This paper proposes a tensor-structured multi-domain channel extrapolation framework to reduce pilot overhead in upper mid-band massive MIMO systems, using a Tucker-based SFT-domain signal model and a…

Low-Pass Flow Matching introduces a spectral bias into the flow matching process, allowing it to better model natural data by transitioning from a standard source spectrum to a frequency-decaying bias…

This paper presents ADAC, a compiler that converts trained differentiable audio models into efficient FAUST code for real-time audio effects.

This paper introduces a dual-layer side-channel attack framework that exploits the variable workload introduced by dynamic image preprocessing in local Vision-Language Models (VLMs) to infer sensitive…

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

The paper introduces S2MDF, a plug-and-play module that enforces a hard constraint to eliminate interpenetrations in multi-object Signed Distance Field (SDF) representations, significantly improving p…

The paper introduces DiffErase, a black-box attack that effectively removes inaudible audio watermarks while preserving perceptual quality by utilizing diffusion models.

This paper demonstrates that in-domain pretraining of BERT significantly improves the detection of DNS exfiltration, particularly in maintaining a low false positive rate.

The paper proposes FOAM, an adaptive damping method that stabilizes the Shampoo optimization algorithm by dynamically controlling damping and eigendecomposition frequency, thereby reducing staleness-i…

The paper proposes CoDe-R, a two-stage framework that significantly improves the accuracy and re-executability of decompiled code generated by LLMs, achieving a new SOTA in the lightweight regime.

The paper presents ExaGEMM, a framework for designing and exploring CPU-native low-bit GEMM via register-resident LUT execution.

This paper proposes a lightweight architectural enhancement for FPGA designs to improve data movement between block RAMs and digital signal processing units for deep learning workloads, incurring negl…

The paper proposes a visual program synthesis framework using a VLM to generate accurate training data for semiconductor inspection, mitigating the sim-to-real gap by applying input binarization to st…

The paper introduces R$^2$A, an adversarial attack that uses suffix optimization to mislead black-box LLM routers into consistently selecting expensive, high-capability models.

The paper introduces FoLoRA, a novel optimization framework that uses a generalized Rayleigh quotient to achieve a superior balance between adapting foundation models to specific tasks and preserving…

A new framework called Geo-DConv is proposed to make multi-channel speech enhancement systems adaptable to diverse microphone array geometries by leveraging microphone coordinates.

A new HLS tool is presented that enables fine-grained pipeline control in a sequential programming model for competitive PPA.