Enabling privacy-preserving AI training on everyday devices
A new method could bring more accurate and efficient AI models to high-stakes applications like health care and finance, even in under-resourced settings.
Archives AI News
Improving Diversity in Black-box Few-shot Knowledge Distillation
arXiv:2604.25795v1 Announce Type: cross Abstract: Knowledge distillation (KD) is a well-known technique to effectively compress a large network (teacher) to a smaller network (student) with little sacrifice in performance. However, most KD methods require a large training set and internal…
Is the Modality Gap a Bug or a Feature? A Robustness Perspective
arXiv:2603.29080v2 Announce Type: replace-cross Abstract: Many modern multi-modal models (e.g. CLIP) seek an embedding space in which the two modalities are aligned. Somewhat surprisingly, almost all existing models show a strong modality gap: the distribution of images is well-separated from…
Egocentric Tactile and Proximity Sensors as Observation Priors for Humanoid Collision Avoidance
arXiv:2604.25554v1 Announce Type: cross Abstract: Collision-free motion is often aided by tactile and proximity sensors distributed on the body of the robot due to their resistance to occlusion as opposed to external cameras. However, how to shape the sensor’s properties,…
A Hybridizable Neural Time Integrator for Stable Autoregressive Forecasting
arXiv:2604.21101v2 Announce Type: replace Abstract: For autoregressive modeling of chaotic dynamical systems over long time horizons, the stability of both training and inference is a major challenge in building scientific foundation models. We present a hybrid technique in which an…
Principled Detection of Hallucinations in Large Language Models via Multiple Testing
arXiv:2508.18473v3 Announce Type: replace-cross Abstract: While Large Language Models (LLMs) have emerged as powerful foundational models to solve a variety of tasks, they have also been shown to be prone to hallucinations, i.e., generating responses that sound confident but are…
JaGuard: Position Error Correction of GNSS Jamming with Deep Temporal Graphs
arXiv:2509.14000v4 Announce Type: replace Abstract: Global Navigation Satellite Systems (GNSS) face growing disruption from intentional jamming, undermining critical infrastructure where precise positioning and timing are essential. Current position error correction (PEC) methods mainly focus on multi-path propagation errors and fail…
Cornserve: A Distributed Serving System for Any-to-Any Multimodal Models
arXiv:2603.12118v2 Announce Type: replace Abstract: Any-to-Any models are an emerging class of multimodal models that accept combinations of multimodal data (e.g., text, image, video, audio) as input and generate them as output. Serving these models are challenging; different requests with…
minAction.net: Energy-First Neural Architecture Design — From Biological Principles to Systematic Validation
arXiv:2604.24805v1 Announce Type: new Abstract: Modern machine learning optimizes for accuracy without explicitly accounting for internal computational cost, even though physical and biological systems operate under intrinsic energy constraints. We evaluate energy-aware learning across 2,203 experiments spanning vision, text, neuromorphic,…
Nautile-370M: Spectral Memory Meets Attention in a Small Reasoning Model
arXiv:2604.24809v1 Announce Type: new Abstract: We present Nautile-370M, a 371-million-parameter small language model designed for efficient reasoning under strict parameter and inference budgets. Nautile-370M uses a hybrid backbone in which two SeqCond Attention (SCA) layers, a linear-time spectral sequence operator…