{"list":"other","total":99,"rows":[{"id":"2402.03300","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","created":"2024-02-05","cited_by_count":9379},{"id":"2501.12948","title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","created":"2025-01-22","cited_by_count":6330},{"id":"2203.11171","title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","created":"2022-03-21","cited_by_count":5708},{"id":"2502.13923","title":"Qwen2.5-VL Technical Report","created":"2025-02-19","cited_by_count":5587},{"id":"2304.10592","title":"MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models","created":"2023-04-20","cited_by_count":2711},{"id":"2205.01917","title":"CoCa: Contrastive Captioners are Image-Text Foundation Models","created":"2022-05-04","cited_by_count":1274},{"id":"2306.13549","title":"A Survey on Multimodal Large Language Models","created":"2023-06-23","cited_by_count":909},{"id":"2305.11738","title":"CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing","created":"2023-05-19","cited_by_count":783},{"id":"2403.05525","title":"DeepSeek-VL: Towards Real-World Vision-Language Understanding","created":"2024-03-08","cited_by_count":733},{"id":"2306.05499","title":"Prompt Injection attack against LLM-integrated Applications","created":"2023-06-08","cited_by_count":605},{"id":"2212.10403","title":"Towards Reasoning in Large Language Models: A Survey","created":"2022-12-20","cited_by_count":596},{"id":"2503.09567","title":"Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models","created":"2025-03-12","cited_by_count":384},{"id":"2407.08693","title":"Robotic Control via Embodied Chain-of-Thought Reasoning","created":"2024-07-11","cited_by_count":346},{"id":"2305.10415","title":"PMC-VQA: Visual Instruction Tuning for Medical Visual Question Answering","created":"2023-05-17","cited_by_count":338},{"id":"2309.11495","title":"Chain-of-Verification Reduces Hallucination in Large Language Models","created":"2023-09-20","cited_by_count":324},{"id":"2412.16339","title":"Deliberative Alignment: Reasoning Enables Safer Language Models","created":"2024-12-20","cited_by_count":308},{"id":"2309.11499","title":"DreamLLM: Synergistic Multimodal Comprehension and Creation","created":"2023-09-20","cited_by_count":297},{"id":"2401.13601","title":"MM-LLMs: Recent Advances in MultiModal Large Language Models","created":"2024-01-24","cited_by_count":278},{"id":"2305.08291","title":"Large Language Model Guided Tree-of-Thought","created":"2023-05-15","cited_by_count":221},{"id":"2504.15895","title":"Dynamic Early Exit in Reasoning Models","created":"2025-04-22","cited_by_count":219},{"id":"2304.01904","title":"REFINER: Reasoning Feedback on Intermediate Representations","created":"2023-04-04","cited_by_count":205},{"id":"2309.15402","title":"Navigate through Enigmatic Labyrinth A Survey of Chain of Thought Reasoning: Advances, Frontiers and Future","created":"2023-09-27","cited_by_count":184},{"id":"2412.18319","title":"Mulberry: Empowering MLLM with o1-like Reasoning and Reflection via Collective Monte Carlo Tree Search","created":"2024-12-24","cited_by_count":175},{"id":"2502.19634","title":"MedVLM-R1: Incentivizing Medical Reasoning Capability of Vision-Language Models (VLMs) via Reinforcement Learning","created":"2025-02-26","cited_by_count":173},{"id":"2309.00236","title":"Image Hijacks: Adversarial Images can Control Generative Models at Runtime","created":"2023-09-01","cited_by_count":172},{"id":"2311.10813","title":"A Language Agent for Autonomous Driving","created":"2023-11-17","cited_by_count":164},{"id":"2408.15221","title":"LLM Defenses Are Not Robust to Multi-Turn Human Jailbreaks Yet","created":"2024-08-27","cited_by_count":151},{"id":"2402.12451","title":"The Revolution