4 papers
Retrieval Needs Multivectors: An Exponential Separation
Mihir Agarwal, Viraj Agrawal, Sabyasachi Basu +2
Recent works have highlighted the expressive limitations of embedding based retrieval models through both theoretical analyses and challenging benchmarks such as LIMIT. While multi…
Reading Between the Pixels: Linking Text-Image Embedding Alignment to Typographic Attack Success on Vision-Language Models
Ravikumar Balakrishnan, Sanket Mendapara, Ankit Garg
We study typographic prompt injection attacks on vision-language models (VLMs), where adversarial text is rendered as images to bypass safety mechanisms, posing a growing threat as…
On Strengths and Limitations of Single-Vector Embeddings
Archish S, Mihir Agarwal, Ankit Garg +2
Recent work (Weller et al., 2025) introduced a naturalistic dataset called LIMIT and showed empirically that a wide range of popular single-vector embedding models suffer substanti…
Incorporating Token Importance in Multi-Vector Retrieval
Archish S, Ankit Garg, Kirankumar Shiragur +1
ColBERT introduced a late interaction mechanism that independently encodes queries and documents using BERT, and computes similarity via fine-grained interactions over token-level…