diamond 产品

来源: githubOPEN_SOURCE开源PythonMIT发布于 2024-05-19

DIAMOND (DIffusion As a Model Of eNvironment Dreams) is a reinforcement learning agent trained in a diffusion world model. NeurIPS 2024 Spotlight.

2041

Stars

153

Forks

1

技术栈

0

替代方案

10

相关事件

人工智能深度学习框架
GitHub官网
关系图谱

diamond · 相关事件

相关事件

TLA-Prover: Verifiable TLA+ Specification Synthesis via Preference-Optimized Low-Rank Adaptation
2026-06-06PRODUCT_LAUNCH影响: MEDIUM
Not All Flips Are Conformity: Decomposing Stance Convergence in Multi-Agent LLM Debate
2026-06-02REGULATION影响: MEDIUM
Not All Flips Are Conformity: Decomposing Stance Convergence in Multi-Agent LLM Debate
2026-06-02PRODUCT_LAUNCH影响: MEDIUM
Diamonds in the Sky: Pareidolic Animals in Clouds
2026-06-02PRODUCT_LAUNCH影响: MEDIUM
Diamonds in the Sky: Pareidolic Animals in Clouds
2026-06-02BREAKTHROUGH影响: HIGH
Empirical Characterization of Inference-Time Elicited Probability Transformations in Large Language Models
2026-06-01PRODUCT_LAUNCH影响: MEDIUM
Reasoning Theater: Disentangling Model Beliefs from Chain-of-Thought
2026-05-29PRODUCT_LAUNCH影响: MEDIUM
HEART-Bench: Do LLM Agents Exhibit Human-like Psychology?
2026-05-29PRODUCT_LAUNCH影响: MEDIUM
The Growing Pains of Frontier Models: When Leaderboards Stop Separating and What to Measure Next
2026-05-26PRODUCT_LAUNCH影响: MEDIUM
Qwen3.7-Max 发布
2026-05-20SHUTDOWN影响: LOW