nunchaku
[ICLR2025 Spotlight] SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models
- 4k
- Python
- Apache-2.0
- 3 mo ago
[ICLR2025 Spotlight] SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models
[ICLR 2025] From anything to mesh like human artists. Official impl. of "MeshAnything: Artist-Created Mesh Generation with Autoregressive Transformers"
[ECCV`24&ICLR`25] CityGaussian Series for High-quality Large-Scale Scene Reconstruction with Gaussians
[ICLR 2025] Animate-X: Universal Character Image Animation with Enhanced Motion Representation
[ICLR 2025] VideoGrain: This repo is the official implementation of "VideoGrain: Modulating Space-Time Attention for Multi-Grained Video Editing"
[ICLR 2025] MLLM can see? Dynamic Correction Decoding for Hallucination Mitigation
[ICLR2025] Detecting Backdoor Samples in Contrastive Language Image Pretraining
MANTRA: The Manifold Triangulations Assemblage (A dataset of manifold triangulations)
The official implementation of ICLR2025 paper for shift-invariant neural networks
MANTRA: The Manifold Triangulations Assemblage (A dataset of manifold triangulations) — Benchmarks Repository
DiffAttnLab — train a real Differential Transformer (Microsoft/Tsinghua, arXiv:2410.05258, ICLR 2025 Oral) in your browser and watch differential attention cancel attention noise. From-scratch Float64 autodiff, gradient-checked.