#Representation Learning

19개의 포스트

[논문리뷰] SciLT: Long-Tailed Classification in Scientific Image Domains

Bing Su이 arXiv에 게시한 'SciLT: Long-Tailed Classification in Scientific Image Domains' 논문에 대한 자세한 리뷰입니다.

#Review #Long-Tailed Recognition #Scientific Image Domain #Foundation Models #Parameter-Efficient Fine-Tuning #Feature Fusion #Domain Shift #Representation Learning

2026년 4월 6일

[논문리뷰] Ghost-FWL: A Large-Scale Full-Waveform LiDAR Dataset for Ghost Detection and Removal

Takahiro Kado이 arXiv에 게시한 'Ghost-FWL: A Large-Scale Full-Waveform LiDAR Dataset for Ghost Detection and Removal' 논문에 대한 자세한 리뷰입니다.

#Review #Full-Waveform LiDAR #Ghost Removal #Masked Autoencoder #Mobile LiDAR #Dataset #Representation Learning

2026년 3월 31일

[논문리뷰] Utonia: Toward One Encoder for All Point Clouds

arXiv에 게시된 'Utonia: Toward One Encoder for All Point Clouds' 논문에 대한 자세한 리뷰입니다.

#Review #Point Clouds #Self-supervised Learning #Multi-domain Learning #Foundation Model #Point Transformer #Representation Learning #Robotics #Spatial Reasoning

2026년 3월 3일

[논문리뷰] InfoNCE Induces Gaussian Distribution

arXiv에 게시된 'InfoNCE Induces Gaussian Distribution' 논문에 대한 자세한 리뷰입니다.

#Review #Contrastive Learning #InfoNCE Loss #Gaussian Distribution #Representation Learning #Self-Supervised Learning #Hyperspherical Uniformity #Thin-Shell Concentration

2026년 3월 1일

[논문리뷰] MAEB: Massive Audio Embedding Benchmark

arXiv에 게시된 'MAEB: Massive Audio Embedding Benchmark' 논문에 대한 자세한 리뷰입니다.

#Review #Audio Embedding #Benchmark #Multimodal #Zero-shot Classification #Clustering #Representation Learning #MTEB Ecosystem #Cross-modal Audio-Text #Multilingual Audio

2026년 2월 18일

[논문리뷰] Modality Gap-Driven Subspace Alignment Training Paradigm For Multimodal Large Language Models

Hanzhen Zhao이 arXiv에 게시한 'Modality Gap-Driven Subspace Alignment Training Paradigm For Multimodal Large Language Models' 논문에 대한 자세한 리뷰입니다.

#Review #Multimodal Large Language Models (MLLMs)#Modality Gap #Subspace Alignment #Unpaired Data #Representation Learning #Pretraining #Geometric Alignment

2026년 2월 9일

[논문리뷰] KV-Embedding: Training-free Text Embedding via Internal KV Re-routing in Decoder-only LLMs

Yi Yang이 arXiv에 게시한 'KV-Embedding: Training-free Text Embedding via Internal KV Re-routing in Decoder-only LLMs' 논문에 대한 자세한 리뷰입니다.

#Review #Text Embedding #Decoder-only LLMs #Training-free #KV Re-routing #Causal Attention #Representation Learning #Intrinsic Dimensionality

2026년 1월 5일

[논문리뷰] Learning from Next-Frame Prediction: Autoregressive Video Modeling Encodes Effective Representations

arXiv에 게시된 'Learning from Next-Frame Prediction: Autoregressive Video Modeling Encodes Effective Representations' 논문에 대한 자세한 리뷰입니다.

#Review #Autoregressive Model #Video Modeling #Generative Pretraining #Representation Learning #Flow-Matching Decoder #Context Isolation #Masked Next-Frame Prediction

2025년 12월 24일

[논문리뷰] In Pursuit of Pixel Supervision for Visual Pre-training

Dong Wang이 arXiv에 게시한 'In Pursuit of Pixel Supervision for Visual Pre-training' 논문에 대한 자세한 리뷰입니다.

#Review #Pixel Supervision #Self-Supervised Learning #Masked Autoencoders (MAE)#Visual Pre-training #Foundation Models #Representation Learning #Web-Scale Data #Computer Vision

2025년 12월 17일

[논문리뷰] DiG-Flow: Discrepancy-Guided Flow Matching for Robust VLA Models

arXiv에 게시된 'DiG-Flow: Discrepancy-Guided Flow Matching for Robust VLA Models' 논문에 대한 자세한 리뷰입니다.

