AI論文解説 Youtubeチャンネル: AI時代の羅針盤

2025年3月頃に公開されたcsカテゴリの論文 (ID: 2503.xxxxx)を被引用数のデータを元にランキングしています。ランキングは随時更新します。
(2025月6月14日更新)

被引用数	タイトル	動画
225	DAPO: An Open-Source LLM Reinforcement Learning System at Scale
190	Gemma 3 Technical Report
142	Understanding R1-Zero-Like Training: A Critical Perspective
123	Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Models	not yet
120	Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models	not yet
117	Visual-RFT: Visual Reinforcement Fine-Tuning	not yet
116	Wan: Open and Advanced Large-Scale Video Generative Models	not yet
113	Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models	not yet
109	SimpleRL-Zoo: Investigating and Taming Zero Reinforcement Learning for Open Base Models in the Wild	not yet
107	Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning	not yet
97	L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning	not yet
91	MM-Eureka: Exploring the Frontiers of Multimodal Reasoning with Rule-based Reinforcement Learning	not yet
89	Cognitive Behaviors that Enable Self-Improving Reasoners, or, Four Habits of Highly Effective STaRs
82	R1-Onevision: Advancing Generalized Multimodal Reasoning through Cross-Modal Formalization	not yet
77	Open-Reasoner-Zero: An Open Source Approach to Scaling Up Reinforcement Learning on the Base Model	not yet
64	R1-VL: Learning to Reason with Multimodal Large Language Models via Step-wise Group Relative Policy Optimization	not yet
64	LMM-R1: Empowering 3B LMMs with Strong Reasoning Abilities Through Two-Stage Rule-Based RL	not yet
64	R1-Searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning	not yet
61	Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond	not yet
59	Qwen2.5-Omni Technical Report	not yet
58	R1-Zero's "Aha Moment" in Visual Reasoning on a 2B Non-SFT Model	not yet
57	Phi-4-Mini Technical Report: Compact yet Powerful Multimodal Language Models via Mixture-of-LoRAs	not yet
54	GR00T N1: An Open Foundation Model for Generalist Humanoid Robots	not yet
49	DAST: Difficulty-Adaptive Slow-Thinking for Large Reasoning Models	not yet
47	Video-R1: Reinforcing Video Reasoning in MLLMs	not yet
45	A Survey of Efficient Reasoning for Large Reasoning Models: Language, Multimodality, and Beyond	not yet
43	ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning	not yet
42	A Survey on Test-Time Scaling in Large Language Models: What, How, Where, and How Well?	not yet
42	Optimizing Test-Time Compute via Meta Reinforcement Fine-Tuning	not yet
38	OpenVLThinker: An Early Exploration to Complex Vision-Language Reasoning via Iterative Self-Improvement	not yet
38	Seg-Zero: Reasoning-Chain Guided Segmentation via Cognitive Reinforcement	not yet
36	Why Do Multi-Agent LLM Systems Fail?
36	VisualPRM: An Effective Process Reward Model for Multimodal Reasoning	not yet
35	Gemini Robotics: Bringing AI into the Physical World	not yet
32	AgiBot World Colosseo: A Large-scale Manipulation Platform for Scalable and Intelligent Embodied Systems	not yet
32	Sketch-of-Thought: Efficient LLM Reasoning with Adaptive Cognitive-Inspired Sketching	not yet
32	An Empirical Study on Eliciting and Improving R1-like Reasoning Models	not yet
30	Model Context Protocol (MCP): Landscape, Security Threats, and Future Research Directions	not yet
30	Reason-RFT: Reinforcement Fine-Tuning for Visual Reasoning	not yet
30	Med-R1: Reinforcement Learning for Generalizable Medical Reasoning in Vision-Language Models	not yet
29	UI-R1: Enhancing Efficient Action Prediction of GUI Agents by Reinforcement Learning	not yet
29	Large Language Model Agent: A Survey on Methodology, Applications and Challenges	not yet
29	Multimodal Chain-of-Thought Reasoning: A Comprehensive Survey	not yet
29	How Well do LLMs Compress Their Own Chain-of-Thought? A Token Complexity Approach	not yet
27	Large Language Models Post-training: Surveying Techniques from Alignment to Reasoning	not yet
26	Monitoring Reasoning Models for Misbehavior and the Risks of Promoting Obfuscation
23	WISE: A World Knowledge-Informed Semantic Evaluation for Text-to-Image Generation	not yet
22	ToRL: Scaling Tool-Integrated RL	not yet
22	What's Behind PPO's Collapse in Long-CoT? Value Optimization Holds the Secret	not yet
21	Which Economic Tasks are Performed with AI? Evidence from Millions of Claude Conversations	not yet
