This paper investigates limitations of learning tanh neural networks under finite-precision computations and Lp accuracy guarantees.

This paper presents a hardware-oriented description of GoldenFloat, a static-split floating-point family, and its concrete artefacts.

The paper proposes ZK-Flex, a flexible software-hardware co-designed framework that significantly accelerates Zero-Knowledge Proof (ZKP) generation by efficiently handling diverse polynomial and ellip…

The paper proposes ZK-Flex, a flexible software-hardware co-designed framework that significantly accelerates Zero-Knowledge Proof (ZKP) generation by efficiently handling diverse polynomial and ellip…

The paper demonstrates that for FFT-based radar imaging on Apple Silicon, the limiting factor for half-precision (FP16) is dynamic range, not mantissa precision, and proposes a block-floating-point (B…

The paper introduces TIGER, a GPU-accelerated framework that significantly speeds up high-precision evaluation of nonlinear layers for encrypted LLM inference using TFHE.

The paper analyzes the expressivity of padded transformers, proving that their computational power is primarily determined by model depth and numeric precision, rather than attention type or width.

This paper analyzes the computational complexity of verifying feedforward neural networks when their weights are restricted to finite-width arithmetic, finding that verification remains NP-complete fo…

The paper introduces the base-m length codec, a canonical and robust encoding scheme that maps byte strings to lists of residues modulo m, essential for finite-ring cryptosystems.

The paper analyzes the structured CVP distance on the log-unit lattice of cyclotomic fields, significantly reducing the conjectured CDPR factor for the ML-KEM cryptosystem from exponential to sub-poly…

The paper introduces Grid Programs, a novel, Turing-complete model of computation where programs are two-dimensional arrangements of instructions, fundamentally departing from linear code structures.

Hawkeye is a system that allows perfect, precision-preserving reproduction of GPU-level matrix multiplication operations on a CPU, enabling efficient and trustworthy third-party auditing of machine le…

O-POPE is a novel outer-product engine that accelerates floating-point GEMM by repurposing FPU pipeline registers as buffers, achieving high utilization and improved energy efficiency.

The paper provides the first machine-checked universal proof, using ring theory, that value-independence implies identical marginal distributions for arithmetic masking, thereby extending the verifica…

The paper analyzes a fragment of Higher-Order Datalog, showing that restricting recursion to a linear form shifts its expressive power from time complexity to space complexity, specifically capturing…

The paper proves that platform-deterministic inference is a necessary and sufficient condition for trustworthy AI, establishing that AI trust fundamentally relies on consistent arithmetic.

This paper provides an explicit cost analysis of Toom-4 multiplication specifically tailored for the incomplete Number Theoretic Transform (NTT) framework, offering a concrete cost model for hybrid la…

The paper introduces and explores Truly Linear FPT (TLFPT), a complexity class defined by $O(n) + f(k)$, demonstrating that it is a strict subset of standard Linear FPT and providing new algorithms fo…

The paper proposes a method for bit-exact verification of AI inference outputs without sacrificing performance, demonstrating that deterministic, precise re-computation is possible even across differe…

The paper analyzes the failure modes of aggressive 2-bit quantization in large reasoning models, proposing lightweight controls like FP16 planning and loop rescue to restore accuracy and achieve pract…