5 papers
Continual Enterprise World Model Discovery in Dynamic Systems
Shambhavi Mishra, David Vazquez, Perouz Taslakian +3
In an enterprise system, updating one field can set another, create a record, or start an approval. These effects are produced by business rules that are not built into the platfor…
Continual Test-Time Adaptation in Computer Vision: Methods, Benchmarks, and Future Directions
Sarthak Kumar Maharana, Shambhavi Mishra, Yunbei Zhang +6
Deep neural nets achieve remarkable performance when training and test data share the same distribution, but this assumption frequently breaks in real-world deployment, where data…
AInstein: Can LLMs Solve Research Problems From Parametric Memory Alone?
Shambhavi Mishra, Gaurav Sahu, Marco Pedersoli +3
Can large language models solve AI research problems using only their parametric knowledge, without fine-tuning, retrieval, or other external aids? We introduce AInstein, a framewo…
Semantic Anchor Transport: Robust Test-Time Adaptation for Vision-Language Models
Shambhavi Mishra, Julio Silva-Rodriguez, Ismail Ben Ayed +2
Large pre-trained vision-language models (VLMs), such as CLIP, have shown unprecedented zero-shot performance across a wide range of tasks. Nevertheless, these models may be unreli…
Do not trust what you trust: Miscalibration in Semi-supervised Learning
Shambhavi Mishra, Balamurali Murugesan, Ismail Ben Ayed +2
State-of-the-art semi-supervised learning (SSL) approaches rely on highly confident predictions to serve as pseudo-labels that guide the training on unlabeled samples. An inherent…