Unverified50% confidenceFactExact time
FlexCast's ablation experiments show that contiguous target masking and context diversity together constitute the main source of performance improvement.
1
Sources
50%
Confidence
Long-term
Relevance
11/16/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe strategy of rounding once every few tokens preserves the decoding speedup brought by the buffer.70% similarUnverifiedIn FlexCast's variable-length masked prediction, each pretraining step randomly selects several contiguous segments as prediction targets and the remaining segments as visible context, with both mask length and position varying dynamically.70% similarUnverifiedFADE improves performance under different scheduling paradigms, indicating that its approach of decoupling capability and difficulty is general.70% similarUnverifiedThe harness replay mechanism identifies high-yield strategies and recurring failure patterns by replaying the research process, and refines the research workflow accordingly.68% similarUnverifiedIn the inference stage, FlexCast supports three modes through a unified mask-predict interface: one-step prediction, confidence-based iterative refinement, and next-token-style generation.67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1174096API
curl https://kongchang.com/api/v1/knowledge/claims/1174096MCP
get_claim(id=1174096)