5 papers · 1 filter
sGPO: Trading Inference FLOPs for Training Efficiency in RLVR
Shivchander Sudalairaj, Kai Xu, Akash Srivastava +1
Standard Reinforcement Learning with Verifiable Rewards (RLVR) training allocates a fixed rollout budget to every query, without regard for what each query's difficulty means for t…
Intrinsic Selection and Particle Resampling for Inference-Time Scaling Beyond Domain Verifiability
Giorgio Giannone, Mustafa Eyceoz, Shabana Baig +5
Inference-Time Scaling (ITS) has largely succeeded in verifiable domains like math and coding, where cheap verification enables scalable output selection. However, extending ITS to…
Mitigating Premature Exploitation in Particle-based Monte Carlo for Inference-Time Scaling
Giorgio Giannone, Guangxuan Xu, Nikhil Shivakumar Nayak +4
Inference-Time Scaling (ITS) improves language models by allocating more computation at generation time. Particle Filtering (PF) has emerged as a strong ITS method for complex math…
Constraining Generative Models for Engineering Design with Negative Data
Lyle Regenwetter, Giorgio Giannone, Akash Srivastava +2
Generative models have recently achieved remarkable success and widespread adoption in society, yet they often struggle to generate realistic and accurate outputs. This challenge e…
Reparameterized Multi-Resolution Convolutions for Long Sequence Modelling
Harry Jake Cunningham, Giorgio Giannone, Mingtian Zhang +1
Global convolutions have shown increasing promise as powerful general-purpose sequence models. However, training long convolutions is challenging, and kernel parameterizations must…