In a nutshell Making ML run fast on every chip is hard. Different CPUs, GPUs, and accelerators need different tricks, especially with features like sparsity and quantization. Manual tuning is slow; many automatic tools are opaque. What’s new * PerfLLM + PerfDojo turn optimization into a reinforcement learning game guided by
AI
Can AI really make trading decisions in the messy, fast-changing real world? LiveTradeBench puts large language models to the test with live market data. * Live streams: Real-time prices and news—no offline backtests or leakage. * Portfolio view: Multi-asset allocation with built-in risk management. * Multi-market: U.S. stocks and Polymarket prediction
When instructions use ambiguous or mismatched terms, even smart LLMs can stumble. A new approach, the Language Graph Model (LGM), helps models clarify what users mean by mapping how concepts relate. * Inheritance: recognizing "a robin is a bird"—a family tree of ideas. * Alias: spotting different names for
AI
Researchers asked a simple question: given just your Big Five personality answers, can an AI “role‑play” how you’d score on other psychology questionnaires? Using responses from 816 people, large language models were prompted to generate answers on nine additional psychological scales. The patterns in the AI’s generated
ultrasound
Ultrasound comes in different "flavors" (grayscale and color flow Doppler), but clinical datasets rarely have both for every view. A new study trains a generative AI to "translate" between them—creating realistic videos to fill the gaps. Trained on 54,975 videos and tested on 8,
AI
What if AI could read routine MRI scans and predict a brain tumor’s genetics — no biopsy? This study pairs computational imaging with large language models (LLMs) to zero-shot predict IDH mutation status in gliomas. * Multi-parametric MRI plus tumor segmentation become interpretable visual attributes and quantitative features. * Those features are
ImitationLearning
What if AI could learn skills the way people do - by watching and copying? This new survey maps the fast-moving world of imitation learning (IL) in the deep learning era. * Data: from full expert trajectories to partial or unlabeled sequences. * New methods tackle big pain points: generalization, covariate shift,
Europe's AI Act says makers of general-purpose AI must mark and detect AI-generated content - and those marks must be reliable, interoperable, effective, and robust. But what does that mean in practice? A new paper by Thomas Souverain maps today's watermarking tech for large language models
AI
Build production-ready AI coding agents, faster Meet the OpenHands Software Agent SDK—a toolkit for turning agent ideas into dependable software-engineering assistants. * Flexible by design: start with a few lines of code, then add custom tools, memory, and more. * Secure and portable: native sandboxed execution, seamless local→remote runs, built-in
Analog chips connect electronics to the real world—but sizing their circuits is still a slow, trial-and-error craft. AnaFlow introduces a different approach: a team of specialized, LLM-powered agents that read a circuit’s topology, understand design goals, and iteratively tune device parameters with human-readable reasoning. An adaptive simulation strategy
Smarter, more transparent fact-checking Large language models sound confident, but not always correct. Knowledge graphs are precise but can miss facts. This study combines both—plus a selective web-search agent—into one interpretable fact-checking pipeline. * Step 1: Rapid one-hop lookups in DBpedia to grab trusted facts. * Step 2: An LLM
GenerativeAI
Build stories like a graph What if writing felt like assembling LEGO? This research introduces a node-based editor that lets you craft multimodal stories—mixing text, images, audio, and video—one beat at a time. * Graph-first storytelling: Each scene is a node you can expand, swap, or refine with natural-language