{"total":61,"rows":[{"id":"2503.16419","title":"Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models","created":"2025-03-20","cited_by_count":464,"area":"lr"},{"id":"2412.14446","title":"VLM-AD: End-to-End Autonomous Driving through Vision-Language Model Supervision","created":"2024-12-19","cited_by_count":86,"area":"lr"},{"id":"2505.16984","title":"UFT: Unifying Supervised and Reinforcement Fine-Tuning","created":"2025-05-22","cited_by_count":59,"area":"lr"},{"id":"2502.07601","title":"Towards Zero-Shot Anomaly Detection and Reasoning with Multimodal Large Language Models","created":"2025-02-11","cited_by_count":54,"area":"lr"},{"id":"2312.02179","title":"Training Chain-of-Thought via Latent-Variable Inference","created":"2023-11-28","cited_by_count":47,"area":"lr"},{"id":"2409.10502","title":"Causal Language Modeling Can Elicit Search and Reasoning Capabilities on Logic Puzzles","created":"2024-09-16","cited_by_count":38,"area":"lr"},{"id":"2507.12856","title":"Supervised Fine Tuning on Curated Data is Reinforcement Learning (and can be improved)","created":"2025-07-17","cited_by_count":38,"area":"lr"},{"id":"2402.01591","title":"BAT: Learning to Reason about Spatial Sounds with Large Language Models","created":"2024-02-02","cited_by_count":36,"area":"lr"},{"id":"2505.15154","title":"Prolonged Reasoning Is Not All You Need: Certainty-Based Adaptive Routing for Efficient LLM/MLLM Reasoning","created":"2025-05-21","cited_by_count":35,"area":"lr"},{"id":"2402.05472","title":"Question Aware Vision Transformer for Multimodal Reasoning","created":"2024-02-08","cited_by_count":32,"area":"lr"},{"id":"2405.01533","title":"OmniDrive: A Holistic Vision-Language Dataset for Autonomous Driving with Counterfactual Reasoning","created":"2024-05-02","cited_by_count":27,"area":"lr"},{"id":"2412.17256","title":"B-STaR: Monitoring and Balancing Exploration and Exploitation in Self-Taught Reasoners","created":"2024-12-23","cited_by_count":26,"area":"lr"},{"id":"2412.20631","title":"Slow Perception: Let's Perceive Geometric Figures Step-by-step","created":"2024-12-30","cited_by_count":24,"area":"lr"},{"id":"2409.13035","title":"TACO-RL: Task Aware Prompt Compression Optimization with Reinforcement Learning","created":"2024-09-19","cited_by_count":22,"area":"lr"},{"id":"2510.06917","title":"SHANKS: Simultaneous Hearing and Thinking for Spoken Language Models","created":"2025-10-08","cited_by_count":19,"area":"lr"},{"id":"2411.18013","title":"FASIONAD : FAst and Slow FusION Thinking Systems for Human-Like Autonomous Driving with Adaptive Feedback","created":"2024-11-27","cited_by_count":18,"area":"lr"},{"id":"2309.08859","title":"Rethinking Learning Rate Tuning in the Era of Large Language Models","created":"2023-09-16","cited_by_count":16,"area":"lr"},{"id":"2502.19587","title":"NeoBERT: A Next-Generation BERT","created":"2025-02-26","cited_by_count":16,"area":"lr"},{"id":"2402.02791","title":"PanGu-$\\pi$ Pro:Rethinking Optimization and Architecture for Tiny Language Models","created":"2024-02-05","cited_by_count":14,"area":"lr"},{"id":"2512.02013","title":"ManualVLA: A Unified VLA Model for Chain-of-Thought Manual Generation and Robotic Manipulation","created":"2025-12-01","cited_by_count":14,"area":"lr"},{"id":"2501.14002","title":"Advancing Mathematical Reasoning in Language Models: The Impact of Problem-Solving