arXiv:2602.15852v2 Announce Type: replace-cross Abstract: Clinical natural language processing (NLP) models have shown promise for supporting hospital discharge planning by leveraging narrative clinical documentation. However, note-based models are particularly vulnerable to temporal and lexical leakage, where documentation artifacts encode future…
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…
arXiv:2602.16979v1 Announce Type: cross Abstract: Despite the recent success of Multimodal Large Language Models (MLLMs), existing approaches predominantly assume the availability of multiple modalities during training and inference. In practice, multimodal data is often incomplete because modalities may be missing,…
arXiv:2602.16829v1 Announce Type: new Abstract: When feedback is absorbed faster than task structure can be evaluated, the learner will favor feedback over truth. A two-timescale model shows this feedback-truth gap is inevitable whenever the two rates differ and vanishes only…
arXiv:2602.17211v1 Announce Type: cross Abstract: Generating samples from limited information is a fundamental problem across scientific domains. Classical maximum entropy methods provide principled uncertainty quantification from moment constraints but require sampling via MCMC or Langevin dynamics, which typically exhibit exponential…
arXiv:2602.16833v1 Announce Type: new Abstract: Exploration remains a key bottleneck for reinforcement learning (RL) post-training of large language models (LLMs), where sparse feedback and large action spaces can lead to premature collapse into repetitive behaviors. We propose Verbalized Action Masking…
By enabling two chips to authenticate each other using a shared fingerprint, this technique can improve privacy and energy efficiency.
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…
arXiv:2512.19941v5 Announce Type: replace-cross Abstract: As Vision Transformers (ViTs) become standard vision backbones, a mechanistic account of their computational phenomenology is essential. Despite architectural cues that hint at dynamical structure, there is no settled framework that interprets Transformer depth as…
arXiv:2510.14974v3 Announce Type: replace Abstract: Few-step diffusion or flow-based generative models typically distill a velocity-predicting teacher into a student that predicts a shortcut towards denoised data. This format mismatch has led to complex distillation procedures that often suffer from a…
