AI論文解説 Youtubeチャンネル: AI時代の羅針盤
2024年11月頃に公開されたcsカテゴリの論文 (ID: 2411.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 |
|---|---|---|
 83 |
Tulu 3: Pushing Frontiers in Open Language Model Post-Training | not yet |
 72 |
A Survey on LLM-as-a-Judge | not yet |
 58 |
LLaVA-CoT: Let Vision Language Models Reason Step-by-Step |  |
 48 |
From Generation to Judgment: Opportunities and Challenges of LLM-as-a-judge | not yet |
 45 |
Generative Agent Simulations of 1,000 People |  |
 42 |
Marco-o1: Towards Open Reasoning Models for Open-Ended Solutions |  |
 40 |
FrontierMath: A Benchmark for Evaluating Advanced Mathematical Reasoning in AI |  |
 30 |
O1 Replication Journey -- Part 2: Surpassing O1-preview through Simple Distillation, Big Progress or Bitter Lesson? | not yet |
 30 |
Measuring short-form factuality in large language models | not yet |
 29 |
Enhancing the Reasoning Ability of Multimodal Large Language Models via Mixed Preference Optimization | not yet |
 27 |
OminiControl: Minimal and Universal Control for Diffusion Transformer | not yet |
 27 |
Logical computation demonstrated with a neutral atom quantum processor | not yet |
 26 |
Randomized Autoregressive Visual Generation | not yet |
 25 |
OpenCoder: The Open Cookbook for Top-Tier Code Large Language Models | not yet |
 25 |
How Far is Video Generation from World Model: A Physical Law Perspective |  |
 24 |
RedPajama: an Open Dataset for Training Large Language Models | not yet |
 24 |
Freeze-Omni: A Smart and Low Latency Speech-to-speech Dialogue Model with Frozen LLM | not yet |
 22 |
Does Prompt Formatting Have Any Impact on LLM Performance? | not yet |
 22 |
Scaling Laws for Precision |  |
 21 |
Enhancing LLM Reasoning with Reward-guided Tree Search | not yet |
 21 |
Circuit Complexity Bounds for RoPE-based Transformer Architecture | not yet |
 20 |
VBench++: Comprehensive and Versatile Benchmark Suite for Video Generative Models | not yet |
 20 |
How to Build a Quantum Supercomputer: Scaling from Hundreds to Millions of Qubits | not yet |
 19 |
Magentic-One: A Generalist Multi-Agent System for Solving Complex Tasks |  |
 18 |
Multimodal Whole Slide Foundation Model for Pathology | not yet |
 18 |
VLRewardBench: A Challenging Benchmark for Vision-Language Generative Reward Models | not yet |
 18 |
SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models | not yet |
 18 |
Taming Rectified Flow for Inversion and Editing | not yet |
 17 |
CAT4D: Create Anything in 4D with Multi-View Video Diffusion Models | not yet |
 17 |
Identity-Preserving Text-to-Video Generation by Frequency Decomposition | not yet |
 17 |
Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision | not yet |
 17 |
Insight-V: Exploring Long-Chain Visual Reasoning with Multimodal Large Language Models | not yet |
 17 |
WavChat: A Survey of Spoken Dialogue Models | not yet |
 17 |
Chinese SimpleQA: A Chinese Factuality Evaluation for Large Language Models | not yet |
 17 |
HourVideo: 1-Hour Video-Language Understanding | not yet |
 17 |
Hunyuan-Large: An Open-Source MoE Model with 52 Billion Activated Parameters by Tencent | not yet |
 16 |
Large Language Model-Brained GUI Agents: A Survey | not yet |
 16 |
On Statistical Rates of Conditional Diffusion Transformers: Approximation, Estimation and Minimax Optimality | not yet |
 16 |
DimensionX: Create Any 3D and 4D Scenes from a Single Image with Controllable Video Diffusion | not yet |
 15 |
Llama Guard 3 Vision: Safeguarding Human-AI Image Understanding Conversations | not yet |
 15 |
Emotion-Aware Interaction Design in Intelligent User Interface Using Multi-Modal Deep Learning | not yet |
 15 |
Towards evaluations-based safety cases for AI scheming | not yet |
 15 |
