GenRecal, A General-purpose Distillation Framework For Lightweight, High-performance Distillation
GenRecal, A General-purpose Distillation Framework For Lightweight, High-performance Distillation
Other
Deep Learning
ProtoReasoning: General-purpose Reasoning Skills Honed Through Logic And Planning
ProtoReasoning: General-purpose Reasoning Skills Honed Through Logic And Planning
Other
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
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
A Comprehensive Survey Of The Current Status And Challenges Of AI-Based Predictive Maintenance In The Steel Industry
A Comprehensive Survey Of The Current Status And Challenges Of AI-Based Predictive Maintenance In Th ...
Prediction Model
Proposal Of An Optimization Method For Activation Functions And CRReLU Using Information Entropy
Proposal Of An Optimization Method For Activation Functions And CRReLU Using Information Entropy
Loss Function
[For Everyone To Enjoy The Convenience... Speaker Adaptation Of Dysarthric Speech Using Whisper
[For Everyone To Enjoy The Convenience... Speaker Adaptation Of Dysarthric Speech Using Whisper
Speech Recognition For The Dysarthric
Speech Processing Model That Defies Common Sense! The Amazing Performance Of The Speech Processing Model "SpeechT5" Developed By M ...
Speech Processing Model That Defies Common Sense! The Amazing Performance Of The Speech Processing M ...
Sound
[You're Using Wav2vec2 For This? It Makes Feature Extraction Of Dysarthric Speech More Efficient!
[You're Using Wav2vec2 For This? It Makes Feature Extraction Of Dysarthric Speech More Efficient!
Speech Recognition For The Dysarthric