activity
20242026
collaborators

9 papers

cs.LG2026

Tydra: An Efficient Hybrid Model for Tabular Data

Mieszko Komisarczyk, Saurabh Mathur, Maurice Kraus +2

Transformer-based tabular foundation models such as TabPFN achieve strong predictive performance but incur quadratic computational cost with context length. On the other hand, subq…

cs.LG2026

A Neurosymbolic Approach for Constructing Planning Domain Models from Clinical Narratives

Ranveer Singh, Saurabh Mathur, Michael Skinner +3

Surgical procedures such as laparoscopic appendectomy are complex, high-stakes processes, yet formalizing their workflows for decision support remains a significant challenge. Indu…

cs.LG2026

Causal Modeling of Adverse Pregnancy Outcomes via Adaptive LLM Proposals

Kavimayil P. Komarasamy, Saurabh Mathur, Ameet Soni +3

Adverse Pregnancy Outcomes (APOs) such as preterm birth and gestational diabetes can have long-term consequences for both the mother and child, yet an understanding of their causes…

cs.LG2026

Context-specific Credibility-aware Multimodal Fusion with Conditional Probabilistic Circuits

Pranuthi Tenali, Sahil Sidheekh, Saurabh Mathur +3

Multimodal fusion requires integrating information from multiple sources that may conflict depending on context. Existing fusion approaches typically rely on static assumptions abo…

cs.AI2026

Depth-Recurrent Attention Mixtures: Giving Latent Reasoning the Attention it Deserves

Jonas Knupp, Jan Hendrik Metzen, Jeremias Bohn +2

Depth-recurrence facilitates latent reasoning by sharing parameters across depths. However, prior work lacks combined FLOP-, parameter-, and memory-matched baselines, underutilizes…

cs.LG2025

Human-Allied Relational Reinforcement Learning

Fateme Golivand Darvishvand, Hikaru Shindo, Sahil Sidheekh +2

Reinforcement learning (RL) has experienced a second wind in the past decade. While incredibly successful in images and videos, these systems still operate within the realm of prop…