5 papers
No Unique Minimizer, No Problem: On the Consistency of Robust Neural Classifiers
Subhabrata Majumdar, Anand Deo, Partha Pratim Saha +1
Neural network classifiers trained by cross-entropy minimization are highly sensitive to label noise and adversarial contamination. While robust alternatives offer bounded influenc…
MENTIS: What Belief Changes Under Alignment? Measuring Multi-Scale Latent Torsion in Language Models
Partha Pratim Saha, Samarth Raina, Mayur Parvatikar +4
Preference alignment has substantially improved the observable behavior of large language models, yet it remains unclear what alignment changes internally. Aligned systems still fa…
SPINAL -- Scaling-law and Preference Integration in Neural Alignment Layers
Arion Das, Partha Pratim Saha, Amit Dhanda +3
Direct Preference Optimization (DPO) is a principled, scalable alternative to RLHF for aligning large language models from pairwise preferences, but its internal geometric footprin…
Prompting Away Stereotypes? Evaluating Bias in Text-to-Image Models for Occupations
Shaina Raza, Maximus Powers, Partha Pratim Saha +2
Text-to-Image (TTI) models are powerful creative tools but risk amplifying harmful social biases. We frame representational societal bias assessment as an image curation and evalua…
A Comprehensive Review on the Advancement of Home Automation System
Md. Rawshan Habib, Md Abu Yusuf, W. M. H Nimsara Warnasuriya +5
In light of its many benefits, home automation systems are one of the subjects that are becoming ever more prevalent. The term "home automation" describes the remote monitoring and…