PAPER·August 1, 2026ReToken: One Token to Improve Vision-Language Models for Visual RetrievalHugging Face Papers
PAPER·August 1, 2026Chimera: Designing and Chinchilla-Scaling Hybrid Visual Diffusion TransformersHugging Face Papers
PAPER·August 1, 2026OmniScope: Modality-Decoupled Token Compression for Omnimodal Large Language ModelsHugging Face Papers
PAPER·July 31, 2026β-OPSD: Deriving with Policy Optimization, Training with Self-DistillationHugging Face Papers
PAPER·July 31, 2026Beyond Geometric Complementarity: Coherent Overlap in Sparse Mixture-of-Experts RoutingHugging Face Papers
PAPER·July 31, 2026Fairness Pruning: Locating Demographic Bias in GLU-MLP Layers via Differential ActivationsHugging Face Papers
PAPER·July 31, 2026Σ-Mem: An Online Reliability Memory for LLM-based Multi-Agent SystemsHugging Face Papers
PAPER·July 31, 2026See2Think: Do Multimodal Models Really Use Intermediate Visual States?Hugging Face Papers
PAPER·July 31, 2026Filesystem-Based Memory for LLM Agents: Organization, Evolution, and SustainabilityHugging Face Papers
PAPER·July 31, 2026Pedestrian Archetypes Extension -- More Pedestrian Models for Autonomous Vehicle Safety TestingHugging Face Papers
PAPER·July 31, 2026Is Deep Research Reliable? Misleading Knowledge Induces False ConclusionsHugging Face Papers
