10 papers
Learning Not to Optimize: Physics-Informed Action-Space Reshaping for Intent-Based Network Control
Zuyuan Zhang, Vaneet Aggarwal, Tian Lan
Modern network policy control maps intent to sequential placement-control decisions. Bellman-style policy optimization primarily asks which action to optimize, while constraints ar…
On the Convergence of Self-Improving Online LLM Alignment
Xudong Wu, Pangpang Liu, Vaneet Aggarwal +1
The Self-Improving Alignment (SAIL) algorithm addresses distribution shift by reducing a bilevel formulation of the problem to an efficient, single-level method. Empirically, SAIL…
BalancedDPO: Adaptive Multi-Metric Alignment
Dipesh Tamboli, Souradip Chakraborty, Aditya Malusare +3
Diffusion models have achieved remarkable progress in text-to-image generation, yet aligning them with human preference remains challenging due to the presence of multiple, sometim…
GeneFlow: Translation of Single-cell Gene Expression to Histopathological Images via Rectified Flow
Mengbo Wang, Shourya Verma, Aditya Malusare +6
Spatial transcriptomics (ST) technologies can be used to align transcriptomes with histopathological morphology, presenting exciting new opportunities for biomolecular discovery. U…
Augmenting generative models with biomedical knowledge graphs improves targeted drug discovery
Aditya Malusare, Vineet Punyamoorty, Vaneet Aggarwal
Recent breakthroughs in generative modeling have demonstrated remarkable capabilities in molecular generation, yet the integration of comprehensive biomedical knowledge into these…
Contrastive Cross-Modal Learning for Infusing Chest X-ray Knowledge into ECGs
Vineet Punyamoorty, Aditya Malusare, Vaneet Aggarwal
Modern diagnostic workflows are increasingly multimodal, integrating diverse data sources such as medical images, structured records, and physiological time series. Among these, el…