about

So does your Car fail? (A Small Harness for Mathematical Exploration) - Part 3

Sep 16 2026 · 8 min read
#maths #ml #research

Part 1: https://omanshuthapliyal.github.io/blog/hrt-conjecture/

Part 2: https://omanshuthapliyal.github.io/blog/hrt-conjecture-part-2/

In the (last couple) (of posts) I explained what the …

Read More…

So does your Car fail? (The Counterexample to HRT Conjecture) - Part 2

Aug 14 2026 · 9 min read
#maths #analysis

Part 1: https://omanshuthapliyal.github.io/blog/hrt-conjecture/

In the previous post, I talked about the HRT conjecture as a rather natural statement about phase space. A signal can be moved in …

Read More…

Contraction can Help Safety Classifiers keep their Promise

Aug 12 2026 · 7 min read
#ml #controls

A safety classifier can tell us that a prompt looks harmful. That is useful. But it is perhaps not the question we should stop at. Suppose a classifier sees a prompt and says that it is safe. Now …

Read More…

So does your Car fail? (An "Uninteresting" Implication of HRT Conjecture) - Part 1

Aug 10 2026 · 4 min read
#maths #abstract

The mathematics community has recently been effervescing with plenty of AI usage stories (notably Terence Tao, nonetheless) 1. In the latest such development, a long-standing conjecture was disproved …

Read More…

Can LLM Finetuning be Stateful? Small states for Large Models - Part 2

Aug 7 2026 · 6 min read
#ml #controls #state_space_models #linear_algebra

The code for this project can be found at: https://github.com/omanshuthapliyal/HRM-adapter. And the paper can be found at: https://arxiv.org/pdf/2606.26290.

In the previous post, I introduced …

Read More…