sGPO: Trading Inference FLOPs for Training Efficiency in RLVR
Paper • 2606.08854 • Published
Giorgio Giannone
georgosgeorgos
AI & ML interests
I am broadly interested in Probabilistic Machine Learning, Perception and Geometry,
with a focus on Conditional Generative Models, Hierarchical Variational Inference,
Few-Shot Generation, Multitask Language Models, and Diffusion Models.
Recent Activity
authored a paper 2 days ago
sGPO: Trading Inference FLOPs for Training Efficiency in RLVR authored a paper 2 days ago
Intrinsic Selection and Particle Resampling for Inference-Time Scaling Beyond Domain Verifiability authored a paper 2 days ago
GIFT: Bootstrapping Image-to-CAD Program Synthesis via Geometric FeedbackOrganizations
authored 4
papers 2 days ago
Intrinsic Selection and Particle Resampling for Inference-Time Scaling Beyond Domain Verifiability
Paper • 2606.08850 • Published
GIFT: Bootstrapping Image-to-CAD Program Synthesis via Geometric Feedback
Paper • 2603.27448 • Published
SCHA-VAE: Hierarchical Context Aggregation for Few-Shot Generation
Paper • 2110.12279 • Published
liked a
dataset 26 days ago
authored 5
papers 8 months ago
From Concept to Manufacturing: Evaluating Vision-Language Models for Engineering Design
Paper • 2311.12668 • Published
Accelerating Material Design with the Generative Toolkit for Scientific Discovery
Paper • 2207.03928 • Published
Mitigating Premature Exploitation in Particle-based Monte Carlo for Inference-Time Scaling
Paper • 2510.05825 • Published
Feedback-Driven Vision-Language Alignment with Minimal Human Supervision
Paper • 2501.04568 • Published
Aligning Optimization Trajectories with Diffusion Models for Constrained Design Generation
Paper • 2305.18470 • Published
updated a
collection 8 months ago
authored a
paper about 3 years ago
liked 4
models about 3 years ago
liked a
Space about 3 years ago