arXiv:2605.12022v1 Announce Type: new
Abstract: Large Language Models (LLMs) achieve strong performance on standard knowledge evaluation benchmarks, yet recent work shows that their knowledge capabilities remain brittle under question variants that te…
arXiv:2605.11010v1 Announce Type: new
Abstract: Federated Learning has emerged as a transformative paradigm for collaborative machine learning across distributed environments. However, its performance is strongly influenced by the aggregation strategy…
arXiv:2605.11014v1 Announce Type: new
Abstract: Fair comparison between diffusion-based OOD detectors is challenging, as conclusions can vary with backbone choice, corruption parameterization, and test-time budget. We address this issue through a Mutu…
arXiv:2510.03206v2 Announce Type: replace-cross
Abstract: Diffusion language models, especially masked discrete diffusion models, have achieved great success recently. While there are some theoretical and primary empirical results showing the advantag…
arXiv:2605.12484v1 Announce Type: new
Abstract: Large language models (LLMs) are trained for downstream tasks by updating their parameters (e.g., via RL). However, updating parameters forces them to absorb task-specific information, which can result i…
arXiv:2605.11506v1 Announce Type: new
Abstract: Score-based diffusion models achieve state-of-the-art performance for inverse problems, but their practical deployment is hindered by long inference times and cumbersome hyperparameter tuning. While pret…
arXiv:2605.11508v1 Announce Type: new
Abstract: Currently, there is a gap in the field of ultra-high-definition (UHD) video dehazing due to the lack of a benchmark for evaluation. Furthermore, existing video dehazing methods cannot run on consumer-gra…
arXiv:2605.02798v1 Announce Type: cross
Abstract: We present an experimental study of energy-to-solution (ETS) of hybrid quantum-classical applications, enabled by direct instrumentation of power consumption of a Forte Enterprise trapped-ion quantum p…
arXiv:2605.05945v2 Announce Type: replace-cross
Abstract: The recent advancement of Vision Language Action (VLA) models has driven a critical demand for large scale egocentric datasets. However, existing datasets are often limited by short episode dur…
arXiv:2605.12128v1 Announce Type: new
Abstract: Large language models are increasingly deployed in safety-critical applications, where their ability to resist harmful instructions is essential. Although post-training aims to make models robust against…