AI論文解説 Youtubeチャンネル: AI時代の羅針盤
2024年12月頃に公開されたcsカテゴリの論文 (ID: 2412.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年4月4日更新)
| 被引用数 | タイトル | 動画 |
|---|---|---|
 595 |
Qwen2.5 Technical Report | not yet |
 456 |
DeepSeek-V3 Technical Report | not yet |
 262 |
OpenAI o1 System Card | not yet |
 147 |
Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling | not yet |
 94 |
HunyuanVideo: A Systematic Framework For Large Video Generative Models |  |
 82 |
Phi-4 Technical Report |  |
 50 |
DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding | not yet |
 48 |
Do NOT Think That Much for 2+3 |  |
 43 |
Training Large Language Models to Reason in a Continuous Latent Space |  |
 39 |
Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference | not yet |
 38 |
Open-Sora Plan: Open-Source Large Video Generation Model |  |
 37 |
ProcessBench: Identifying Process Errors in Mathematical Reasoning | not yet |
 36 |
Open-Sora: Democratizing Efficient Video Production for All | not yet |
 36 |
Structured 3D Latents for Scalable and Versatile 3D Generation | not yet |
 34 |
Deliberative Alignment: Reasoning Enables Safer Language Models | not yet |
 33 |
Imitate, Explore, and Self-Improve: A Reproduction Report on Slow-thinking Reasoning Systems | not yet |
 30 |
LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods | not yet |
 26 |
Free Process Rewards without Process Labels | not yet |
 25 |
Alignment faking in large language models | not yet |
 25 |
Infinity: Scaling Bitwise AutoRegressive Modeling for High-Resolution Image Synthesis |  |
 23 |
LongBench v2: Towards Deeper Understanding and Reasoning on Realistic Long-context Multitasks | not yet |
 23 |
Flow Matching Guide and Code | not yet |
 23 |
Flexible-Antenna Systems: A Pinching-Antenna Perspective | not yet |
 22 |
Mulberry: Empowering MLLM with o1-like Reasoning and Reflection via Collective Monte Carlo Tree Search | not yet |
 22 |
NVILA: Efficient Frontier Visual Language Models | not yet |
 22 |
Global MMLU: Understanding and Addressing Cultural and Linguistic Biases in Multilingual Evaluation | not yet |
 20 |
HuatuoGPT-o1, Towards Medical Complex Reasoning with LLMs |  |
 20 |
Thinking in Space: How Multimodal Large Language Models See, Remember, and Recall Spaces | not yet |
 20 |
Byte Latent Transformer: Patches Scale Better Than Tokens |  |
 20 |
Aya Expanse: Combining Research Breakthroughs for a New Multilingual Frontier | not yet |
 20 |
GLM-4-Voice: Towards Intelligent and Human-Like End-to-End Spoken Chatbot | not yet |
 19 |
TokenFlow: Unified Image Tokenizer for Multimodal Understanding and Generation | not yet |
 18 |
Large Concept Models: Language Modeling in a Sentence Representation Space |  |
 18 |
VisionZip: Longer is Better but Not Necessary in Vision Language Models |  |
 18 |
PaliGemma 2: A Family of Versatile VLMs for Transfer |  |
 17 |
Fast Gradient Computation for RoPE Attention in Almost Linear Time | not yet |
 17 |
Scaling of Search and Learning: A Roadmap to Reproduce o1 from Reinforcement Learning Perspective |  |
 16 |
Experimental Demonstration of Logical Magic State Distillation | not yet |
 16 |
MetaMorph: Multimodal Understanding and Generation via Instruction Tuning | not yet |
 16 |
ExBody2: Advanced Expressive Humanoid Whole-Body Control | not yet |
 16 |
Frontier Models are Capable of In-context Scheming | not yet |
 16 |
