4 papers
Remember, Revisit, Revise: Scaffold Memory for Long-Horizon 3D Geometry
Soumick Sarker, Mengmi Zhang
Geometry foundation models estimate camera poses and 3D scene structure from video sequences, but maintaining consistent reconstructions over long horizons remains challenging. Fee…
Structural Interpretations of Protein Language Model Representations via Differentiable Graph Partitioning
Siddhant Dutta, Edward Tan Beng Wai, Soumick Sarker +2
Protein language models such as ESM-2 learn rich residue representations that achieve strong performance on protein function prediction, but their features remain difficult to inte…
Fin-ExBERT: User Intent based Text Extraction in Financial Context using Graph-Augmented BERT and trainable Plugin
Soumick Sarker, Abhijit Kumar Rai
Financial dialogue transcripts pose a unique challenge for sentence-level information extraction due to their informal structure, domain-specific vocabulary, and variable intent de…
Learning to See the Elephant in the Room: Self-Supervised Context Reasoning in Humans and AI
Xiao Liu, Soumick Sarker, Ankur Sikarwar +4
Humans rarely perceive objects in isolation but interpret scenes through relationships among co-occurring elements. How such contextual knowledge is acquired without explicit super…