Data, Data Synthesis Methods, and Training Stages","created":"2025-01-23","cited_by_count":13,"area":"lr"},{"id":"2402.16844","title":"Think Big, Generate Quick: LLM-to-SLM for Fast Autoregressive Decoding","created":"2024-02-26","cited_by_count":11,"area":"lr"},{"id":"2505.17923","title":"Language models can learn implicit multi-hop reasoning, but only if they have lots of training data","created":"2025-05-23","cited_by_count":11,"area":"lr"},{"id":"2512.22939","title":"ColaVLA: Leveraging Cognitive Latent Reasoning for Hierarchical Parallel Trajectory Planning in Autonomous Driving","created":"2025-12-28","cited_by_count":11,"area":"lr"},{"id":"2509.26140","title":"OWL: Geometry-Aware Spatial Reasoning for Audio Large Language Models","created":"2025-09-30","cited_by_count":10,"area":"lr"},{"id":"2505.20325","title":"Guided by Gut: Efficient Test-Time Scaling with Reinforced Intrinsic Confidence","created":"2025-05-23","cited_by_count":8,"area":"lr"},{"id":"2509.24299","title":"SVGThinker: Instruction-Aligned and Reasoning-Driven Text-to-SVG Generation","created":"2025-09-29","cited_by_count":8,"area":"lr"},{"id":"2403.15245","title":"Reasoning-Enhanced Object-Centric Learning for Videos","created":"2024-03-22","cited_by_count":7,"area":"lr"},{"id":"2508.06533","title":"The Art of Breaking Words: Rethinking Multilingual Tokenizer Design","created":"2025-08-03","cited_by_count":6,"area":"lr"},{"id":"2601.22582","title":"MC-GRPO: Median-Centered Group Relative Policy Optimization for Small-Rollout Reinforcement Learning","created":"2026-01-30","cited_by_count":6,"area":"lr"},{"id":"2407.04212","title":"Smart Vision-Language Reasoners","created":"2024-07-05","cited_by_count":5,"area":"lr"},{"id":"2505.12744","title":"Incentivizing Multimodal Reasoning in Large Models for Direct Robot Manipulation","created":"2025-05-19","cited_by_count":5,"area":"lr"},{"id":"2604.14568","title":"Learning Adaptive Reasoning Paths for Efficient Visual Reasoning","created":"2026-04-16","cited_by_count":5,"area":"lr"},{"id":"2203.05186","title":"Suspected Object Matters: Rethinking Model's Prediction for One-stage Visual Grounding","created":"2022-03-10","cited_by_count":4,"area":"lr"},{"id":"2604.10506","title":"A Progressive Training Strategy for Embodied Vision-Language Models to Mitigate Spatio-Temporal Hallucinations","created":"2026-04-12","cited_by_count":4,"area":"lr"},{"id":"2505.10292","title":"StoryReasoning Dataset: Using Chain-of-Thought for Scene Understanding and Grounded Story Generation","created":"2025-05-15","cited_by_count":3,"area":"lr"},{"id":"2505.20753","title":"Understand, Think, and Answer: Advancing Visual Reasoning with Large Multimodal Models","created":"2025-05-27","cited_by_count":3,"area":"lr"},{"id":"2511.19333","title":"Learning to Reason: Training LLMs with GPT-OSS or DeepSeek R1 Reasoning Traces","created":"2025-11-24","cited_by_count":3,"area":"lr"},{"id":"2603.18003","title":"Universal Skeleton Understanding via Differentiable Rendering and MLLMs","created":"2026-03-18","cited_by_count":3,"area":"lr"},{"id":"2302.14431","title":"Efficient Masked Autoencoders with Self-Consistency","created":"2023-02-28","cited_by_count":2,"area":"lr"},{"id":"2511.10301","title":"Rethinking Visual Information Processing in Multimodal LLMs","created":"2025-11-13","cited_by_count":2,"area":"lr"},{"id":"2604.11188","title":"MathAgent: Adversarial Evolution of Constraint Graphs for Mathematical Reasoning Data Synthesis","created":"2026-04-13","cited_by_count":2,"area":"lr"},{"id":"2605.18871","title":"Distributional Energy-Based Models for Uncertainty-Aware Structured LLM Reasoning","created":"2026-05-15","cited_by_count":2,"area":"lr"},{"id":"2505.00025","title":"A Method for the Architecture of a Medical Vertical Large Language Model Based on Deepseek R1","created":"2025-04-25","cited_by_count":1,"area":"lr"},{"id":"2507.00754","title":"Enhancing Self-Supervised Visual Representation Learning via Low-Rank Adapted LLMs","created":"2025-07-01","cited_by_count":1,"area":"lr"},{"id":"2510.23217","title":"Process Reward Models for Sentence-Level Verification of LVLM Radiology Reports","created":"2025-10-27","cited_by_count":1,"area":"lr"},{"id":"2511.19648","title":"Efficient Multi-Hop Question Answering over Knowledge Graphs via LLM Planning and Embedding-Guided Search","created":"2025-11-24","cited_by_count":1,"area":"lr"},{"id":"2602.17993","title":"Turbo Connection: Reasoning as Information Flow from Higher to Lower Layers","created":"2026-02-20","cited_by_count":1,"area":"lr"},{"id":"2602.20608","title":"VAGNet: Grounding 3D Affordance from Human-Object Interactions in Videos","created":"2026-02-24","cited_by_count":1,"area":"lr"},{"id":"2606.05025","title":"Invariant Gradient Alignment for Robust Reasoning Distillation","created":"2026-06-03","cited_by_count":1,"area":"lr"},{"id":"2606.10392","title":"Instruction Finetuning DeepSeek-R1-8B Model Using LoRA and NEFTune","created":"2026-06-09","cited_by_count":1,"area":"lr"},{"id":"2509.22688","title":"Robust Object Detection for Autonomous Driving via Curriculum-Guided Group Relative Policy Optimization","created":"2025-09-19","cited_by_count":0,"area":"lr"},{"id":"2602.20973","title":"Linear Reasoning vs. Proof by Cases: Obstacles for Large Language Models in FOL Problem Solving","created":"2026-02-24","cited_by_count":0,"area":"lr"},{"id":"2603.10335","title":"Fuel Gauge: Estimating Chain-of-Thought Length Ahead of Time in Large Multimodal Models","created":"2026-03-11","cited_by_count":0,"area":"lr"},{"id":"2605.06165","title":"Post-Reasoning: Improving the Performance of Non-Thinking Models at No Cost","created":"2026-05-07","cited_by_count":0,"area":"lr"},{"id":"2607.18266","title":"Structured Synthetic Reasoning Data for Arithmetic Fine-Tuning of Small Language Models","created":"2026-05-21","cited_by_count":0,"area":"lr"},{"id":"2607.24199","title":"Reasoning to Regulate: Chain-of-Thought for Traffic Rule Understanding","created":"2026-07-27","cited_by_count":0,"area":"lr"},{"id":"2607.28375","title":"HyperClaim: Fine-Grained Cross-Modal Hypergraph Reasoning for Video Misinformation Detection","created":"2026-07-30","cited_by_count":0,"area":"lr"},{"id":"2608.02470","title":"Grounding Agentic VLMs with Dedicated Segmentation for Fine-Grained Vehicle Damage Assessment","created":"2026-08-03","cited_by_count":0,"area":"lr"},{"id":"2609.31751","title":"EgoTSR++: Egocentric Spatiotemporal Reasoning for Task Progress Understanding","created":"2026-09-23","cited_by_count":0,"area":"lr"},{"id":"2610.08830","title":"MoR-MLLM: Mixture of Recursions for Efficient Multimodal Large Language Models","created":"2026-09-27","cited_by_count":0,"area":"lr"}],"next_cursor":null}