11 citations · 27 across the 12 of their papers we have counts for
14 papers
Stepwise Credit Assignment for GRPO on Flow-Matching Models
Yash Savani, Branislav Kveton, Yuchen Liu +5
Flow-GRPO successfully applies reinforcement learning to flow models, but uses uniform credit assignment across all steps. This ignores the temporal structure of diffusion generati…
Antidistillation Fingerprinting
Yixuan Even Xu, John Kirchenbauer, Yash Savani +5
Model distillation enables efficient emulation of frontier large language models (LLMs), creating a need for robust mechanisms to detect when a third-party student model has traine…
Safety Pretraining: Toward the Next Generation of Safe AI
Pratyush Maini, Sachin Goyal, Dylan Sam +7
As large language models (LLMs) are increasingly deployed in high-stakes settings, the risk of generating harmful or toxic content remains a central challenge. Post-hoc alignment m…
Not All Rollouts are Useful: Down-Sampling Rollouts in LLM Reinforcement Learning
Yixuan Even Xu, Yash Savani, Fei Fang +1
Reinforcement learning with verifiable rewards (RLVR) has emerged as the leading approach for enhancing reasoning capabilities in large language models. However, it faces a fundame…
Antidistillation Sampling
Yash Savani, Asher Trockman, Zhili Feng +5
Frontier models that generate extended reasoning traces inadvertently produce rich token sequences that can facilitate model distillation. Recognizing this vulnerability, model own…
Diffusing Differentiable Representations
Yash Savani, Marc Finzi, J. Zico Kolter
We introduce a novel, training-free method for sampling differentiable representations (diffreps) using pretrained diffusion models. Rather than merely mode-seeking, our method ach…
Efficient neural supersampling on a novel gaming dataset
Antoine Mercier, Ruan Erasmus, Yashesh Savani +3
Real-time rendering for video games has become increasingly challenging due to the need for higher resolutions, framerates and photorealism. Supersampling has emerged as an effecti…
QuickSRNet: Plain Single-Image Super-Resolution Architecture for Faster Inference on Mobile Platforms
Guillaume Berger, Manik Dhingra, Antoine Mercier +3
In this work, we present QuickSRNet, an efficient super-resolution architecture for real-time applications on mobile platforms. Super-resolution clarifies, sharpens, and upscales a…
Deep Equilibrium Optical Flow Estimation
Shaojie Bai, Zhengyang Geng, Yash Savani +1
Many recent state-of-the-art (SOTA) optical flow models use finite-step recurrent update operations to emulate traditional algorithms by encouraging iterative refinements toward a…
NAS-Bench-x11 and the Power of Learning Curves
Shen Yan, Colin White, Yash Savani +1
While early research in neural architecture search (NAS) required extreme computational resources, the recent releases of tabular and surrogate benchmarks have greatly increased th…
A Study on Encodings for Neural Architecture Search
Colin White, Willie Neiswanger, Sam Nolen +1
Neural architecture search (NAS) has been extensively studied in the past few years. A popular approach is to represent each neural architecture in the search space as a directed a…
Intra-Processing Methods for Debiasing Neural Networks
Yash Savani, Colin White, Naveen Sundar Govindarajulu
As deep learning models become tasked with more and more decisions that impact human lives, such as criminal recidivism, loan repayment, and face recognition for law enforcement, b…
Exploring the Loss Landscape in Neural Architecture Search
Colin White, Sam Nolen, Yash Savani
Neural architecture search (NAS) has seen a steep rise in interest over the last few years. Many algorithms for NAS consist of searching through a space of architectures by iterati…
BANANAS: Bayesian Optimization with Neural Architectures for Neural Architecture Search
Colin White, Willie Neiswanger, Yash Savani
Over the past half-decade, many methods have been considered for neural architecture search (NAS). Bayesian optimization (BO), which has long had success in hyperparameter optimiza…