RealCompanion: Benchmarking Human Understanding from Reasoning over Longitudinal Real-World Conversations Paper • 2610.01780 • Published 6 days ago • 269
Diptych: Scoped, AI-Interpreted Comparison for Reference Listening in Music Production Paper • 2609.39963 • Published 7 days ago • 20
Scaling Properties of Same-Family On-Policy Distillation Paper • 2609.32722 • Published 11 days ago • 324
ROSS: Relearning from Self-Generated Rollouts through Selective Supervision Paper • 2609.35954 • Published 9 days ago • 50
Asking for What Was Never Requested: Horizontal and Vertical Proactivity in Agents Paper • 2609.37236 • Published 8 days ago • 40
Beyond Dyadic Memory: Interaction-Aware Multimodal Memory with Adaptive Agentic Retrieval for Multi-Party Spoken Conversations Paper • 2609.32522 • Published 11 days ago • 81
Periodic Weak Spots: Phase Sensitivity from Chunked KV-Cache Compression Paper • 2609.36322 • Published 9 days ago • 111