o1-Coder: an o1 Replication for Coding | not yet |
 15 |
Token-Budget-Aware LLM Reasoning | not yet |
 15 |
ARC Prize 2024: Technical Report |  |
 15 |
Best-of-N Jailbreaking | not yet |
 14 |
Theoretical Constraints on the Expressive Power of $\mathsf{RoPE}$-based Tensor Attention Transformers | not yet |
 14 |
Motion Prompting: Controlling Video Generation with Motion Trajectories | not yet |
 13 |
CosyVoice 2: Scalable Streaming Speech Synthesis with Large Language Models | not yet |
 13 |
Forest-of-Thought: Scaling Test-Time Compute for Enhancing LLM Reasoning | not yet |
 13 |
Mobile-TeleVision: Predictive Motion Priors for Humanoid Whole-Body Control | not yet |
 13 |
From Slow Bidirectional to Fast Autoregressive Video Diffusion Models |  |
 13 |
The Computational Limits of State-Space Models and Mamba via the Lens of Circuit Complexity | not yet |
 12 |
Formal Mathematical Reasoning: A New Frontier in AI | not yet |
 12 |
FlowAR: Scale-wise Autoregressive Image Generation Meets Flow Matching | not yet |
 12 |
TheAgentCompany: Benchmarking LLM Agents on Consequential Real World Tasks |  |
 12 |
RoboMIND: Benchmark on Multi-embodiment Intelligence Normative Data for Robot Manipulation | not yet |
 12 |
Compressed Chain of Thought: Efficient Reasoning Through Dense Representations | not yet |
 12 |
Apollo: An Exploration of Video Understanding in Large Multimodal Models |  |
 12 |
Machine Unlearning Doesn't Do What You Think: Lessons for Generative AI Policy, Research, and Practice |  |
 11 |
An analytic theory of creativity in convolutional diffusion models | not yet |
 11 |
LMFusion: Adapting Pretrained Language Models for Multimodal Generation | not yet |
 11 |
Flex Attention: A Programming Model for Generating Optimized Attention Kernels | not yet |
 11 |
InstantSwap: Fast Customized Concept Swapping across Sharp Shape Differences | not yet |
 10 |
A Survey on Large Language Model Acceleration based on KV Cache Management | not yet |
 10 |
MEDEC: A Benchmark for Medical Error Detection and Correction in Clinical Notes |  |
 10 |
Jasper and Stella: distillation of SOTA embedding models | not yet |
 10 |
DRT: Deep Reasoning Translation via Long Chain-of-Thought | not yet |
 10 |
Taming Multimodal Joint Training for High-Quality Video-to-Audio Synthesis | not yet |
 10 |
Parallelized Autoregressive Visual Generation | not yet |
 10 |
AceMath: Advancing Frontier Math Reasoning with Post-Training and Reward Modeling | not yet |
 10 |
Autoregressive Video Generation without Vector Quantization | not yet |
 10 |
Towards Generalist Robot Policies: What Matters in Building Vision-Language-Action Models | not yet |
 10 |
LazyDiT: Lazy Learning for the Acceleration of Diffusion Transformers | not yet |
 10 |
InternLM-XComposer2.5-OmniLive: A Comprehensive Multimodal System for Long-term Streaming Video and Audio Interactions | not yet |
 10 |
The BrowserGym Ecosystem for Web Agent Research | not yet |
 10 |
Aguvis: Unified Pure Vision Agents for Autonomous GUI Interaction | not yet |
 10 |
Liquid: Language Models are Scalable and Unified Multi-modal Generators | not yet |
 10 |
Explainable and Interpretable Multimodal Large Language Models: A Comprehensive Survey | not yet |
 10 |
[CLS] Attention is All You Need for Training-Free Visual Token Pruning: Make VLM Inference Faster | not yet |
 9 |
OS-Genesis: Automating GUI Agent Trajectory Construction via Reverse Task Synthesis | not yet |
