The pitfalls of next-token prediction

Can a mere next-token predictor faithfully model human intelligence? We crystallize this intuitive concern, which is fragmented in the literature. As a starting point, we argue that the two often-conflated phases of next-token prediction -- autoregressive inference and teacher-forced training -- must be treated distinctly. The popular criticism that errors can compound during autoregressive inference, crucially assumes that teacher-forcing has learned an accurate next-token predictor. This assumption sidesteps a more deep-rooted problem we expose: in certain classes of tasks, teacher-forcing can simply fail to learn an accurate next-token predictor in the first place. We describe a general mechanism of how teacher-forcing can fail, and design a minimal planning task where both the Transformer and the Mamba architecture empirically fail in that manner -- remarkably, despite the task being straightforward to learn. We provide preliminary evidence that this failure can be resolved when training to predict multiple tokens in advance. We hope this finding can ground future debates and inspire explorations beyond the next-token prediction paradigm. We make our code available under https://github.com/gregorbachmann/Next-Token-Failures

A Language Model's Guide Through Latent Space

Concept guidance has emerged as a cheap and simple way to control the behavior of language models by probing their hidden representations for concept vectors and using them to perturb activations at inference time. While the focus of previous work has largely been on truthfulness, in this paper we extend this framework to a richer set of concepts such as appropriateness, humor, creativity and quality, and explore to what degree current detection and guidance strategies work in these challenging settings. To facilitate evaluation, we develop a novel metric for concept guidance that takes into account both the success of concept elicitation as well as the potential degradation in fluency of the guided model. Our extensive experiments reveal that while some concepts such as truthfulness more easily allow for guidance with current techniques, novel concepts such as appropriateness or humor either remain difficult to elicit, need extensive tuning to work, or even experience confusion. Moreover, we find that probes with optimal detection accuracies do not necessarily make for the optimal guides, contradicting previous observations for truthfulness. Our work warrants a deeper investigation into the interplay between detectability, guidability, and the nature of the concept, and we hope that our rich experimental test-bed for guidance research inspires stronger follow-up approaches.

How Good is a Single Basin?

The multi-modal nature of neural loss landscapes is often considered to be the main driver behind the empirical success of deep ensembles. In this work, we probe this belief by constructing various "connected" ensembles which are restricted to lie in the same basin. Through our experiments, we demonstrate that increased connectivity indeed negatively impacts performance. However, when incorporating the knowledge from other basins implicitly through distillation, we show that the gap in performance can be mitigated by re-discovering (multi-basin) deep ensembles within a single basin. Thus, we conjecture that while the extra-basin knowledge is at least partially present in any given basin, it cannot be easily harnessed without learning it from other basins.

Disentangling Linear Mode-Connectivity

Linear mode-connectivity (LMC) (or lack thereof) is one of the intriguing characteristics of neural network loss landscapes. While empirically well established, it unfortunately still lacks a proper theoretical understanding. Even worse, although empirical data points are abound, a systematic study of when networks exhibit LMC is largely missing in the literature. In this work we aim to close this gap. We explore how LMC is affected by three factors: (1) architecture (sparsity, weight-sharing), (2) training strategy (optimization setup) as well as (3) the underlying dataset. We place particular emphasis on minimal but non-trivial settings, removing as much unnecessary complexity as possible. We believe that our insights can guide future theoretical works on uncovering the inner workings of LMC.

Navigating Scaling Laws: Accelerating Vision Transformer's Training via Adaptive Strategies

In recent years, the state-of-the-art in deep learning has been dominated by very large models that have been pre-trained on vast amounts of data. The paradigm is very simple: Investing more computational resources (optimally) leads to better performance, and even predictably so; neural scaling laws have been derived that accurately forecast the performance of a network for a desired level of compute. This leads to the notion of a "compute-optimal" model, i.e. a model that allocates a given level of compute during training optimally to maximise performance. In this work, we extend the concept of optimality by allowing for an "adaptive" model, i.e. a model that can change its shape during the course of training. By allowing the shape to adapt, we can optimally traverse between the underlying scaling laws, leading to a significant reduction in the required compute to reach a given target performance. We focus on vision tasks and the family of Vision Transformers, where the patch size as well as the width naturally serve as adaptive shape parameters. We demonstrate that, guided by scaling laws, we can design compute-optimal adaptive models that beat their "static" counterparts.

Scaling MLPs: A Tale of Inductive Bias

In this work we revisit the most fundamental building block in deep learning, the multi-layer perceptron (MLP), and study the limits of its performance on vision tasks. Empirical insights into MLPs are important for multiple reasons. (1) Given the recent narrative "less inductive bias is better", popularized due to transformers eclipsing convolutional models, it is natural to explore the limits of this hypothesis. To that end, MLPs offer an ideal test bed, being completely free of any inductive bias. (2) MLPs have almost exclusively been the main protagonist in the deep learning theory literature due to their mathematical simplicity, serving as a proxy to explain empirical phenomena observed for more complex architectures. Surprisingly, experimental datapoints for MLPs are very difficult to find in the literature, especially when coupled with large pre-training protocols. This discrepancy between practice and theory is worrying: Do MLPs reflect the empirical advances exhibited by practical models? Or do theorists need to rethink the role of MLPs as a proxy? We provide insights into both these aspects. We show that the performance of MLPs drastically improves with scale (93% on CIFAR10, 79% on CIFAR100, 69% on TinyImageNet), highlighting that lack of inductive bias can indeed be compensated. We observe that MLPs mimic the behaviour of their modern counterparts faithfully, with some components in the learning setting however surprisingly exhibiting stronger or unexpected behaviours. Due to their inherent computational efficiency, large pre-training experiments become more accessible for academic researchers. All of our experiments were run on a single GPU.

