10

Apply video compression on KV cache to 10,000x less error at Q4 quant (github.com/cenconq25)

12 hours ago polymorph1sm github.com

1

In Forecasting, Search >> Distillation (spylab.ai)

4 weeks ago polymorph1sm spylab.ai

1

Benchmarking the continuous improvement of language agents in deployment (arxiv.org)

a year ago polymorph1sm arxiv.org