Trending Research
Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data
To this end, we scale up the dataset by designing a data engine to collect and automatically annotate large-scale unlabeled data (~62M), which significantly enlarges the data coverage and thus is able to reduce the generalization error.
Ranked #1 on
Monocular Depth Estimation
on NYU-Depth V2
(using extra training data)
Code Generation with AlphaCodium: From Prompt Engineering to Flow Engineering
Hence, many of the optimizations and tricks that have been successful in natural language generation may not be effective for code tasks.
InstantID: Zero-shot Identity-Preserving Generation in Seconds
There has been significant progress in personalized image synthesis with methods such as Textual Inversion, DreamBooth, and LoRA.
Self-Rewarding Language Models
lucidrains/self-rewarding-lm-pytorch
•
•
We posit that to achieve superhuman agents, future models require superhuman feedback in order to provide an adequate training signal.
Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model
hustvl/vim
•
•
The results demonstrate that Vim is capable of overcoming the computation & memory constraints on performing Transformer-style understanding for high-resolution images and it has great potential to become the next-generation backbone for vision foundation models.
Efficiently Programming Large Language Models using SGLang
SGLang is designed for the efficient programming of LLMs and incorporates primitives for common LLM programming patterns.
TaskWeaver: A Code-First Agent Framework
TaskWeaver provides support for rich data structures, flexible plugin usage, and dynamic plugin selection, and leverages LLM coding capabilities for complex logic.
VMamba: Visual State Space Model
mzeromiko/vmamba
•
•
Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs) stand as the two most popular foundation models for visual representation learning.
PhotoMaker: Customizing Realistic Human Photos via Stacked ID Embedding
Recent advances in text-to-image generation have made remarkable progress in synthesizing realistic human photos conditioned on given text prompts.
Scalable Pre-training of Large Autoregressive Image Models
apple/ml-aim
•
•
Specifically, we highlight two key findings: (1) the performance of the visual features scale with both the model capacity and the quantity of data, (2) the value of the objective function correlates with the performance of the model on downstream tasks.
Ranked #322 on
Image Classification
on ImageNet
(using extra training data)
