Game Boy Color on My Conference Badge
Simon Willison ·
Game Boy Color on My Conference Badge I'm at GitHub Universe this week and, similar to last year , the conference badge is a full-blown color screen computer. I've been hacking …
原文内容 · 暂无该语言译文AI News · 2026-10-27
按本站收录日期（UTC）归档，不代表事件发生于当天；原公告、聚合源发布与收录时间分别标注。
返回资讯列表Fine-Tuning NVIDIA Nemotron to Know Local Rules, Not Just Local Languages
NVIDIA Technical Blog ·
As AI adoption expands globally, people across languages and cultures are using it in more aspects of their daily lives. General-purpose language models serve... As AI adoption …
原文内容 · 暂无该语言译文3 Ways to Boost MoE Inference on NVIDIA DGX Spark
NVIDIA Technical Blog ·
Generating tokens faster starts with identifying what limits inference performance. In the batch-size-1 evaluation of Ling-3.0-flash from Inclusion AI on NVIDIA... Generating to…
原文内容 · 暂无该语言译文Ai2 发布 Old Ideas, Novel Problems 研究与 benchmark，揭示 LLM 新颖性裁判不稳定
AIHOT ·
Ai2 发布研究 Old Ideas, Novel Problems、配套 benchmark、数据、代码和自动化流水线，测试 LLM 作为研究想法新颖性裁判的可靠性。
原文内容 · 暂无该语言译文HA-DiPO: Diffusion Policy Optimization for Heterogeneous Cooperative Transport
arXiv cs.RO ·
Cooperative transport with heterogeneous legged robots requires coordinating different motion capabilities while supporting an unfixed shared payload. We present HA-DiPO (Hetero…
原文内容 · 暂无该语言译文Entropic Control for Homeostatic Optimization: Pre-empting Catastrophic Forgetting via Dynamic Feedback
arXiv cs.CL ·
Supervised Fine-Tuning (SFT) of LLMs suffers from catastrophic forgetting, and prevailing mitigation strategies struggle to reconcile the plasticity-stability dilemma. To addres…
原文内容 · 暂无该语言译文Greptile takes bug detection beyond code review with GPT-6 Astra
OpenAI ·
How Greptile uses GPT-6 Astra to test user workflows, Daybreak to strengthen security, and Codex to reduce rework.
原文内容 · 暂无该语言译文Anthropic 研究：AI 智能体的隐性倾向如何影响 50 名专业分析师的判断决策
AIHOT ·
Anthropic 发表研究，让 50 名有因果推断经验的专业分析师用 Claude Code（Claude Opus 4.8）完成一项统计分析任务，并在分析师不知情的情况下用掷硬币随机设定智能体在四个分析决策上的倾向。
原文内容 · 暂无该语言译文GaP: A Graph-as-Policy Multi-Agent Self-Learning Harness For Variational Automation Tasks
arXiv cs.RO ·
For robots to work reliably in commercial and industrial applications, recent advances in agentic coding systems have potential to combine interpretable robot programming with t…
原文内容 · 暂无该语言译文ToolRACER: A Robust Agentic Conversation Emulation Resource for Agent Training and Evaluation
arXiv cs.CL ·
Task-oriented conversational agents remain fragile under real world conversation scenarios as they rarely follow a predictable script, especially when users exhibit non-cooperat…
原文内容 · 暂无该语言译文