Unverified50% confidenceFactExact time
WildMAE proposes a decoder-side improvement scheme that achieves significant reconstruction metric gains at a 75% masking ratio.
1
Sources
50%
Confidence
Long-term
Relevance
10/21/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe researchers proposed a heteroscedasticity-aware extension of quantile loss, whose core approach is to use input-dependent label smoothing as a mitigation measure.59% similarUnverifiedSlimWise prunes experts during the inference serving stage and decouples the prefill and decode phases, combined with KV cache reuse and lightweight distillation, achieving up to 1.81× decoding speedup with minimal accuracy loss.59% similarUnverifiedAdaptation substantially improved in-domain diarization performance, and this improvement transferred to an independent corpus.59% similarUnverifiedBoth methods are estimated via alternating optimization, and the sparse components have closed-form solution updates58% similarUnverified掩码自编码器（MAE）由 He et al.（2021）提出，其核心创新在于采用 75% 极高遮盖率随机遮盖图像块后让模型重建57% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1079200API
curl https://kongchang.com/api/v1/knowledge/claims/1079200MCP
get_claim(id=1079200)