4 papers
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…
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…
Patch-aware Vector Quantized Codebook Learning for Unsupervised Visual Defect Detection
Qisen Cheng, Shuhui Qu, Janghwan Lee
Unsupervised visual defect detection is critical in industrial applications, requiring a representation space that captures normal data features while detecting deviations. Achievi…
Efficient Generation of Molecular Clusters with Dual-Scale Equivariant Flow Matching
Akshay Subramanian, Shuhui Qu, Cheol Woo Park +3
Amorphous molecular solids offer a promising alternative to inorganic semiconductors, owing to their mechanical flexibility and solution processability. The packing structure of th…