arXiv:2606.28153v1 Announce Type: cross Abstract: Jailbreak attacks bypass LLM safety alignment, yet their mechanisms remain poorly understood. We provide evidence…
arXiv:2606.26102v2 Announce Type: replace-cross Abstract: Standard post-training pipelines apply supervised fine-tuning (SFT) and reinforcement learning (RL) to make language models…
arXiv:2606.28179v1 Announce Type: cross Abstract: Identifying robust associations between cardiac imaging phenotypes and clinical diseases is fundamental to population-scale cardiovascular…
arXiv:2606.27382v1 Announce Type: new Abstract: While the primary function of computers lies in computation and processing, the core value of…
arXiv:2606.26530v2 Announce Type: replace-cross Abstract: The Abstraction and Reasoning Corpus (ARC) contains tasks that require summarizing patterns from limited grid…
arXiv:2606.26933v1 Announce Type: cross Abstract: AI-assisted vulnerability discovery has proven effective for bug classes like memory safety, where instrumentation confirms…
arXiv:2606.26155v1 Announce Type: new Abstract: Interpreting and controlling model behaviors through activation steering methods requires many pairs of contrastive samples…
arXiv:2606.26535v1 Announce Type: cross Abstract: Current VLM evaluations often conflate language priors with genuine spatial reasoning. To address this, we…
