Articles
RStar2-Agent: State-of-the-Art Mathematical Reasoning Reached By Efficient Agent-Based Reinforcement Learning With GRPO-RoC
RStar2-Agent: State-of-the-Art Mathematical Reasoning Reached By Efficient Agent-Based Reinforcement ...
Pref-GRPO: A New Method For Stable Reinforcement Learning Of Text Image Generation Using Pairwise Comparison
Pref-GRPO: A New Method For Stable Reinforcement Learning Of Text Image Generation Using Pairwise Co ...
TRACEALIGN: Tracing Causes Of Alignment Drift In Large Language Models And Defensive Measures
TRACEALIGN: Tracing Causes Of Alignment Drift In Large Language Models And Defensive Measures
AlignGuard-LoRA: A New Regularization Method That Combines Efficient Fine-Tuning And Safety Preservation
AlignGuard-LoRA: A New Regularization Method That Combines Efficient Fine-Tuning And Safety Preserva ...
ChartCap: Suppressing Chart Captioning Hallucinations With Large Data Sets And New Evaluation Indexes
ChartCap: Suppressing Chart Captioning Hallucinations With Large Data Sets And New Evaluation Indexe ...
LAMIC: A Learning-free, Layout-controllable, Multi-reference Image Generation Method
LAMIC: A Learning-free, Layout-controllable, Multi-reference Image Generation Method
LiveMCPBench: A New Benchmark For Evaluating LLM Agents In Large Tool Environments
LiveMCPBench: A New Benchmark For Evaluating LLM Agents In Large Tool Environments
Goedel-Prover-V2: New Developments In Efficient Automated Theorem Proving By Self-Correction And Stepwise Data Synthesis
Goedel-Prover-V2: New Developments In Efficient Automated Theorem Proving By Self-Correction And Ste ...
New Developments In Multi-person Conversation Video Generation! MIT Dataset And Baseline Model "CovOG
New Developments In Multi-person Conversation Video Generation! MIT Dataset And Baseline Model "CovO ...
ToolTrain: A New Method For Repository Deep Search And Issue Localization With LLM
ToolTrain: A New Method For Repository Deep Search And Issue Localization With LLM
Mechanism And Effect Of "Representation Shift" Token Compression For FlashAttention
Mechanism And Effect Of "Representation Shift" Token Compression For FlashAttention
CRINN: Automatic Optimization Of Approximate Nearest Neighbor Search Algorithms Using Reinforcement Learning
CRINN: Automatic Optimization Of Approximate Nearest Neighbor Search Algorithms Using Reinforcement ...
CompassVerifier: A New Benchmark And Robust Model To Revolutionize LLM Solution Verification
CompassVerifier: A New Benchmark And Robust Model To Revolutionize LLM Solution Verification
LongVie: A New Era Of 1-minute Ultra-High Quality Video Generation Realized By Multimodal Control
LongVie: A New Era Of 1-minute Ultra-High Quality Video Generation Realized By Multimodal Control
Skywork UniPic: Next-generation Multimodal Model That Integrates Image Understanding, Generation, And Editing With High Efficiency
Skywork UniPic: Next-generation Multimodal Model That Integrates Image Understanding, Generation, An ...
Seed Diffusion Preview: Next-generation Code Generation Model That Combines Fast Inference And High Performance
Seed Diffusion Preview: Next-generation Code Generation Model That Combines Fast Inference And High ...
MATE: Multi-agent Accessibility-specific Modality Transformation Framework
MATE: Multi-agent Accessibility-specific Modality Transformation Framework
Wavelet Diffusion: The Fastest Diffusion Model
Wavelet Diffusion: The Fastest Diffusion Model
Image Generation
Improved Accuracy And Transparency Of Face Recognition With ChatGPT, New Developments In Soft Biometrics
Improved Accuracy And Transparency Of Face Recognition With ChatGPT, New Developments In Soft Biomet ...
Large Language Models
![[RL-GPT] A Framework](https://aisholar.s3.ap-northeast-1.amazonaws.com/media/March2024/rl-gpt-520x300.png)
[RL-GPT] A Framework To Acquire Diamonds Several Times Faster Than Usual With Mincraft Is Now Available
[RL-GPT] A Framework To Acquire Diamonds Several Times Faster Than Usual With Mincraft Is Now Availa ...
Machine Learning
A Framework Is Now Available That Allows LLMs To Assess Human Personality Using The MBTI!
A Framework Is Now Available That Allows LLMs To Assess Human Personality Using The MBTI!
ChatGPT
VCRL: A New Approach To LLM Reinforcement Learning That Controls Learning Difficulty With Reward Variance
VCRL: A New Approach To LLM Reinforcement Learning That Controls Learning Difficulty With Reward Var ...
Easy! High Accuracy! Attractiveness Of The Anomaly Detection Model PatchCore
Easy! High Accuracy! Attractiveness Of The Anomaly Detection Model PatchCore
Object Detection
![[DPO] A Method For D](https://aisholar.s3.ap-northeast-1.amazonaws.com/media/January2024/direct_preference_optimization-520x300.png)
[DPO] A Method For Directly Matching Large-scale Language Models To User Preferences Without Using Reinforcement Learning
[DPO] A Method For Directly Matching Large-scale Language Models To User Preferences Without Using R ...
RLHF
Machine Learning Model Tackles Soccer Match Prediction In Sports Betting
Machine Learning Model Tackles Soccer Match Prediction In Sports Betting
Sports Analytics
The Challenge Of Social-MAE, A Social AI That Uses Self-supervised Learning To Decipher Emotions, Laughter, And Personality
The Challenge Of Social-MAE, A Social AI That Uses Self-supervised Learning To Decipher Emotions, La ...
![Qwen2-VL] Latest VLM](https://aisholar.s3.ap-northeast-1.amazonaws.com/media/October2024/qwen2-vl-520x300.png)
Qwen2-VL] Latest VLM That Can Process Images And Videos In Different Resolutions
Qwen2-VL] Latest VLM That Can Process Images And Videos In Different Resolutions
Large Language Models
ImmerseGen: Agent-guided, Lightweight X Highly Realistic Next-generation VR Scene Generation
ImmerseGen: Agent-guided, Lightweight X Highly Realistic Next-generation VR Scene Generation
Superior To ViT! A New Underlying Model For Large-Scale CNNs! : InternImage
Superior To ViT! A New Underlying Model For Large-Scale CNNs! : InternImage
Deep Learning
![[Swin Transformer] T](https://aisholar.s3.ap-northeast-1.amazonaws.com/media/February2024/swin_transformer-520x300.png)
[Swin Transformer] Transformer-based Image Recognition Models To Keep Now!
[Swin Transformer] Transformer-based Image Recognition Models To Keep Now!
Image Recognition
U-Net And Transformer Combined! Introducing Swin Unet, A New Network For Medical Image Segmentation.
U-Net And Transformer Combined! Introducing Swin Unet, A New Network For Medical Image Segmentation.
Medical