2 papers
cs.AI2026
Few Bits, One Law: Toward W2A4KV2
Kai Yi, Tarek Elgamal, Sruthikesh Surineni +3
Extreme low-bit LLM compression is most challenging when weights, activations, and KV caches are quantized together: their distributions differ, and quantization errors interact th…
cs.LG2026
JacQuant: STE-Free Quantization-Aware Training via Learned Jacobian Surrogates
Kai Yi, Vignesh Vivekraja, Harshit Khaitan +1
Quantization-aware training (QAT) is widely deployed but typically relies on the Straight-Through Estimator (STE), which passes gradients through non-differentiable quantizers by f…