相关论文: The EOS Decision and Length Extrapolation

Transformer language models have demonstrated impressive generalization capabilities in natural language domains, yet we lack a fine-grained understanding of how such generalization arises. In this paper, we investigate length…

As breakthroughs in deep learning transform key industries, models are increasingly required to extrapolate on datapoints found outside the range of the training set, a challenge we coin as out-of-support (OoS) generalisation. However,…

Models such as Sequence-to-Sequence and Image-to-Sequence are widely used in real world applications. While the ability of these neural architectures to produce variable-length outputs makes them extremely effective for problems like…

Large language models (LLMs) have made significant advancements in addressing diverse natural language processing (NLP) tasks. However, their performance is often limited by inherent comprehension of problems. To address this limitation, we…

While Reinforcement Learning (RL) has advanced LLM reasoning, applying it to long-context scenarios is hindered by sparsity of outcome rewards. This limitation fails to penalize ungrounded "lucky guesses," leaving the critical process of…

Although generative models hold promise for discovering molecules with optimized desired properties, they often fail to suggest synthesizable molecules that improve upon the known molecules seen in training. We find that a key limitation is…

A recent paradigm views deep neural networks as discretizations of certain controlled ordinary differential equations, sometimes called neural ordinary differential equations. We make use of this perspective to link expressiveness of deep…

As model context lengths continue to grow, concerns about whether models effectively use the full context length have persisted. While several carefully designed long-context evaluations have recently been released, these evaluations tend…

Neural networks (NN) have been recently applied together with evolutionary algorithms (EAs) to solve dynamic optimization problems. The applied NN estimates the position of the next optimum based on the previous time best solutions. After…

Recent advances in language models (LMs) have led to significant improvements in quality on complex NLP tasks, but at the expense of increased inference costs. Cascading offers a simple strategy to achieve more favorable cost-quality…

Out-of-distribution (OOD) generalization is a favorable yet challenging property for deep neural networks. The core challenges lie in the limited availability of source domains that help models learn an invariant representation from the…

Previous works on human motion prediction follow the pattern of building a mapping relation between the sequence observed and the one to be predicted. However, due to the inherent complexity of multivariate time series data, it still…

Large language models (LLMs) are increasingly optimized for long reasoning, under the assumption that more reasoning leads to better performance. However, emerging evidence suggests that longer responses can sometimes degrade accuracy…

We study the problem of extrapolative controlled generation, i.e., generating sequences with attribute values beyond the range seen in training. This task is of significant importance in automated design, especially drug discovery, where…

There has been a long history of works showing that neural networks have hard time extrapolating beyond the training set. A recent study by Balestriero et al. (2021) challenges this view: defining interpolation as the state of belonging to…

The increased computerization in recent years has resulted in the production of a variety of different software, however measures need to be taken to ensure that the produced software isn't defective. Many researchers have worked in this…

Data-driven models are central to scientific discovery. In efforts to achieve state-of-the-art model accuracy, researchers are employing increasingly complex machine learning algorithms that often outperform simple regressions in…

Large language models are increasingly trained via reinforcement learning for personalized recommendation tasks, but standard methods like GRPO rely on sparse, sequence-level rewards. These obscure which tokens actually contribute to…

We discuss deep learning inference for the neutron star equation of state (EoS) using the real observational data of the mass and the radius. We make a quantitative comparison between the conventional polynomial regression and the neural…

Early-Exit Large Language Models (EE-LLMs) enable high throughput inference by allowing tokens to exit early at intermediate layers. However, their throughput is limited by the computational and memory savings. Existing EE-LLM frameworks…