arxiv:2605.17640
Debashish C PRO
d3bach
AI & ML interests
omni-modal inference and training. GPUs
Recent Activity
upvoted a paper 17 days ago
Accelerating Streaming Video Large Language Models via Hierarchical Token Compression upvoted a paper 24 days ago
VL-JEPA: Joint Embedding Predictive Architecture for Vision-language upvoted a paper 26 days ago
Scaling Audio-Text Retrieval with Multimodal Large Language ModelsOrganizations
