4 papers
The Geometry of Language Model Logits: Generic Structure and Learned Departures
Swathi Shree Narashiman, Aravind Ramana Venkatramanan, Nambi Seshadri
Autoregressive language models produce, at every prediction step, a vocabulary-sized logit vector whose structure determines the conditional next-token distribution. We empirically…
Selective Interference Suppression of Siamese-Net in Heterogeneous Interference Channels
Arkadeep Sinha, Shubham Paul, R. Manivasakan +2
We study an end-to-end learnt short-block codes for a -user real Gaussian interference channel with heterogeneous pairwise interference strengths, while keeping single-user deco…
Learning Robust Representations for Communications over Interference-limited Channels
Shubham Paul, Sudharsan Senthil, Preethi Seshadri +2
In the context of cellular networks, users located at the periphery of cells are particularly vulnerable to substantial interference from neighbouring cells, which can be represent…
Learning Robust Representations for Communications over Noisy Channels
Sudharsan Senthil, Shubham Paul, Nambi Seshadri +1
We explore the use of FCNNs (Fully Connected Neural Networks) for designing end-to-end communication systems without taking any inspiration from existing classical communications m…