S. Soatto

TL;DR: This paper proposes X-DETR, whose architecture has three major components: an object detector, a language encoder, and vision-language alignment, which shows good accuracy and fast speeds for multiple instance-wise vision- language tasks, e.g., 16.4 AP on LVIS detection of 1.2K categories at ∼ 20 frames per second without using any LVIS annotation during training.

TL;DR: Multi-Modal Hallucination Control by Visual Information Grounding reduces hallucinations by mitigating visually ungrounded answers and improving the accuracy on VQA benchmarks.

TL;DR: APT as mentioned in this paper is a transformer-based scheme to tune prompts on distinct data so that they can be arbitrarily composed at inference time, which achieves state-of-the-art performance.

TL;DR: The learned approach can outperform prior hand-designed model selection methods significantly when relevant training history is available and enables integrating existing model selection scores as additional features and scales with more historical data.