الباحثون

Parag Singla

المنشورات 2

نسخة أولية وصول مفتوح

LinSlot: Exploiting Linear Representation hypothesis for unsupervised attribute discovery from slot based object representation

Sanket Gandhi, Utkarsh Giri, Varun Subramanium وآخرون · 2026

This paper studies the problem of learning disentangled representations of objects and their attributes from raw, unstructured image data. Slot-based methods have shown considerable success in unsupervised learning of object representations from images. Block-slot attention-based methods extend this framework to attrib …

نسخة أولية وصول مفتوح

Teaching LLMs to Generate Challenging MILP Instances via Solver Feedback

Jitin Singla, Parikshit Pareek, Pratik Jawanpuria وآخرون · 2026

Generating optimization instances that are both feasible and computationally challenging is crucial for benchmarking solvers and training learning-based optimization algorithms. Existing non-LLM generators rely on seed instances or parameter tuning, resulting in high test-time computational cost, while existing LLM gen …

المؤلفون المشاركون