arXiv:2403.15509v3 Announce Type: replace-cross Abstract: Knowledge distillation (KD) has been widely used to improve lightweight AI models by…
Category: AI
WNM-3D: A World Navigation Model with 3D Scene Conditioning for Closed-Loop VLN
arXiv:2608.07267v2 Announce Type: replace Abstract: Recent vision-language navigation (VLN) systems increasingly adapt pretrained vision-language models…
Nvidia just showed that the harness, not the AI model, is now the real hero
Nvidia research shows that AI agents can perform well, and not go off the deep end, through fine-tuning, even if the AI model isn’t that great at the task.
Voicy Review: I Replaced My Keyboard With My Voice
As a writer who tests and reviews AI software, I spend most of my day with my hands on a keyboard: researching a new tool, testing it for myself, and then…
LongRCA Bench: Diagnosing Responsible Roles and Root Causes in Long-Horizon Agent Failures
arXiv:2608.15242v2 Announce Type: replace Abstract: When a long-horizon agent execution fails, outcome-level evaluation reveals the unsuccessful result…
Anthropic puts its most powerful model Claude Mythos 5 to work for cyber defense
Anthropic is now running its security scanner Claude Security on Claude Mythos 5. The tool scans codebases for vulnerabilities, provides severity ratings…
Graph Surgery and the Do-Operator: A Precise Correspondence for Acyclic Structural Causal Models
arXiv:2608.17634v2 Announce Type: replace Abstract: The $\operatorname{do}$-operator is described graphically by deleting arrows into its targets and…
Stripe agrees to buy OpenRouter as AI model routing expands
Stripe has agreed to acquire OpenRouter, an AI model-routing platform that gives developers access to hundreds of models through a single interface. The…
Andy: A Mathematical Agent for Rigorous Proof and Autonomous Research
arXiv:2608.15052v2 Announce Type: replace Abstract: Andy is an autonomous mathematical research agent that turns a mathematical problem into a traceable…
Binance now lets AI agents trade, but keeping them in check is largely up to users
Binance’s Agent OS works with tools such as ChatGPT, Claude Code, and Cursor.