20	CoT-VLA: Visual Chain-of-Thought Reasoning for Vision-Language-Action Models	not yet
20	Proof or Bluff? Evaluating LLMs on 2025 USA Math Olympiad
20	A Linear Collider Vision for the Future of Particle Physics	not yet
20	GoT: Unleashing Reasoning Capability of Multimodal Large Language Model for Visual Generation and Editing	not yet
20	VACE: All-in-One Video Creation and Editing	not yet
20	Boosting the Generalization and Reasoning of Vision Language Models with Curriculum Reinforcement Learning	not yet
19	Crossing the Reward Bridge: Expanding RL with Verifiable Rewards Across Diverse Domains	not yet
19	CPPO: Accelerating the Training of Group Relative Policy Optimization-Based Reasoning Models
19	SoK: Security Analysis of Blockchain-based Cryptocurrency	not yet
19	SWEET-RL: Training Multi-Turn LLM Agents on Collaborative Reasoning Tasks	not yet
19	RWKV-7 "Goose" with Expressive Dynamic State Evolution	not yet
19	Efficient Test-Time Scaling via Self-Calibration	not yet
18	Reinforcement Learning for Reasoning in Small LLMs: What Works and What Doesn't	not yet
18	Measuring AI Ability to Complete Long Tasks	not yet
17	Harnessing the Reasoning Economy: A Survey of Efficient Reasoning for Large Language Models	not yet
17	Fin-R1: A Large Language Model for Financial Reasoning through Reinforcement Learning	not yet
17	ReCamMaster: Camera-Controlled Generative Rendering from A Single Video	not yet
17	HybridVLA: Collaborative Diffusion and Autoregression in a Unified Vision-Language-Action Model	not yet
17	All Roads Lead to Likelihood: The Value of Reinforcement Learning in Fine-Tuning	not yet
17	Safety Tax: Safety Alignment Makes Your Large Reasoning Models Less Reasonable	not yet
16	Vision-R1: Evolving Human-Free Alignment in Large Vision-Language Models via Vision-Guided Reinforcement Learning	not yet
16	What Makes a Reward Model a Good Teacher? An Optimization Perspective	not yet
16	LLM Agents for Education: Advances and Applications	not yet
16	EasyControl: Adding Efficient and Flexible Control for Diffusion Transformer	not yet
16	The First Few Tokens Are All You Need: An Efficient and Effective Unsupervised Prefix Fine-Tuning Method for Reasoning Models	not yet
16	Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens	not yet
15	Efficient Inference for Large Reasoning Models: A Survey	not yet
15	Transformers without Normalization
15	KodCode: A Diverse, Challenging, and Verifiable Synthetic Dataset for Coding	not yet
15	DeepRetrieval: Hacking Real Search Engines and Retrievers with Large Language Models via Reinforcement Learning	not yet
14	Open Deep Search: Democratizing Search with Open-source Reasoning Agents
14	A Comprehensive Survey on Long Context Language Modeling	not yet
14	OThink-MR1: Stimulating multimodal generalized reasoning capabilities via dynamic reinforcement learning	not yet
14	Cosmos-Reason1: From Physical Common Sense To Embodied Reasoning	not yet
14	VGGT: Visual Geometry Grounded Transformer	not yet
14	ReMA: Learning to Meta-think for LLMs with Multi-Agent Reinforcement Learning	not yet
14	Seedream 2.0: A Native Chinese-English Bilingual Image Generation Foundation Model	not yet
14	START: Self-taught Reasoner with Tools	not yet
14	EAGLE-3: Scaling up Inference Acceleration of Large Language Models via Training-Time Test	not yet
13	Reasoning-SQL: Reinforcement Learning with SQL Tailored Partial Rewards for Reasoning-Enhanced Text-to-SQL	not yet
13	Think Twice: Enhancing LLM Reasoning by Scaling Multi-round Test-time Thinking	not yet
13	1.4 Million Open-Source Distilled Reasoning Dataset to Empower Large Language Model Training	not yet
13	XAttention: Block Sparse Attention with Antidiagonal Scoring	not yet
13	A Survey on Trustworthy LLM Agents: Threats and Countermeasures	not yet
13	Open-Sora 2.0: Training a Commercial-Level Video Generation Model in $200k	not yet
13	YuE: Scaling Open Foundation Models for Long-Form Music Generation	not yet
13	InftyThink: Breaking the Length Limits of Long-Context Reasoning in Large Language Models	not yet
13	R1-Omni: Explainable Omni-Multimodal Emotion Recognition with Reinforcement Learning	not yet
13	Audio Flamingo 2: An Audio-Language Model with Long-Audio Understanding and Expert Reasoning Abilities	not yet
13	MultiAgentBench: Evaluating the Collaboration and Competition of LLM agents	not yet
