RealCompanion: Benchmarking Human Understanding from Reasoning over Longitudinal Real-World Conversations
Paper • 2610.01780 • Published • 283
持田 ゆき
yukimochida
AI & ML interests
None yet
Recent Activity
upvoted a paper 6 days ago
From Gradients to Capabilities: Understanding Multi-Teacher On-Policy DistillationOrganizations
None yet
upvoted 4
papers 6 days ago
Learning from Runtime Feedback through Failure-Bank Self-Evolution for Vision-Language-Action Models
Paper • 2609.39820 • Published • 31
From Gradients to Capabilities: Understanding Multi-Teacher On-Policy Distillation
Paper • 2610.02179 • Published • 20
Rethinking Token Reweighting for SFT: Suppress, Reverse, and Extrapolate Learned Features
Paper • 2609.33463 • Published • 12
upvoted 4
papers 11 days ago
Scaling Properties of Same-Family On-Policy Distillation
Paper • 2609.32722 • Published • 326
Beyond Selection: Token Parameterization for Extreme Visual Token Compression
Paper • 2609.35232 • Published • 8
FurE: Efficient Instance-Specific 3D Fur Reconstruction without Animal-Fur Datasets
Paper • 2609.35770 • Published • 9
Improved Distributional Diffusion Models
Paper • 2609.37147 • Published • 6