Now You See the Hate: Adaptive View Retrieval for Hidden Hateful Illusions
arXiv:2607.19061v2 Announce Type: replace-cross Abstract: Hateful optical illusions expose a serious gap in current multimodal safety systems. On original-view hateful…
SysAdmin: Measuring Instrumental Power-Seeking in Frontier AI
arXiv:2607.18239v1 Announce Type: new Abstract: Power-seeking defined as behaviors where AI systems acquire resources, evade oversight, or resist termination beyond…
Enhancing Rubric-based RL via Self-Distillation
arXiv:2607.18082v2 Announce Type: replace-cross Abstract: Rubric-based RL has recently shown promise in improving LLMs on open-ended tasks. A widely recognized…
SFGA: A Statistics-First Gating Architecture with Adjudicative Escalation for Trustworthy SFT Data Procurement
arXiv:2607.18960v1 Announce Type: cross Abstract: Procuring supervised fine-tuning (SFT) data forces a buyer to decide, before any downstream training, whether…
Dual Adversarial Fine-tuning for Enhancing Robustness of Large Vision Language Model
arXiv:2607.18958v1 Announce Type: cross Abstract: While Large Vision-Language Models (LVLMs), represented by LLaVA and GPT-4V, have demonstrated remarkable capabilities, their…
Alignment of a Total Automation Economy
arXiv:2607.17015v2 Announce Type: replace-cross Abstract: We consider economic theory from the perspective of a total automation economy, one with no…
Rater State Bias in RLHF Preference Data: An Audit Framework
arXiv:2607.16195v1 Announce Type: new Abstract: We identify a structured confound in Reinforcement Learning from Human Feedback (RLHF). Pairwise preference labels…
When Does Muon Help Agentic Reinforcement Learning?
arXiv:2607.16169v2 Announce Type: replace-cross Abstract: Muon is competitive with AdamW in large-scale pre-training, but its value for reinforcement-learning (RL) post-training…
Kernelized Linear Attention: Breaking the Capacity Wall with Symmetric Cones
arXiv:2607.17419v1 Announce Type: cross Abstract: Linear attention promises constant-time recurrent inference but degrades sharply on associative recall. We formulate attention…