Single-Round Vector RAG vs an LLM-Compiled Wiki: A Preregistered Comparison on a Small Multi-Domain Research CorpusResearchOct 6, 2026
PerturBot: Breaking Shortcut Priors in Vision-Language-Action Models with Perturbative TrainingResearchOct 6, 2026
The Poisoned Conversation: Privacy-Leaking Watermarks in Unified Multimodal ModelsResearchOct 6, 2026
Discovered, Not Designed: Population Evolution for Collaborative and Compute-Intensive Model DiscoveryResearchOct 6, 2026
Correct Code, Broken Contributions? SWE-CC: Benchmarking Repository Policy Compliance for Coding AgentsResearchOct 6, 2026
APOD: reasoning-guided agentic population ordinary differential equation discovery for pharmacological digital twinsResearchOct 6, 2026