SLTarch: Towards Scalable Point-Based Neural Rendering by Taming Workload Imbalance and Memory Irregularity
arxiv.org·2d
🌐WebGPU
Lobsters Interview with Icefox
lobste.rs·6h·
Discuss: Lobsters
🗣️Language Servers
“Opponent shaping” as a model for manipulation and cooperation
lesswrong.com·14h
🧮Linear Algebra
Open source PDF reader built with Rust, Dioxus and PDFium
github.com·1d·
Discuss: Hacker News
🌐WebGPU
SketchMind: A Multi-Agent Cognitive Framework for Assessing Student-Drawn Scientific Sketches
arxiv.org·19h
🤖AI
Probabilistic Directed Distance Fields for Ray-Based Shape Representations
arxiv.org·2d
🕯️Candle
BANG: Dividing 3D Assets via Generative Exploded Dynamics
arxiv.org·2d
🎮Game Engines
GSFusion:Globally Optimized LiDAR-Inertial-Visual Mapping for Gaussian Splatting
arxiv.org·19h
🎮Game Engines
No Redundancy, No Stall: Lightweight Streaming 3D Gaussian Splatting for Real-time Rendering
arxiv.org·2d
🌐WebGPU
AI paradigm for solving differential equations: first-principles data generation and scale-dilation operator AI solver
arxiv.org·19h
🤖AI
I designed my own ridiculously fast game streaming video codec
themaister.net·4d·
Discuss: Lobsters, Hacker News
🎮Game Engines
VizGenie: Toward Self-Refining, Domain-Aware Workflows for Next-Generation Scientific Visualization
arxiv.org·2d
🌐WebGPU
CST Anti-UAV: A Thermal Infrared Benchmark for Tiny UAV Tracking in Complex Scenes
arxiv.org·19h
🔢SIMD Programming
Distance and Collision Probability Estimation from Gaussian Surface Models
arxiv.org·1d
🎮Game Engines
Discrete Tokenization for Multimodal LLMs: A Comprehensive Survey
arxiv.org·19h
🗣️Language Servers
Lobsters Interview with Icefox
lobste.rs·6h·
Discuss: Lobsters
🗣️Language Servers
A Massively Parallel Performance Portable Free-space Spectral Poisson Solver
arxiv.org·2d
🎮Game Engines
Good Learners Think Their Thinking: Generative PRM Makes Large Reasoning Model More Efficient Math Learner
arxiv.org·19h
🕯️Candle
X-NeMo: Expressive Neural Motion Reenactment via Disentangled Latent Attention
arxiv.org·19h
🤖AI
Cardiac-CLIP: A Vision-Language Foundation Model for 3D Cardiac CT Images
arxiv.org·2d
🕯️Candle