DREAM: Where Visual Understanding Meets Text-to-Image Generation
Paper
• 2603.02667 • Published
• 4
Shlok Kumar Mishra
shlokm
AI & ML interests
Self-Supervised Learning
Recent Activity
authored
a paper
about 23 hours ago
DREAM: Where Visual Understanding Meets Text-to-Image Generation authored
a paper
about 23 hours ago
Think Then Embed: Generative Context Improves Multimodal Embedding authored
a paper
about 23 hours ago
StreamMem: Query-Agnostic KV Cache Memory for Streaming Video
Understanding Organizations
None yet
authored 6 papers about 23 hours ago
Think Then Embed: Generative Context Improves Multimodal Embedding
Paper
• 2510.05014 • Published
StreamMem: Query-Agnostic KV Cache Memory for Streaming Video Understanding
Paper
• 2508.15717 • Published
• 1
Transfer between Modalities with MetaQueries
Paper
• 2504.06256 • Published
• 2
MAGE: MAsked Generative Encoder to Unify Representation Learning and Image Synthesis
Paper
• 2211.09117 • Published
HaLP: Hallucinating Latent Positives for Skeleton-based Self-Supervised Learning of Actions
Paper
• 2304.00387 • Published
authored a paper 11 days ago