Quality follows upgrading
Academic
arXiv:2604.06422v1 Announce Type: new Abstract: Understanding when Vision-Language Models (VLMs) will behave unexpectedly, whether models can reliably predict their own behavior, and if models adhere …
arXiv:2604.06558v1 Announce Type: new Abstract: We present the first systematic study of when target context helps molecular property prediction, evaluating context conditioning across 10 diverse …
arXiv:2604.06228v1 Announce Type: new Abstract: We introduce probabilistic language tries (PLTs), a unified representation that makes explicit the prefix structure implicitly defined by any generative …
arXiv:2604.06265v1 Announce Type: new Abstract: Quantum-inspired tensor networks algorithms have shown to be effective and efficient models for machine learning tasks, including anomaly detection. Here, …
arXiv:2604.06502v1 Announce Type: new Abstract: Vision-Language Models (VLMs) face significant safety vulnerabilities from malicious prompt attacks due to weakened alignment during visual integration. Existing defenses …
arXiv:2604.06752v1 Announce Type: new Abstract: We present EmBolic - a novel fully hyperbolic deep learning architecture for fine-grained emotion analysis from textual messages. The underlying …
arXiv:2604.06260v1 Announce Type: new Abstract: Test-time scaling investigates whether a fixed diffusion language model (DLM) can generate better outputs when given more inference compute, without …
arXiv:2604.06395v1 Announce Type: new Abstract: Spiking reservoir computing provides an energy-efficient approach to temporal processing, but reliably tuning reservoirs to operate at the edge-of-chaos is …
arXiv:2604.06374v1 Announce Type: new Abstract: Latent reasoning via continuous chain-of-thoughts (Latent CoT) has emerged as a promising alternative to discrete CoT reasoning. Operating in continuous …
arXiv:2604.06256v1 Announce Type: new Abstract: Training dynamics during grokking concentrate along a small number of dominant update directions -- the spectral edge -- which reliably …
arXiv:2604.06647v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) systems are typically evaluated under static assumptions, despite being frequently corrected through user or expert feedback in …
arXiv:2604.06349v1 Announce Type: new Abstract: Generalizing from a single labeled source domain to unseen target domains, without access to any target data during training, remains …