4 papers
Synthetic Data Generation for Long-Tail Medical Image Classification: A Case Study in Skin Lesions
Jiaxiang Jiang, Mahesh Subedar, Omesh Tickoo
Long-tailed class distributions are pervasive in multi-class medical datasets and pose significant challenges for deep learning models which typically underperform on tail classes…
EigenTrack: Spectral Activation Feature Tracking for Hallucination and Out-of-Distribution Detection in LLMs and VLMs
Davide Ettori, Nastaran Darabi, Sina Tayebati +4
Large language models (LLMs) offer broad utility but remain prone to hallucination and out-of-distribution (OOD) errors. We propose EigenTrack, an interpretable real-time detector…
PEFA-AI: Advancing Open-source LLMs for RTL generation using Progressive Error Feedback Agentic-AI
Athma Narayanan, Mahesh Subedar, Omesh Tickoo
We present an agentic flow consisting of multiple agents that combine specialized LLMs and hardware simulation tools to collaboratively complete the complex task of Register Transf…
DOSA: Differentiable Model-Based One-Loop Search for DNN Accelerators
Charles Hong, Qijing Huang, Grace Dinh +2
In the hardware design space exploration process, it is critical to optimize both hardware parameters and algorithm-to-hardware mappings. Previous work has largely approached this…