Trending Research
LLoCO: Learning Long Contexts Offline
We introduce LLoCO, a technique that combines context compression, retrieval, and parameter-efficient finetuning using LoRA.
ChangeMamba: Remote Sensing Change Detection with Spatio-Temporal State Space Model
For the change decoder, which is available in all three architectures, we propose three spatio-temporal relationship modeling mechanisms, which can be naturally combined with the Mamba architecture and fully utilize its attribute to achieve spatio-temporal interaction of multi-temporal features, thereby obtaining accurate change information.
Ranked #1 on
2D Semantic Segmentation
on xBD
DEADiff: An Efficient Stylization Diffusion Model with Disentangled Representations
The Q-Formers are trained using paired images rather than the identical target, in which the reference image and the ground-truth image are with the same style or semantics.
A Survey of Large Language Models
To discriminate the difference in parameter scale, the research community has coined the term large language models (LLM) for the PLMs of significant size.
MiniCPM: Unveiling the Potential of Small Language Models with Scalable Training Strategies
openbmb/minicpm
•
•
For data scaling, we introduce a Warmup-Stable-Decay (WSD) learning rate scheduler (LRS), conducive to continuous training and domain adaptation.
Matching 2D Images in 3D: Metric Relative Pose from Metric Correspondences
Usually, correspondences are 2D-to-2D and the pose we estimate is defined only up to scale.
Griffin: Mixing Gated Linear Recurrences with Local Attention for Efficient Language Models
google-deepmind/recurrentgemma
•
•
Recurrent neural networks (RNNs) have fast inference and scale efficiently on long sequences, but they are difficult to train and hard to scale.
Patch n' Pack: NaViT, a Vision Transformer for any Aspect Ratio and Resolution
pku-yuangroup/open-sora-plan
•
•
The ubiquitous and demonstrably suboptimal choice of resizing images to a fixed resolution before processing them with computer vision models has not yet been successfully challenged.
GoMVS: Geometrically Consistent Cost Aggregation for Multi-View Stereo
wuuu3511/gomvs
•
•
More specifically, we correspond and propagate adjacent costs to the reference pixel by leveraging the local geometric smoothness in conjunction with surface normals.
JetMoE: Reaching Llama2 Performance with 0.1M Dollars
Large Language Models (LLMs) have achieved remarkable results, but their increasing resource demand has become a major obstacle to the development of powerful and accessible super-human intelligence.
