2 papers
q-bio.NC2026
Prediction emerges in RNNs trained for perception
Akanksha Gupta, Alejandro Tabas
The brain is highly proficient at making sense of noisy and ambiguous sensory inputs. Predictive processing hypothesises that this ability relies on prediction. However, it is uncl…
cs.CL2025
Small Language Models (SLMs) Can Still Pack a Punch: A survey (updated 2026)
Akanksha Gupta, Bijo Thomas, Harshita Asnani +5
As foundation AI models continue to increase in size, an important question arises - is massive scale the only path forward? This survey of about 160 papers presents a family of Sm…