3 papers
cs.CV2026
Not All Patches Are Equally Forgettable: Spatially Localized Domain Unlearning in Vision-Language Models
Akanksha Singh, Vinod K. Kurmi
Pre-trained vision-language models (VLMs) exhibit strong cross-domain recognition performance even without additional training. However, this robustness can also preserve undesirab…
cs.IR2026
Query-Aware Token Budgeting for Efficient Late-Interaction Visual Document Retrieval
PS Rishi, Rajeev Ranjan Dwivedi, Vinod K Kurmi
Late-interaction visual document retrievers preserve fine-grained page evidence by storing many token embeddings per page, but the resulting storage and query-time interaction cost…
cs.CL2026
Selective Capability Unlearning in End-to-End Spoken Language Understanding
Akanksha Singh, Vinod Kumar Kurmi
Modern spoken language understanding (SLU) systems are increasingly deployed in real-world settings, where specific functionalities may need to be removed due to policy or safety c…