activity
20242026
collaborators

12 papers

cs.LG2026

Privacy Policy Enforcement Guardrails for Data-Sensitive Retrieval-Augmented Generation

Osama Zafar, Alexander Nemecek, Yiqian Zhang +5

Standard PII filters often miss contextual data leakage in RAG systems, such as non-regulated attribute clusters that collectively identify individuals. We introduce a Privacy Poli…

cs.LG2026

CausalGuard: Conformal Inference under Graph Uncertainty

Vikash Singh, Weicong Chen, Debargha Ganguly +12

Estimating treatment effects from observational data requires choosing an adjustment set, but valid adjustment depends on an unknown causal graph. Graph misspecification can cause…

quant-ph2026

InterQ: Communication-Aware Scheduling Across Modular QPUs with Classical and Quantum Links

Vinooth Kulkarni, Jaehyun Lee, Lauren Li +5

As quantum computing scales toward practical workloads, future systems are expected to move beyond single monolithic processors toward modular architectures that connect multiple Q…

cs.CV2026

Toward Guarantees for Clinical Reasoning in Vision Language Models via Formal Verification

Vikash Singh, Debargha Ganguly, Haotian Yu +5

Vision-language models (VLMs) show promise in drafting radiology reports, yet they frequently suffer from logical inconsistencies, generating diagnostic impressions unsupported by…

cs.LG2026

Robust Ultra-High-Dimensional Variable Selection With Correlated Structure Using Group Testing

Wanru Guo, Juan Xie, Binbin Wang +4

Background: High-dimensional genomic data exhibit strong group correlation structures that challenge conventional feature selection methods, which often assume feature independence…

cs.CL2026

Trust The Typical

Debargha Ganguly, Sreehari Sankar, Biyao Zhang +8

Current approaches to LLM safety fundamentally rely on a brittle cat-and-mouse game of identifying and blocking known threats via guardrails. We argue for a fresh approach: robust…