arXiv:2607.15467v1 Announce Type: new Abstract: Knowledge distillation enables an adversary to replicate a proprietary classifier by querying its prediction interface and training a surrogate on the…
arXiv:2607.15457v1 Announce Type: new Abstract: We study robust peak-cost constrained reinforcement learning (RP-CRL), where the objective is to maximize expected reward while controlling the maximum cost…
arXiv:2607.14345v2 Announce Type: replace Abstract: People use language models for practical questions whose answers are difficult to verify. We show that models exhibit covert value leakage:…
arXiv:2607.15456v1 Announce Type: new Abstract: Looped, weight-tied Transformers reduce parameters by reusing a block, but decoding still stores a separate K/V cache for every recurrence step.…
arXiv:2605.15422v3 Announce Type: replace Abstract: Modern RL post-training methods such as GRPO and DAPO train on N response sequences of R tokens sampled from a shared…
arXiv:2607.15449v1 Announce Type: new Abstract: Using the language of Wilsonian renormalization group theory (RG), we treat the Transformer's attention mechanism as a perturbation of the trained…
arXiv:2510.19248v2 Announce Type: replace Abstract: Clustering-based features are widely used in machine learning, but most methods must choose a resolution -- a choice that is global,…
arXiv:2607.15447v1 Announce Type: new Abstract: Recent research in clinical machine learning, focusing on outcome predictions in intensive care unit (ICU), has shifted from bespoke supervised models…
arXiv:2502.06818v4 Announce Type: replace Abstract: Recent works modify CLIP to perform open-vocabulary semantic segmentation in a training-free manner (TF-OVSS). In vanilla CLIP, patch-wise image representations mainly…
arXiv:2607.15394v1 Announce Type: new Abstract: Black-box models limit the adoption of artificial intelligence in medicine due to their lack of interpretability and reproducibility. We introduce a…
arXiv:2607.15412v1 Announce Type: new Abstract: Multi-objective learning (MOL) aims to optimize multiple objectives simultaneously. The multi-gradient descent algorithm (MGDA) is a workhorse that iteratively updates along…
arXiv:2607.15414v1 Announce Type: new Abstract: Large Language Models (LLMs) have emerged as powerful tools for processing the heterogeneous information environments of modern financial markets. This paper…
arXiv:2607.15433v1 Announce Type: new Abstract: We characterize and compare the inherent interpretability offerings of a standard linear model with a single qubit mixed state model for…
arXiv:2607.15446v1 Announce Type: new Abstract: The cost of healthcare remains a concern in the United States and may have been influenced by disruptions associated with the…
arXiv:2607.15440v1 Announce Type: new Abstract: We introduce Stochastic Reset Pathfinding (SRP), an episodic learning problem on a known directed graph with unknown stationary edge success probabilities.…
arXiv:2606.29519v2 Announce Type: replace Abstract: Long-range learning is hard for recurrent networks trained with stochastic gradient descent, because the influence of a past input fades with…
arXiv:2602.04643v2 Announce Type: replace Abstract: Time-series anomaly prediction aims to forecast future system failures before they fully emerge, making latent predictive models such as JEPA a…
arXiv:2605.20982v2 Announce Type: replace-cross Abstract: AlltoAll dispatch is the dominant bottleneck of MoE expert parallelism, and the interconnect community has responded with four families of mitigations:…
arXiv:2507.21018v2 Announce Type: replace-cross Abstract: Automated assessment of human motion plays a vital role in rehabilitation, enabling objective evaluation of patient performance and progress. Unlike general…
arXiv:2607.15898v1 Announce Type: cross Abstract: Current world models operate at a single level of abstraction, with most prioritizing perceptual fidelity while lacking the spatial reasoning and…
arXiv:2607.15823v1 Announce Type: cross Abstract: We study aggregation of statistical evidence under unknown and potentially complex dependence using group-invariance. Building on permutation-based constructions that treat transformed…
arXiv:2607.16122v1 Announce Type: cross Abstract: Evaluations should do more than measure a models current performance. They should tell us what to fix for the next model…
arXiv:2607.15527v1 Announce Type: new Abstract: Physical simulations that predict the behavior of urban disasters, such as climate-related flooding, play a crucial role in disaster prevention and…
arXiv:2603.11593v2 Announce Type: replace Abstract: Instruction-based image editing aims to modify specific content within existing images according to user-provided instructions while preserving non-target regions. Beyond traditional…