RealCompanion: Benchmarking Human Understanding from Reasoning over Longitudinal Real-World Conversations
Paper • 2610.01780 • Published • 193
持田 ゆき
yukimochida
AI & ML interests
None yet
Recent Activity
upvoted a paper about 3 hours ago
RealCompanion: Benchmarking Human Understanding from Reasoning over Longitudinal Real-World Conversations upvoted a paper about 3 hours ago
Learning from Runtime Feedback through Failure-Bank Self-Evolution for Vision-Language-Action Models upvoted a paper about 3 hours ago
From Gradients to Capabilities: Understanding Multi-Teacher On-Policy DistillationOrganizations
None yet
upvoted 4
papers about 3 hours ago
Learning from Runtime Feedback through Failure-Bank Self-Evolution for Vision-Language-Action Models
Paper • 2609.39820 • Published • 9
From Gradients to Capabilities: Understanding Multi-Teacher On-Policy Distillation
Paper • 2610.02179 • Published • 6
Rethinking Token Reweighting for SFT: Suppress, Reverse, and Extrapolate Learned Features
Paper • 2609.33463 • Published • 7
upvoted 4
papers 5 days ago
Scaling Properties of Same-Family On-Policy Distillation
Paper • 2609.32722 • Published • 322
Beyond Selection: Token Parameterization for Extreme Visual Token Compression
Paper • 2609.35232 • Published • 7
FurE: Efficient Instance-Specific 3D Fur Reconstruction without Animal-Fur Datasets
Paper • 2609.35770 • Published • 8
Improved Distributional Diffusion Models
Paper • 2609.37147 • Published • 5
