Trending Research
Planning-oriented Autonomous Driving
Oriented at this, we revisit the key components within perception and prediction, and prioritize the tasks such that all these tasks contribute to planning.
DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing
We thus propose a new gradient-disentangled embedding sharing method that avoids the tug-of-war dynamics, improving both training efficiency and the quality of the pre-trained model.
Ranked #1 on
Question Answering
on SWAG
Natural Language Inference
Natural Language Understanding
+2
Generative Semantic Segmentation
fudan-zvg/gss
•
•
To that end, the segmentation mask is expressed with a special type of image (dubbed as maskige).
Deep Learning for Camera Calibration and Beyond: A Survey
kangliao929/awesome-deep-camera-calibration
•
•
In this paper, we provide a comprehensive survey of learning-based camera calibration techniques, by analyzing their strengths and limitations.
GPT Understands, Too
THUDM/GLM
•
•
On the SuperGlue benchmark, GPTs achieve comparable and sometimes better performance to similar-sized BERTs in supervised learning.
LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale
We develop a procedure for Int8 matrix multiplication for feed-forward and attention projection layers in transformers, which cut the memory needed for inference by half while retaining full precision performance.
Ranked #2 on
Language Modelling
on C4
Spherical Transformer for LiDAR-based 3D Recognition
dvlab-research/sphereformer
•
•
In this work, we study the varying-sparsity distribution of LiDAR points and present SphereFormer to directly aggregate information from dense close points to the sparse distant ones.
Ranked #1 on
LIDAR Semantic Segmentation
on nuScenes
DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation
cloneofsimo/lora
•
•
Once the subject is embedded in the output domain of the model, the unique identifier can be used to synthesize novel photorealistic images of the subject contextualized in different scenes.
TriAAN-VC: Triple Adaptive Attention Normalization for Any-to-Any Voice Conversion
The existing methods do not simultaneously satisfy the above two aspects of VC, and their conversion outputs suffer from a trade-off problem between maintaining source contents and target characteristics.
On the De-duplication of LAION-2B
Generative models, such as DALL-E, Midjourney, and Stable Diffusion, have societal implications that extend beyond the field of computer science.
