John Foster

Harbor-Xmiller's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a paper 5 days ago

KV4-RL: Unlocking Faster Asynchronous Rollouts for RLVR with INT4 KV Cache Quantization

Paper • 2610.14448 • Published 10 days ago • 46

upvoted a paper 9 days ago

Frozen Models, Evolving Expertise: Model-Agnostic Learning from Deployment Experience for Multimodal Medical AI

Paper • 2610.09146 • Published 14 days ago • 6

upvoted a paper 12 days ago

Agentic RAG Evaluation: Budget Allocation Across Questions, Trajectories, and Reads

Paper • 2610.05034 • Published 16 days ago • 22

upvoted a paper 17 days ago

Adaptive Reward Routing: Dynamic Multi-Reward Optimization for Joint Audio-Video Diffusion via Forward-Process RL

Paper • 2609.37200 • Published 21 days ago • 141

upvoted 3 papers about 1 month ago

Self-Evolving Search Index

Paper • 2609.19656 • Published Sep 17 • 63

Online Draft Co-Training for Speculative Decoding in Large-Scale, Long-Context RL Post-Training

Paper • 2609.07108 • Published Sep 7 • 35

MOLE: Detecting Insider Threats in AI Agents

Paper • 2609.06966 • Published Sep 7 • 18

upvoted a paper about 2 months ago

WorldReward: Reward Modeling for Camera-Conditioned World Models

Paper • 2609.03952 • Published Sep 3 • 28