PAPER·May 29, 2026Got a Secret? LLM Agents Can't Keep It: Evaluating Privacy in Multi-Agent SystemsHugging Face Papers
PAPER·May 29, 2026How and What to Imagine? Visual Thinking in Unified Multimodal Models for Cross-View Spatial ReasoningHugging Face Papers
PAPER·May 29, 2026How Accurate are Video Quality Models for Diffusion-Based Video Super-Resolution?Hugging Face Papers
PAPER·May 29, 2026GUI-CIDER: Mid-training GUI Agents via Causal Internalization and Density-aware Exemplar ReselectionHugging Face Papers
PAPER·May 29, 2026Breaking the Chains of Probability: Neutrosophic Logic as a New Framework for Epistemic Uncertainty in Large Language ModelsHugging Face Papers
PAPER·May 29, 2026Your Agents Are Aging Too: Agent Lifespan Engineering for Deployed SystemsHugging Face Papers
PAPER·May 29, 2026Don't Guess, Just Ask: Resolving Ambiguity in Referring Segmentation via Multi-turn ClarificationHugging Face Papers
PAPER·May 29, 2026Category-Level 3D Correspondence in Camera Space via Morphable Object PriorsHugging Face Papers
PAPER·May 28, 2026AgentHijack: Benchmarking Computer Use Agent Robustness to Common Environment CorruptionsHugging Face Papers
PAPER·May 28, 2026Rethinking How to Remember: Beyond Atomic Facts in Lifelong LLM Agent MemoryHugging Face Papers
PAPER·May 28, 2026The Fragility of Chain-of-Thought Monitoring Across Typologically Diverse LanguagesHugging Face Papers
