Omni-Dish: Photorealistic and Faithful Image Generation and Editing for Arbitrary Chinese Dishes
Paper
• 2504.09948 • Published
KangarooGroup
non-profit
AI & ML interests
None defined yet.
hujiefrank
authored 13 papers 3 months ago
High-Resolution Image Synthesis via Next-Token Prediction
Paper
• 2411.14808 • Published
HyperSeg: Towards Universal Visual Segmentation with Large Language Model
Paper
• 2411.17606 • Published
• 1
Denoising with a Joint-Embedding Predictive Architecture
Paper
• 2410.03755 • Published
• 1
Kangaroo: A Powerful Video-Language Model Supporting Long-context Video Input
Paper
• 2408.15542 • Published
Controllable Text Generation for Large Language Models: A Survey
Paper
• 2408.12599 • Published
• 65
Fine-gained Zero-shot Video Sampling
Paper
• 2407.21475 • Published
• 6
Involution: Inverting the Inherence of Convolution for Visual Recognition
Paper
• 2103.06255 • Published
Gather-Excite: Exploiting Feature Context in Convolutional Neural Networks
Paper
• 1810.12348 • Published
Squeeze-and-Excitation Networks
Paper
• 1709.01507 • Published
DisTime: Distribution-based Time Representation for Video Large Language Models
Paper
• 2505.24329 • Published
• 1
MagicMirror: A Large-Scale Dataset and Benchmark for Fine-Grained Artifacts Assessment in Text-to-Image Generation
Paper
• 2509.10260 • Published
• 3
LongCat-Image Technical Report
Paper
• 2512.07584 • Published
• 23
Adding `safetensors` variant of this model
#5 opened over 1 year ago
by
SFconvertbot
hujiefrank
updated a model over 1 year ago