渡辺 美加子

kanakobayashi's activity

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

upvoted 2 papers 4 days ago

Player-1: Learning to Play from Synthetic Experience

Paper • 2610.20584 • Published 6 days ago • 343

ActionOPD: Distilling Decisions, Not Tokens

Paper • 2610.19820 • Published 6 days ago • 60

upvoted a paper 7 days ago

Can AI Agents Learn Their Way to the Top? Evaluating Heuristic Learning in a Long-Running Game Agent Competition

Paper • 2610.12341 • Published 12 days ago • 48

upvoted a paper 11 days ago

Recurrent Looped Transformer

Paper • 2610.07591 • Published 14 days ago • 33

upvoted a paper 14 days ago

MinkowskiPE: Minkowski Positional Encoding for Spatiotemporal Perception

Paper • 2609.33804 • Published 23 days ago • 18

upvoted a paper 16 days ago

Do Audio LLMs Listen Before They Act? Diagnosing Acoustic-Context Gating in Voice Agents

Paper • 2609.32536 • Published 24 days ago • 13

upvoted 2 papers about 1 month ago

HyQuant: Hybrid-Precision Quantization for LLM Attention

Paper • 2608.27875 • Published Aug 28 • 29

SQS: Bayesian DNN Compression through Sparse Quantized Sub-distributions

Paper • 2510.08999 • Published Sep 7 • 19