arXiv:2510.26200v1 Announce Type: cross Abstract: While diffusion language models (DLMs) enable fine-grained refinement, their practical controllability remains fragile. We identify and formally characterize a central failure mode called update forgetting, in which uniform and context agnostic updates induce token level fluctuations across timesteps, erasing earlier semantic edits and disrupting the cumulative refinement process, thereby degrading […]
MaskCaptioner: Learning to Jointly Segment and Caption Object Trajectories in Videos
arXiv:2510.14904v2 Announce Type: replace-cross Abstract: Dense Video Object Captioning (DVOC) is the task of jointly detecting, tracking, and captioning object trajectories in a video, requiring the ability to understand spatio-temporal details and describe them in natural language. Due to the complexity of the task and the high cost associated with manual annotation, previous approaches resort […]
Distributional Multi-objective Black-box Optimization for Diffusion-model Inference-time Multi-Target Generation
arXiv:2510.26278v1 Announce Type: cross Abstract: Diffusion models have been successful in learning complex data distributions. This capability has driven their application to high-dimensional multi-objective black-box optimization problem. Existing approaches often employ an external optimization loop, such as an evolutionary algorithm, to the diffusion model. However, these approaches treat the diffusion model as a black-box refiner, […]
Approximating Human Preferences Using a Multi-Judge Learned System
arXiv:2510.25884v1 Announce Type: new Abstract: Aligning LLM-based judges with human preferences is a significant challenge, as they are difficult to calibrate and often suffer from rubric sensitivity, bias, and instability. Overcoming this challenge advances key applications, such as creating reliable reward models for Reinforcement Learning from Human Feedback (RLHF) and building effective routing systems that […]
Linear Causal Discovery with Interventional Constraints
arXiv:2510.26342v1 Announce Type: cross Abstract: Incorporating causal knowledge and mechanisms is essential for refining causal models and improving downstream tasks such as designing new treatments. In this paper, we introduce a novel concept in causal discovery, termed interventional constraints, which differs fundamentally from interventional data. While interventional data require direct perturbations of variables, interventional constraints […]
Evaluating the effectiveness of Stochastic CTMC and deterministic models in correlating rabies persistence in human and dog populations
arXiv:2510.25777v1 Announce Type: new Abstract: Rabies continues to pose a significant zoonotic threat, particularly in areas with high populations of domestic dogs that serve as viral reservoirs. This study conducts a comparative analysis of Stochastic Continuous-Time Markov Chain (CTMC) and deterministic models to gain insights into rabies persistence within human and canine populations. By employing […]
SSCL-BW: Sample-Specific Clean-Label Backdoor Watermarking for Dataset Ownership Verification
arXiv:2510.26420v1 Announce Type: cross Abstract: The rapid advancement of deep neural networks (DNNs) heavily relies on large-scale, high-quality datasets. However, unauthorized commercial use of these datasets severely violates the intellectual property rights of dataset owners. Existing backdoor-based dataset ownership verification methods suffer from inherent limitations: poison-label watermarks are easily detectable due to label inconsistencies, while […]
SciTrust 2.0: A Comprehensive Framework for Evaluating Trustworthiness of Large Language Models in Scientific Applications
arXiv:2510.25908v1 Announce Type: new Abstract: Large language models (LLMs) have demonstrated transformative potential in scientific research, yet their deployment in high-stakes contexts raises significant trustworthiness concerns. Here, we introduce SciTrust 2.0, a comprehensive framework for evaluating LLM trustworthiness in scientific applications across four dimensions: truthfulness, adversarial robustness, scientific safety, and scientific ethics. Our framework incorporates […]
Evaluating the Impact of LLM-Assisted Annotation in a Perspectivized Setting: the Case of FrameNet Annotation
arXiv:2510.25904v1 Announce Type: cross Abstract: The use of LLM-based applications as a means to accelerate and/or substitute human labor in the creation of language resources and dataset is a reality. Nonetheless, despite the potential of such tools for linguistic research, comprehensive evaluation of their performance and impact on the creation of annotated datasets, especially under […]
The End of Manual Decoding: Towards Truly End-to-End Language Models
arXiv:2510.26697v1 Announce Type: cross Abstract: The “end-to-end” label for LLMs is a misnomer. In practice, they depend on a non-differentiable decoding process that requires laborious, hand-tuning of hyperparameters like temperature and top-p. This paper introduces AutoDeco, a novel architecture that enables truly “end-to-end” generation by learning to control its own decoding strategy. We augment the […]