🔬 Deep Learning - saeedesmaili · Scour

Evaluating the Representation Space of Diffusion Models via Self-Supervised Principles

🤖Data science Academic

RightNow-AI/AutoMegaKernel: An agent harness that compiles a model into one provably-correct, self-retargeting CUDA megakernel and self-tunes it past cuBLAS at batch-1 LLM decode.

⚡CUDA Code

github.com··Hacker News

Phantom transitions in language model fine-tuning

🎯Fine-tuning Academic

ND-TNN: Tensor-Neural-Network Approximation for High-Dimensional Nonlocal Diffusion Models

🧠Neural Networks Academic

Nonparametric undirected graphical model selection using diffusion models

📈Optimization Academic

Towards Robust Arabic Speech Emotion Recognition with Deep Learning

🧠Neural Networks Academic

Spiking Neural Network inference on FPGAs with hls4ml

🤖Machine Learning Academic

Diffusion Models for Adaptive Sequential Data Generation

🧠Neural Networks Academic

Less Is More: Training-Free Acceleration Framework of 3D Diffusion Models for Low-Count PET Denoising via Global-Local Trajectory Reduction

🔥PyTorch Academic

Geometry-Aware Dataset Condensation for Diffusion Model Training

🤖Machine Learning Academic

BiWM: Advancing Open-Source Interactive Video World Models with Bidirectional Autoregression

🧠LLMs Academic

Predicting Physical and Physical-Chemical Properties of Molecular-Based Materials Using Computational Neural Networks

🧠Neural Networks Academic

The Invisible Hand of Physics: When Video Diffusion Models Know More Than They Show

🧠Neural Networks Academic

AutoMegaKernel: A Statically-Checked Agent Harness for Self-Retargeting Megakernel Synthesis

⚡CUDA Academic

arxiv.org··Hacker News

Forward-Only Convolutional Neural Networks with Learnable Channel-Class Assignment

🧠Neural Networks Academic

LLM-Based Porting of Optimized C++ to CUDA Through Deoptimization and Reoptimization

⚡CUDA Academic

Optimality of FSQ Tokens for Continuous Diffusion for Categorical Data with Application to Text-to-Speech

💬Natural Language Processing Academic

Diffusion Models Observe Only Gradients: A Geometric Perspective on Score Matching Errors

🤖Data science Academic

ZIPP:Zero-shot Image Personalization from Personas

📸Street Photography Academic

SET: Stream-Event-Triggered Scheduling for Efficient CUDA Graph Pipelines

⚡CUDA Academic

Sign up or log in to see more results

Log in to enable infinite scrolling