Machine learning news — deep learning, reinforcement learning, neural architecture search, diffusion models, and new ML frameworks and libraries.
Researchers have demonstrated that large language models can serve as selective surrogates for GPU kernel performance evaluation, accurately forecasting kernel runtime without requiring repeated compilation and execution…
On June 2, 2026, Hcompany released Holo3.1, the first production-grade computer use model family with quantized checkpoints—FP8, NVFP4, and Q4 GGUF—designed for fully local inference. The release enables GUI automation a…
TPG Telecom demonstrated an AI-driven monitoring and remediation system at its investor day that uses three AI models to measure customer experience across mobile, fixed broadband and enterprise networks. The system, pre…
Researchers have developed ReLoRA, a knowledge-reusing re-adaptation framework that enables fast recovery of task-specific Low-Rank Adaptation (LoRA) adapters after large language model (LLM) base-model updates. The meth…
Researchers have developed a lightweight custom convolutional neural network to improve the security of EEG-based brain-computer interfaces against adversarial attacks. The proposed model outperformed existing EEG-specif…
Researchers from multiple institutions evaluated machine learning and deep learning models for satellite-derived bathymetry using Sentinel-2 imagery, finding that preserving spatial continuity during training was the mos…
A new study proves the Spectral Alignment Decomposition, which explains why the curvature exponent $\alpha$ — governing how Hessian eigenvalues scale with gradient singular values — varies across neural network layers, w…
Researchers have developed a two-stage geometric registration method that aligns CAD models to CT scans of cylindrical objects by detecting elliptical cross-sections and estimating the 3D rotation axis. The approach achi…
Researchers found that visual graph scaffolds significantly improve large language models' multi-hop reasoning compared to flattened text representations of graph structures. In experiments on question-answering tasks, g…
Researchers have developed MetaWorld, a framework that scales multi-agent video world models to open-domain environments using only single-view video data. The system addresses data scarcity and world state alignment cha…
Researchers introduced ToolGate, a lightweight external controller that predicts whether to execute or skip tool calls proposed by vision-language agents, addressing the pre-call control problem where many tool execution…
Researchers found that transformer-based language models perform better when deeper attention layers learn context-free value vectors that preserve original token information, rather than relying on the residual stream f…
Linear probes applied to Qwen3-14B hidden states achieve 100% accuracy in distinguishing deductive, inductive, and abductive reasoning tasks, but this separation is entirely driven by format confounds such as source iden…
Researchers have developed WRIT (Write-Read Intensive Trajectory Synthesis), a pipeline that generates multi-turn training data for user-facing agents by creating tasks with both high write-decision counts and heavy read…
Researchers have developed EURO-5K, a new dataset of sentence-level reporting obligations from 136 EU legislative acts, to improve automated extraction of regulatory requirements. Benchmarking discriminative BERT-style m…
NVIDIA researchers introduced Cosmos 3, a family of omnimodal world models that jointly process and generate language, image, video, audio, and action sequences within a unified mixture-of-transformers architecture. The …
Researchers introduced Mixture of Pathway Experts (MoPE), a knowledge-distillation framework that uses RNA-derived pathway information during training to improve computational pathology models that only analyze whole-sli…
Researchers have developed a Marchenko-Pastur (MP) random-matrix approach for pruning deep neural networks that requires minimal post-pruning fine-tuning. The method provides deterministic data-path certificates for accu…
Researchers have developed AURA-Mem, a memory system for robot policies that maintains a constant 4,224-byte inference state regardless of episode length, compared to a KV-cache that grows 6,061 times larger over 100,000…
A study evaluating encoder-only Transformer and LSTM frameworks for streamflow prediction in ungauged basins found that the LSTM outperformed the Transformer across both upstream-only and combined configurations. Incorpo…