{"total":50,"rows":[{"id":"2401.15077","title":"EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty","created":"2024-01-26","cited_by_count":578,"area":"lr"},{"id":"2404.02657","title":"Rethinking Kullback-Leibler Divergence in Knowledge Distillation for Large Language Models","created":"2024-04-03","cited_by_count":65,"area":"lr"},{"id":"2504.02807","title":"MegaMath: Pushing the Limits of Open Math Corpora","created":"2025-04-03","cited_by_count":51,"area":"lr"},{"id":"2405.10431","title":"Thinking Fair and Slow: On the Efficacy of Structured Prompts for Debiasing Language Models","created":"2024-05-16","cited_by_count":45,"area":"lr"},{"id":"2503.18866","title":"Reasoning to Learn from Latent Thoughts","created":"2025-03-24","cited_by_count":45,"area":"lr"},{"id":"2509.02350","title":"Implicit Reasoning in Large Language Models: A Comprehensive Survey","created":"2025-09-02","cited_by_count":43,"area":"lr"},{"id":"2408.13518","title":"Selective Preference Optimization via Token-Level Reward Function Estimation","created":"2024-08-24","cited_by_count":25,"area":"lr"},{"id":"2412.01282","title":"Align-KD: Distilling Cross-Modal Alignment Knowledge for Mobile Vision-Language Model Enhancement","created":"2024-12-02","cited_by_count":23,"area":"lr"},{"id":"2509.23184","title":"PonderLM-2: Pretraining LLM with Latent Thoughts in Continuous Space","created":"2025-09-27","cited_by_count":16,"area":"lr"},{"id":"2405.19737","title":"Beyond Imitation: Learning Key Reasoning Steps from Dual Chain-of-Thoughts in Reasoning Distillation","created":"2024-05-30","cited_by_count":14,"area":"lr"},{"id":"2410.08048","title":"VerifierQ: Enhancing LLM Test Time Compute with Q-Learning-based Verifiers","created":"2024-10-10","cited_by_count":14,"area":"lr"},{"id":"2502.00997","title":"MergeME: Model Merging Techniques for Homogeneous and Heterogeneous MoEs","created":"2025-02-03","cited_by_count":13,"area":"lr"},{"id":"2404.16333","title":"AI Coders Are Among Us: Rethinking Programming Language Grammar Towards Efficient Code Generation","created":"2024-04-25","cited_by_count":10,"area":"lr"},{"id":"2501.03265","title":"Cognitive Edge Computing: A Comprehensive Survey on Optimizing Large Models and AI Agents for Pervasive Deployment","created":"2025-01-04","cited_by_count":10,"area":"lr"},{"id":"2603.01914","title":"AdaPonderLM: Gated Pondering Language Models with Token-Wise Adaptive Depth","created":"2026-03-02","cited_by_count":10,"area":"lr"},{"id":"2410.09407","title":"CAMPHOR: Collaborative Agents for Multi-input Planning and High-Order Reasoning On Device","created":"2024-10-12","cited_by_count":6,"area":"lr"},{"id":"2507.06719","title":"A Neural Representation Framework with LLM-Driven Spatial Reasoning for Open-Vocabulary 3D Visual Grounding","created":"2025-07-09","cited_by_count":6,"area":"lr"},{"id":"2509.05602","title":"Mitigating Spurious Correlations Between Question and Answer via Chain-of-Thought Correctness Perception Distillation","created":"2025-09-06","cited_by_count":6,"area":"lr"},{"id":"2511.06256","title":"VLDrive: Vision-Augmented Lightweight MLLMs for Efficient Language-grounded Autonomous Driving","created":"2025-11-09","cited_by_count":6,"area":"lr"},{"id":"2512.00305","title":"ChartPoint: Guiding MLLMs with Grounding Reflection for Chart Reasoning","created":"2025-11-29","cited_by_count":6,"area":"lr"},{"id":"2601.06103","title":"The Impact of Post-training on Data Contamination","created":"2026-01-03","cited_by_count":5,"area":"lr"},{"id":"2502.16806","title":"CoT2Align: Cross-Chain of Thought Distillation via Optimal Transport Alignment for Language Models with Different Tokenizers","created":"2025-02-24","cited_by_count":4,"area":"lr"},{"id":"2511.05184","title":"Effectiveness of Chain-of-Thought in Distilling Reasoning Capability from Large Language Models","created":"2025-11-07","cited_by_count":4,"area":"lr"},{"id":"2512.22867","title":"MUSON: A Reasoning-oriented Multimodal Dataset for Socially Compliant Navigation in Urban Environments","created":"2025-12-28","cited_by_count":4,"area":"lr"},{"id":"2406.03725","title":"LLMEmbed: Rethinking Lightweight LLM's Genuine Function in Text Classification","created":"2024-06-06","cited_by_count":3,"area":"lr"},{"id":"2412.08347","title":"SmolTulu: Higher Learning Rate to Batch Size Ratios Can Lead to Better Reasoning in