If you’re working with text-to-image models like Stable Diffusion, you’ve likely faced the trade-off between customization and efficiency. Full fine-tuning…
EvalPlus: Rigorously Evaluate LLM-Generated Code with 80× More Test Cases and Realistic Performance Metrics 1652
When large language models (LLMs) generate code, how do you know it’s actually correct? Traditional code evaluation benchmarks like HumanEval…
Personalize-SAM: One-Shot Personalized Segmentation Without Training for Photos, Videos, and Generative AI Workflows 1638
Imagine you have a photo album filled with images of your dog—but you want to automatically isolate your pet in…
CRATE: Interpretable, Parameter-Efficient Vision Transformers for Structured Unsupervised Learning 1245
In an era where deep learning models grow ever larger and more opaque, the demand for interpretable, efficient, and theoretically…
NeuralForecast: Accurate, Easy-to-Use Neural Time Series Forecasting for Real-World Applications 3883
Time series forecasting remains a core challenge across industries—from retail and energy to finance and logistics. While deep learning has…
Qwen3-Omni: One Unified Model for Text, Image, Audio, and Video—Without Compromise 3063
Imagine a single AI model that natively understands and generates responses across text, images, audio, and video—all in real time,…
FramePack: Generate Long, High-Quality Videos on a Laptop—Without Cloud Costs or Drifting Artifacts 16308
Creating long, coherent, and visually rich videos with AI has long been bottlenecked by computational complexity, memory constraints, and error…
Second-Me: Your Private, Persistent AI Self That Eliminates Repetitive Data Entry and Reclaims Your Digital Identity 14752
In a world where AI assistants increasingly mediate our interactions with apps, services, and even other people, a critical problem…
MultiTalk: Generate Realistic Multi-Person Conversational Videos from Audio with Precise Speaker Binding 2704
Creating lifelike videos of people talking has long been dominated by “talking head” technologies—tools that animate a single face from…
DGM: Self-Improving AI Agents That Evolve Their Own Code Without Human Redesign 1762
Most AI systems today are stuck in time. Their architectures, prompts, and tooling are all hand-crafted by engineers—once deployed, they…