5 citations · 11 across the 12 of their papers we have counts for
8 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…
Rollout Roulette: A Probabilistic Inference Approach to Inference-Time Scaling of LLMs using Particle-Based Monte Carlo Methods
Isha Puri, Shivchander Sudalairaj, Guangxuan Xu +2
Large language models (LLMs) have achieved significant performance gains via scaling up model sizes and/or data. However, recent evidence suggests diminishing returns from such app…
Unveiling the Secret Recipe: A Guide For Supervised Fine-Tuning Small LLMs
Aldo Pareja, Nikhil Shivakumar Nayak, Hao Wang +10
The rise of large language models (LLMs) has created a significant disparity: industrial research labs with their computational resources, expert teams, and advanced infrastructure…
Post-processing Private Synthetic Data for Improving Utility on Selected Measures
Hao Wang, Shivchander Sudalairaj, John Henning +2
Existing private synthetic data generation algorithms are agnostic to downstream tasks. However, end users may have specific requirements that the synthetic data must satisfy. Fail…
Multi-Symmetry Ensembles: Improving Diversity and Generalization via Opposing Symmetries
Charlotte Loh, Seungwook Han, Shivchander Sudalairaj +5
Deep ensembles (DE) have been successful in improving model performance by learning diverse members via the stochasticity of random initialization. While recent works have attempte…
On the Importance of Calibration in Semi-supervised Learning
Charlotte Loh, Rumen Dangovski, Shivchander Sudalairaj +5
State-of-the-art (SOTA) semi-supervised learning (SSL) methods have been highly successful in leveraging a mix of labeled and unlabeled data by combining techniques of consistency…