Machine learning news — deep learning, reinforcement learning, neural architecture search, diffusion models, and new ML frameworks and libraries.
Researchers introduced OmniPath, a multi-modal agentic framework that audits wheelchair accessibility by fusing OpenStreetMap data with aerial LiDAR to create high-fidelity 3D models. The system analyzes pedestrian surfa…
Researchers propose Strategy-Guided Policy Optimization (SGPO), a method that replaces trajectory-level imitation with reusable strategy distillation to improve LLM reasoning. SGPO extracts structured strategies from str…
Researchers introduced a multi-objective reinforcement learning framework for recommender systems that uses a Pareto-DQN agent with semantic embeddings to optimize engagement, diversity, and fairness as separate reward s…
Researchers introduce ARIA, a framework that adaptively allocates training effort across regions of the conditioning space to improve distillation of conditional diffusion models. By focusing updates where teacher-studen…
Researchers introduced Sesame, a diffusion-based molecular generation model that conditions on partial molecular structure and protein pockets via spatial density maps, enabling both de novo drug design and fragment-base…
Researchers compared six offline reinforcement-learning methods for distilling reasoning from large language models into smaller ones, finding that SFT, RFT, and RIFT produce nearly identical weight updates and accuracy,…
Researchers developed low-power analogue neural networks with trainable nonlinear connections, inspired by Kolmogorov-Arnold networks, achieving efficient continuous control tasks like robotic kinematics and photovoltaic…
Researchers reconstructed GRACE-like terrestrial water storage anomalies back to 1940 using a spatio-temporal graph neural network (MTGNN) applied to South America. The model achieved high correlations and low bias, outp…
A developer built a real-time gesture-controlled invisibility cloak using Python, MediaPipe, and OpenCV. The system uses hand gestures such as a pinch to create a moving portal of invisibility or an open left hand to ful…
Developer Monish released NOVA-VAD, an open-source voice activity detector that achieves 93% accuracy on noisy audio, outperforming Silero, Pyannote, and WebRTC while remaining lightweight and explainable. The tool uses …
Researchers stress-tested Natural Language Autoencoders (NLAs) by optimizing activation vectors to flip AV explanations while preserving model behavior, achieving an 81.4% flip rate with 99.6% label preservation. Further…
A researcher proposes Tree Transformers, a generalization of the transformer architecture that operates directly on tree-structured data instead of vectors, preserving internal data structure. The approach defines self-a…
MoEngage acquired AI startup Aampe for tens of millions of dollars to integrate per-customer reinforcement-learning decisioning into its platform. The deal aims to help MoEngage win enterprise clients migrating from Sale…
Alibaba's Qwen team released Qwen-AgentWorld-35B-A3B and Qwen-AgentWorld-397B-A17B, the first language world models capable of simulating agentic environments across seven domains via long chain-of-thought reasoning. The…
Researchers released DiffusionBench, a unified codebase for holistic evaluation of generative diffusion transformers across tasks like ImageNet and text-to-image generation. The benchmark supports training and evaluation…
MoEngage acquired Aampe in an all-cash deal worth tens of millions, integrating Aampe's reinforcement learning engine that handles 200 billion personalized decisions per week for brands like Swiggy and Grab. The acquisit…
A new framework proposes four dimensions—diffuseness, agency, severity, and probability—to quantify and tame fear, mapping emotions like dread and panic onto numerical vectors. The model aims to help people study and red…
JP Hutchins benchmarks Python struct definition speed, finding that metaprogramming approaches like decorators and metaclasses incur higher upfront runtime costs than manual type definitions. The analysis focuses on comp…
A developer's platform for structured compliance-training programmes repeatedly failed internal quality checks on an ISO 42001 Lead Auditor course due to subtle drift into other standards. Investigation revealed 22 disti…
Nous Research announced that its Hermes Agent can now learn from any source material, including code, API docs, manuals, PDFs, and configs, distilling them into verifiable reusable skills.