Articles
Semantics-Oriented Reward Design With "PrefBERT," A New Evaluation Method To Evolve Long Sentence Generation
Semantics-Oriented Reward Design With "PrefBERT," A New Evaluation Method To Evolve Long Sentence Ge ...
The Challenge Of "Embodied Web Agents," The Next Generation AI That Fuses The Physical And Digital
The Challenge Of "Embodied Web Agents," The Next Generation AI That Fuses The Physical And Digital
A New Wave Of Multispeaker Speech Recognition! The Challenge Of High Accuracy Systems By DiCoW And DiariZen
A New Wave Of Multispeaker Speech Recognition! The Challenge Of High Accuracy Systems By DiCoW And D ...
GenRecal, A General-purpose Distillation Framework For Lightweight, High-performance Distillation
GenRecal, A General-purpose Distillation Framework For Lightweight, High-performance Distillation
ProtoReasoning: General-purpose Reasoning Skills Honed Through Logic And Planning
ProtoReasoning: General-purpose Reasoning Skills Honed Through Logic And Planning
A Proposal For Mixed-first Optimization That Revolutionizes The Inference Performance Of Multimodal LLMs!
A Proposal For Mixed-first Optimization That Revolutionizes The Inference Performance Of Multimodal ...
UnifiedCrawl: A New Approach To Low-Resource Language Data Collection And Efficient LLM Adaptation
UnifiedCrawl: A New Approach To Low-Resource Language Data Collection And Efficient LLM Adaptation
Other
OpenScholar: Knowledge Synthesis And Reliability Enhancement Of Scientific Literature With LLM
OpenScholar: Knowledge Synthesis And Reliability Enhancement Of Scientific Literature With LLM
LLMs As Mentors Instead Of Humans? Reinforcement Learning Agents Trained In Natural Language
LLMs As Mentors Instead Of Humans? Reinforcement Learning Agents Trained In Natural Language
Ultra-Sparse Memory Network: A New Method To Change Transformer Memory Efficiency
Ultra-Sparse Memory Network: A New Method To Change Transformer Memory Efficiency
Hymba, A New Architecture That Pushes The Limits Of Small LLMs
Hymba, A New Architecture That Pushes The Limits Of Small LLMs
Insight-V: A New Strategy For Multimodal Reasoning Connecting Vision And Thought
Insight-V: A New Strategy For Multimodal Reasoning Connecting Vision And Thought
Stable Flow: Visualization Of The "really Important Layers" Behind Image Generation
Stable Flow: Visualization Of The "really Important Layers" Behind Image Generation
Open Vocabulary Object Detection Enabled By OWL-ViT
Open Vocabulary Object Detection Enabled By OWL-ViT
Neural Network
![SOK-Bench] Situation](https://aisholar.s3.ap-northeast-1.amazonaws.com/media/February2025/sok-bench-520x300.png)
SOK-Bench] Situational Video Inference Benchmark Using Real-World Knowledge In Video
SOK-Bench] Situational Video Inference Benchmark Using Real-World Knowledge In Video
Computer Vision
![Libra] A New Multimo](https://aisholar.s3.ap-northeast-1.amazonaws.com/media/February2025/libra-520x300.png)
Libra] A New Multimodal Design Of Large Language Models Using Separate Vision Systems
Libra] A New Multimodal Design Of Large Language Models Using Separate Vision Systems
Large Language Models
![DrHouse] Diagnostic](https://aisholar.s3.ap-northeast-1.amazonaws.com/media/February2025/drhouse-520x300.png)
DrHouse] Diagnostic System Using Sensor Information And Expertise
DrHouse] Diagnostic System Using Sensor Information And Expertise
Medical
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
![[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
![Qwen2.5-Coder] LLM S](https://aisholar.s3.ap-northeast-1.amazonaws.com/media/October2024/qwen2-5-coder-520x300.png)
Qwen2.5-Coder] LLM Specialized For Code Generation, Completion, And Mathematical Reasoning Tasks
Qwen2.5-Coder] LLM Specialized For Code Generation, Completion, And Mathematical Reasoning Tasks
Large Language Models
NeurIPS2020 Highlights
NeurIPS2020 Highlights
Survey
Easy! High Accuracy! Attractiveness Of The Anomaly Detection Model PatchCore
Easy! High Accuracy! Attractiveness Of The Anomaly Detection Model PatchCore
Object Detection
GAIA: New Benchmark Reveals Limitations Of Large-Scale Language Models
GAIA: New Benchmark Reveals Limitations Of Large-Scale Language Models
Large Language Models
![[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
AI Art Vs Human Art -Which Do People Prefer?
AI Art Vs Human Art -Which Do People Prefer?
Image Generation
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
The Latest Comprehensive Review Of Activation Functions!
The Latest Comprehensive Review Of Activation Functions!
Survey
Simulate The Behavior Of 25 AI Agents In A Virtual Space City!
Simulate The Behavior Of 25 AI Agents In A Virtual Space City!
Large Language Models