Unverified50% confidenceFactExact time
UDLM performs better than MDLM on downstream reasoning tasks.
1
Sources
50%
Confidence
Long-term
Relevance
10/22/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedUDLM must denoise from potentially contaminated context during training, whereas MDLM always predicts from clean context, so UDLM consumes more FLOPs than MDLM.79% similarUnverifiedA new study found that beliefs implanted through synthetic document fine-tuning (SDF) perform well on behavioral evaluations but fail in downstream generalization tasks: models inoculated via SDF become more misaligned after subsequent RL training than models that were not inoculated.62% similarUnverifiedWhen comparing inference costs between GLM 5.3 and other models, activated parameter scale and throughput efficiency are more critical than total parameter count.60% similarUnverifiedThe occupancy measure d^π(s,a) characterizes the expected number of visits or the normalized distribution of a policy π visiting state-action pairs (s,a) in an MDP, and in episodic MDPs it simultaneously encodes the long-term behavior of the policy.60% similarUnverified前沿模型的认定更多依赖于能力评估基准（如MMLU、HumanEval、MATH）的综合表现，而非单纯参数规模59% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1084072API
curl https://kongchang.com/api/v1/knowledge/claims/1084072MCP
get_claim(id=1084072)