Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2606. 27793v1 Announce Type: cross Abstract: Long-context language models suffer from position bias, where information in middle positions is underutilized.
arXiv:2606. 27685v1 Announce Type: cross Abstract: Pervasive data contamination -- stemming from measurement errors, outliers, or adversarial corruption -- has motivated the development of robust statistical methods.
arXiv:2606. 27939v1 Announce Type: cross Abstract: Protein language models are standard priors for biological sequence generation, but steering them toward explicit distributional design targets remains largely unexplored.
arXiv:2606. 27440v1 Announce Type: new Abstract: Foundation models for structural biology have achieved remarkable performance in predicting biomolecular structure and show promise for the design of proteins and small molecules.
arXiv:2606. 27580v1 Announce Type: cross Abstract: Reinforcement learning from human feedback (RLHF) in production does not always have a synchronous reward signal.
arXiv:2605. 29729v2 Announce Type: replace Abstract: We introduce scheming honeypot evaluations, a framework for testing whether models will pursue instrumental goals if given the opportunity.
arXiv:2606. 27818v1 Announce Type: cross Abstract: We present MMD-Reg, a novel correspondence-free approach to point-cloud registration that is differentiable and has linear computational complexity in the number of points.
arXiv:2606. 27608v1 Announce Type: cross Abstract: We present Qwen-Image-2.
arXiv:2606. 28215v1 Announce Type: cross Abstract: Extracting dynamic 4D object interactions from massive, in-the-wild monocular videos offers a highly efficient data collection pathway for scaling Embodied AI and training VLAs.
arXiv:2606. 28179v1 Announce Type: cross Abstract: Identifying robust associations between cardiac imaging phenotypes and clinical diseases is fundamental to population-scale cardiovascular research and reliable risk stratification.
arXiv:2606. 28122v1 Announce Type: cross Abstract: Neural operators provide deep neural networks for learning mappings between function spaces.
arXiv:2606. 28128v1 Announce Type: cross Abstract: Video generation models have emerged as a promising paradigm for embodied world simulation.
arXiv:2606. 28083v1 Announce Type: cross Abstract: Micro-expression recognition is challenging due to subtle and short-lived facial muscle movements.
arXiv:2606. 27766v1 Announce Type: cross Abstract: Offline reinforcement learning enables policy learning from fixed datasets without additional environment interaction, making it appealing for safety-critical applications where online exploration is costly or unsafe.
arXiv:2606. 27567v1 Announce Type: cross Abstract: Prompt injection is the top security risk for LLM-integrated applications, yet every defense proposed so far has been broken.
arXiv:2606. 27577v1 Announce Type: cross Abstract: This paper formulates frame-level freeway risk assessment as a multi-agent scene graph-level binary classification problem, where each video or trajectory frame is labeled risky if any TTC- or PET-based conflict violates a specified severity threshold.
arXiv:2606. 27381v1 Announce Type: cross Abstract: Queue overflow, a severe consequence of urban traffic congestion, occurs when vehicle queues exceed intersection capacity, obstructing upstream traffic and triggering cascading gridlocks.
arXiv:2606. 28270v1 Announce Type: new Abstract: The transition from static chat bots to autonomous agents--equipped with persistent memory, tool-use protocols, and multi-agent collaboration--has fundamentally expanded the AI threat landscape.
arXiv:2606. 27771v1 Announce Type: new Abstract: Reinforcement learning (RL) post-training improves the reward alignment of flow-based generators, but often degrades perceptual quality in ways that are not captured by the reward proxy.
arXiv:2606. 27731v1 Announce Type: cross Abstract: Despite their strong general capabilities, large language models (LLMs) often remain unreliable when outputs must be numerically precise.