Personalization of Large Language Models: A Survey | not yet |
 14 |
Self-Generated Critiques Boost Reward Modeling for Language Models | not yet |
 14 |
Fundamental Limits of Prompt Tuning Transformers: Universality, Capacity and Efficiency | not yet |
 14 |
Hymba: A Hybrid-head Architecture for Small Language Models |  |
 14 |
The Surprising Effectiveness of Test-Time Training for Few-Shot Learning | not yet |
 13 |
RE-Bench: Evaluating frontier AI R&D capabilities of language model agents against human experts | not yet |
 13 |
Learning Humanoid Locomotion with Perceptive Internal Model | not yet |
 13 |
OpenScholar: Synthesizing Scientific Literature with Retrieval-augmented LMs | not yet |
 13 |
SageAttention2: Efficient Attention with Thorough Outlier Smoothing and Per-thread INT4 Quantization | not yet |
 13 |
Metric Learning for Tag Recommendation: Tackling Data Sparsity and Cold Start Issues | not yet |
 13 |
A Comprehensive Survey of Small Language Models in the Era of Large Language Models: Techniques, Enhancements, Applications, Collaboration with LLMs, and Trustworthiness | not yet |
 13 |
Improving Steering Vectors by Targeting Sparse Autoencoder Features | not yet |
 12 |
Inference Scaling fLaws: The Limits of LLM Resampling with Imperfect Verifiers | not yet |
 12 |
OphCLIP: Hierarchical Retrieval-Augmented Learning for Ophthalmic Surgical Video-Language Pretraining | not yet |
 12 |
DINO-X: A Unified Vision Model for Open-World Object Detection and Understanding |  |
 12 |
Self-Supervised Learning in Deep Networks: A Pathway to Robust Few-Shot Classification | not yet |
 12 |
A Preview of XiYan-SQL: A Multi-Generator Ensemble Framework for Text-to-SQL | not yet |
 12 |
Safety case template for frontier AI: A cyber inability argument | not yet |
 12 |
JanusFlow: Harmonizing Autoregression and Rectified Flow for Unified Multimodal Understanding and Generation | not yet |
 12 |
DiT4Edit: Diffusion Transformer for Image Editing | not yet |
 12 |
Hunyuan3D 1.0: A Unified Framework for Text-to-3D and Image-to-3D Generation | not yet |
 12 |
Addressing Representation Collapse in Vector Quantized Models with One Linear Layer | not yet |
 12 |
Vision-Language Models Can Self-Improve Reasoning via Reflection | not yet |
 12 |
DynaMath: A Dynamic Visual Benchmark for Evaluating Mathematical Reasoning Robustness of Vision Language Models | not yet |
 12 |
AutoGLM: Autonomous Foundation Agents for GUIs | not yet |
 12 |
PatternBoost: Constructions in Mathematics with a Little Help from AI | not yet |
 11 |
Critical Tokens Matter: Token-Level Contrastive Estimation Enhances LLM's Reasoning Capability | not yet |
 11 |
Scaling Speech-Text Pre-training with Synthetic Interleaved Data | not yet |
 11 |
Enhancing Few-Shot Learning with Integrated Data and GAN Model Approaches | not yet |
 11 |
All Languages Matter: Evaluating LMMs on Culturally Diverse 100 Languages | not yet |
 11 |
Optimizing Gesture Recognition for Seamless UI Interaction Using Convolutional Neural Networks | not yet |
 11 |
Graph Neural Network-Based Entity Extraction and Relationship Reasoning in Complex Knowledge Graphs | not yet |
 11 |
OASIS: Open Agent Social Interaction Simulations with One Million Agents | not yet |
 11 |
Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Model | not yet |
 11 |
ReCapture: Generative Video Camera Controls for User-Provided Videos using Masked Video Fine-Tuning | not yet |
 11 |
MM-Embed: Universal Multimodal Retrieval with Multimodal LLMs | not yet |
 11 |
MdEval: Massively Multilingual Code Debugging | not yet |
 11 |
Rule Based Rewards for Language Model Safety | not yet |
 11 |
Survey of Cultural Awareness in Language Models: Text and Beyond | not yet |
 11 |
