Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
ReQAT: Achieving Full-Precision Reasoning Accuracy with 4-bit Floating-Point Quantization-Aware Training
Janghwan Lee, Sihwa Lee, Jinseok Kim +4
Large Reasoning Models (LRMs) achieve strong problem-solving through long chain-of-thought, but their deployment is constrained by the high cost of full-precision inference and gro…
cs.LG2026
ReSET: Accurate Latency-Critical NVFP4 Reasoning via Step-Aware Temperature Scaling
Sihwa Lee, Janghwan Lee, Donghoon Yoo +4
Large reasoning models (LRMs) improve complex problem-solving by generating long intermediate reasoning traces, but this substantially increases inference costs. NVFP4 inference of…