News
News
- 2026-10-01Four papers submitted to SPIE Medical Imaging 2027 and four to ICASSP 2027 Submissions, under review.
- 2026-09-01VERIFY accepted at COLM 2026 A benchmark of visual reasoning for multimodal reasoning fidelity.
- 2026-08-26Radiology-report agents presented at SPIE Emerging Topics in Artificial Intelligence 2026 Multi-agent planning and generation of radiology reports.
- 2026-06-04I^2 in the CVPR 2026 Workshop Proceedings (AISTORY) Instructional illustrations from procedural text with text-conditioned diffusion.
- 2026-04-01PromptReverb: oral paper at ICASSP 2026 48 kHz room impulse responses from text via latent rectified flow matching.
- 2026-02-01Best Demonstration Award Runner-up, AAAI 2026 Caption Anything in Video (team demonstration).
- 2026-01-05Machine Learning Intern at Apple, January to August 2026 A multi-agent multimodal system.
- 2025-12-01MMPerspective at NeurIPS 2025 Do multimodal LLMs understand perspective?
- 2025-09-01AVVA at EUSIPCO 2025 LLM-based curation for a data-efficient audio-video foundation model; AVE-2 released.
- 2025-06-01Research Scientist Intern at Smule, June to September 2025 Generative audio for product.
- 2025-02-01lsAGC in NeuroImage 2025 Large-scale augmented Granger causality for fMRI.
- 2025-01-15Invited research talk at Dolby Laboratories Multimodal AI research: from benchmarks to product.
- 2024-10-17Two posters at SANE 2024 at Google, Cambridge, MA Counterfactual audio-language learning; AVVA.