RealCompanion: Benchmarking Human Understanding from Reasoning over Longitudinal Real-World Conversations
Paper • 2610.01780 • Published • 299
湖南AI打工人
hunanAI
AI & ML interests
None yet
Recent Activity
upvoted a paper 21 days ago
From Gradients to Capabilities: Understanding Multi-Teacher On-Policy Distillation upvoted a paper 21 days ago
Receiver-Conditioned Latent Communication gives 94% CacheBackOrganizations
None yet
upvoted 5
papers 21 days ago
From Gradients to Capabilities: Understanding Multi-Teacher On-Policy Distillation
Paper • 2610.02179 • Published • 21
Receiver-Conditioned Latent Communication gives 94% CacheBack
Paper • 2609.32046 • Published • 13
Rethinking Token Reweighting for SFT: Suppress, Reverse, and Extrapolate Learned Features
Paper • 2609.33463 • Published • 12
From Retrieval to Typed Decisions: Calibrated System One Models from Biomedical Sentence Encoders
Paper • 2610.02486 • Published • 12
upvoted 4
papers 26 days ago
Scaling Properties of Same-Family On-Policy Distillation
Paper • 2609.32722 • Published • 328
Asking for What Was Never Requested: Horizontal and Vertical Proactivity in Agents
Paper • 2609.37236 • Published • 41
Learning Beyond What You Sample: Off-Policy-Aware Cross-Model Trajectory Exchange for RLVR
Paper • 2609.37868 • Published • 65
APM-Bench: Benchmarking Cross-session Persistent Memory for Egocentric Streaming Video Assistants
Paper • 2609.37559 • Published • 47
liked 5
models 26 days ago
ganmoor-ai-labs/finanalyzer-indian-bank-statements
Text Generation • 2B • Updated • 328 • 16
OpenIntelligenceNet/Spark-X2.5-4B-Uncensored-GGUF
4B • Updated • 745 • 4
ykirchhoff/LongiTrack
Image Segmentation • Updated • 37 • 6
Logics-MLLM/Logics-SWE-Qwen3.6-27B
Text Generation • 27B • Updated • 298 • 12
0xSero/GLM-5.3-Flash-EXL3-Spark
Text Generation • 48B • Updated • 540 • 9