arXiv:2403.02290v2 Announce Type: replace Abstract: The Bellman equation and its continuous form, the Hamilton-Jacobi-Bellman equation, are ubiquitous in reinforcement learning and control theory. However, these equations become intractable for high-dimensional or nonlinear systems. This paper develops two new reinforcement learning algorithms based on the data-driven Koopman operator, which lifts a nonlinear system into new coordinates […]
MAEPose: Self-Supervised Spatiotemporal Learning for Human Pose Estimation on mmWave Video
arXiv:2605.00242v1 Announce Type: cross Abstract: Millimetre-wave (mmWave) radar offers a more privacy-preserving alternative to RGB-based human pose estimation. However, existing methods typically rely on pre-extracted intermediate representations such as sparse point clouds or spectrogram images, where the rich spatiotemporal information naturally present in radar video streams is discarded for model learning, while such signal processing […]
When Do Diffusion Models learn to Generate Multiple Objects?
arXiv:2605.00273v1 Announce Type: cross Abstract: Text-to-image diffusion models achieve impressive visual fidelity, yet they remain unreliable in multi-object generation. Despite extensive empirical evidence of these failures, the underlying causes remain unclear. We begin by asking how much of this limitation arises from the data itself. To disentangle data effects, we consider two regimes across different […]
Reconstruction of glymphatic transport fields from subject-specific imaging data, with particular emphasis on cerebrospinal fluid flow and tracer conservation
arXiv:2605.00730v1 Announce Type: cross Abstract: The reconstruction of physically valid transport fields from subject-specific imaging data is a fundamental challenge in image-based computational modeling due to measurement noise, modeling uncertainties and discretization errors. Without a methodology to construct models that faithfully reflect the underlying physics, mechanistic understanding of complex biological systems is inherently limited. In […]
Unsupervised Denoising of Real Clinical Low Dose Liver CT with Perceptual Attention Networks
arXiv:2605.00793v1 Announce Type: cross Abstract: With the development of deep learning, medical image processing has been widely used to assist clinical research. This paper focuses on the denoising problem of low-dose computed tomography using deep learning. Although low-dose computed tomography reduces radiation exposure to patients, it also introduces more noise, which may interfere with visual […]
Directed Social Regard: Surfacing Targeted Advocacy, Opposition, Aid, Harms, and Victimization in Online Media
arXiv:2605.00776v1 Announce Type: cross Abstract: The language in online platforms, influence operations, and political rhetoric frequently directs a mix of pro-social sentiment (e.g., advocacy, helpfulness, compassion) and anti-social sentiment (e.g., threats, opposition, blame) at different topics, all in the same message. While many natural language processing (NLP) tools classify or score a text’s overall sentiment […]
SUDP: Secret-Use Delegation Protocol for Agentic Systems
arXiv:2604.24920v2 Announce Type: replace-cross Abstract: Agentic systems increasingly act with user secrets for APIs, messaging platforms, and cloud services. Today’s bearer-secret interfaces implement authorization by exposure: enabling action often means placing a reusable secret, or a reusable artifact derived from it, within a model-steerable boundary, so a transient prompt-injection or tool-side compromise becomes durable account […]
Preference Goal Tuning: Post-Training as Latent Control for Frozen Policies
arXiv:2412.02125v2 Announce Type: replace Abstract: Goal-conditioned policies enable decision-making models to execute diverse behaviors based on specified goals, yet their downstream performance is often highly sensitive to the choice of instructions or prompts. To bypass the limitations of discrete text prompts, we formulate post-training adaptation as a latent control problem, where the goal embedding serves […]
The $textitSilicon Society$ Cookbook: Design Space of LLM-based Social Simulations
arXiv:2605.00197v1 Announce Type: cross Abstract: Studies attempting to simulate human behavior with $textitSilicon Societies$ grow in numbers while LLM-only social networks have started appearing outside of controlled settings. However, the design space of these networks remains under-studied, which contributes to a gap in validating model realism. To enable future works to make more informed design […]
Attention Is Where You Attack
arXiv:2605.00236v1 Announce Type: cross Abstract: Safety-aligned large language models rely on RLHF and instruction tuning to refuse harmful requests, yet the internal mechanisms implementing safety behavior remain poorly understood. We introduce the Attention Redistribution Attack (ARA), a white-box adversarial attack that identifies safety-critical attention heads and crafts nonsemantic adversarial tokens that redirect attention away from […]
RSAT: Structured Attribution Makes Small Language Models Faithful Table Reasoners
arXiv:2605.00199v1 Announce Type: cross Abstract: When a language model answers a table question, users have no way to verify which cells informed which reasoning steps. We introduce RSAT, a method that trains small language models (SLMs, 1-8B) to produce step-by-step reasoning with cell-level citations grounded in table evidence. Phase 1 (SFT) teaches a structured JSON […]
REALM: An RGB and Event Aligned Latent Manifold for Cross-Modal Perception
arXiv:2605.00271v2 Announce Type: cross Abstract: Event cameras provide several unique advantages over standard frame-based sensors, including high temporal resolution, low latency, and robustness to extreme lighting. However, existing learning-based approaches for event processing are typically confined to narrow, task-specific silos and lack the ability to generalize across modalities. We address this gap with REALM, a […]