본문으로 건너뛰기

최신 포스트

[논문리뷰] ZipTok3D: High-Fidelity 3D Tokenization with Compact Token Prefixes

댓글 수 로딩 중

[논문리뷰] Wasserstein-Barycentric Interaction Fields for Spatial Factor Models: Evidence from Language-Model Representations

댓글 수 로딩 중

[논문리뷰] SolarWM: Open Data and Scalable Training for Long-Horizon Video World Models

댓글 수 로딩 중

[논문리뷰] SnapBench: Benchmarking Snap-and-Ask Multimodal Retrieval for Mobile Interactions

댓글 수 로딩 중

[논문리뷰] Portfolio Risk Bounds without Cross-Asset Return Covariances: Distributional Fields from Language-Model Representations

댓글 수 로딩 중

[논문리뷰] On the Design Fundamentals of Pixel Text Representation Learning

댓글 수 로딩 중

[논문리뷰] NeoMME: A Single-Tower Multimodal-Native Multilingual Foundation Encoder for Efficient Fine-Tuning and Inference

댓글 수 로딩 중

[논문리뷰] Kirin: Animal Motion Generation from In-the-Wild Video

댓글 수 로딩 중

[논문리뷰] It Takes Two to Match: Co-Evolving Generative Retriever with Reinforcement Learning

댓글 수 로딩 중

[논문리뷰] Institutional Newspapers Pipeline: Deriving billions of high quality tokens from historical newspapers

댓글 수 로딩 중

[논문리뷰] Influence-Directed Distillation: Solving the Diversity Bottleneck in Sampled-Token On-Policy Distillation

댓글 수 로딩 중