ActiveVLN is a Vision-and-Language Navigation (VLN) framework designed to enable active exploration through multi-turn reinforcement learning. Unlike traditional VLN methods, which rely on imitation ...

Penguin-VL is a compact vision-language model family built to study how far multimodal efficiency can be pushed by redesigning the vision encoder, rather than only scaling data or model size.

Abstract: In this paper, we examine a key limitation in query-based detectors for temporal action detection (TAD), which arises from their direct adaptation of originally designed architectures for ...

Consider a neural implant dubbed the Microscale Optoelectronic Tetherless Electrode, or MOTE, developed at Cornell University ...

Abstract: Recently, 3D multi-object tracking (MOT) has widely adopted the standard tracking-by-detection paradigm, which solves the association problem between detections and tracks. Many ...