arXiv:2601.17644v3 Announce Type: replace-cross Abstract: The growing adoption of multimodal Retrieval-Augmented Generation (mRAG) pipelines for vision-centric tasks (e.g., visual QA) introduces important privacy challenges. In particular, while mRAG provides a practical capability to connect private datasets and improve model performance, it risks the leakage of private information from these datasets. In this paper, we perform […]
RoboEval: Where Robotic Manipulation Meets Structured and Scalable Evaluation
arXiv:2507.00435v2 Announce Type: replace-cross Abstract: We introduce RoboEval, a structured evaluation framework and benchmark for robotic manipulation that augments binary success with principled behavioral and outcome metrics. Existing evaluations often collapse performance into outcome counts, masking differences in execution quality and obscuring failure structure. RoboEval provides eight bimanual tasks with systematically controlled variations, more than […]
Bootstrapped Mixed Rewards for RL Post-Training: Injecting Canonical Action Order
arXiv:2512.04277v3 Announce Type: replace-cross Abstract: Post-training with reinforcement learning (RL) typically optimizes a single scalar objective and ignores structure in how solutions are produced. We ask whether a scalar hint toward a canonical solver ordering, used only during RL post-training, improves performance even when fine-tuned on randomized solution sequences. On Zebra puzzles, we fine-tune a […]
Amortized Variational Inference for Joint Posterior and Predictive Distributions in Bayesian Uncertainty Quantification
arXiv:2605.03710v1 Announce Type: cross Abstract: Bayesian predictive inference propagates parameter uncertainty to quantities of interest through the posterior-predictive distribution. In practice, this is typically performed using a two-stage procedure: first approximating the posterior distribution of model parameters, and then propagating posterior samples through the predictive model via Monte Carlo simulation. This sequential workflow can be […]
Magic-Informed Quantum Architecture Search
arXiv:2605.03932v1 Announce Type: cross Abstract: Nonstabilizerness, commonly referred to as magic, is a fundamental resource underpinning quantum advantage. In this paper, we propose a magic-informed quantum architecture search (QAS) technique that enables control over a quantum resource within the general framework of circuit design. Inspired by the AlphaGo approach, we tackle the problem with a […]
n:m Phase-Locking of Heterogeneous and Strongly Coupled Oscillators
arXiv:2409.14566v3 Announce Type: replace Abstract: We introduce a scalar reduction method for forced or coupled systems with nonlinearities in both heterogeneity and coupling strength. Heterogeneity is formulated as a relatively weak but nonlinear alteration of the vector field(s). The method can be used to determine the existence and stability of $n:m$ phase-locked states in a […]
Soft Tournament Equilibrium
arXiv:2604.04328v3 Announce Type: replace Abstract: The evaluation of general-purpose artificial agents, particularly those based on LLMs, presents a significant challenge due to the non-transitive nature of their interactions. When agent A defeats B, B defeats C, and C defeats A, traditional ranking methods that force a linear ordering can be misleading and unstable. We argue […]
Understanding and Mitigating Bias Inheritance in LLM-based Data Augmentation on Downstream Tasks
arXiv:2502.04419v3 Announce Type: replace-cross Abstract: Generating synthetic datasets via large language models (LLMs) has emerged as a promising approach to improve LLM performance. However, LLMs inherently reflect biases in their training data, leading to a critical challenge: when models are trained on synthetic data, they may propagate and amplify the inherent biases that can significantly […]
Scaling Laws and Symmetry, Evidence from Neural Force Fields
arXiv:2510.09768v2 Announce Type: replace-cross Abstract: We present an empirical study in the geometric task of learning interatomic potentials, which shows equivariance matters even more at larger scales; we show a clear power-law scaling behaviour with respect to data, parameters and compute with “architecture-dependent exponents”. In particular, we observe that equivariant architectures, which leverage task symmetry, […]
Evaluating Semantic Fragility in Text-to-Audio Generation Systems Under Controlled Prompt Perturbations
arXiv:2603.13824v2 Announce Type: replace-cross Abstract: Recent advances in text-to-audio generation enable models to translate natural-language descriptions into diverse musical output. However, the robustness of these systems under semantically equivalent prompt variations remains largely unexplored. Small linguistic changes may lead to substantial variation in generated audio, raising concerns about reliability in practical use. In this study, […]
From Mirage to Grounding: Towards Reliable Multimodal Circuit-to-Verilog Code Generation
arXiv:2604.27969v2 Announce Type: replace-cross Abstract: Multimodal large language models (MLLMs) are increasingly used to translate visual artifacts into code, from UI mockups into HTML to scientific plots into Python scripts. A circuit diagram can be viewed as a visual domain-specific language for hardware: it encodes timing, topology, and bit level semantics that are invisible to […]
A Skill-Based AI Agentic Pipeline for Library of Congress Subject Indexing
arXiv:2605.03537v1 Announce Type: cross Abstract: This paper presents a modular AI agentic skill pipeline for automating subject indexing with Library of Congress Subject Headings (LCSH). Subject indexing – the process of analyzing a work’s aboutness, selecting controlled vocabulary terms, and encoding them as MARC21 subject access fields – is one of the most time-consuming components […]