4 papers · 1 filter
Going Down Memory Lane: Scaling Tokens for Video Stream Understanding with Dynamic KV-Cache Memory
Vatsal Agarwal, Saksham Suri, Matthew Gwilliam +2
Streaming video understanding requires models to robustly encode, store, and retrieve information from a continuous video stream to support accurate video question answering (VQA).…
Towards Multimodal Understanding via Stable Diffusion as a Task-Aware Feature Extractor
Vatsal Agarwal, Matthew Gwilliam, Gefen Kohavi +3
Recent advances in multimodal large language models (MLLMs) have enabled image-based question-answering capabilities. However, a key limitation is the use of CLIP as the visual enc…
Do text-free diffusion models learn discriminative visual representations?
Soumik Mukhopadhyay, Matthew Gwilliam, Yosuke Yamaguchi +6
While many unsupervised learning models focus on one family of tasks, either generative or discriminative, we explore the possibility of a unified representation learner: a model w…
LEIA: Latent View-invariant Embeddings for Implicit 3D Articulation
Archana Swaminathan, Anubhav Gupta, Kamal Gupta +3
Neural Radiance Fields (NeRFs) have revolutionized the reconstruction of static scenes and objects in 3D, offering unprecedented quality. However, extending NeRFs to model dynamic…