6 papers
MASS: Multi-mask Selective Self-Distillation for Leakage-Resilient Reasoning
Xiuqi Liu, Oveys Delafrooz Noroozi, Upamanyu Madhow
On-policy self-distillation enables the same model to act as student and teacher, with dense token-level supervision obtained by the teacher being given access to privileged inform…
PerQ: Inverse Generative Modeling for Neural Image Compression via Quantization Error Compensation
Tianhao Peng, Ho Man Kwan, Fan Zhang +2
Neural image codecs face a fundamental trade-off between pixel fidelity and perceptual quality. Distortion-optimized codecs preserve pixel-wise fidelity but produce blurred reconst…
Scaling Wideband Hybrid Beamforming for sub-THz Communication
Amirmohammad Haddad, Oveys Delafrooz Noroozi, Canan Cebeci +2
We investigate the capacity attainable for a multiuser MIMO uplink as we scale both array size and bandwidth for regimes in which all-digital arrays incur excessive hardware comple…
Beamspace Dimensionality Reduction for Massive MU-MIMO: Geometric Insights and Information-Theoretic Limits
Canan Cebeci, Oveys Delafrooz Noroozi, Upamanyu Madhow
Beamspace dimensionality reduction, a classical tool in array processing, has been shown in recent work to significantly reduce computational complexity and training overhead for a…
Tiled Beamspace MVDR for 1024-element Wideband Radar
Oveys Delafrooz Noroozi, Jiyoon Han, Wei Tang +2
We present a tiled architecture for computationally efficient digital beamforming for wideband massive MIMO radar, using beamspace dimension reduction for each tile, and coordinate…
Scaling Wideband Massive MIMO Radar via Beamspace Dimension Reduction
Oveys Delafrooz Noroozi, Jiyoon Han, Wei Tang +2
We present an architecture for scaling digital beamforming for wideband massive MIMO radar. Conventional spatial processing becomes computationally prohibitive as array size grows;…