of Multimodal Large Language Models: A Survey","created":"2024-02-19","cited_by_count":137},{"id":"2502.12025","title":"SafeChain: Safety of Language Models with Long Chain-of-Thought Reasoning Capabilities","created":"2025-02-17","cited_by_count":136},{"id":"2305.04160","title":"X-LLM: Bootstrapping Advanced Large Language Models by Treating Multi-Modalities as Foreign Languages","created":"2023-05-07","cited_by_count":128},{"id":"2502.18080","title":"Towards Thinking-Optimal Scaling of Test-Time Compute for LLM Reasoning","created":"2025-02-25","cited_by_count":119},{"id":"2410.20290","title":"Fast Best-of-N Decoding via Speculative Rejection","created":"2024-10-26","cited_by_count":112},{"id":"2501.18492","title":"GuardReasoner: Towards Reasoning-based LLM Safeguards","created":"2025-01-30","cited_by_count":100},{"id":"2503.05379","title":"R1-Omni: Explainable Omni-Multimodal Emotion Recognition with Reinforcement Learning","created":"2025-03-07","cited_by_count":100},{"id":"2305.02677","title":"Caption Anything: Interactive Image Description with Diverse Multimodal Controls","created":"2023-05-04","cited_by_count":99},{"id":"2502.02542","title":"OverThink: Slowdown Attacks on Reasoning LLMs","created":"2025-02-04","cited_by_count":96},{"id":"2503.02318","title":"Audio-Reasoner: Improving Reasoning Capability in Large Audio Language Models","created":"2025-03-04","cited_by_count":95},{"id":"2504.10903","title":"Efficient Reasoning Models: A Survey","created":"2025-04-15","cited_by_count":95},{"id":"2502.12659","title":"The Hidden Risks of Large Reasoning Models: A Safety Assessment of R1","created":"2025-02-18","cited_by_count":91},{"id":"2401.12242","title":"BadChain: Backdoor Chain-of-Thought Prompting for Large Language Models","created":"2024-01-20","cited_by_count":80},{"id":"2502.02384","title":"STAIR: Improving Safety Alignment with Introspective Reasoning","created":"2025-02-04","cited_by_count":77},{"id":"2405.16640","title":"A Survey of Multimodal Large Language Model from A Data-centric Perspective","created":"2024-05-26","cited_by_count":75},{"id":"2501.19201","title":"Efficient Reasoning with Hidden Thinking","created":"2025-01-31","cited_by_count":75},{"id":"2405.20773","title":"Visual-RolePlay: Universal Jailbreak Attack on MultiModal Large Language Models via Role-playing Image Character","created":"2024-05-25","cited_by_count":68},{"id":"2403.16996","title":"DriveCoT: Integrating Chain-of-Thought Reasoning with End-to-End Driving","created":"2024-03-25","cited_by_count":67},{"id":"2502.14881","title":"A Survey of Safety on Large Vision-Language Models: Attacks, Defenses and Evaluations","created":"2025-02-14","cited_by_count":67},{"id":"2504.17704","title":"Safety in Large Reasoning Models: A Survey","created":"2025-04-24","cited_by_count":64},{"id":"2501.10074","title":"SpatialCoT: Advancing Spatial Reasoning through Coordinate Alignment and Chain-of-Thought for Embodied Task Planning","created":"2025-01-17","cited_by_count":62},{"id":"2410.16033","title":"TreeBoN: Enhancing Inference-Time Alignment with Speculative Tree-Search and Best-of-N Sampling","created":"2024-10-18","cited_by_count":61},{"id":"2501.18841","title":"Trading Inference-Time Compute for Adversarial Robustness","created":"2025-01-31","cited_by_count":61},{"id":"2504.10081","title":"RealSafe-R1: Safety-Aligned DeepSeek-R1 without Compromising Reasoning Capability","created":"2025-04-14","cited_by_count":59},{"id":"2407.06057","title":"Variational Best-of-N Alignment","created":"2024-07-08","cited_by_count":51},{"id":"2412.11974","title":"Emma-X: An Embodied Multimodal Action Model with Grounded Chain of Thought and Look-ahead Spatial Reasoning","created":"2024-12-16","cited_by_count":47},{"id":"2412.13736","title":"MedCoT: