7 citations · 18 across the 19 of their papers we have counts for
23 papers
AIProver: Agentic Auto-Formalization of Mathematical Research via Certificate-Driven Evolving Harness
Prithwish Jana, Viet Bach Hoang, Logan Luna +9
Proof auto-formalization translates natural-language (NL) theorems and proofs into a formal language (FL) such as Lean, enabling mechanical verification. Despite rapid progress, re…
Towards Certificate-Driven Software Porting: A Self-Improving Agentic Harness for Scientific Program Optimization
Piyush Jha, Aishik Ghosh, Vijay Ganesh
The upgrade and rewriting of large scientific codebases has traditionally been a major challenge. While evolutionary search with large language models (LLMs) can port and accelerat…
Learning Scattering Amplitudes with Transformer Reinforcement Learning
Philip Velie, Tianji Cai, Piyush Jha +2
We introduce a transformer reinforcement learning algorithm that learns to solve high loop-level scattering amplitudes in planar N = 4 Super Yang-Mills theory. Our algorithm improv…
CDRL: Certification-Driven Reinforcement Learning for Neutrino Flavor Model Discovery
Piyush Jha, Jake Rudolph, Victoria Knapp-Pérez +3
Many scientific discovery problems require searching combinatorial hypothesis spaces under complex domain constraints. Reinforcement learning (RL) offers a promising approach, but…
Making Embodied AI Reliable: A Community Agenda from Testing to Formal Verification
Xi Zheng, Dulanga Weerakoon, Yintong Huo +8
Embodied AI systems are increasingly deployed in open-world environments, yet ensuring their reliability remains a fundamental challenge. Drawing on discussions from the AAAI'26 Br…
Symbolic Regression via Latent Iterative Refinement
Xieting Chu, Sriram Vishwanath, Vijay Ganesh
Symbolic regression (SR) seeks closed-form mathematical expressions that fit observed data. Neural SR methods amortize the search by training an encoder to map observations directl…
MathConstraint: Automated Generation of Verified Combinatorial Reasoning Instances for LLMs
Viresh Pati, Zhengyu Li, Piyush Jha +3
We introduce MathConstraint, a hard, adaptive benchmark for evaluating the combinatorial reasoning capabilities of LLMs. We combine constraint satisfaction problems with rigorous s…
Understanding CDCL Solvers via Scalability Studies and Proofdoors
Shimin Zhang, Yechuan Xia, Chunxiao Li +3
Over the past several decades, CDCL SAT solvers have proven remarkably effective on large industrial formulas, despite SAT being NP-complete and widely believed to be intractable.…
Proofdoors and Efficiency of CDCL Solvers
Sunidhi Singh, Vincent Liew, Marc Vinyals +1
We propose a new parameter called proofdoor in an attempt to explain the efficiency of CDCL SAT solvers over a certain class of formulas derived from circuit (esp., arithmetic) ver…
An Exponential Separation between Deterministic CDCL and DPLL Solvers
Sahil Samar, Marc Vinyals, Vijay Ganesh
We prove that there exists a deterministic configuration of Conflict Driven Clause Learning (CDCL) SAT solvers using a variant of the VSIDS branching heuristic that solves instance…
Towards AI-assisted Neutrino Flavor Theory Design
Jason Benjamin Baretz, Max Fieg, Vijay Ganesh +4
Particle physics theories, such as those which explain neutrino flavor mixing, arise from a vast landscape of model-building possibilities. A model's construction typically relies…
Abstractions-of-Thought: Intermediate Representations for LLM Reasoning in Hardware Design
Matthew DeLorenzo, Kevin Tieu, Prithwish Jana +4
Large language models (LLMs) have achieved impressive proficiency on logic and programming tasks, often rivaling expert-level performance. However, generating functionally correct…
LLMStinger: Jailbreaking LLMs using RL fine-tuned LLMs
Piyush Jha, Arnav Arora, Vijay Ganesh
We introduce LLMStinger, a novel approach that leverages Large Language Models (LLMs) to automatically generate adversarial suffixes for jailbreak attacks. Unlike traditional metho…
Extended Resolution Clause Learning via Dual Implication Points
Sam Buss, Jonathan Chung, Vijay Ganesh +1
We present a new extended resolution clause learning (ERCL) algorithm, implemented as part of a conflict-driven clause-learning (CDCL) SAT solver, wherein new variables are dynamic…
RLSF: Fine-tuning LLMs via Symbolic Feedback
Piyush Jha, Prithwish Jana, Pranavkrishna Suresh +2
Large Language Models (LLMs) have transformed AI but often struggle with tasks that require domain-specific reasoning and logical alignment. Traditional fine-tuning methods do not…
A Reinforcement Learning based Reset Policy for CDCL SAT Solvers
Chunxiao Li, Charlie Liu, Jonathan Chung +3
Restart policy is an important technique used in modern Conflict-Driven Clause Learning (CDCL) solvers, wherein some parts of the solver state are erased at certain intervals durin…
Layered and Staged Monte Carlo Tree Search for SMT Strategy Synthesis
Zhengyang Lu, Stefan Siemer, Piyush Jha +3
Modern SMT solvers, such as Z3, offer user-controllable strategies, enabling users to tailor solving strategies for their unique set of instances, thus dramatically enhancing solve…
AlphaMapleSAT: An MCTS-based Cube-and-Conquer SAT Solver for Hard Combinatorial Problems
Piyush Jha, Zhengyu Li, Zhengyang Lu +3
This paper introduces AlphaMapleSAT, a Cube-and-Conquer (CnC) parallel SAT solver that integrates Monte Carlo Tree Search (MCTS) with deductive feedback to efficiently solve challe…
BertRLFuzzer: A BERT and Reinforcement Learning Based Fuzzer
Piyush Jha, Joseph Scott, Jaya Sriram Ganeshna +2
We present a novel tool BertRLFuzzer, a BERT and Reinforcement Learning (RL) based fuzzer aimed at finding security vulnerabilities for Web applications. BertRLFuzzer works as foll…
CGDTest: A Constrained Gradient Descent Algorithm for Testing Neural Networks
Vineel Nagisetty, Laura Graves, Guanting Pan +2
In this paper, we propose a new Deep Neural Network (DNN) testing algorithm called the Constrained Gradient Descent (CGD) method, and an implementation we call CGDTest aimed at exp…
Learning Modulo Theories
Matt Fredrikson, Kaiji Lu, Saranya Vijayakumar +3
Recent techniques that integrate \emph{solver layers} into Deep Neural Networks (DNNs) have shown promise in bridging a long-standing gap between inductive learning and symbolic re…
A Solver + Gradient Descent Training Algorithm for Deep Neural Networks
Dhananjay Ashok, Vineel Nagisetty, Christopher Srinivasa +1
We present a novel hybrid algorithm for training Deep Neural Networks that combines the state-of-the-art Gradient Descent (GD) method with a Mixed Integer Linear Programming (MILP)…
xAI-GAN: Enhancing Generative Adversarial Networks via Explainable AI Systems
Vineel Nagisetty, Laura Graves, Joseph Scott +1
Generative Adversarial Networks (GANs) are a revolutionary class of Deep Neural Networks (DNNs) that have been successfully used to generate realistic images, music, text, and othe…