2 papers
cs.CL2026
MAGE: Understanding Stability-Performance Trade-offs in Multi-component Prompt Optimization
Prateek Singh
How do different components of iterative prompt optimization interact, and what happens when they are combined? We investigate this through MAGE (Memory-Augmented Goal-directed Pro…
cs.LG2026
RDQ: Residual Distribution Quantization for Large Language Models
Prateek Singh
Post-training quantization (PTQ) of large language models degrades sharply below 4-bit precision. We identify the root cause as residual stream distributional drift: quantization n…