Trending Research
Less-to-More Generalization: Unlocking More Controllability by In-Context Generation
bytedance/uno
•
•
In this study, we propose a highly-consistent data synthesis pipeline to tackle this challenge.
Conditional Image Generation
Personalized Image Generation
+1
Kimi-VL Technical Report
We present Kimi-VL, an efficient open-source Mixture-of-Experts (MoE) vision-language model (VLM) that offers advanced multimodal reasoning, long-context understanding, and strong agent capabilities - all while activating only 2. 8B parameters in its language decoder (Kimi-VL-A3B).
TorchFX: A modern approach to Audio DSP with PyTorch and GPU acceleration
In response, we introduce TorchFX: a GPU-accelerated Python library for DSP, specifically engineered to facilitate sophisticated audio signal processing.
REPA-E: Unlocking VAE for End-to-End Tuning of Latent Diffusion Transformers
We show that while diffusion loss is ineffective, end-to-end training can be unlocked through the representation-alignment (REPA) loss -- allowing both VAE and diffusion model to be jointly tuned during the training process.
Ranked #2 on
Image Generation
on ImageNet 256x256
SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models
To address this, we co-design an inference engine Nunchaku that fuses the kernels of the low-rank branch into those of the low-bit branch to cut off redundant memory access.
VGGT: Visual Geometry Grounded Transformer
We present VGGT, a feed-forward neural network that directly infers all key 3D attributes of a scene, including camera parameters, point maps, depth maps, and 3D point tracks, from one, a few, or hundreds of its views.
PixelFlow: Pixel-Space Generative Models with Flow
We present PixelFlow, a family of image generation models that operate directly in the raw pixel space, in contrast to the predominant latent-space models.
DDT: Decoupled Diffusion Transformer
MCG-NJU/DDT
•
•
For ImageNet $256\times256$, Our DDT-XL/2 achieves a new state-of-the-art performance of {1. 31 FID}~(nearly $4\times$ faster training convergence compared to previous diffusion transformers).
Ranked #2 on
Image Generation
on ImageNet 256x256
Agent S2: A Compositional Generalist-Specialist Framework for Computer Use Agents
Computer use agents automate digital tasks by directly interacting with graphical user interfaces (GUIs) on computers and mobile devices, offering significant potential to enhance human productivity by completing an open-ended space of user queries.
Zep: A Temporal Knowledge Graph Architecture for Agent Memory
We introduce Zep, a novel memory layer service for AI agents that outperforms the current state-of-the-art system, MemGPT, in the Deep Memory Retrieval (DMR) benchmark.
