Trending Research
GLU Variants Improve Transformer
BlinkDL/RWKV-LM
•
•
Gated Linear Units (arXiv:1612. 08083) consist of the component-wise product of two linear projections, one of which is first passed through a sigmoid function.
OPT: Open Pre-trained Transformer Language Models
Large language models, which are often trained for hundreds of thousands of compute days, have shown remarkable capabilities for zero- and few-shot learning.
Ranked #1 on
Stereotypical Bias Analysis
on CrowS-Pairs
A Lightweight Instrument-Agnostic Model for Polyphonic Note Transcription and Multipitch Estimation
Despite its simplicity, benchmark results show our system's note estimation to be substantially better than a comparable baseline, and its frame-level accuracy to be only marginally below those of specialized state-of-the-art AMT systems.
Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning
r-three/t-few
•
•
ICL incurs substantial computational, memory, and storage costs because it involves processing all of the training examples every time a prediction is made.
Ranked #1 on
Few-Shot Text Classification
on RAFT
SVTR: Scene Text Recognition with a Single Visual Model
Dominant scene text recognition models commonly contain two building blocks, a visual model for feature extraction and a sequence model for text transcription.
DualDis: Dual-Branch Disentangling with Adversarial Learning
To effectively separate the information, we propose to use a combination of regular and adversarial classifiers to guide the two branches in specializing for class and attribute information respectively.
Surface Representation for Point Clouds
hancyran/RepSurf
•
•
Based on a simple baseline of PointNet++ (SSG version), Umbrella RepSurf surpasses the previous state-of-the-art by a large margin for classification, segmentation and detection on various benchmarks in terms of performance and efficiency.
Ranked #1 on
3D Point Cloud Classification
on ScanObjectNN
View Synthesis with Sculpted Neural Points
princeton-vl/snp
•
•
We address the task of view synthesis, which can be posed as recovering a rendering function that renders new views from a set of existing images.
READ: Large-Scale Neural Scene Rendering for Autonomous Driving
In this paper, a large-scale neural rendering method is proposed to synthesize the autonomous driving scene~(READ), which makes it possible to synthesize large-scale driving scenarios on a PC through a variety of sampling schemes.
Ranked #1 on
Novel View Synthesis
on KITTI
Implementation of an Automated Learning System for Non-experts
This paper detailed the engineering system implementation of an automated machine learning system called YMIR, which completely relies on graphical interface to interact with users.
