From the 1 of 11 linked papers with an AI index.
11 papers
Flow Map Learning via Nongradient Vector Flow
Mark Goldstein, Anshuk Uppal, Raghav Singhal +2
The paper proposes SGFlow, a method that learns flow maps for diffusion and flow‑based generative models without requiring model invertibility or backpropagation through repeated m…
Controllably Efficient Language Models
Jatin Prakash, Aahlad Puli, Rajesh Ranganath
The substantial inference costs of attention in transformers motivated the development of efficient sequence mixers: namely sparse and sliding window attention, convolutions and li…
To Use or not to Use Muon: How Simplicity Bias in Optimizers Matters
Sara DragutinoviÄ, Yedi Zhang, Rajesh Ranganath
While Adam has long been the ubiquitous default optimizer for deep neural networks, Muon has recently seen rapid adoption due to its superior training speed. Although much of the l…
What LLMs explain is not what they believe: Evaluating explanation sufficiency under models' own input beliefs
Nhi Nguyen, Shauli Ravfogel, Rajesh Ranganath
Large language models (LLMs) are increasingly deployed in high-stakes domains, where free-text explanations such as chain-of-thought and post-hoc rationales are used to justify mod…
Estimating Tail Risks in Language Model Output Distributions
Rico Angell, Raghav Singhal, Zachary Horvitz +4
Language models are increasingly capable and are being rapidly deployed on a population-level scale. As a result, the safety of these models is increasingly high-stakes. Fortunatel…
KL-Regularized Reinforcement Learning is Designed to Mode Collapse
Anthony GX-Chen, Jatin Prakash, Jeff Guo +2
It is commonly believed that optimizing the reverse KL divergence results in "mode seeking", while optimizing forward KL results in "mass covering", with the latter being preferred…