lnyan 的提交内容

Diffusion Models for Optical Flow and Monocular Depth Estimation

Probabilistic Adaptation of Text-to-Video Models

HeadSculpt: Crafting 3D Head Avatars with Text

Lossless-cut: The Swiss army knife of lossless video/audio editing

The Finest Windows Optimizer

Category Theory for Everyone

Large language models do not recognize identifier swaps in Python

Cinematic Mindscapes: High-Quality Video Reconstruction from Brain Activity

Connect() – a new API for creating TCP sockets from Cloudflare Workers

Shortest Path to Boundary for Self-Intersecting Meshes

Common Diffusion Noise Schedules and Sample Steps Are Flawed

Real-Time Neural Appearance Models

Pake: Convert Website to Desktop App with Rust

The Forward-Forward Algorithm: Some Preliminary Investigations (2022)

Learning Locally Editable Virtual Humans

DreamFace: Progressive Generation of Animatable 3D Faces Under Text Guidance

Why is a conditional move not vulnerable to Branch Prediction Failure

Pyro: Deep universal probabilistic programming with Python and PyTorch

JaxPruner: A concise library for sparsity research

We're afraid language models aren't modeling ambiguity

ChatVideo: A Tracklet-Centric Multimodal Video Understanding System

How Does GPT Obtain Its Ability? Tracing Emergent Ability of LMs to Its Sources

Geometry Processing – Curvature

What is this vmmem program that is using up all my CPU and memory (2018)

On-Device Acceleration of Large Diffusion Models via GPU-Aware Optimizations

Transform 2D Diffusion into 3D, alleviate Janus problem and Beyond

HOSNeRF: Dynamic Human-Object-Scene Neural Radiance Fields from a Single Video

SA3D: Segment Anything in 3D with NeRFs

Track Anything: Segment Anything Meets Videos