Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
Reinforcement learning can align diffusion models with human preferences and task-specific objectives, but endpoint rewards do not specify how an intermediate denoising prediction should change. We in...
Credit risk models increasingly need to combine predictive accuracy with transparent explanations and auditable fairness constraints. Logistic regression remains attractive because its coefficients ar...
Imaging factor disentanglement in text-to-image generation aims to independently control image acquisition properties such as types of camera lenses, sensor types, viewpoints, and domains to enable co...
Machine learning models are widely used in financial fraud and credit-risk detection, yet their adversarial robustness remains difficult to evaluate because financial tabular data involve domain-speci...
Surgical instrument segmentation (SIS) is fundamental for computer-assisted surgery, where reliable instrument masks enable precise scene understanding and clinical assistance. Recently, adapting foun...
Uncertainty quantification (UQ) methods are widely used for hallucination detection in large language models (LLMs) in closed-book settings where ground-truth evidence is unavailable at inference time...
Mechanistic Localization bridges mechanistic interpretability and post-training optimization by isolating critical parameters via interpretative approaches and then guiding parameter-efficient Supervi...
End-to-end multimodal driving has progressed rapidly by fusing camera and LiDAR streams. Existing pipelines remain fragile under asymmetric sensor degradation, where either an entire modality or only...
Self-supervised pretraining enables transferable representations for medical imaging, yet most CT encoders remain biased toward coarse semantic understanding, limiting their sensitivity to fine-graine...
Safeguarding language model agents requires assessing complete execution trajectories under context-dependent safety policies. Existing policy-aware safeguards mainly rely on prompting or supervised f...
LLM-as-judge is essential for evaluating open-ended text and steering post-training, yet improving the judge itself typically relies on expensive annotations, reward models, or distillation from stron...
Aligning large language models to human preferences is crucial for real-world deployment but frequently incurs an alignment tax, leading to the catastrophic forgetting of pre-trained general capabilit...
The article discusses how watermarks function during moments of uncertainty in AI models, paralleling safety checks that identify mistakes. It examines the roles of hallucinations, watermarks, and removal techniques in ensuring model reliability. The piece also touches on the metaphor of a squeezed balloon to illustrate constraints on model output.
Industrial actor--critic methods usually represent continuous actions as anonymous numerical coordinates. They must therefore learn from limited interactions which process variables each action affect...
Universal multimodal embeddings are becoming a core component of modern AI systems, enabling heterogeneous content to be represented in a shared space for applications such as retrieval, recommendatio...
arXiv:2507.04356v3 Announce Type: replace-cross Abstract: Research, innovation and practical capital investment have been increasing rapidly toward the realization of autonomous physical agents. This...
arXiv:2608.23476v1 Announce Type: new Abstract: Narrow fine-tuning on small, domain-specific datasets can produce broad and surprising changes in model behavior-a phenomenon called weird generalizati...
arXiv:2608.22102v1 Announce Type: cross Abstract: We present GCA (Gaussian Constitutive Alignment), a framework for learning implicit constitutive laws from monocular dynamic video of deformable obje...
arXiv:2608.22917v1 Announce Type: new Abstract: We present TSWAP, a deployed eight-language conversational wellness advisor grounded, via retrieval-augmented generation, in a verified knowledge base...
arXiv:2608.21895v1 Announce Type: cross Abstract: Locally deployed Large Language Models (LLMs) via inference engines such as Ollama run without the moderation and abuse detection present in API-serv...