Machine learning news — deep learning, reinforcement learning, neural architecture search, diffusion models, and new ML frameworks and libraries.
Researchers propose EMRFormer, a spiking neural network architecture that applies spike-driven transformers to automatic modulation recognition, achieving state-of-the-art accuracy while reducing theoretical energy consu…
Researchers constructed large-scale algorithm co-occurrence networks in natural language processing based on full-text academic papers, analyzing their structural characteristics and centrality measures. The study found …
Researchers propose TheProfessor, a multi-teacher prompt distillation method for vision-language models that ensembles a domain-finetuned teacher and a zero-shot teacher. On four datasets, confidence-weighted ensembling …
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 developed a hybrid machine learning model combining ensemble feature selection and Harris Hawks optimization to predict depression in female sex workers with 95.78% accuracy. The model identified post-traumat…
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 at arXiv found that self-generated text recognition (SGTR) finetuning can prevent and reverse emergent misalignment in large language models, outperforming other interventions. The study across GPT-4.1, Qwen2…
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 developed a hybrid machine learning approach combining EfficientNetB0 feature extraction with Random Forest classification to achieve 94.58% accuracy and sub-millisecond inference for real-time melt pool moni…
Researchers introduced the degeneracy distillery, a method that automatically detects and resolves degenerate parameter combinations in physical models by estimating and flattening the Fisher information matrix. The appr…
Researchers developed an automated pipeline to explore heterogeneous 4-expert mixture-of-experts architectures, generating 4,463 candidate models over 28 days. The search was biased toward the AirNet family due to an enu…
Researchers introduced Sol Video Inference Engine, an agent-native full-stack acceleration framework for video diffusion models that achieves over 2x end-to-end speedup with near-lossless quality across models from 2B to…
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 introduced the MELD dataset to evaluate whether embedding models capture mathematical equivalence, finding that current models group statements by terminology rather than underlying math. They proposed a cont…
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…