openai/openai-python v3.33.0
3.33.0 (2026-10-16) Features · api: add safety identifiers to image requests and responses · api: share Decisions cache breakpoint parameter type
#안전·정렬
7건 · 최신순
Latent SpaceLatent Space 뉴스레터
[AINews] Agents disprove Polysemanticity; greatly improve Interpretability & Alignment
Nick Cammarata out of nowhere with some major claims!
Hugging FaceHugging Face 일일 논문
RoTA-Bench: Evaluating 3D Spatial Reasoning through Interactive Projection Alignment
Can vision-language models turn 2D observations into 3D understanding that supports precise action? This requires inferring object geometry, anticipating the effects of rotation, and refining actions through visual feedback.
Hugging FaceHugging Face 일일 논문
CarryOn: A Dual-Loop Harness for Personalized and Reliable Robot Assistance
While generalist vision-language-action (VLA) models have enabled diverse open-world manipulation, real-world robotic assistance requires two critical capabilities they currently lack: personalization and reliable execution.
Hugging FaceHugging Face 일일 논문
SUPRA-TEX: 3D Generation with Super-Aligned Texture
Single image 3D generation aims to dress a given 3D mesh with relightable materials while faithfully preserving the visual details of a reference image.
Hugging FaceHugging Face 일일 논문
Mine, Sample, Render: Test-Time Diversity Alignment Of Generative Models
Modern generative models produce high-quality individual outputs but struggle to sample diversely, even when explicitly instructed to do so.
Hugging FaceHugging Face 일일 논문
Equal CER, Unequal Damage: Severity-Weighted Character Error Rate for OCR
Character Error Rate (CER), the standard metric for OCR and vision-language models (VLMs), charges a typo as much as a wrong name.