27 citations · 29 across the 9 of their papers we have counts for
10 papers
Pretraining Recurrent Networks without Recurrence
Akarsh Kumar, Phillip Isola
Training recurrent neural networks (RNNs) requires assigning credit across long sequences of computations. Standard backpropagation through time (BPTT) addresses this problem poorl…
The Truth Lies Somewhere in the Middle (of the Generated Tokens)
Sophie L. Wang, Phillip Isola, Brian Cheung
How should hidden states generated autoregressively be collapsed into a representation that reflects a language model's internal state? Despite tokens being generated under causal…
End-to-End Training for Unified Tokenization and Latent Denoising
Shivam Duggal, Xingjian Bai, Zongze Wu +5
Latent diffusion models (LDMs) enable high-fidelity synthesis by operating in learned latent spaces. However, training state-of-the-art LDMs requires complex staging: a tokenizer m…
Neural Thickets: Diverse Task Experts Are Dense Around Pretrained Weights
Yulu Gan, Phillip Isola
Pretraining produces a learned parameter vector that is typically treated as a starting point for further iterative adaptation. In this work, we instead view the outcome of pretrai…
Words That Make Language Models Perceive
Sophie L. Wang, Phillip Isola, Brian Cheung
Large language models (LLMs) trained purely on text ostensibly lack any direct perceptual experience, yet their internal representations are implicitly shaped by multimodal regular…
Training Transformers with Enforced Lipschitz Constants
Laker Newhouse, R. Preston Hess, Franz Cesista +3
Neural networks are often highly sensitive to input and weight perturbations. This sensitivity has been linked to pathologies such as vulnerability to adversarial examples, diverge…
Cycle Consistency as Reward: Learning Image-Text Alignment without Human Preferences
Hyojin Bahng, Caroline Chan, Fredo Durand +1
Measuring alignment between language and vision is a fundamental challenge, especially as multimodal data becomes increasingly detailed and complex. Existing methods often rely on…
Scalable Optimization in the Modular Norm
Tim Large, Yang Liu, Minyoung Huh +3
To improve performance in contemporary deep learning, one is interested in scaling up the neural network in terms of both the number and the size of the layers. When ramping up the…
The Platonic Representation Hypothesis
Minyoung Huh, Brian Cheung, Tongzhou Wang +1
We argue that representations in AI models, particularly deep networks, are converging. First, we survey many examples of convergence in the literature: over time and across multip…
Training Neural Networks from Scratch with Parallel Low-Rank Adapters
Minyoung Huh, Brian Cheung, Jeremy Bernstein +2
The scalability of deep learning models is fundamentally limited by computing resources, memory, and communication. Although methods like low-rank adaptation (LoRA) have reduced th…