User profiles for Alexander Ku
Alexander KuGoogle DeepMind, Princeton University Verified email at princeton.edu Cited by 4350 |
A universal SNP and small-indel variant caller using deep neural networks
Despite rapid advances in sequencing technologies, accurately calling genetic variants
present in an individual genome from billions of short, errorful sequence reads remains …
present in an individual genome from billions of short, errorful sequence reads remains …
[PDF][PDF] Scaling autoregressive models for content-rich text-to-image generation
We present the Pathways [1] Autoregressive Text-to-Image (Parti) model, which generates
high-fidelity photorealistic images and supports content-rich synthesis involving complex …
high-fidelity photorealistic images and supports content-rich synthesis involving complex …
Image transformer
Image generation has been successfully cast as an autoregressive sequence generation or
transformation problem. Recent work has shown that self-attention is an effective way of …
transformation problem. Recent work has shown that self-attention is an effective way of …
Vector-quantized image modeling with improved vqgan
Pretraining language models with next-token prediction on massive text corpora has delivered
phenomenal zero-shot, few-shot, transfer learning and multi-tasking capabilities on both …
phenomenal zero-shot, few-shot, transfer learning and multi-tasking capabilities on both …
Room-across-room: Multilingual vision-and-language navigation with dense spatiotemporal grounding
We introduce Room-Across-Room (RxR), a new Vision-and-Language Navigation (VLN)
dataset. RxR is multilingual (English, Hindi, and Telugu) and larger (more paths and …
dataset. RxR is multilingual (English, Hindi, and Telugu) and larger (more paths and …
Stay on the path: Instruction fidelity in vision-and-language navigation
Advances in learning and representations have reinvigorated work that connects language
to other modalities. A particularly exciting direction is Vision-and-Language Navigation(VLN), …
to other modalities. A particularly exciting direction is Vision-and-Language Navigation(VLN), …
Transferable representation learning in vision-and-language navigation
Vision-and-Language Navigation (VLN) tasks such as Room-to-Room (R2R) require
machine agents to interpret natural language instructions and learn to act in visually realistic …
machine agents to interpret natural language instructions and learn to act in visually realistic …
General evaluation for instruction conditioned navigation using dynamic time warping
In instruction conditioned navigation, agents interpret natural language and their surroundings
to navigate through an environment. Datasets for studying this task typically contain pairs …
to navigate through an environment. Datasets for studying this task typically contain pairs …
A new path: Scaling vision-and-language navigation with synthetic instructions and imitation learning
Recent studies in Vision-and-Language Navigation (VLN) train RL agents to execute natural-language
navigation instructions in photorealistic environments, as a step towards robots …
navigation instructions in photorealistic environments, as a step towards robots …
Gaussian process probes (gpp) for uncertainty-aware probing
Understanding which concepts models can and cannot represent has been fundamental to
many tasks: from effective and responsible use of models to detecting out of distribution data. …
many tasks: from effective and responsible use of models to detecting out of distribution data. …