#Review #VLA Models #Flow Matching #Robotics #Robustness #Distribution Shift #Wasserstein Distance #Geometric Regularization #Representation Learning

2025년 12월 2일

[논문리뷰] FedRE: A Representation Entanglement Framework for Model-Heterogeneous Federated Learning

Simin Chen이 arXiv에 게시한 'FedRE: A Representation Entanglement Framework for Model-Heterogeneous Federated Learning' 논문에 대한 자세한 리뷰입니다.

#Review #Federated Learning #Model Heterogeneity #Representation Learning #Privacy Preservation #Communication Efficiency #Entangled Representation #Knowledge Transfer

2025년 11월 30일

[논문리뷰] Virtual Width Networks

arXiv에 게시된 'Virtual Width Networks' 논문에 대한 자세한 리뷰입니다.

#Review #Virtual Width Networks #Transformer #Mixture-of-Experts (MoE)#Scaling Laws #Representation Learning #Model Efficiency #Multi-Token Prediction #Hyper-Connections

2025년 11월 16일

[논문리뷰] RECALL: REpresentation-aligned Catastrophic-forgetting ALLeviation via Hierarchical Model Merging

arXiv에 게시된 'RECALL: REpresentation-aligned Catastrophic-forgetting ALLeviation via Hierarchical Model Merging' 논문에 대한 자세한 리뷰입니다.

#Review #Catastrophic Forgetting #Continual Learning #Model Merging #LLMs #Representation Learning #Data-free Learning #Hierarchical Parameter Fusion

2025년 10월 27일

[논문리뷰] Language Models are Injective and Hence Invertible

arXiv에 게시된 'Language Models are Injective and Hence Invertible' 논문에 대한 자세한 리뷰입니다.

#Review #Language Models #Injectivity #Invertibility #Transformer #Representation Learning #Exact Recovery #SIPIT Algorithm #Real Analysis

2025년 10월 23일

[논문리뷰] UniME-V2: MLLM-as-a-Judge for Universal Multimodal Embedding Learning

Ziyong Feng이 arXiv에 게시한 'UniME-V2: MLLM-as-a-Judge for Universal Multimodal Embedding Learning' 논문에 대한 자세한 리뷰입니다.

#Review #Multimodal Embeddings #MLLM-as-a-Judge #Hard Negative Mining #Semantic Alignment #Representation Learning #Reranking #Contrastive Learning

2025년 10월 16일

[논문리뷰] Spatial Forcing: Implicit Spatial Representation Alignment for Vision-language-action Model

arXiv에 게시된 'Spatial Forcing: Implicit Spatial Representation Alignment for Vision-language-action Model' 논문에 대한 자세한 리뷰입니다.

#Review #Vision-Language-Action Models #Spatial Perception #Implicit Representation Alignment #3D Foundation Models #Robotics #Data Efficiency #Representation Learning

2025년 10월 15일

[논문리뷰] Scaling Language-Centric Omnimodal Representation Learning

arXiv에 게시된 'Scaling Language-Centric Omnimodal Representation Learning' 논문에 대한 자세한 리뷰입니다.

#Review #Multimodal Embeddings #MLLMs #Contrastive Learning #Cross-modal Alignment #Generative Pretraining #Representation Learning #Scaling Laws

2025년 10월 15일

[논문리뷰] Advancing End-to-End Pixel Space Generative Modeling via Self-supervised Pre-training

arXiv에 게시된 'Advancing End-to-End Pixel Space Generative Modeling via Self-supervised Pre-training' 논문에 대한 자세한 리뷰입니다.

#Review #Pixel-space Generative Models #Diffusion Models #Consistency Models #Self-supervised Pre-training #End-to-end Training #Image Generation #FID #Representation Learning

2025년 10월 15일

[논문리뷰] Latent Zoning Network: A Unified Principle for Generative Modeling, Representation Learning, and Classification

Wenyu Wang이 arXiv에 게시한 'Latent Zoning Network: A Unified Principle for Generative Modeling, Representation Learning, and Classification' 논문에 대한 자세한 리뷰입니다.

#Review #Generative Modeling #Representation Learning #Classification #Unified Framework #Latent Space #Flow Matching #Deep Learning #Image Generation

2025년 9월 22일