Unverified50% confidenceBenchmarkExact time
On the HG2.9K benchmark, PLLM+ resolved 1,500 snippets while the baseline method PLLM resolved only 1,169, representing an improvement of approximately 28%.
1
Sources
50%
Confidence
Long-term
Relevance
9/24/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedIn the experiment, ResNet-56 has only 2,752 more parameters than plain-56 (approximately one-third of a percent of the total), and these extra parameters come solely from 1×1 projection layers at locations where the number of channels changes.59% similarUnverifiedThe GLM-OCR model has 0.9B (900 million) parameters.57% similarUnverifiedLoRA decomposes the fine-tuning weight change ΔW into the product of two low-rank matrices, with a parameter count of only 0.1%–1% of the original model, achieving a parameter compression ratio as high as 256× when r=8 and d=4096.57% similarUnverifiedIn the inventory management task, the RL policy scored 194.5, slightly below the base-stock baseline's 196.7, but rediscovered the analytically optimal base-stock policy from scratch.57% similarUnverifiedCompared to pure decoder architectures (such as GPT), GLM achieves an average improvement of 8–15 percentage points on Chinese NLU tasks; compared to encoder-decoder architectures (such as T5), inference efficiency is improved by approximately 40%.56% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/946084API
curl https://kongchang.com/api/v1/knowledge/claims/946084MCP
get_claim(id=946084)