arXiv:2604.05339v1 Announce Type: new
Abstract: As LLMs become increasingly integrated into human society, evaluating their orientations on human values from social science has drawn growing attention. Nevertheless, it is still unclear why human value…
arXiv:2604.02623v2 Announce Type: replace-cross
Abstract: Memory makes LLM-based web agents personalized, powerful, yet exploitable. By storing past interactions to personalize future tasks, agents inadvertently create a persistent attack surface that…
arXiv:2602.15195v3 Announce Type: replace-cross
Abstract: LoRA adapters let users fine-tune large language models (LLMs) efficiently. However, LoRA adapters are shared through open repositories like Hugging Face Hub \citep{huggingface_hub_docs}, makin…
arXiv:2509.17183v2 Announce Type: replace-cross
Abstract: Alignment plays a crucial role in Large Language Models (LLMs) in aligning with human preferences on a specific task/domain. Traditional alignment methods suffer from catastrophic forgetting, w…
arXiv:2604.05350v1 Announce Type: new
Abstract: Enterprise IT support interactions are fundamentally diagnostic: effective resolution requires iterative evidence gathering from ambiguous user reports to identify an underlying root cause. While retriev…
arXiv:2604.05230v1 Announce Type: cross
Abstract: Efficient and robust optimization is essential for neural networks, enabling scientific machine learning models to converge rapidly to very high accuracy — faithfully capturing complex physical behavi…
arXiv:2604.05477v1 Announce Type: new
Abstract: Autonomous GUI agents based on vision-language models (VLMs) often assume deterministic environment responses, generating actions without verifying whether previous operations succeeded. In real-world se…
arXiv:2604.05522v1 Announce Type: new
Abstract: Omni Large Language Models (Omni-LLMs) have demonstrated impressive capabilities in holistic multi-modal perception, yet they consistently falter in complex scenarios requiring synergistic omni-modal rea…
arXiv:2604.05546v1 Announce Type: new
Abstract: Large Vision-Language Models (LVLMs) enable sophisticated reasoning over images and videos, yet their inference is hindered by a systemic efficiency barrier known as visual token dominance. This overhead…
arXiv:2601.05905v2 Announce Type: replace-cross
Abstract: As Large Language Models (LLMs) are increasingly deployed in real-world settings, correctness alone is insufficient. Reliable deployment requires maintaining truthful beliefs under contextual p…