4 papers
Compositional Entailment Learning for Hyperbolic Vision-Language Models
Avik Pal, Max van Spengler, Guido Maria D'Amely di Melendugno +3
Image-text representation learning forms a cornerstone in vision-language models, where pairs of images and textual descriptions are contrastively aligned in a shared embedding spa…
In-Context Learning Improves Compositional Understanding of Vision-Language Models
Matteo Nulli, Anesa Ibrahimi, Avik Pal +2
Vision-Language Models (VLMs) have shown remarkable capabilities in a large number of downstream tasks. Nonetheless, compositional image understanding remains a rather difficult ta…
[RE] Modeling Personalized Item Frequency Information for Next-basket Recommendation
Sławomir Garcarz, Avik Pal, Pim Praat
This paper focuses on reproducing and extending the results of the paper: "Modeling Personalized Item Frequency Information for Next-basket Recommendation" which introduced the TIF…
Hitting "Probe"rty with Non-Linearity, and More
Avik Pal, Madhura Pawar
Structural probes learn a linear transformation to find how dependency trees are embedded in the hidden states of language models. This simple design may not allow for full exploit…