Archives AI News

On the Existence and Behavior of Secondary Attention Sinks

arXiv:2512.22213v2 Announce Type: replace Abstract: Attention sinks are tokens, often the beginning-of-sequence (BOS) token, that receive disproportionately high attention despite limited semantic relevance. In this work, we identify a class of attention sinks, which we term secondary sinks, that differ…

Efficient Tail-Aware Generative Optimization via Flow Model Fine-Tuning

arXiv:2602.16796v1 Announce Type: new Abstract: Fine-tuning pre-trained diffusion and flow models to optimize downstream utilities is central to real-world deployment. Existing entropy-regularized methods primarily maximize expected reward, providing no mechanism to shape tail behavior. However, tail control is often essential:…

Goal Inference from Open-Ended Dialog

arXiv:2410.13957v2 Announce Type: replace-cross Abstract: Embodied AI Agents are quickly becoming important and common tools in society. These embodied agents should be able to learn about and accomplish a wide range of user goals and preferences efficiently and robustly. Large…

TopoFlow: Physics-guided Neural Networks for high-resolution air quality prediction

arXiv:2602.16821v1 Announce Type: new Abstract: We propose TopoFlow (Topography-aware pollutant Flow learning), a physics-guided neural network for efficient, high-resolution air quality prediction. To explicitly embed physical processes into the learning framework, we identify two critical factors governing pollutant dynamics: topography…

Bongard-RWR+: Real-World Representations of Fine-Grained Concepts in Bongard Problems

arXiv:2508.12026v2 Announce Type: replace-cross Abstract: Bongard Problems (BPs) provide a challenging testbed for abstract visual reasoning (AVR), requiring models to identify visual concepts fromjust a few examples and describe them in natural language. Early BP benchmarks featured synthetic black-and-white drawings,…

HiVAE: Hierarchical Latent Variables for Scalable Theory of Mind

arXiv:2602.16826v1 Announce Type: new Abstract: Theory of mind (ToM) enables AI systems to infer agents’ hidden goals and mental states, but existing approaches focus mainly on small human understandable gridworld spaces. We introduce HiVAE, a hierarchical variational architecture that scales…

A Unifying Framework for Robust and Efficient Inference with Unstructured Data

arXiv:2505.00282v3 Announce Type: replace-cross Abstract: To analyze unstructured data (text, images, audio, video), economists typically first extract low-dimensional structured features with a neural network. Neural networks do not make generically unbiased predictions, and biases will propagate to estimators that use…