Ananth Grama

Unified Multi-Modal Interactive and Reactive 3D Motion Generation via Rectified Flow

DRIFT: Learning from Abundant User Dissatisfaction in Real-World Preference Learning

How to Retrain Online Models Optimally with Few Updates

LLMs Can Get "Brain Rot"!

RestoRect: Degraded Image Restoration via Latent Rectified Flow & Feature Distillation

Perturbation Guided Drug Molecule Design via Latent Rectified Flow

Transcriptomics-Morphology Generation Via Treatment Conditioning With Rectified Flow

GeneFlow: Translation of Single-cell Gene Expression to Histopathological Images via Rectified Flow

Agnostic Continuous-Time Online Learning

Cascade Reward Sampling for Efficient Decoding-Time Alignment

Robust Integrated Learning and Pauli Noise Mitigation for Parametrized Quantum Circuits

More is Less: The Pitfalls of Multi-Model Synthetic Preference Data in DPO Safety Alignment

From Low Rank Gradient Subspace Stabilization to Low-Rank Weights: Observations, Theories, and Applications

No Free Lunch: Fundamental Limits of Learning Non-Hallucinating Generative Models

Cascade Reward Sampling for Efficient Decoding-Time Alignment