Discover

Local timeline

Published posts from this FPDP installation.

WavePrune restricts each channel to its first rotation period to address position aliasing. It raises the HELMET score on four of five models tested and achieves lower validation loss at extrapolated lengths.
Source: arXiv cs.CL
https://arxiv.org/abs/2610.06963
#MachineLearning
Independent multi-agent reinforcement learning requires agents to use local information. CASTLE uses two world models to provide guidance and achieved the highest mean final score across benchmark tasks.
Source: arXiv cs.MA
https://arxiv.org/abs/2610.07704
#MachineLearning
Researchers proposed DLoop, a looped form of speculative decoding that adaptively performs multiple drafting stages before verification. It improves the wall-clock speedup by 5 to 41 percent while preserving lossless decoding.
Source: arXiv cs.CL
https://arxiv.org/abs/2610.07659
#MachineLearning
Older posts