4 papers
Demystifying LLM-as-a-Judge: Analytically Tractable Model for Inference-Time Scaling
Indranil Halder, Cengiz Pehlevan
Recent developments in large language models have shown advantages in reallocating a notable share of computational resource from training time to inference time. However, the prin…
A solvable generative model with a linear, one-step denoiser
Indranil Halder
We develop an analytically tractable single-step diffusion model based on a linear denoiser and present an explicit formula for the Kullback-Leibler divergence between the generate…
Stretched horizon, replica trick and off-shell winding condensate, and all that
Indranil Halder, Daniel L. Jafferis
corrections to near-horizon dynamics of a Schwarzschild black hole in a large number of spacetime dimensions are governed by the worldsheet theory composed of the cigar C…
A disorder-averaged framework for evaluating the Witten index
Indranil Halder, Daniel L. Jafferis, Debmalya Sarkar
We study supersymmetric indices in disordered systems, in particular an supersymmetric Sachdev-Ye-Kitaev-type quantum mechanics. In cases where the disordered param…