Adding Error Bars to Evals: A Statistical Approach to Language Model Evaluations | not yet |
 10 |
VLSBench: Unveiling Visual Leakage in Multimodal Safety | not yet |
 10 |
INCLUDE: Evaluating Multilingual Language Understanding with Regional Knowledge | not yet |
 10 |
CogACT: A Foundational Vision-Language-Action Model for Synergizing Cognition and Action in Robotic Manipulation | not yet |
 10 |
Auto-RAG: Autonomous Retrieval-Augmented Generation for Large Language Models | not yet |
 10 |
Leveraging Semi-Supervised Learning to Enhance Data Mining for Image Classification under Limited Labeled Data | not yet |
 10 |
ShowUI: One Vision-Language-Action Model for GUI Visual Agent | not yet |
 10 |
Adaptive Cache Management for Complex Storage Systems Using CNN-LSTM-Based Spatiotemporal Prediction | not yet |
 10 |
SAMURAI: Adapting Segment Anything Model for Zero-Shot Visual Tracking with Motion-Aware Memory |  |
 10 |
High-fidelity universal gates in the $^{171}$Yb ground state nuclear spin qubit | not yet |
 10 |
Zero-Shot Automatic Annotation and Instance Segmentation using LLM-Generated Datasets: Eliminating Field Imaging and Manual Annotation for Deep Learning Model Development | not yet |
 10 |
The Dawn of GUI Agent: A Preliminary Case Study with Claude 3.5 Computer Use | not yet |
 10 |
LoRA-LiteE: A Computationally Efficient Framework for Chatbot Preference-Tuning | not yet |
 10 |
Spider 2.0: Evaluating Language Models on Real-World Enterprise Text-to-SQL Workflows | not yet |
 10 |
Rethinking Bradley-Terry Models in Preference-Based Reward Modeling: Foundations, Theory, and Alternatives | not yet |
 10 |
From Medprompt to o1: Exploration of Run-Time Strategies for Medical Challenge Problems and Beyond | not yet |
 10 |
Large Language Models Orchestrating Structured Reasoning Achieve Kaggle Grandmaster Level | not yet |
 10 |
TableGPT2: A Large Multimodal Model with Tabular Data Integration | not yet |
 10 |
Fish-Speech: Leveraging Large Language Models for Advanced Multilingual Text-to-Speech Synthesis | not yet |
 9 |
GRAPE: Generalizing Robot Policy via Preference Alignment | not yet |
 9 |
AC3D: Analyzing and Improving 3D Camera Control in Video Diffusion Transformers | not yet |
 9 |
TimeMarker: A Versatile Video-LLM for Long and Short Video Understanding with Superior Temporal Localization Ability | not yet |
 9 |
SALMONN-omni: A Codec-free LLM for Full-duplex Speech Understanding and Generation | not yet |
 9 |
WF-VAE: Enhancing Video VAE by Wavelet-Driven Energy Flow for Latent Video Diffusion Model | not yet |
 9 |
MME-Survey: A Comprehensive Survey on Evaluation of Multimodal LLMs | not yet |
 9 |
XGrammar: Flexible and Efficient Structured Generation Engine for Large Language Models | not yet |
 9 |
Towards Next-Generation Medical Agent: How o1 is Reshaping Decision-Making in Medical Scenarios | not yet |
 9 |
Multimodal Autoregressive Pre-training of Large Vision Encoders | not yet |
 9 |
BALROG: Benchmarking Agentic LLM and VLM Reasoning On Games | not yet |
 9 |
Disentangling Memory and Reasoning Ability in Large Language Models | not yet |
 9 |
A Combined Encoder and Transformer Approach for Coherent and High-Quality Text Generation | not yet |
 9 |
BlueLM-V-3B: Algorithm and System Co-Design for Multimodal Large Language Models on Mobile Devices | not yet |
 9 |
Large Wireless Model (LWM): A Foundation Model for Wireless Channels | not yet |
 9 |
Is Your LLM Secretly a World Model of the Internet? Model-Based Planning for Web Agents | not yet |
 9 |
A Survey on Kolmogorov-Arnold Network | not yet |
 9 |
Dynamic-SUPERB Phase-2: A Collaboratively Expanding Benchmark for Measuring the Capabilities of Spoken Language Models with 180 Tasks | not yet |
 9 |
