Related papers: Revisiting Weak-to-Strong Generalization in Theory…

The forward Kullback-Leibler (KL) divergence is a ubiquitous objective for fitting a parameterized distribution to samples due to its tractability and equivalence to maximum likelihood estimation (MLE). Its inherent asymmetry, however, may…

As post-training optimization becomes central to improving large language models, we observe a persistent saturation bottleneck: once models grow highly confident, further training yields diminishing returns. While existing methods continue…

Human guidance in reinforcement learning (RL) is often impractical for large-scale applications due to high costs and time constraints. Large Language Models (LLMs) offer a promising alternative to mitigate RL sample inefficiency and…

Finetuning large language models on narrowly harmful datasets can cause them to become emergently misaligned, giving stereotypically `evil' responses across diverse unrelated settings. Concerningly, a pre-registered survey of experts failed…

Vision-language (VL) models often exhibit a limited understanding of complex expressions of visual objects (e.g., attributes, shapes, and their relations), given complex and diverse language queries. Traditional approaches attempt to…

Reinforcement Learning with Verifiable Rewards (RLVR) is a central paradigm for turning large language models (LLMs) into reliable problem solvers, especially in logic-heavy domains. Despite its empirical success, it remains unclear whether…

Weakly-supervised learning is a paradigm for alleviating the scarcity of labeled data by leveraging lower-quality but larger-scale supervision signals. While existing work mainly focuses on utilizing a certain type of weak supervision, we…

This paper proposes a novel framework to reinforce classification models using language-guided generated counterfactual images. Deep learning classification models are often trained using datasets that mirror real-world scenarios. In this…

The past two decades have witnessed the great success of the algorithmic modeling framework advocated by Breiman et al. (2001). Nevertheless, the excellent prediction performance of these black-box models rely heavily on the availability of…

Large language models (LLMs) are vulnerable to jailbreak attacks - resulting in harmful, unethical, or biased text generations. However, existing jailbreaking methods are computationally costly. In this paper, we propose the weak-to-strong…

There is no such thing as a perfect dataset. In some datasets, deep neural networks discover underlying heuristics that allow them to take shortcuts in the learning process, resulting in poor generalization capability. Instead of using…

How can we train models to perform well on hard test data when hard training data is by definition difficult to label correctly? This question has been termed the scalable oversight problem and has drawn increasing attention as language…

Reinforcement Learning with Verifiable Rewards (RLVR) has become a central approach for improving the reasoning ability of large language models. Recent work studies RLVR through token entropy, arguing that high-entropy tokens drive…

Large Language Models (LLMs) are typically trained to predict in the forward direction of time. However, recent works have shown that prompting these models to look back and critique their own generations can produce useful feedback.…

Reinforcement learning with verifiable rewards (RLVR) has demonstrated superior performance in enhancing the reasoning capability of large language models (LLMs). However, this accuracy-oriented learning paradigm often suffers from entropy…

The fact that deep neural networks are susceptible to crafted perturbations severely impacts the use of deep learning in certain domains of application. Among many developed defense models against such attacks, adversarial training emerges…

Reinforcement learning is used to align language models with human preference signals after first pre-training the model to predict the next token of text within a large corpus using likelihood maximization. Before being deployed in a…

Language models demonstrate remarkable abilities when pre-trained on large text corpora and fine-tuned for specific tasks, but how and why pre-training shapes the success of the final model remains poorly understood. Notably, although…

Classifier-guided diffusion models generate conditional samples by augmenting the reverse-time score with the gradient of the log-probability predicted by a probabilistic classifier. In practice, this classifier is usually obtained by…

Value functions are a central component of deep reinforcement learning (RL). These functions, parameterized by neural networks, are trained using a mean squared error regression objective to match bootstrapped target values. However,…