arXiv:2510.17795v1 Announce Type: cross Abstract: Replicating AI research is a crucial yet challenging task for large language model (LLM) agents. Existing approaches often struggle to generate executable code, primarily due to insufficient background knowledge and the limitations of retrieval-augmented generation…
arXiv:2510.15990v1 Announce Type: new Abstract: Reinforcement Learning with Verifiable Rewards (RLVR), primarily driven by the Group Relative Policy Optimization (GRPO) algorithm, is a leading approach for enhancing the reasoning abilities of Large Language Models (LLMs). Despite its wide adoption, GRPO’s…
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:2502.01272v2 Announce Type: replace Abstract: Graph Neural Networks (GNNs) have achieved notable success in tasks such as social and transportation networks. However, recent studies have highlighted the vulnerability of GNNs to backdoor attacks, raising significant concerns about their reliability in…
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.…