LLM2CLIP: Powerful Language Model Unlocks Richer Visual Representation |  |
 9 |
GUI Agents with Foundation Models: A Comprehensive Survey | not yet |
 9 |
Advanced RAG Models with Graph Structures: Optimizing Complex Knowledge Reasoning and Text Generation | not yet |
 9 |
Distributionally Robust Optimization | not yet |
 9 |
Attacking Vision-Language Computer Agents via Pop-ups | not yet |
 9 |
WebRL: Training LLM Web Agents via Self-Evolving Online Curriculum Reinforcement Learning | not yet |
 9 |
On Targeted Manipulation and Deception when Optimizing LLMs for User Feedback | not yet |
 9 |
DexHub and DART: Towards Internet Scale Robot Data Collection | not yet |
 9 |
GameGen-X: Interactive Open-world Game Video Generation |  |
 9 |
A Public Dataset Tracking Social Media Discourse about the 2024 U.S. Presidential Election on Twitter/X | not yet |
 9 |
RSL-SQL: Robust Schema Linking in Text-to-SQL Generation | not yet |
 8 |
Beyond Examples: High-level Automated Reasoning Paradigm in In-Context Learning via MCTS | not yet |
 8 |
Filter, Correlate, Compress: Training-Free Token Reduction for MLLM Acceleration | not yet |
 8 |
Transformers are Deep Optimizers: Provable In-Context Learning for Deep Model Training | not yet |
 8 |
LLaMA-MoE v2: Exploring Sparsity of LLaMA from Perspective of Mixture-of-Experts with Post-Training | not yet |
 8 |
FocusLLaVA: A Coarse-to-Fine Approach for Efficient and Effective Visual Token Compression | not yet |
 8 |
Evaluating the Robustness of Analogical Reasoning in Large Language Models | not yet |
 8 |
When Precision Meets Position: BFloat16 Breaks Down RoPE in Long-Context Training | not yet |
 8 |
Video-RAG: Visually-aligned Retrieval-Augmented Long Video Comprehension | not yet |
 8 |
Procedural Knowledge in Pretraining Drives Reasoning in Large Language Models |  |
 8 |
Understanding Chain-of-Thought in LLMs through Information Theory | not yet |
 8 |
ACE2: Accurately learning subseasonal to decadal atmospheric variability and forced responses | not yet |
 8 |
AnimateAnything: Consistent and Controllable Animation for Video Generation | not yet |
 8 |
Seeing Clearly by Layer Two: Enhancing Attention Heads to Alleviate Hallucination in LVLMs | not yet |
 8 |
Golden Noise for Diffusion Models: A Learning Framework |  |
 8 |
Game-theoretic LLM: Agent Workflow for Negotiation Games | not yet |
 8 |
Autoregressive Models in Vision: A Survey | not yet |
 8 |
LLMs as Research Tools: A Large Scale Survey of Researchers' Usage and Perceptions | not yet |
 8 |
Quantum speedups in solving near-symmetric optimization problems by low-depth QAOA | not yet |
 8 |
Language Models are Hidden Reasoners: Unlocking Latent Reasoning Capabilities via Self-Rewarding | not yet |
 8 |
Science and Project Planning for the Forward Physics Facility in Preparation for the 2024-2026 European Particle Physics Strategy Update | not yet |
 8 |
Evaluation data contamination in LLMs: how do we measure it and (when) does it matter? | not yet |
 8 |
Align-SLM: Textless Spoken Language Models with Reinforcement Learning from AI Feedback | not yet |
 8 |
What do sin$(x)$ and arcsinh$(x)$ have in Common? | not yet |
 8 |
Lingma SWE-GPT: An Open Development-Process-Centric Language Model for Automated Software Improvement | not yet |
 8 |
A Lorentz-Equivariant Transformer for All of the LHC | not yet |
 8 |
Project Sid: Many-agent simulations toward AI civilization | not yet |
 7 |
Lift3D Foundation Policy: Lifting 2D Large-Scale Pretrained Models for Robust 3D Robotic Manipulation | not yet |
 7 |
$H^3$Fusion: Helpful, Harmless, Honest Fusion of Aligned LLMs | not yet |
 7 |
I2VControl: Disentangled and Unified Video Motion Synthesis Control | 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/