 9 |
Dora: Sampling and Benchmarking for 3D Shape Variational Auto-Encoders | not yet |
 9 |
LearnLM: Improving Gemini for Learning |  |
 9 |
Offline Reinforcement Learning for LLM Multi-Step Reasoning | not yet |
 9 |
Score-based Generative Diffusion Models for Social Recommendations | not yet |
 9 |
Inference-Aware Fine-Tuning for Best-of-N Sampling in Large Language Models | not yet |
 9 |
Entropy-Regularized Process Reward Model | not yet |
 9 |
TraceVLA: Visual Trace Prompting Enhances Spatial-Temporal Awareness for Generalist Robotic Policies | not yet |
 9 |
FlowEdit: Inversion-Free Text-Based Editing Using Pre-Trained Flow Models | not yet |
 9 |
UniReal: Universal Image Generation and Editing via Learning Real-world Dynamics | not yet |
 9 |
A Consolidated Volatility Prediction with Back Propagation Neural Network and Genetic Algorithm | not yet |
 9 |
On Evaluating the Durability of Safeguards for Open-Weight LLMs | not yet |
 9 |
Gated Delta Networks: Improving Mamba2 with Delta Rule | not yet |
 9 |
BatchTopK Sparse Autoencoders | not yet |
 9 |
Comprehensive Evaluation of Multimodal AI Models in Medical Imaging Diagnosis: From Data Augmentation to Preference-Based Comparison | not yet |
 9 |
MAmmoTH-VL: Eliciting Multimodal Reasoning with Instruction Tuning at Scale | not yet |
 9 |
Evaluating and Aligning CodeLLMs on Human Preference | not yet |
 9 |
RandAR: Decoder-only Autoregressive Visual Generation in Random Orders | not yet |
 9 |
Scaling New Frontiers: Insights into Large Recommendation Models | not yet |
 8 |
Training Software Engineering Agents and Verifiers with SWE-Gym | not yet |
 8 |
Aria-UI: Visual Grounding for GUI Instructions | not yet |
 8 |
Align Anything: Training All-Modality Models to Follow Instructions with Language Feedback | not yet |
 8 |
Categorical Symmetries in Spin Models with Atom Arrays | not yet |
 8 |
GUI Agents: A Survey | not yet |
 8 |
RAG-Star: Enhancing Deliberative Reasoning with Retrieval Augmented Verification and Refinement | not yet |
 8 |
Fault-Tolerant Operation and Materials Science with Neutral Atom Logical Qubits | not yet |
 8 |
Hierarchical Split Federated Learning: Convergence Analysis and System Optimization | not yet |
 8 |
On the Expressive Power of Modern Hopfield Networks | not yet |
 8 |
International Scientific Report on the Safety of Advanced AI (Interim Report) | not yet |
 8 |
Diffusion-VLA: Scaling Robot Foundation Models via Unified Diffusion and Autoregression | not yet |
 8 |
U-MATH: A University-Level Benchmark for Evaluating Mathematical Skills in LLMs | not yet |
 8 |
Mind the Gap: Examining the Self-Improvement Capabilities of Large Language Models | not yet |
 8 |
An Automated Data Mining Framework Using Autoencoders for Feature Extraction and Dimensionality Reduction | not yet |
 7 |
TradingAgents: Multi-Agents LLM Financial Trading Framework | not yet |
 7 |
SegKAN: High-Resolution Medical Image Segmentation with Long-Distance Dependencies | not yet |
 7 |
DrivingGPT: Unifying Driving World Modeling and Planning with Multi-modal Autoregressive Transformers | not yet |
 7 |
KG4Diagnosis: A Hierarchical Multi-Agent LLM Framework with Knowledge Graph Enhancement for Medical Diagnosis | not yet |
 7 |
Progressive Multimodal Reasoning via Active Retrieval | not yet |
 7 |
MegaPairs: Massive Data Synthesis For Universal Multimodal Retrieval | not yet |
 7 |
