Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
Steering Under Compression: Dose-Response, Capability Cost, and Failure Asymmetry in Quantized LLMs
Saurav Bhandari, Benjamin Wade
Inference-time activation steering enables behavioral control of large language models without parameter modification, while post-training quantization reduces memory and compute c…
cs.LG2025
Diversity Conscious Refined Random Forest
Sijan Bhattarai, Saurav Bhandari, Girija Bhusal +2
Random Forest (RF) is a widely used ensemble learning technique known for its robust classification performance across diverse domains. However, it often relies on hundreds of tree…