SentZero: sentence-centric VL pretraining boosts zero-shot multi-task chest X-ray analysis
Hangyul Yoon · hf · 2026-09-30
SentZero is a sentence-centric vision-language pretraining framework for zero-shot, multi-task chest X-ray analysis. Targeting limited positive-pair diversity and false negatives from clinically equivalent sentences recurring across patients, it uses LLM-based abstract-level sentence structuring to expand positive pairs, adds a loss term to mitigate false negatives, and applies sentence-conditioned residual modulation of visual embeddings. It outperforms prior multi-task zero-shot methods across diverse downstream tasks and datasets.
More from Research
- Tempo (UIST 2026): A computer-use agent that reasons about your long-term goals — kenziyuliu · 2026-09-30
- UMAP Author Teases New Release Built for Much Larger Datasets — leland_mcinnes · 2026-09-30
- Chollet: The Test for Human-Level AGI Is Passing ARC-AGI-(n+1) on Release — fchollet · 2026-09-30
- Jev as a Reranker: a Solid Cost/Speed Default, but Not a Drop-In Silver Bullet — amaarora · 2026-09-30
- Reality Check: 4 Open-Source Models, 14,400 Real-World Rollouts to Benchmark Robot Policies — YuXiang_IRVL · 2026-09-30
- Agent kept misdiagnosing complaints — team shares 4 memory design decisions that fixed it — Financial-Shirt2304 · 2026-09-30