Search Results for author:
Found 23 papers, 7 papers with code
What Algorithms can Transformers Learn? A Study in Length Generalization
Large language models exhibit surprising emergent generalization properties, yet also struggle on many simple reasoning tasks such as arithmetic and parity.
Matryoshka Diffusion Models
Diffusion models are the de facto approach for generating high-quality images and videos, but learning high-dimensional models remains a formidable task due to computational and optimization challenges.
Adaptivity and Modularity for Efficient Generalization Over Task Complexity
We investigate how the use of a mechanism for adaptive and modular computation in transformers facilitates the learning of tasks that demand generalization over the number of sequential computation steps (i. e., the depth of the computation graph).
Generative Modeling with Phase Stochastic Bridges
In this work, we introduce a novel generative modeling framework grounded in \textbf{phase space dynamics}, where a phase space is defined as {an augmented space encompassing both position and velocity.}
Boolformer: Symbolic Regression of Logic Functions with Transformers
In this work, we introduce Boolformer, the first Transformer architecture trained to perform end-to-end symbolic regression of Boolean functions.
Construction of Paired Knowledge Graph-Text Datasets Informed by Cyclic Evaluation
Guided by these observations, we construct a new, improved dataset called LAGRANGE using heuristics meant to improve equivalence between KG and text and show the impact of each of the heuristics on cyclic evaluation.
Value function estimation using conditional diffusion models for control
A fairly reliable trend in deep reinforcement learning is that the performance scales with the number of parameters, provided a complimentary scaling in amount of training data.
BOOT: Data-free Distillation of Denoising Diffusion Models with Bootstrapping
Diffusion models have demonstrated excellent potential for generating diverse images.
Control3Diff: Learning Controllable 3D Diffusion Models from Single-view Images
To address these challenges, We present Control3Diff, a 3D diffusion model that combines the strengths of diffusion models and 3D GANs for versatile, controllable 3D-aware image synthesis for single-view datasets.
Stabilizing Transformer Training by Preventing Attention Entropy Collapse
We show that $\sigma$Reparam provides stability and robustness with respect to the choice of hyperparameters, going so far as enabling training (a) a Vision Transformer {to competitive performance} without warmup, weight decay, layer normalization or adaptive optimizers; (b) deep architectures in machine translation and (c) speech recognition to competitive performance without warmup and adaptive optimizers.
MAST: Masked Augmentation Subspace Training for Generalizable Self-Supervised Priors
We do so by Masked Augmentation Subspace Training (or MAST) to encode in the single feature space the priors from different data augmentations in a factorized way.
NerfDiff: Single-image View Synthesis with NeRF-guided Distillation from 3D-aware Diffusion
Novel view synthesis from a single image requires inferring occluded regions of objects and scenes whilst simultaneously maintaining semantic and physical consistency with the input.
f-DM: A Multi-stage Diffusion Model via Progressive Signal Transformation
In this work, we propose f-DM, a generalized family of DMs which allows progressive signal transformation.
GAUDI: A Neural Architect for Immersive 3D Scene Generation
We introduce GAUDI, a generative model capable of capturing the distribution of complex and realistic 3D scenes that can be rendered immersively from a moving camera.
Ranked #1 on
Image Generation
on ARKitScenes
Efficient Representation Learning via Adaptive Context Pooling
Inspired by the success of ConvNets that are combined with pooling to capture long-range dependencies, we learn to pool neighboring features for each token before computing attention in a given attention layer.
Learning Representation from Neural Fisher Kernel with Low-rank Approximation
We show that the low-rank approximation of NFKs derived from unsupervised generative models and supervised learning models gives rise to high-quality compact representations of data, achieving competitive results on a variety of machine learning tasks.
Robust Robotic Control from Pixels using Contrastive Recurrent State-Space Models
Modeling the world can benefit robot learning by providing a rich training signal for shaping an agent's latent state space.
Regularized Training of Nearest Neighbor Language Models
In particular, we find that the added L2 regularization seems to improve the performance for high-frequency words without deteriorating the performance for low frequency ones.
An Attention Free Transformer
We introduce Attention Free Transformer (AFT), an efficient variant of Transformers that eliminates the need for dot product self attention.
MetricOpt: Learning to Optimize Black-Box Evaluation Metrics
This leads to consistent improvements since the value function provides effective metric supervision during finetuning, and helps to correct the potential bias of loss-only supervision.
Equivariant Neural Rendering
We propose a framework for learning neural scene representations directly from images, without 3D supervision.
Addressing the Loss-Metric Mismatch with Adaptive Loss Alignment
In most machine learning training paradigms a fixed, often handcrafted, loss function is assumed to be a good proxy for an underlying evaluation metric.
Learning from Simulated and Unsupervised Images through Adversarial Training
With recent progress in graphics, it has become more tractable to train models on synthetic images, potentially avoiding the need for expensive annotations.
Ranked #3 on
Image-to-Image Translation
on Cityscapes Labels-to-Photo
(Per-class Accuracy metric)