Medical Chain of Thought via Hierarchical Expert","created":"2024-12-18","cited_by_count":46},{"id":"2503.21696","title":"Embodied-Reasoner: Synergizing Visual Search, Reasoning, and Action for Embodied Interactive Tasks","created":"2025-03-27","cited_by_count":44},{"id":"2308.08614","title":"Boosting Logical Reasoning in Large Language Models through a New Framework: The Graph of Thought","created":"2023-08-16","cited_by_count":41},{"id":"2410.04509","title":"ErrorRadar: Benchmarking Complex Mathematical Reasoning of Multimodal Large Language Models Via Error Detection","created":"2024-10-06","cited_by_count":37},{"id":"2503.10621","title":"DriveLMM-o1: A Step-by-Step Reasoning Dataset and Large Multimodal Model for Driving Scenario Understanding","created":"2025-03-13","cited_by_count":36},{"id":"2503.24377","title":"Harnessing the Reasoning Economy: A Survey of Efficient Reasoning for Large Language Models","created":"2025-03-31","cited_by_count":36},{"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},{"id":"2406.13246","title":"GSR-BENCH: A Benchmark for Grounded Spatial Reasoning Evaluation via Multimodal LLMs","created":"2024-06-19","cited_by_count":33},{"id":"2410.17885","title":"Theorem-Validated Reverse Chain-of-Thought Problem Generation for Geometric Reasoning","created":"2024-10-23","cited_by_count":32},{"id":"2501.01306","title":"Think More, Hallucinate Less: Mitigating Hallucinations via Dual Process of Fast and Slow Thinking","created":"2025-01-02","cited_by_count":31},{"id":"2502.13458","title":"ThinkGuard: Deliberative Slow Thinking Leads to Cautious Guardrails","created":"2025-02-19","cited_by_count":31},{"id":"2411.18363","title":"ChatRex: Taming Multimodal LLM for Joint Perception and Understanding","created":"2024-11-27","cited_by_count":30},{"id":"2504.05605","title":"ShadowCoT: Cognitive Hijacking for Stealthy Reasoning Backdoors in LLMs","created":"2025-04-08","cited_by_count":30},{"id":"2501.11110","title":"Chain-of-Reasoning: Towards Unified Mathematical Reasoning in Large Language Models via a Multi-Paradigm Perspective","created":"2025-01-19","cited_by_count":29},{"id":"2504.08813","title":"SafeMLRM: Demystifying Safety in Multi-modal Large Reasoning Models","created":"2025-04-09","cited_by_count":29},{"id":"2410.20971","title":"BlueSuffix: Reinforced Blue Teaming for Vision-Language Models Against Jailbreak Attacks","created":"2024-10-28","cited_by_count":28},{"id":"2404.12065","title":"RAGAR, Your Falsehood Radar: RAG-Augmented Reasoning for Political Fact-Checking using Multimodal Large Language Models","created":"2024-04-18","cited_by_count":27},{"id":"2405.10529","title":"Safeguarding Vision-Language Models Against Patched Visual Prompt Injectors","created":"2024-05-17","cited_by_count":27},{"id":"2502.15109","title":"Social Genome: Grounded Social Reasoning Abilities of Multimodal Models","created":"2025-02-21","cited_by_count":26},{"id":"2308.06207","title":"Thinking Like an Expert:Multimodal Hypergraph-of-Thought (HoT) Reasoning to boost Foundation Modals","created":"2023-08-11","cited_by_count":24},{"id":"2402.11140","title":"Boosting of Thoughts: Trial-and-Error Problem Solving with Large Language Models","created":"2024-02-17","cited_by_count":22},{"id":"2405.07990","title":"Plot2Code: A Comprehensive Benchmark for Evaluating Multi-modal Large Language Models in Code Generation from Scientific Plots","created":"2024-05-13","cited_by_count":21},{"id":"2501.03226","title":"BoostStep: Boosting mathematical capability of Large Language Models via improved single-step reasoning","created":"2025-01-06","cited_by_count":21},{"id":"2409.19510","title":"Making LLMs Better Many-to-Many Speech-to-Text