Trending Research
Ankh: Optimized Protein Language Model Unlocks General-Purpose Modelling
agemagician/Ankh
•
•
As opposed to scaling-up protein language models (PLMs), we seek improving performance via protein-specific optimization.
Long-tail Detection with Effective Class-Margins
Large-scale object detection and instance segmentation face a severe data imbalance.
KERPLE: Kernelized Relative Positional Embedding for Length Extrapolation
Relative positional embeddings (RPE) have received considerable attention since RPEs effectively model the relative distance among tokens and enable length extrapolation.
Robust Speech Recognition via Large-Scale Weak Supervision
openai/whisper
•
•
Preprint 2022
We study the capabilities of speech processing systems trained simply to predict large amounts of transcripts of audio on the internet.
Ranked #1 on
Speech Recognition
on CHiME6
Muse: Text-To-Image Generation via Masked Generative Transformers
Compared to pixel-space diffusion models, such as Imagen and DALL-E 2, Muse is significantly more efficient due to the use of discrete tokens and requiring fewer sampling iterations; compared to autoregressive models, such as Parti, Muse is more efficient due to the use of parallel decoding.
Ranked #11 on
Text-to-Image Generation
on COCO
Atlas: Few-shot Learning with Retrieval Augmented Language Models
Retrieval augmented models are known to excel at knowledge intensive tasks without the need for as many parameters, but it is unclear whether they work in few-shot settings.
Ranked #1 on
Question Answering
on Natural Questions
SensorX2car: Sensors-to-car calibration for autonomous driving in road scenarios
To this end, we present SensorX2car, a calibration toolbox for the online calibration of sensor-to-car coordinate systems in road scenes.
Word, Subword or Character? An Empirical Study of Granularity in Chinese-English NMT
Our experiments show that subword model performs best for Chinese-to-English translation with the vocabulary which is not so big while hybrid word-character model is most suitable for English-to-Chinese translation.
LAION-5B: An open large-scale dataset for training next generation image-text models
mlfoundations/open_clip
•
•
NeurIPS 2022 Datasets and Benchmarks 2022
We show successful replication and fine-tuning of foundational models like CLIP, GLIDE and Stable Diffusion using the dataset, and discuss further experiments enabled with an openly available dataset of this scale.
Mask3D for 3D Semantic Instance Segmentation
Modern 3D semantic instance segmentation approaches predominantly rely on specialized voting mechanisms followed by carefully designed geometric clustering techniques.
Ranked #1 on
3D Instance Segmentation
on ScanNet200
