GARDiff: Graph-Aligned Residual Diffusion for Probabilistic Multivariate Time-Series ForecastingResearchSep 30, 2026
AgentBug-Smith: Automatically Reproducing Real-World Harness Bugs in Agentic SystemsResearchSep 30, 2026
Learning Beyond What You Sample: Off-Policy-Aware Cross-Model Trajectory Exchange for RLVRResearchSep 30, 2026
Predictive Self-Supervised Learning Provably Identifies Stochastic Signals under NuisanceResearchSep 30, 2026
Privy to the Foil: Recasting Value Estimation with a Self-Privileged Critic for RLVRResearchSep 30, 2026
Thinking in Depth, Speaking Directly: Recurrent Latent Reasoning for Paralinguistically Grounded Spoken DialogueResearchSep 30, 2026
Arbitrary-Accuracy Neural Approximation with Optimal Neuron Count and Near-Optimal Bit ComplexityResearchSep 30, 2026