Related papers: Cross-functional Analysis of Generalisation in Beh…

Vision-Language-Action (VLA) models demonstrate promising generalization in robotic manipulation, driven by advances in large-scale vision and language pre-training. This progress can be misleading. Despite the zero-shot perception and…

Recent advances in vision-language pre-training (VLP) have demonstrated impressive performance in a range of vision-language (VL) tasks. However, there exist several challenges for measuring the community's progress in building general…

Cross-task generalization is a significant outcome that defines mastery in natural language understanding. Humans show a remarkable aptitude for this, and can solve many different types of tasks, given definitions in the form of textual…

Reinforcement learning (RL) has demonstrated its capability in solving various tasks but is notorious for its low sample efficiency. In this paper, we propose RLingua, a framework that can leverage the internal knowledge of large language…

This paper presents a novel holistic deep learning framework that simultaneously addresses the challenges of vulnerability to input perturbations, overparametrization, and performance instability from different train-validation splits. The…

In-context learning (ICL) is a central capability of Transformer models, but the structures in data that enable its emergence and govern its robustness remain poorly understood. In this work, we study how the structure of pretraining tasks…

Using prompted language models as classifiers enables classification in domains with limited training data, but misses some of the robustness and performance benefits that fine-tuning can bring. We study whether training on multiple…

Bayesian Reinforcement Learning (BRL), a subclass of Meta-Reinforcement Learning (Meta-RL), provides a principled framework for generalisation by explicitly incorporating Bayesian task parameters into transition and reward models. However,…

Natural Language Understanding (NLU) is a basic task in Natural Language Processing (NLP). The evaluation of NLU capabilities has become a trending research topic that attracts researchers in the last few years, resulting in the development…

Evaluation in NLP is usually done by comparing the scores of competing systems independently averaged over a common set of test instances. In this work, we question the use of averages for aggregating evaluation scores into a final number…

Most recent CNN architectures use average pooling as a final feature encoding step. In the field of fine-grained recognition, however, recent global representations like bilinear pooling offer improved performance. In this paper, we…

The large capacity of neural networks enables them to learn complex functions. To avoid overfitting, networks however require a lot of training data that can be expensive and time-consuming to collect. A common practical approach to…

Batch Normalization (BN) improves both convergence and generalization in training neural networks. This work understands these phenomena theoretically. We analyze BN by using a basic block of neural networks, consisting of a kernel layer, a…

The compositional generalization abilities of neural models have been sought after for human-like linguistic competence. The popular method to evaluate such abilities is to assess the models' input-output behavior. However, that does not…

Large language models (LLMs) are trained and tested extensively on symbolic representations such as code and graphs, yet real-world user tasks are often specified in natural language. To what extent can LLMs generalize across these…

Reinforcement learning (RL)-based post-training often improves the reasoning performance of large language models (LLMs) beyond the training domain, while supervised fine-tuning (SFT) frequently leads to general capabilities forgetting.…

Human daily behavior unfolds as complex sequences shaped by intentions, preferences, and context. Effectively modeling these behaviors is crucial for intelligent systems such as personal assistants and recommendation engines. While recent…

Human linguistic capacity is often characterized by compositionality and the generalization it enables -- human learners can produce and comprehend novel complex expressions by composing known parts. Several benchmarks exploit…

Feature learning strength (FLS), i.e., the inverse of the effective output scaling of a model, plays a critical role in shaping the optimization dynamics of neural nets. While its impact has been extensively studied under the asymptotic…

Large Language Models (LLMs) display strikingly different generalization behaviors: supervised fine-tuning (SFT) often narrows capability, whereas reinforcement-learning (RL) tuning tends to preserve it. The reasons behind this divergence…