We have 5 of 19 papers
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
Ultra-low-bit scalar quantization offers a regular arithmetic structure for efficient deployment of large language models, but preserving predictive behavior at extreme precision remains challenging: with only a few reconstruction levels, accurate weight representation must translate into consistent predictions from a...
Experiments show that PRQuant substantially reduces down-projection reconstruction error, with scaling and residual compensation providing the main numerical gains while permutation enables a hardware-friendly contiguous layout.
The quadratic cost of attention is a major bottleneck in diffusion-based video generation models. MXFP4 attention provides a promising path toward efficient inference, but direct MXFP4 quantization often degrades generation quality due to two numerical issues: the clipping-underflow trade-off from power-of-two scaling...
Kaleido is presented, an algorithm hardware codesign that accelerates all operations in vDiTs by exploiting channel-wise spatiotemporal correlations in latent space and skips redundant computations by reusing partial results while preserving higher generative quality than prior methods.
BiSCo-LLM is presented, a codebook-free binary spherical coding framework for extreme low-bit LLM weight compression and its reported storage budget includes binary codes, neural decoders, protected-channel payloads, LoRA adapters, and metadata.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
