Tag
MeshWeaver presents an autoregressive mesh generation framework that directly predicts vertices using a multi-level sparse-voxel encoder, achieving state-of-the-art compression and geometric fidelity for high-poly meshes.
Introduces Amortized Factor Inference Networks (AFINs), a family of encode-merge-decode inference networks that generalize across varying priors, likelihoods, and dimensionality, achieving posterior accuracy comparable to NUTS with much less compute.
Thermocompute is a PyTorch emulator for thermodynamic probabilistic computing that enables neural network layers to achieve constant modeled physical time inference by exploiting parallel thermodynamic substrate, with immediate GPU-usable stochastic layers.
AutoMCU is a multi-agent system leveraging LLMs to automate neural network design for microcontroller units, significantly reducing customization time while ensuring feasibility under hardware constraints.
VirtualPC is an open-source 8-bit computer simulator that can train small neural networks from assembly code, demonstrating machine learning at the bare-metal level.
A web-based tool that visualizes a neural network (using PPO) learning to play Snake in real-time, with configurable parameters and 3D rendering.
This paper introduces a neural network architecture that learns lifted action schemas from fully observed state traces with unobserved action arguments, aiming to enable robust learning of planning domains for neuro-symbolic models.
A highly efficient AI model architecture using ternary weights (-1, 0, 1) that achieves competitive performance while requiring only 1.58 bits per parameter, enabling deployment on extremely constrained devices.
FramePack is a neural network structure that compresses input frames to fix transformer context length regardless of video length, enabling video diffusion models to process many frames with computation similar to image diffusion and improving batch sizes. It also introduces an anti-drifting sampling method to reduce exposure bias.