NVAlign: Direct-Gradient Optimization for Non-Verbal Control in Continuous Autoregressive Flow Matching Text-to-SpeechResearchSep 29, 2026
M3-Score: Fidelity, Memorization and Coverage as Separate Axes for Evaluating Generative Radiology Image ModelsResearchSep 29, 2026
RSI-Router: Evolving Subtask-Level LLM Routing and Skills for Cost-Efficient AgentsResearchSep 29, 2026
When Do Model Internals Help? Exploring the Role of Representation Engineering in LLM SafetyResearchSep 29, 2026
PDE-JEPA: Predictive Representation Learning of Latent Dynamics Modeling for Parametric PDEsResearchSep 29, 2026
Before the Token Commits: Trajectory-Level Benchmarking of Visual Hallucinations in Diffusion VLMsResearchSep 29, 2026
Page-Aware Retrieval-Augmented Generation for EvalLLM 2026: A Five-Variant Study on French PDFsResearchSep 29, 2026
BEHAVE: Functional Behavior Modeling Enables Self-Improving Agents for Hardware Design and VerificationResearchSep 29, 2026
Eyes on the Road: A Naturalistic Comparison of MTW Rider Gaze in Urban Indian TrafficResearchSep 29, 2026