RealCompanion: Benchmarking Human Understanding from Reasoning over Longitudinal Real-World Conversations
Paper • 2610.01780 • Published • 193
Oriol Puig
oriol-p
·
AI & ML interests
None yet
Recent Activity
upvoted a paper about 2 hours ago
RealCompanion: Benchmarking Human Understanding from Reasoning over Longitudinal Real-World Conversations upvoted a paper about 2 hours ago
Efficient Reasoning Training Does Not Always Harm CoT Faithfulness and Monitorability upvoted a paper 5 days ago
Scaling Properties of Same-Family On-Policy DistillationOrganizations
None yet
upvoted 2
papers about 2 hours ago
upvoted 4
papers 5 days ago
Scaling Properties of Same-Family On-Policy Distillation
Paper • 2609.32722 • Published • 322
Periodic Weak Spots: Phase Sensitivity from Chunked KV-Cache Compression
Paper • 2609.36322 • Published • 111
SAKI: Maximal-Coupling-Routed Teacher Supervision for On-Policy Distillation
Paper • 2609.36601 • Published • 94
What Makes World Action Models Generalize? An Empirical Study of Test-Time Future Modeling
Paper • 2609.34981 • Published • 136
liked a
dataset 5 days ago
liked a
model 5 days ago
