Aditya V. Thakur
where else to find them
no profile links on file
what they talk about
all 4 in the filters
where they keep going back
no series more than once — all 5 in the filters
on a stage with
all 8 in the filters
who talks about the same things
nobody close enough yet
| title | conference | date |
|---|---|---|
| Interleaving Static Analysis and LLM Prompting | SOAP 2024 | 2024-06-25 |
A static analyzer (EESI) calls an LLM whenever a function’s error-specification lattice value is bottom, and the LLM output is converted to EESI’s abstract… | ||
| Architecture-Preserving Provable Repair of Deep Neural Networks | PLDI 2023 | 2023-06-17 |
Presents an algorithm that modifies only network parameters to yield architecture-preserving fixes that are provably correct on entire V-polytopes, encoding… | ||
| Abstract Neural Networks | SPLASH 2022 | 2022-12-05 |
The paper introduces Abstract Neural Networks that soundly overapproximate a DNN while using far fewer nodes by replacing weight matrices with elements of an… | ||
| Abstract Neural Networks | SAS 2020 | 2020-11-18 |
Paper claims a procedure to compress a large DNN into a smaller Abstract Neural Network (ANN) that soundly over-approximates every input-output behavior, and… | ||
| Memory-Efficient Fixpoint Computation | SAS 2020 | 2020-11-18 |
A technique interleaves assertion checks with Bourdoncle-style recursive fixpoint iteration to free abstract values early, implemented as MIKOS extends IKOS… | ||
| Analogy-Making as a Core Primitive in the Software Engineering Toolbox | Onward! 2020 | 2020-11-15 |
Presents Sifter, a new analogy-making algorithm that represents code and docs as triplet structures plus a small DSL of update rules, and applies it to three… | ||
| nothing matches | ||