Full-text search across 70367 articles. Combine with topic and date filters; results sorted by relevance.
Xiaomi has open-sourced MiDashengLM-Spatial, an audio-language model that combines general sound understanding with spatial awareness, releasing the model weights and inference code under the Apache 2.0 license. Built on…
China's Ministry of Commerce and Ministry of Science and Technology jointly issued a draft plan on Friday proposing export bans on 14 technologies, including AI-driven technology for generating and mutating malicious cod…
The CL-UNK-1211 espionage campaign used AI-assisted workflows to infiltrate government entities and state-affiliated Linux infrastructure between October 2025 and April 2026, according to the report. The attackers embedd…
A developer built Front Desk, a browser-based site chatbot for small businesses that restricts a Gemma 4 E2B model (via WebLLM at temperature 0) to drafting answers while plain code validates every response against the s…
A developer's Claude-assisted analysis claims that agent swarms communicating in Hyperlambda (HL) rather than natural language (NL) plus a sandbox would cut electricity consumption by 5 to 7 orders of magnitude and reduc…
Gitsu launched as an AI-native, keyboard-first Mac and web issue tracker built on top of existing GitHub Projects and issues, with background syncing to GitHub. The web version is free, while Gitsu Pro costs $4.99 per se…
Researchers developed ReviewPilot, a conversational multi-agent system that automates the PRISMA systematic review workflow from paper screening to information extraction, according to an arXiv paper (arXiv:2610.21042v1)…
Researchers introduced RenoLayout, a framework that formulates residential design as a design-point-guided conditional generation task and translates a pre-design residential state plus a design-point set into an executa…
Researchers released VELD-QA, a benchmark of 15,000 human-authored question-answer pairs spanning 5,859 real-world PDFs and 372,445 pages, designed to test visual evidence grounding and question answering in long documen…
Researchers at Tongji University's TJUNLP lab released VALCON, a role-driven benchmark framework that tests whether large language models keep consistent values when switching between generating actions and evaluating th…
A Duke University NLP lab study (arXiv:2610.21062v1) found that the state-of-the-art Pangram 4 AI-text detector loses accuracy as mathematical content increases, especially on PDF-extracted text rather than LaTeX. The re…
Researchers proposed Competitive Token Selection (CoTS), a training-free framework that dynamically balances discrete token commitment and soft latent exploration at each reasoning step using the probability competition …
Researchers introduced FLOWBUDGET, a training-free estimator of solver-relative sampling complexity for flow matching models, detailed in arXiv paper 2610.20636v1. FLOWBUDGET normalizes leading one-step discretization er…
Researchers released ARIA (Agent Runtime Inspection and Amendment), a framework for learning when and how to repair ongoing LLM-based multi-agent executions, built on a dataset of 3,953 execution-verified repair pairs dr…
Researchers propose EvolvingBrain, an adaptive skill system that lets multi-modal agents self-evolve in open worlds by extracting Procedural and Problematic Patterns from model-specific trajectories and organizing them i…
Researchers proposed PRISM, a post-training method that improves LLM multi-agent topology generators by learning from privileged sibling graphs, according to arXiv paper 2610.20628v1. PRISM uses a teacher with a zero-ini…
A framework called PRISM, introduced in arXiv paper 2610.20808v1, shows that safety interventions estimated from quantized NF4 behavioral labels transfer across languages and model scales, reducing unsafe tool-call viola…
Perplexity AI Inc. has open-sourced SPACE, a sandbox for isolating AI agents, making the tool available to all developers as of today. SPACE is already deployed by CoreWeave Inc., Akamai Technologies Inc. and Crusoe Inc.…
A developer published a step-by-step Python approach for handling malformed JSON returned by LLMs, which fails roughly one time in 20 in production. The technique strips markdown code fences and surrounding prose, extrac…
Full-stack developer MithrilMan released an improved distillation of the Kokoro text-to-speech model at roughly 9MB with about 25x real-time factor, publishing the Apache-2.0 code on GitHub and weights on Hugging Face un…