Agent-SafetyBench: Evaluating the Safety of LLM Agents | not yet |
 7 |
Minimum Data Rate Maximization for Uplink Pinching-Antenna Systems | not yet |
 7 |
Large Language Model Enhanced Recommender Systems: A Survey | not yet |
 7 |
SafeAgentBench: A Benchmark for Safe Task Planning of Embodied LLM Agents | not yet |
 7 |
Attentive Eraser: Unleashing Diffusion Model's Object Removal Potential via Self-Attention Redirection Guidance | not yet |
 7 |
C3oT: Generating Shorter Chain-of-Thought without Compromising Effectiveness | not yet |
 7 |
Reinforcement Learning Enhanced LLMs: A Survey | not yet |
 7 |
SCBench: A KV Cache-Centric Analysis of Long-Context Methods | not yet |
 7 |
SPT: Sequence Prompt Transformer for Interactive Image Segmentation | not yet |
 7 |
Simple Guidance Mechanisms for Discrete Diffusion Models | not yet |
 7 |
A Survey on Uncertainty Quantification of Large Language Models: Taxonomy, Open Research Challenges, and Future Directions | not yet |
 7 |
APOLLO: SGD-like Memory, AdamW-level Performance | not yet |
 7 |
EXAONE 3.5: Series of Large Language Models for Real-world Use Cases |  |
 7 |
NaVILA: Legged Robot Vision-Language-Action Model for Navigation | not yet |
 7 |
Advanced Risk Prediction and Stability Assessment of Banks Using Time Series Transformer Models | not yet |
 7 |
Navigation World Models | not yet |
 7 |
ChatTS: Aligning Time Series with LLMs via Synthetic Data for Enhanced Understanding and Reasoning | not yet |
 7 |
Enhancing Recommendation Systems with GNNs and Addressing Over-Smoothing | not yet |
 7 |
Prithvi-EO-2.0: A Versatile Multi-Temporal Foundation Model for Earth Observation Applications | not yet |
 7 |
HUGSIM: A Real-Time, Photo-Realistic and Closed-Loop Simulator for Autonomous Driving | not yet |
 7 |
Are We There Yet? Revealing the Risks of Utilizing Large Language Models in Scholarly Peer Review | not yet |
 7 |
FullStack Bench: Evaluating LLMs as Full Stack Coders | not yet |
 7 |
Task Singular Vectors: Reducing Task Interference in Model Merging | not yet |
 6 |
VisionReward: Fine-Grained Multi-Dimensional Human Preference Learning for Image and Video Generation | not yet |
 6 |
GME: Improving Universal Multimodal Retrieval by Multimodal LLMs | not yet |
 6 |
Universal Machine Learning Interatomic Potentials are Ready for Phonons | not yet |
 6 |
Ensembling Large Language Models with Process Reward-Guided Tree Search for Better Complex Reasoning | not yet |
 6 |
Multi-LLM Text Summarization | not yet |
 6 |
AutoTrust: Benchmarking Trustworthiness in Large Vision Language Models for Autonomous Driving | not yet |
 6 |
MMLU-CF: A Contamination-free Multi-task Language Understanding Benchmark | not yet |
 6 |
How to Synthesize Text Data without Model Collapse? | not yet |
 6 |
Numerical Pruning for Efficient Autoregressive Models | not yet |
 6 |
Wonderland: Navigating 3D Scenes from a Single Image | not yet |
 6 |
ExecRepoBench: Multi-level Executable Code Completion Evaluation | not yet |
 6 |
A Survey of Mathematical Reasoning in the Era of Multimodal Large Language Model: Benchmark, Method & Challenges | not yet |
 6 |
SPaR: Self-Play with Tree-Search Refinement to Improve Instruction-Following in Large Language Models | not yet |
 6 |
ChatTime: A Unified Multimodal Time Series Foundation Model Bridging Numerical and Textual Data | 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/