3 papers
cs.LG2026
Locating and Steering Refusal Beyond Attention
Preethi Carmel Bosco, Gopalakrishnan Srinivasan
Where inside a language model does refusal live, and does that place change when the architecture does? In a transformer, refusal is governed by a single direction in the residual…
cs.NE2025
Scaling Equilibrium Propagation to Deeper Neural Network Architectures
Sankar Vinayak Elayedam, Gopalakrishnan Srinivasan
Equilibrium propagation has been proposed as a biologically plausible alternative to the backpropagation algorithm. The local nature of gradient computations, combined with the use…
cs.CL2025
ShishuLM : Achieving Optimal and Efficient Parameterization with Low Attention Transformer Models
Shivanshu Kumar, Gopalakrishnan Srinivasan
While the transformer architecture has achieved state-of-the-art performance on natural language processing tasks, these models impose substantial memory and computational overhead…