12	VBench-2.0: Advancing Video Generation Benchmark Suite for Intrinsic Faithfulness	not yet
12	Reasoning to Learn from Latent Thoughts
12	Defeating Prompt Injections by Design	not yet
12	MetaSpatial: Reinforcing 3D Spatial Reasoning in VLMs for the Metaverse	not yet
12	FastCuRL: Curriculum Reinforcement Learning with Stage-wise Context Scaling for Efficient Training R1-like Reasoning Models	not yet
12	SAEBench: A Comprehensive Benchmark for Sparse Autoencoders in Language Model Interpretability	not yet
12	Unified Reward Model for Multimodal Understanding and Generation	not yet
12	Personalized Generation In Large Model Era: A Survey	not yet
12	Audio-Reasoner: Improving Reasoning Capability in Large Audio Language Models	not yet
11	SCORE: Story Coherence and Retrieval Enhancement for AI Narratives	not yet
11	Agentic Large Language Models, a survey	not yet
11	GAIA-2: A Controllable Multi-View Generative World Model for Autonomous Driving	not yet
11	Learning Multi-Level Features with Matryoshka Sparse Autoencoders	not yet
11	Survey on Evaluation of LLM-based Agents	not yet
11	Deconstructing Long Chain-of-Thought: A Structured Reasoning Optimization Framework for Long CoT Distillation	not yet
11	Think or Not Think: A Study of Explicit Thinking in Rule-Based Visual Reinforcement Fine-Tuning	not yet
11	CameraCtrl II: Dynamic Scene Exploration via Camera-controlled Video Diffusion Models	not yet
11	Long Context Tuning for Video Generation	not yet
11	Block Diffusion: Interpolating Between Autoregressive and Diffusion Language Models
11	Agentic AI for Scientific Discovery: A Survey of Progress, Challenges, and Future Directions	not yet
11	Chain-of-Thought Reasoning In The Wild Is Not Always Faithful	not yet
11	AlphaDrive: Unleashing the Power of VLMs in Autonomous Driving via Reinforcement Learning and Reasoning	not yet
11	Remasking Discrete Diffusion Models with Inference-Time Scaling	not yet
10	Effectively Controlling Reasoning Models through Thinking Intervention	not yet
10	A Survey of WebAgents: Towards Next-Generation AI Agents for Web Automation with Large Foundation Models	not yet
10	Think Before Recommend: Unleashing the Latent Reasoning Power for Sequential Recommendation	not yet
10	Exploring Data Scaling Trends and Effects in Reinforcement Learning from Human Feedback
10	Embodied-Reasoner: Synergizing Visual Search, Reasoning, and Action for Embodied Interactive Tasks	not yet
10	Social Network User Profiling for Anomaly Detection Based on Graph Neural Networks	not yet
10	AgentRxiv: Towards Collaborative Autonomous Research	not yet
10	Safe RLHF-V: Safe Reinforcement Learning from Multi-modal Human Feedback	not yet
10	Towards Understanding the Safety Boundaries of DeepSeek Models: Evaluation and Findings	not yet
10	Time-R1: Post-Training Large Vision Language Model for Temporal Video Grounding	not yet
10	MMLU-ProX: A Multilingual Benchmark for Advanced Large Language Model Evaluation	not yet
10	SANA-Sprint: One-Step Diffusion with Continuous-Time Consistency Distillation	not yet
10	MedAgentsBench: Benchmarking Thinking Models and Agent Frameworks for Complex Medical Reasoning	not yet
10	SafeArena: Evaluating the Safety of Autonomous Web Agents
10	OTTER: A Vision-Language-Action Model with Text-Aware Visual Feature Extraction	not yet
10	A New $\sim 5\sigma$ Tension at Characteristic Redshift from DESI-DR1 BAO and DES-SN5YR Observations	not yet
9	XLRS-Bench: Could Your Multimodal LLMs Understand Extremely Large Ultra-High-Resolution Remote Sensing Imagery?	not yet
9	Large Language Models Pass the Turing Test	not yet
9	Q-Insight: Understanding Image Quality via Visual Reinforcement Learning	not yet
9	Lumina-Image 2.0: A Unified and Efficient Image Generative Framework	not yet
9	Challenging the Boundaries of Reasoning: An Olympiad-Level Math Benchmark for Large Language Models	not yet
9	ResearchBench: Benchmarking LLMs in Scientific Discovery via Inspiration-Based Task Decomposition
9	Unlocking Efficient Long-to-Short LLM Reasoning with Model Merging	not yet
9	LEGO-Puzzles: How Good Are MLLMs at Multi-Step Spatial Reasoning?	not yet
9	HALHF: a hybrid, asymmetric, linear Higgs factory using plasma- and RF-based acceleration	not yet
9	HunyuanPortrait: Implicit Condition Control for Enhanced Portrait Animation	not yet

※ 被引用数は更新日における NASA ADSのデータを参照しています
https://ui.adsabs.harvard.edu/