ARC-GEN: A Mimetic Procedural Benchmark Generator for the Abstraction and Reasoning Corpus
"ARC-AGI" 相关文章
无RLHF，7M小模型反超DeepSeek-R1：三星团队用递归思考取代规模堆叠
Tiny Recursive Model (TRM): A Tiny 7M Model that Surpass DeepSeek-R1, Gemini 2.5 pro, and o3-mini at Reasoning on both ARG-AGI 1 and ARC-AGI 2
Tiny Recursive Model (TRM): A Tiny 7M Model that Surpass DeepSeek-R1, Gemini 2.5 pro, and o3-mini at Reasoning on both ARG-AGI 1 and ARC-AGI 2
无RLHF，7M小模型反超DeepSeek-R1：三星团队用递归思考取代规模堆叠
无RLHF，7M小模型反超DeepSeek-R1：三星团队用递归思考取代规模堆叠
Samsung’s tiny AI model beats giant reasoning LLMs
Samsung’s tiny AI model beats giant reasoning LLMs
Samsung’s tiny AI model beats giant reasoning LLMs
Samsung’s tiny AI model beats giant reasoning LLMs
Less is More: Recursive Reasoning with Tiny Networks
Less is More: Recursive Reasoning with Tiny Networks
Do AI Models Perform Human-like Abstract Reasoning Across Modalities?
An N=1 observational study on interpretability of Natural General Intelligence (NGI)
马斯克开始疯狂剧透Grok 5了
📆 ThursdAI - Sep 18 - Gpt-5-Codex, OAI wins ICPC, Reve, ARC-AGI SOTA Interview, Meta AI Glasses & more AI news
400万人围观的分层推理模型，「分层架构」竟不起作用？性能提升另有隐情？
Out-of-Distribution Generalization in the ARC-AGI Domain: Comparing Execution-Guided Neural Program Synthesis and Test-Time Fine-Tuning
o3狂烧3万美金解一题，反被AGI榜单除名！试错1024次不如10岁小孩哥4分钟
OpenAI o3 模型运行成本估算大幅上调：单次任务从 3000 美元涨至 3 万美元
