19 papers
NOVA: Fundamental Limits of Knowledge Discovery Through AI
Salman Avestimehr, Ken Duffy, Muriel Médard +1
Can AI systems discover new knowledge through iterative self-improvement, and at what cost? We introduce NOVA, which models the ``generate, verify, accumulate, retrain'' loop as an…
ATHENA: Adaptive Test-Time Steering for Improving Count Fidelity in Diffusion Models
Mohammad Shahab Sepehri, Asal Mehradfar, Berk Tinaz +2
Text-to-image diffusion models achieve high visual fidelity but surprisingly exhibit systematic failures in numerical control when prompts specify explicit object counts. To addres…
EM-Aware Physical Synthesis: Neural Inductor Modeling and Intelligent Placement & Routing for RF Circuits
Yilun Huang, Asal Mehradfar, Salman Avestimehr +1
This paper presents an ML-driven framework for automated RF physical synthesis that transforms circuit netlists into manufacturable GDSII layouts. While recent ML approaches demons…
HARMONY: Hidden Activation Representations and Model Output-Aware Uncertainty Estimation for Vision-Language Models
Erum Mushtaq, Zalan Fabian, Yavuz Faruk Bakman +3
Uncertainty Estimation (UE) plays a central role in quantifying the reliability of model outputs and reducing unsafe generations via selective prediction. In this regard, most exis…
GeoToken: Hierarchical Geolocalization of Images via Next Token Prediction
Narges Ghasemi, Amir Ziashahabi, Salman Avestimehr +1
Image geolocalization, the task of determining an image's geographic origin, poses significant challenges, largely due to visual similarities across disparate locations and the lar…
Reject Only Critical Tokens: Pivot-Aware Speculative Decoding
Amir Ziashahabi, Yavuz Faruk Bakman, Duygu Nur Yaldiz +3
Speculative Decoding (SD) ensures that the output matches the target model's distribution exactly. However, we argue that this distribution matching requirement is too stringent an…