arXiv:2603.07084v2 Announce Type: replace Abstract: Reward hacking is a form of misalignment in which models overoptimize proxy rewards without genuinely solving the underlying task. Precisely measuring reward hacking occurrence remains challenging because true task rewards are often expensive or impossible…
arXiv:2502.19499v3 Announce Type: replace Abstract: Diffusion models have achieved remarkable progress in various domains with an intriguing ability to produce new data that do not exist in the training set. In this work, we study the hypothesis that such creativity…
arXiv:2509.18611v2 Announce Type: replace Abstract: Pretraining on large-scale collections of PDE-governed spatiotemporal trajectories has recently shown promise for building generalizable models of dynamical systems. Yet most existing PDE foundation models rely on deterministic Transformer architectures, which lack generative flexibility for…
arXiv:2604.15109v2 Announce Type: replace-cross Abstract: Despite the rapid advancement of Large Language Models (LLMs), uncertainty quantification in LLM generation is a persistent challenge. Although recent approaches have achieved strong performance by restricting LLMs to produce short or constrained answer sets,…
arXiv:2604.18319v1 Announce Type: cross Abstract: Selection bias arises when the probability that an observation enters a dataset depends on variables related to the quantities of interest, leading to systematic distortions in estimation and uncertainty quantification. For example, in epidemiological or…
arXiv:2604.16362v1 Announce Type: new Abstract: Data scarcity and weak supervision continue to limit the performance of machine learning models in many real-world applications, such as mammography, where Multiple Instance Learning (MIL) often offers the best formulation. While recent foundation models…
arXiv:2510.12831v3 Announce Type: replace-cross Abstract: Multi-turn Text-to-SQL aims to translate a user’s conversational utterances into executable SQL while preserving dialogue coherence and grounding to the target schema. However, most existing systems only regard this task as a simple text translation…
arXiv:2604.16335v1 Announce Type: new Abstract: Despite recent progress in Large Language Model (LLM) Agents for Software Engineering (SWE) tasks, end-to-end fine-tuning typically relies on verifiable terminal rewards such as whether all unit tests pass. While these binary signals reflect whether…
arXiv:2604.16358v1 Announce Type: new Abstract: MLLMs are increasingly deployed in multi-turn settings, where attackers can escalate unsafe intent through the evolving visual-text history and exploit long-context safety decay. Yet safety alignment is still dominated by single-turn data and fixed-template dialogues,…
arXiv:2604.16334v1 Announce Type: new Abstract: The use of Deep Neural Network based systems in the real world is growing. They have achieved state-of-the-art performance on many image, speech and text datasets. They have been shown to be powerful systems that…
