Stay Informed

The End of Relational AI?

Why have so many people been saying for months that AI models are getting worse?Continue reading on Medium »

Medium AI·22h ago

arXiv Machine Learning·1d ago

Dynamic Influence-Weighted Distillation for Single-IMU Activity Recognition

arXiv:2608.24904v1 Announce Type: new Abstract: Inertial sensors at multiple body locations can improve activity recognition, but requiring every sensor at inference increases the deployment burden. We study whether four synchronized IMUs available during training can improve a student that uses only the right-arm IMU during fitting and inference. A frozen four-IMU teacher provides logit and feature targets. Fixed-weight knowledge distillation applies each target with the same strength to every fitting sample, although the student may not benefit equally from them. We introduce dynamic influence weighting (DIW), which tests a one-step candidate update on separate fold-internal training participants. DIW then assigns separate sample-wise gates to the logit and feature losses. On WEAR, we evaluate 19 labels and 68,298 complete windows from 22 participants using subject-disjoint five-fold cross-validation. Pooled out-of-fold macro-F1 is 0.561820 for Supervised and 0.571623 for Fixed-weigh

arXiv Machine Learning·1d ago

GreenLeaf Law Embed Tiny: A Compact Embedding Model for Legal Domain Retrieval

arXiv:2608.24936v1 Announce Type: new Abstract: We present GreenLeaf Law Embed Tiny, a 0.6B parameter embedding model for legal domain retrieval. GreenLeaf-Tiny achieves 75.11% on the Massive Legal Embedding Benchmark (MLEB) and 64.38% on MTEB(Law, v1),demonstrating competitive performance among models under 1B parameters. Our approach combines a two-stage training pipeline that first distills knowledge from a larger teacher model into a compact student architecture, then applies domain-specific fine-tuning with hard negative mining; a carefully curated dataset of 3.4 million query-passage pairs, including 150,000 human-curated samples across diverse legal jurisdictions; and an efficient inference architecture supporting multiple quantization levels (BF16, INT8, binary) enabling deployment in resource-constrained environments. We provide detailed analysis of our training methodology, architectural choices, and comprehensive evaluation across legal retrieval tasks. Our results demonstra

ROS2 Connect: A new ROS2 over WAN Solution

arXiv:2608.25102v1 Announce Type: new Abstract: The Robot Operating System 2 (ROS2) has become a widely adopted framework for the development of distributed robotic systems. However, its communication architecture, based on DDS and RTPS, relies on multicast discovery mechanisms that are typically unavailable in wide-area network (WAN) environments, making remote operation challenging. This work presents ROS2 Connect, a WebSocket-based communication framework that enables transparent and secure ROS2 interaction across routed networks without requiring modifications to network infrastructure or DDS configurations. The proposed client-server architecture supports bidirectional exchange of topics, services, actions, and system data while integrating authentication and access control mechanisms. Experimental evaluation over a real WAN connection demonstrates significantly lower latency, higher stability, and improved scalability compared to existing solutions, including DDS Router, rosbridg

arXiv Robotics·1d ago

GaussVLA: Geometry-Aware Spatial Reasoning for Vision-Language-Action Model

arXiv:2608.24959v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models encode visual observations as flat 2D patch tokens that carry no intrinsic geometric structure, and augmenting them with dense monocular depth injects per-pixel scalar values that encode neither surface orientation nor geometric confidence. This leaves the policy with limited structured spatial reasoning for action prediction. We propose GaussVLA, a Mamba-based VLA that incorporates two custom modules: Gaussian Spatial Tokenizer (GST) to lift frozen semantic and depth features into compact 3D Gaussian tokens, pools geometrically salient regions with learned queries, and \emph{Depth-Aware Chain-of-Thought (DA-CoT)} that performs structured, non-autoregressive geometric reasoning under language and flow-time conditioning. Across both simulation and real-world evaluations, GaussVLA demonstrates strong spatial-manipulation performance while remaining parameter-efficient. On LIBERO, it achieves 93.5% average

arXiv Robotics·1d ago

ChatGPT Ads Launch Across Europe: 31 Markets and What Brands Should Do Next

ChatGPT ads launch across Europe in 31 markets. See the early data, market context, and what advertisers should do next.Continue reading on Medium »

The Accuracy Illusion: Why Your AI System Is Lying to You

I built a fraud detection system with 98.46% accuracy. When the auditors arrived, I could not explain a single decision it had made.Continue reading on Medium »

Pope Leo on AI: A Tower of Babel or an Ecosystem of Intelligence?

Will AI be a centralized Tower of Babel or an ecosystem for human collaboration? Pope Leo asks for technology with conscience. POND Continue reading on The Singularity Project »

Sorry, It’s Not Just Taste That Matters

In the age of AI, it s so easy to feel like you are now suddenly an expert in everything.Continue reading on Medium »