Shot Learners","created":"2025-12-29","cited_by_count":65,"area":null},{"id":"2506.07900","title":"MiniCPM4: Ultra-Efficient LLMs on End Devices","created":"2025-06-09","cited_by_count":52,"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":"2505.17826","title":"Trinity-RFT: A General-Purpose and Unified Framework for Reinforcement Fine-Tuning of Large Language Models","created":"2025-05-23","cited_by_count":19,"area":null},{"id":"2510.14751","title":"Beyond Multi-Token Prediction: Pretraining LLMs with Future Summaries","created":"2025-10-16","cited_by_count":15,"area":null},{"id":"2512.17495","title":"GroundingME: Exposing the Visual Grounding Gap in MLLMs through Multi-Dimensional Evaluation","created":"2025-12-19","cited_by_count":9,"area":null},{"id":"2512.03575","title":"UniComp: Rethinking Video Compression Through Informational Uniqueness","created":"2025-12-03","cited_by_count":7,"area":null},{"id":"2606.14502","title":"From Chatbot to Digital Colleague: The Paradigm Shift Toward Persistent Autonomous AI","created":"2026-06-12","cited_by_count":6,"area":null},{"id":"2605.02944","title":"Exploring Pass-Rate Reward in Reinforcement Learning for Code Generation","created":"2026-05-01","cited_by_count":4,"area":null},{"id":"2605.09920","title":"Verifier-Free RL for LLMs via Intrinsic Gradient-Norm Reward","created":"2026-05-11","cited_by_count":3,"area":null},{"id":"2605.27378","title":"OralAgent: Integrating Reasoning, Tools, and Knowledge for Interactive Dental Image Analysis","created":"2026-04-09","cited_by_count":3,"area":null},{"id":"2606.00750","title":"I-WebGenBench : Evaluating Interactivity in LLM-Generated Scientific Web Applications","created":"2026-05-30","cited_by_count":3,"area":null},{"id":"2607.24593","title":"PIVOT: Efficient Query-Group Indexing for Token-Level Sparse Attention","created":"2026-07-27","cited_by_count":3,"area":null},{"id":"2510.23477","title":"MMTutorBench: The First Multimodal Benchmark for AI Math Tutoring","created":"2025-10-27","cited_by_count":2,"area":null},{"id":"2511.06057","title":"MIND Your Reasoning: A Meta-Cognitive Intuitive-Reflective Network for Dual-Reasoning in Multimodal Stance Detection","created":"2025-11-08","cited_by_count":1,"area":null},{"id":"2606.04517","title":"Treat Traffic Like Trees: A Semantic-Preserving Hierarchical Graph-Based Expert Framework for Encrypted Traffic Analysis","created":"2026-06-03","cited_by_count":1,"area":null},{"id":"2609.32248","title":"Anytime-Valid LLM Leaderboards via Benchmark-weighted and Block-Factorized e-Processes","created":"2026-09-26","cited_by_count":1,"area":null},{"id":"2511.12130","title":"PRISM of Opinions: A Persona-Reasoned Multimodal Framework for User-centric Conversational Stance Detection","created":"2025-11-15","cited_by_count":0,"area":null},{"id":"2601.07423","title":"SAD: A Large-Scale Strategic Argumentative Dialogue Dataset","created":"2026-01-12","cited_by_count":0,"area":null},{"id":"2601.21744","title":"Temporal Guidance for Large Language Models","created":"2026-01-29","cited_by_count":0,"area":null},{"id":"2602.22145","title":"When AI Writes, Whose Voice Remains? Quantifying Cultural Marker Erasure Across World English Varieties in Large Language Models","created":"2026-02-25","cited_by_count":0,"area":null},{"id":"2604.22050","title":"LayerBoost: Layer-Aware Attention Reduction for Efficient LLMs","created":"2026-04-23","cited_by_count":0,"area":null},{"id":"2607.10251","title":"Behavioural Signatures of Risk-Sensitive Decision-Making in Large Language Models","created":"2026-07-11","cited_by_count":0,"area":null},{"id":"2608.00434","title":"AdaMTP: An Adaptive Training Paradigm for Multi-Token Prediction","created":"2026-08-01","cited_by_count":0,"area":null},{"id":"2609.08755","title":"Kairos: A Dataset for Fine-Grained Video-Language Modeling over Space, Time, and Dynamics","created":"2026-09-08","cited_by_count":0,"area":null},{"id":"2609.09081","title":"Everything in Moderation: Per-Domain Coverage Optima and Alignment-Resistant Domain Gaps in Multi-Domain Mid-Training","created":"2026-09-08","cited_by_count":0,"area":null},{"id":"2609.16648","title":"GrowMTP: Can RL Grow Its Own Draft Head?","created":"2026-09-15","cited_by_count":0,"area":null},{"id":"2609.22146","title":"GRRR: The Geometry of Reshaping, Rotation, and Routing in Decoder LLM post-training","created":"2026-08-26","cited_by_count":0,"area":null},{"id":"2609.36659","title":"On-Policy Parameter Update Direction Underlies Generalization in LLM Post-Training","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.39661","title":"The Evolution of Attention in Large Language Models: Mechanisms, Trade-offs, and Emerging Trends","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.00888","title":"Match the Distribution, Not the Compute: Post-Training Multi-Token Prediction Heads","created":"2026-10-01","cited_by_count":0,"area":null}],"next_cursor":null}