The paper introduces a transition-based derandomization framework for dense binary hypervector codebooks used in hyperdimensional computing. It targets two similarity families—exponential and linear decay with scalar separation—and separates the similarity law, derandomization variant, and generator construction. The authors formalize variants that constrain initial Hamming weight, update-count variability, and update balance, deriving exact finite-dimensional expressions for bias, variance, and RMS error, and validate the theory with simulations to guide practical codebook design.
arXiv:2608.30384v1 Announce Type: new Abstract: By introducing RSLM (Rotated Scaled Lloyd-Max), a family of training-free vector quantization codecs compressing embeddings to 1--4 bits per dimension,...
FineSID introduces a new quantization framework for semantic identifier learning in generative recommendation systems. By replacing the traditional Top‑1 hard assignment with a soft, differentiable approach, it distributes gradient updates across all codewords, leading to balanced codebook optimization and reduced identifier collisions. Experiments on public benchmarks show that FineSID improves codebook utilization and recommendation accuracy without relying on complex initialization strategies.
The paper introduces D-Quant, a KV cache quantization framework that addresses the memory bottleneck of large language models by using a drift mechanism to convert entropy-coded representations into fixed-size bitstreams. This approach leverages the non-uniform distribution of KV cache values—after rotation and normalization, they approximate a normal distribution—allowing entropy coding to assign shorter codewords to frequent symbols while maintaining regular memory layouts suitable for parallel attention kernels. D-Quant thus aims to reduce memory footprint and bandwidth usage without sacrificing performance.
arXiv:2608.30908v1 Announce Type: new Abstract: Fine-tuning Low-bit models aims to adapt a quantized model while keeping the final deployed checkpoint in the same low-bit form. This setting is practi...
arXiv:2608. 06763v1 Announce Type: new Abstract: Weight quantization for large-language-model inference must balance adaptive reconstruction levels with representations regular enough for efficient GPU execution.
arXiv:2609.26147v1 Announce Type: new Abstract: Modern LLMs are deployed as families of post-trained variants (base, instruct, chat, code) derived from a shared set of pre-trained weights. We present...
arXiv:2608. 06860v1 Announce Type: cross Abstract: Hyperdimensional computing (HDC) is an approach from the cognitive science literature for solving information processing tasks using data represented as high-dimensional random vectors.
arXiv:2607. 11936v1 Announce Type: new Abstract: Hyperdimensional Computing (HDC) represents symbols using high-dimensional hypervectors of dimension $D$.
Weight quantization for large-language-model inference must balance adaptive reconstruction levels with representations regular enough for efficient GPU execution. Uniform integers constrain each group to a linear grid.
arXiv:2509. 23449v2 Announce Type: replace Abstract: Binary code similarity detection is a core task in reverse engineering.
arXiv:2606. 04050v1 Announce Type: cross Abstract: Existing quantization methods are fundamentally limited by rigid, integer-based bit-widths (e.
arXiv:2607. 01065v1 Announce Type: new Abstract: The deployment of Large Language Models (LLMs) with extended context windows is increasingly constrained by the linear growth of Key-Value (KV) cache memory.