Translators with Curriculum Learning","created":"2024-09-29","cited_by_count":20},{"id":"2501.18617","title":"DarkMind: Latent Chain-of-Thought Backdoor in Customized LLMs","created":"2025-01-24","cited_by_count":20},{"id":"2502.08859","title":"EnigmaEval: A Benchmark of Long Multimodal Reasoning Challenges","created":"2025-02-13","cited_by_count":19},{"id":"2505.06538","title":"Think in Safety: Unveiling and Mitigating Safety Alignment Collapse in Multimodal Large Reasoning Model","created":"2025-05-10","cited_by_count":19},{"id":"2412.02025","title":"PKRD-CoT: A Unified Chain-of-thought Prompting for Multi-Modal Large Language Models in Autonomous Driving","created":"2024-12-02","cited_by_count":17},{"id":"2503.22048","title":"ThinkEdit: Interpretable Weight Editing to Mitigate Overly Short Thinking in Reasoning Models","created":"2025-03-27","cited_by_count":17},{"id":"2404.12372","title":"MedThink: Explaining Medical Visual Question Answering via Multimodal Decision-Making Rationale","created":"2024-04-18","cited_by_count":14},{"id":"2411.02570","title":"TI-PREGO: Chain of Thought and In-Context Learning for Online Mistake Detection in PRocedural EGOcentric Videos","created":"2024-11-04","cited_by_count":10},{"id":"2412.07472","title":"SmartAgent: Chain-of-User-Thought for Embodied Personalized Agent in Cyber World","created":"2024-12-10","cited_by_count":10},{"id":"2503.11089","title":"EmbodiedVSR: Dynamic Scene Graph-Guided Chain-of-Thought Reasoning for Visual Spatial Tasks","created":"2025-03-14","cited_by_count":10},{"id":"2503.19326","title":"Process or Result? Manipulated Ending Tokens Can Mislead Reasoning LLMs to Ignore the Correct Reasoning Steps","created":"2025-03-25","cited_by_count":9},{"id":"2506.19257","title":"MSR-Align: Policy-Grounded Multimodal Alignment for Safety-Aware Reasoning in Vision-Language Models","created":"2025-06-24","cited_by_count":7},{"id":"2411.14476","title":"StreetviewLLM: Extracting Geographic Information Using a Chain-of-Thought Multimodal Large Language Model","created":"2024-11-19","cited_by_count":6},{"id":"2407.06309","title":"Multimodal Chain-of-Thought Reasoning via ChatGPT to Protect Children from Age-Inappropriate Apps","created":"2024-07-08","cited_by_count":5},{"id":"2412.00846","title":"Improving Multimodal LLMs Ability In Geometry Problem Solving, Reasoning, And Multistep Scoring","created":"2024-12-01","cited_by_count":5},{"id":"2412.12627","title":"Make Imagination Clearer! Stable Diffusion-based Visual Imagination for Multimodal Machine Translation","created":"2024-12-17","cited_by_count":5},{"id":"2406.15768","title":"MR-MLLM: Mutual Reinforcement of Multimodal Comprehension and Vision Perception","created":"2024-06-22","cited_by_count":3},{"id":"2410.23402","title":"VisualCoder: Guiding Large Language Models in Code Execution with Fine-grained Multimodal Chain-of-Thought Reasoning","created":"2024-10-30","cited_by_count":3},{"id":"2504.09532","title":"Humanoid Agent via Embodied Chain-of-Action Reasoning with Multimodal Foundation Models for Zero-Shot Loco-Manipulation","created":"2025-04-13","cited_by_count":3},{"id":"2504.16913","title":"Tracing Thought: Using Chain-of-Thought Reasoning to Identify the LLM Behind AI-Generated Text","created":"2025-04-23","cited_by_count":3},{"id":"2405.11640","title":"Inquire, Interact, and Integrate: A Proactive Agent Collaborative Framework for Zero-Shot Multimodal Medical Reasoning","created":"2024-05-19","cited_by_count":2},{"id":"2410.09449","title":"Continuous Risk Prediction","created":"2024-10-12","cited_by_count":2},{"id":"2412.16410","title":"Application of Multimodal Large Language Models in Autonomous Driving","created":"2024-12-21","cited_by_count":1}],"next_cursor":null}