96 Mark Gurman attend Apple TV et HomePod mini dès lautomne , le HomePad pourrait arriver plus tard igen.fr · 28m ago
98 You’ve been using your power bank wrong, and airline rules make that obvious zdnet.com · 2h 27m ago
95 Fish Audio raises $50M seed to build AI voice models for creators and enterprises techcrunch.com · 1h 9m ago
100 QFoldAgent: An Autonomous Quantum Optimization Multi-Agent System for Protein Structure Prediction arxiv.org · 7h 11m ago
100 Same Question, Different Answers: Evaluating LLM Reliability Beyond Accuracy arxiv.org · 7h 11m ago
100 DeepLens Diagnosis Agent: Agentic Workflow Design Lets a Small Reasoning Model Compete with Frontier LLMs arxiv.org · 7h 11m ago
100 MIITA: Memory-Induced Inference-Time Adaptation for Continual Learning with Small Language Models arxiv.org · 7h 11m ago
100 MedLoCoMo: A Long-Context Multi-Session Medical Dialogue Benchmark for Large Language Models arxiv.org · 7h 11m ago
100 Keyword Matters: Unveiling the Energy Sensitivity of On-Device LLM Prompting arxiv.org · 7h 11m ago
100 SCAIR: Schema-Conditioned Agentic Iterative Reasoning for Enterprise Knowledge Graphs arxiv.org · 7h 11m ago
100 Temporal Context Reinstatement Drives Episodic-Like Order Memory in Long-Context Language Models arxiv.org · 7h 11m ago
92 At AI Summit, South Korea Outlines Its AI Future With NVIDIA and Partners blogs.nvidia.com · 4d 7h ago
92 [AINews] Black Forest Labs FLUX 3 — Multimodal Flow Models that beat Seedance 2.0, Gemini Omni and Grok Imagine, and FLUX-mimic video-action robotics model latent.space · 4d 7h ago
81 What is Good? Extracting and Testing Implicit Theories of Literary Quality from LLM Reasoning Traces arxiv.org · 4d 7h ago
81 Is MoE Routing a Huffman Code? Discovering the Frequency-Diversity Law in Chain-of-Thought arxiv.org · 4d 7h ago
81 Moir: Let the Model Direct Its Own Story for Robust Cross-Domain Knowledge Editing arxiv.org · 4d 7h ago
81 Belief Propagation in LLM World Models: Measuring Strategic Information Bias with Prediction Markets arxiv.org · 4d 7h ago
81 Naver-News-KO: A Korean News Summarization Dataset for Open-Source Fine-Tuning of Summarization Models arxiv.org · 4d 7h ago
81 Distinguishing Artificial from Authentic: Evaluating LLMs for Detecting LLM-Generated Content arxiv.org · 4d 7h ago
81 The Storyteller in the Model: Narrative Pattern Inheritance, Escalation Dynamics, and Alignment Governance in LLMs arxiv.org · 4d 7h ago
81 ShriNep@EEUCA 2026: RAKSHAK — Multi-Task DeBERTa with Rationale Distillation and Jigsaw-Augmented Training for Toxic Intent Classification arxiv.org · 4d 7h ago
33 BTL-3: A 27B open-weight agent model for agentic coding and structural tool use huggingface.co · 4d 9h ago
30 Show HN: Continuum – switch AI coding agents without re-explaining your project github.com · 4d 9h ago
30 Japanese AI Robots Used to Replicate Skilled Confectioners’ Abilities japannews.yomiuri.co.jp · 4d 9h ago
26 HN: FlowShelf –free,native macOS shelf/clipboard/screenshot app,on-device AI flowshelf.app · 4d 8h ago
22 Codex Slides: open-source AI slide studio powered by Codex. Prompt, repo to deck github.com · 4d 10h ago
1 Розборки ШІ : OpenAI зламала американську ШІ — платформу на порятунок прийшла китайська ШІ — модель itc.ua · 4d 9h ago