2 papers
cs.CV2026
Breaking Spurious Correlations via Generative Randomization and Cross-Variant Self-Supervised Learning
Suraj Yadav, Anjaneya Sharma, Siddharth Yadav
Deep neural networks trained with Empirical Risk Minimization (ERM) often fail under distribution shifts because they exploit spurious correlations between object labels and backgr…
cs.LG2026
Limits of Difficulty Scaling: Hard Samples Yield Diminishing Returns in GRPO-Tuned SLMs
Suraj Yadav, Siddharth Yadav, Parth Goyal
Recent alignment work on Large Language Models (LLMs) suggests preference optimization can improve reasoning by shifting probability mass toward better solutions. We test this clai…