Multi-CLIP: Contrastive Vision-Language Pre-training for Question Answering tasks in 3D Scenes

Training models to apply common-sense linguistic knowledge and visual concepts from 2D images to 3D scene understanding is a promising direction that researchers have only recently started to explore. However, it still remains understudied whether 2D distilled knowledge can provide useful representations for downstream 3D vision-language tasks such as 3D question answering. In this paper, we propose a novel 3D pre-training Vision-Language method, namely Multi-CLIP, that enables a model to learn language-grounded and transferable 3D scene point cloud representations. We leverage the representational power of the CLIP model by maximizing the agreement between the encoded 3D scene features and the corresponding 2D multi-view image and text embeddings in the CLIP space via a contrastive objective. To validate our approach, we consider the challenging downstream tasks of 3D Visual Question Answering (3D-VQA) and 3D Situated Question Answering (3D-SQA). To this end, we develop novel multi-modal transformer-based architectures and we demonstrate how our pre-training method can benefit their performance. Quantitative and qualitative experimental results show that Multi-CLIP outperforms state-of-the-art works across the downstream tasks of 3D-VQA and 3D-SQA and leads to a well-structured 3D scene feature space.

CLIP-Guided Vision-Language Pre-training for Question Answering in 3D Scenes

Training models to apply linguistic knowledge and visual concepts from 2D images to 3D world understanding is a promising direction that researchers have only recently started to explore. In this work, we design a novel 3D pre-training Vision-Language method that helps a model learn semantically meaningful and transferable 3D scene point cloud representations. We inject the representational power of the popular CLIP model into our 3D encoder by aligning the encoded 3D scene features with the corresponding 2D image and text embeddings produced by CLIP. To assess our model's 3D world reasoning capability, we evaluate it on the downstream task of 3D Visual Question Answering. Experimental quantitative and qualitative results show that our pre-training method outperforms state-of-the-art works in this task and leads to an interpretable representation of 3D scene features.

Random Teachers are Good Teachers

In this work, we investigate the implicit regularization induced by teacher-student learning dynamics. To isolate its effect, we describe a simple experiment where instead of trained teachers, we consider teachers at random initialization. Surprisingly, when distilling a student into such a random teacher, we observe that the resulting model and its representations already possess very interesting characteristics; (1) we observe a strong improvement of the distilled student over its teacher in terms of probing accuracy. (2) The learnt representations are highly transferable between different tasks but deteriorate strongly if trained on random inputs. (3) The student checkpoint suffices to discover so-called lottery tickets, i.e. it contains identifiable, sparse networks that are as performant as the full network. These observations have interesting consequences for several important areas in machine learning: (1) Self-distillation can work solely based on the implicit regularization present in the gradient dynamics without relying on any \textit{dark knowledge}, (2) self-supervised learning can learn features even in the absence of data augmentation and (3) SGD already becomes stable when initialized from the student checkpoint with respect to batch orderings. Finally, we shed light on an intriguing local property of the loss landscape: the process of feature learning is strongly amplified if the student is initialized closely to the teacher. This raises interesting questions about the nature of the landscape that have remained unexplored so far.

The Curious Case of Benign Memorization

Despite the empirical advances of deep learning across a variety of learning tasks, our theoretical understanding of its success is still very restricted. One of the key challenges is the overparametrized nature of modern models, enabling complete overfitting of the data even if the labels are randomized, i.e. networks can completely memorize all given patterns. While such a memorization capacity seems worrisome, in this work we show that under training protocols that include data augmentation, neural networks learn to memorize entirely random labels in a benign way, i.e. they learn embeddings that lead to highly non-trivial performance under nearest neighbour probing. We demonstrate that deep models have the surprising ability to separate noise from signal by distributing the task of memorization and feature learning to different layers. As a result, only the very last layers are used for memorization, while preceding layers encode performant features which remain largely unaffected by the label noise. We explore the intricate role of the augmentations used for training and identify a memorization-generalization trade-off in terms of their diversity, marking a clear distinction to all previous works. Finally, we give a first explanation for the emergence of benign memorization by showing that malign memorization under data augmentation is infeasible due to the insufficient capacity of the model for the increased sample size. As a consequence, the network is forced to leverage the correlated nature of the augmentations and as a result learns meaningful features. To complete the picture, a better theory of feature learning in deep neural networks is required to fully understand the origins of this phenomenon.