Raviteja Vemulapalli

Learning to Reason for Hallucination Span Detection

Learning from Self Critique and Refinement for Faithful LLM Summarization

COMPASS: A Multi-Turn Benchmark for Tool-Mediated Planning & Preference Optimization

DiCoH: Rethinking Self-Supervised Pretraining for Semantic Segmentation in Homogenous Medical Domains

Proxy-FDA: Proxy-based Feature Distribution Alignment for Fine-tuning Vision Foundation Models without Forgetting

TiC-LM: A Multi-Year Benchmark for Continual Pretraining of Language Models

Proxy-FDA: Proxy-based Feature Distribution Alignment for Fine-tuning Vision Foundation Models without Forgetting

FocalLens: Instruction Tuning Enables Zero-Shot Conditional Image Representations