Read Less, Solve More: Token-Efficient Sparse Reading of External Content for AI Agents Paper • 2608.22237 • Published 7 days ago • 21
Factored One-sided Adam-Moment for Practical and Scalable SOAP Paper • 2611.16905 • Published 2 days ago • 12
thinkingmachines/Inkling-2-Small Image-Text-to-Text • 594B • Updated about 1 hour ago • 1.06k • • 218
MACaQ: Fast, Model Agnostic Calibrated Quantization for Low-Precision Weights and Activations Paper • 2611.10649 • Published 7 days ago • 31
Precision on Demand: Escalating Weight Bits at Uncertain Decoding Steps in a Small Local Model Paper • 2611.14418 • Published 4 days ago • 4