Bryan Catanzaro

6

Papers

93

Total Citations

Papers (6)

MM-EMBED: UNIVERSAL MULTIMODAL RETRIEVAL WITH MULTIMODAL LLMS

Prismatic Synthesis: Gradient-based Data Diversification Boosts Generalization in LLM Reasoning

NeurIPS 2025arXiv

RADIOv2.5: Improved Baselines for Agglomerative Vision Foundation Models

InstructRetro: Instruction Tuning post Retrieval-Augmented Pretraining

Audio Flamingo: A Novel Audio Language Model with Few-Shot Learning and Dialogue Abilities

ODIN: Disentangled Reward Mitigates Hacking in RLHF