PGPO: Prototype-Guided Progressive Obfuscation for Privacy-Preserving LLM-Enhanced Recommendation Paper • 2611.23236 • Published Aug 26 • 3
Recurrent Domain Incremental Adaptation of Time-Series Foundation Models Paper • 2611.24075 • Published 3 days ago • 3
ResWAM: Learning What Changes, Not What Stays, for World-Action Models Paper • 2611.19559 • Published 7 days ago • 5
MedJev: A System One Vision-Language Decision Model for Fast and Effective Medical Image Understanding Paper • 2611.20992 • Published 5 days ago • 13
Skill2Real: Agentic Skill Learning for Zero-Shot Sim-to-Real Robot Manipulation Paper • 2610.02788 • Published Oct 2 • 6
From Gradients to Capabilities: Understanding Multi-Teacher On-Policy Distillation Paper • 2610.02179 • Published Oct 1 • 7
RealCompanion: Benchmarking Human Understanding from Reasoning over Longitudinal Real-World Conversations Paper • 2610.01780 • Published Oct 1 • 43
From Retrieval to Typed Decisions: Calibrated System One Models from Biomedical Sentence Encoders Paper • 2610.02486 • Published Oct 1 • 4
Collective Bias Mitigation via Model Routing and Collaboration Paper • 2610.03240 • Published Oct 2 • 5