RealCompanion: Benchmarking Human Understanding from Reasoning over Longitudinal Real-World Conversations
Paper • 2610.01780 • Published • 274
湖南AI打工人
hunanAI
AI & ML interests
None yet
Recent Activity
View all activity
Organizations
None yet
upvoted 5
papers 1 day ago
From Gradients to Capabilities: Understanding Multi-Teacher On-Policy Distillation
Paper • 2610.02179 • Published • 15
Receiver-Conditioned Latent Communication gives 94% CacheBack
Paper • 2609.32046 • Published • 11
Rethinking Token Reweighting for SFT: Suppress, Reverse, and Extrapolate Learned Features
Paper • 2609.33463 • Published • 11
From Retrieval to Typed Decisions: Calibrated System One Models from Biomedical Sentence Encoders
Paper • 2610.02486 • Published • 11
upvoted 4
papers 7 days ago
Scaling Properties of Same-Family On-Policy Distillation
Paper • 2609.32722 • Published • 324
Asking for What Was Never Requested: Horizontal and Vertical Proactivity in Agents
Paper • 2609.37236 • Published • 40
Learning Beyond What You Sample: Off-Policy-Aware Cross-Model Trajectory Exchange for RLVR
Paper • 2609.37868 • Published • 63
APM-Bench: Benchmarking Cross-session Persistent Memory for Egocentric Streaming Video Assistants
Paper • 2609.37559 • Published • 46