Software Engineering Hacker News

NUMA: Cores, memory, and the distance between them

A discussion on NUMA (Non-Uniform Memory Access) architecture, focusing on the relationship between CPU cores and memory distance.

AI/ML arXiv cs.AI

Hippocampus-DETR: An Explicit Memory Object Detection Framework Based on Hippocampus Modeling

Introduction of Hippocampus-DETR, an object detection framework that simulates biological hippocampal memory for better generalization and data efficiency.

AI/ML arXiv cs.AI

WattLayer: Get Layers Right to Estimate Inference Energy of Neural Networks

WattLayer proposes a layer-wise energy estimation model to accurately measure the inference energy consumption of neural networks across different hardware.

AI/ML arXiv cs.AI

Applicability of memorization indicators for early spotting of overfitting while recalibrating sEMG-decoders on low sample sizes

Research on using ReLU activation statistics as memorization indicators to spot overfitting early during sEMG-decoder recalibration with low sample sizes.

AI/ML arXiv cs.AI

GNBAN: Graph Neural Basis Attention Networks for Long-Horizon Forecasting over Large Entity Sets

GNBAN is a Graph Neural Basis Attention Network designed for scalable and interpretable long-horizon forecasting of large entity sets in retail.

AI/ML arXiv cs.AI

S$^2$-VLA: State-Space Guided Vision-Language-Action Models for Long-Horizon Manipulation

S^2-VLA introduces a state-space guided adaptive attention mechanism to improve long-horizon robotic manipulation by dynamically fusing visual and language features.

AI/ML arXiv cs.AI

SpatialUAV: Benchmarking Spatial Intelligence for Low-Altitude UAV Perception, Collaboration, and Motion

SpatialUAV provides a benchmark for evaluating spatial intelligence in low-altitude UAVs, focusing on 3D inference and multi-view collaboration.

AI/ML arXiv cs.AI

A Study of Temporal Fusion Strategies for Named Entity Recognition in Historical Texts

A study on using temporal metadata and fusion strategies to improve Named Entity Recognition (NER) in historical texts.

Hardware/Chips arXiv cs.AI

SEADA: An efficient methodology for optimizing mixed-precision DNNs on multi-precision spatial architectures

SEADA is a methodology for optimizing mixed-precision DNNs on multi-precision spatial architectures to reduce latency and energy footprint.

AI/ML arXiv cs.AI

Triadic Werewolf: A Jester Role for Multi-Hop Theory of Mind in LLMs

Triadic Werewolf evaluates LLM Theory-of-Mind by introducing a 'Jester' role to test multi-agent reasoning across conflicting utility functions.

AI/ML arXiv cs.AI

Drop-Then-Recovery: How Redundant Are Vision-Language-Action Models?

Researchers introduce Drop-Then-Recovery (DTR) to analyze architectural redundancy in Vision-Language-Action (VLA) models, finding that language backbones are often highly redundant for robotic tasks.

AI/ML arXiv cs.AI

RS-Diffuser: Risk-Sensitive Diffusion Planning with Distributional Value Guidance

RS-Diffuser is a risk-sensitive offline diffusion planning framework that uses distributional value critics to allow flexible risk-averse or risk-seeking behaviors in robotic navigation.

AI/ML arXiv cs.AI

Improving Adversarial Robustness via Activation Amplification and Attenuation

The A3 module improves adversarial robustness in neural networks by jointly learning to amplify and attenuate signals through a lightweight activation scaling mechanism.

AI/ML arXiv cs.AI

Output-Space Allocation Costs for Calibration-Guided LLM Compression: An Empirical Study

An empirical study on LLM compression explores whether aligning allocation costs with output-space objectives improves fidelity, noting a tradeoff between accuracy and perplexity.

AI/ML arXiv cs.AI

SHIFT: Gate-Modulated Activation Steering for Knowledge Conflict Mitigation in Retrieval-Augmented Generation

SHIFT is a framework that uses gate-modulated activation steering to resolve knowledge conflicts between retrieved context and parametric knowledge in RAG systems.

AI/ML arXiv cs.AI

NLL-Guided Full-Attention Layer Selection for Training-Free Sliding-Window Adaptation

A training-free method for selecting full-attention layers in hybrid models using Negative Log-Likelihood (NLL) guidance to optimize long-context inference efficiency.

AI/ML arXiv cs.AI

Position Bias Correction is Insufficient for One-Pass Attention Sorting

Research indicates that simple position bias correction is insufficient to match the performance of iterative attention sorting for long-context language models.

AI/ML arXiv cs.AI

Optimizing Teacher-Student Partitioning for Scalable Knowledge Distillation on HPC Systems

A new HPC-aware methodology for knowledge distillation decouples teacher and student partitioning to achieve up to 67% higher throughput than the TRL library.

AI/ML arXiv cs.AI

Parameter-Efficient Quantum-Inspired Fast Weight Programmers for Traffic-Matrix Forecasting

The paper proposes QKAN-FWPs, quantum-inspired recurrent models that provide efficient traffic-matrix forecasting with significantly lower memory and training budgets.

AI/ML arXiv cs.AI

Pepti-drift: Toxicity-Repulsive Drifting for Antigen-Conditioned Discrete Peptide Generation

Pepti-drift is a toxicity-aware latent refinement framework designed to generate antigen-specific binding peptides while avoiding toxicity.