arXiv:2407.20999v4 Announce Type: replace Abstract: Large language models (LLMs) have demonstrated remarkable capabilities across a wide range of tasks. Typically, LLMs are first pre-trained on large corpora and subsequently fine-tuned on task-specific datasets. However, during fine-tuning, LLMs may forget some…
arXiv:2510.15992v1 Announce Type: new Abstract: The growing industrial demand for customized and cost-efficient large language models (LLMs) is fueled by the rise of vertical, domain-specific tasks and the need to optimize performance under constraints such as latency and budget. Knowledge…
arXiv:2505.23135v2 Announce Type: replace Abstract: Large language models (LLMs) are increasingly integrated in software development, but ensuring correctness in LLM-generated code remains challenging and often requires costly manual review. Verifiable code generation — jointly generating code, specifications, and proofs of…
arXiv:2509.01042v2 Announce Type: replace Abstract: Synthesis procedures play a critical role in materials research, as they directly affect material properties. With data-driven approaches increasingly accelerating materials discovery, there is growing interest in extracting synthesis procedures from scientific literature as structured…
arXiv:2310.06328v4 Announce Type: replace Abstract: Wi-Fi sensing systems are severely hindered by cross domain problem when deployed in unseen real-world environments. Existing methods typically design separate frameworks for either domain adaptation or domain generalization, often relying on extensive labeled data.…
arXiv:2502.18300v4 Announce Type: replace Abstract: Bayesian methods have shown success in deep learning applications. For example, in predictive tasks, Bayesian neural networks leverage Bayesian reasoning of model uncertainty to improve the reliability and uncertainty awareness of deep neural networks. In…
arXiv:2510.16983v1 Announce Type: cross Abstract: Diffusion and flow models achieve high generative quality but remain computationally expensive due to slow multi-step sampling. Distillation methods accelerate them by training fast student generators, yet most existing objectives lack a unified theoretical foundation.…
arXiv:2510.17512v1 Announce Type: cross Abstract: Prevailing practice in learning-based audio watermarking is to pursue robustness by expanding the set of simulated distortions during training. However, such surrogates are narrow and prone to overfitting. This paper presents AWARE (Audio Watermarking with…
arXiv:2510.15955v1 Announce Type: new Abstract: Most realistic task automation problems require large language models (LLMs) to call tools, which often return complex JSON responses. These responses must be further processed to derive the information necessary for task completion. The ability…
arXiv:2506.20048v2 Announce Type: replace-cross Abstract: In reinforcement learning, distributional off-policy evaluation (OPE) focuses on estimating the return distribution of a target policy using offline data collected under a different policy. This work focuses on extending the widely used fitted Q-evaluation…
