HyperBrowseComp: A Multilingual and Multimodal Stress Test for Web-Browsing Agents Paper • 2610.03574 • Published 4 days ago • 42
EditHero: A Benchmark for Long-Horizon Part-Level 3D Editing and Vibe Modeling Paper • 2610.02298 • Published 5 days ago • 26
Latent-MOPD: Latent Multi-Teacher On-Policy Distillation Paper • 2610.02381 • Published 5 days ago • 31
RealCompanion: Benchmarking Human Understanding from Reasoning over Longitudinal Real-World Conversations Paper • 2610.01780 • Published 5 days ago • 193
Learning from Runtime Feedback through Failure-Bank Self-Evolution for Vision-Language-Action Models Paper • 2609.39820 • Published 6 days ago • 9
MinkowskiPE: Minkowski Positional Encoding for Spatiotemporal Perception Paper • 2609.33804 • Published 9 days ago • 9
When Does Dense Retrieval Need Asymmetric Geometry? A Bias-Variance Theory of Shared and Dual Projections Paper • 2609.32488 • Published 10 days ago • 26
EmoRES-TTS: Residual-Enhanced Vector Steering for Emotional Speech Generation Paper • 2609.38157 • Published 7 days ago • 20
Scaling Properties of Same-Family On-Policy Distillation Paper • 2609.32722 • Published 10 days ago • 322
OmniTaskonomy: When Does Visual Generation Improve Visual Understanding? Paper • 2609.38079 • Published 7 days ago • 55
Learning Beyond What You Sample: Off-Policy-Aware Cross-Model Trajectory Exchange for RLVR Paper • 2609.37868 • Published 7 days ago • 62
Think Before You Score: Thinking Reward Model for Visual Generation Paper • 2609.37372 • Published 7 days ago • 101
Raven: The Harness of Harnesses for Composable Agentic Intelligence Paper • 2609.33439 • Published 9 days ago • 564