Machine learning news — deep learning, reinforcement learning, neural architecture search, diffusion models, and new ML frameworks and libraries.
Researchers introduced the Epi-LLM framework, which integrates agent-based modeling, real-world epigames, and large language models to simulate behavioral responses during infectious-disease outbreaks, according to an ar…
Microsoft AI announced the release of seven new in-house models spanning image, voice, transcription, coding, and reasoning, forming the MAI model family. The models, including the flagship reasoning model MAI-Thinking-1…
Software organizations are approaching a shift where building software features becomes nearly instantaneous, reducing development time from weeks to hours. This transformation will break existing structures across three…
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 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 ChatHealthAI, a multimodal reasoning framework that aligns structured electronic health record (EHR) representations from a pretrained foundation model with the semantic space of a frozen large…
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…
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…
Researchers have developed Fast-dLLM++, a training-free extension to diffusion large language models that accelerates inference by selecting parallel token commit sets based on the full sorted confidence profile rather t…
Researchers introduced the Ghost Annotator framework, which combines conformal prediction with collaborative filtering to model how large language models (LLMs) behave compared to human annotators in content moderation t…
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…
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 Adaptive Latent Agentic Reasoning (ALAR), a dual-mode framework that reduces unnecessary textual reasoning in LLM agents by using compact latent reasoning for routine tasks and reserving explic…
Researchers have developed a multi-agent AI system that uses economic principles—specifically market-based auctions and wealth accumulation—to enable decentralized coordination among agents without centralized control. T…
A systematic human audit of the NL-to-FOL benchmarks FOLIO and MALLS found that approximately 39% and 36% of entries, respectively, contain incorrect FOL formalizations, with additional errors in ambiguous natural langua…
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…
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…