3 citations · 7 across the 9 of their papers we have counts for
9 papers
RuleFlow : Generating Reusable Program Optimizations with LLMs
Avaljot Singh, Dushyant Bharadwaj, Stefanos Baziotis +2
Optimizing Pandas programs is a challenging problem. Existing systems and compiler-based approaches offer reliability but are either heavyweight or support only a limited set of op…
AgentRx: Diagnosing AI Agent Failures from Execution Trajectories
Shraddha Barke, Arnav Goyal, Alind Khare +3
AI agents often fail in ways that are difficult to localize because executions are probabilistic, long-horizon, multi-agent, and mediated by noisy tool outputs. We address this gap…
Lumos: Let there be Language Model System Certification
Isha Chaudhary, Vedaant Jain, Prineet Parhar +4
We introduce the first principled framework, Lumos, for specifying and formally certifying Language Model System (LMS) behaviors. Lumos is an imperative probabilistic programming D…
SAIL: Sound Abstract Interpreters with LLMs
Qiuhan Gu, Avaljot Singh, Gagandeep Singh
How to construct globally sound abstract interpreters to safely approximate program behaviors remains a bottleneck in abstract interpretation. In this paper, we show the potential…
Automatic Tensor-level Execution of Abstract Interpreters for Neural Networks
Avaljot Singh, Yasmin Chandini Sarita, Yamin Chandini Sarita +4
Developing new abstract interpretation-based DNN certifiers is difficult because their mathematical design is expressed at the neuron level, while implementations must operate at t…
Automated Verification of Soundness of DNN Certifiers
Avaljot Singh, Yasmin Chandini Sarita, Charith Mendis +1
The uninterpretability of Deep Neural Networks (DNNs) hinders their use in safety-critical applications. Abstract Interpretation-based DNN certifiers provide promising avenues for…
Efficient Ranking Function-Based Termination Analysis with Bi-Directional Feedback
Yasmin Sarita, Avaljot Singh, Shaurya Gomber +2
Synthesizing ranking functions is a common technique for proving the termination of loops. A ranking function must be bounded and decrease by a specified amount with each iteration…
ConstraintFlow: A DSL for Specification and Verification of Neural Network Analyses
Avaljot Singh, Yasmin Sarita, Charith Mendis +1
We develop a declarative DSL - \cf - that can be used to specify Abstract Interpretation-based DNN certifiers. In \cf, programmers can easily define various existing and new abstra…
Interpreting Robustness Proofs of Deep Neural Networks
Debangshu Banerjee, Avaljot Singh, Gagandeep Singh
In recent years numerous methods have been developed to formally verify the robustness of deep neural networks (DNNs). Though the proposed techniques are effective in providing mat…