SLMs","created":"2024-12-11","cited_by_count":3,"area":"lr"},{"id":"2506.13404","title":"Effective Learning for Small Reasoning Models: An Empirical Study on 0.5B Reasoning LLMs","created":"2025-06-16","cited_by_count":3,"area":"lr"},{"id":"2604.15701","title":"Improving Reasoning Capabilities in Small Models through Mixture-of-Layers Distillation with Stepwise Attention on Key Information","created":"2026-04-17","cited_by_count":3,"area":"lr"},{"id":"2605.05227","title":"Rethinking Data Curation in LLM Training: Online Reweighting Offers Better Generalization than Offline Methods","created":"2026-04-19","cited_by_count":3,"area":"lr"},{"id":"2412.08393","title":"Learning to Reason via Self-Iterative Process Feedback for Small Language Models","created":"2024-12-11","cited_by_count":2,"area":"lr"},{"id":"2502.21309","title":"Reasoning is Periodicity? Improving Large Language Models Through Effective Periodicity Modeling","created":"2025-02-28","cited_by_count":2,"area":"lr"},{"id":"2504.15188","title":"Synergistic Weak-Strong Collaboration by Aligning Preferences","created":"2025-04-21","cited_by_count":2,"area":"lr"},{"id":"2505.19511","title":"Causal Distillation: Transferring Structured Explanations from Large to Compact Language Models","created":"2025-05-26","cited_by_count":2,"area":"lr"},{"id":"2506.01531","title":"STORM-BORN: A Challenging Mathematical Derivations Dataset Curated via a Human-in-the-Loop Multi-Agent Framework","created":"2025-06-02","cited_by_count":2,"area":"lr"},{"id":"2605.15044","title":"SpeakerLLM: A Speaker-Specialized Audio-LLM for Speaker Understanding and Verification Reasoning","created":"2026-05-14","cited_by_count":2,"area":"lr"},{"id":"2403.06400","title":"DivCon: Divide and Conquer for Complex Numerical and Spatial Reasoning in Text-to-Image Generation","created":"2024-03-11","cited_by_count":1,"area":"lr"},{"id":"2412.17052","title":"ViLBias: Detecting and Reasoning about Bias in Multimodal Content","created":"2024-12-22","cited_by_count":1,"area":"lr"},{"id":"2502.15120","title":"Unveiling Reasoning Thresholds in Language Models: Scaling, Fine-Tuning, and Interpretability through Attention Maps","created":"2025-02-21","cited_by_count":1,"area":"lr"},{"id":"2509.10744","title":"Automated MCQA Benchmarking at Scale: Evaluating Reasoning Traces as Retrieval Sources for Domain Adaptation of Small Language Models","created":"2025-09-12","cited_by_count":1,"area":"lr"},{"id":"2605.28919","title":"CosmicFish-HRM: Adaptive Reasoning via Hierarchical Recurrent Mechanisms in Compact Language Models","created":"2026-05-27","cited_by_count":1,"area":"lr"},{"id":"2606.17687","title":"SuCo: Sufficiency-guided Continuous Adaptive Reasoning","created":"2026-06-16","cited_by_count":1,"area":"lr"},{"id":"2608.08113","title":"Think Deep, Speak Once: Relit, A Recursive Latent Implicit Transformer Framework","created":"2026-08-08","cited_by_count":1,"area":"lr"},{"id":"2410.07062","title":"TinyEmo: Scaling down Emotional Reasoning via Metric Projection","created":"2024-10-09","cited_by_count":0,"area":"lr"},{"id":"2506.14158","title":"S$^4$C: Speculative Sampling with Syntactic and Semantic Coherence for Efficient Inference of Large Language Models","created":"2025-06-17","cited_by_count":0,"area":"lr"},{"id":"2509.20105","title":"PEPS: Quantum-Inspired Reinforcement Learning for Coherent Reasoning Traces in LLMs","created":"2025-09-24","cited_by_count":0,"area":"lr"},{"id":"2511.05820","title":"From Ranking to Reasoning: Explainable Web API Recommendation via Semantic Reasoning","created":"2025-11-08","cited_by_count":0,"area":"lr"},{"id":"2604.17574","title":"Beyond Fine-Tuning: In-Context Learning and Chain-of-Thought for Reasoned Distractor Generation","created":"2026-04-19","cited_by_count":0,"area":"lr"},{"id":"2605.12520","title":"BoostTaxo: Zero-Shot Taxonomy Induction via Boosting-Style Agentic Reasoning and Constraint-Aware Calibration","created":"2026-04-03","cited_by_count":0,"area":"lr"},{"id":"2608.14685","title":"Rethinking Reverse KL as Adaptive Entropy Distillation","created":"2026-08-05","cited_by_count":0,"area":"lr"},{"id":"2610.02066","title":"External Observers May See More Clearly: Cross-Model Span-Level Hallucination Detection in Large Language Models via Hidden State Probing","created":"2026-10-01","cited_by_count":0,"area":"lr"}],"next_cursor":null}