Unverified50% confidenceBenchmarkExact time
When doing 50% pruning on Qwen3-4B, CACTUS reduced the gap between C4 perplexity and the dense model by 45%.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/14/2026
First Seen
Valid until: 1/12/2027
Sources
Related Entities
Related Claims
UnverifiedOn Qwen3-4B, after pruning MLP layers to 2:4 sparsity and adding rank-64 correction, CACTUS combined with LoGRA still maintains 0.711 cosine alignment with the C4 gradients of dense LoGRA after projection.79% similarUnverifiedWhen doing 50% pruning on Qwen3-4B, CACTUS raised the compressed-dense per-sample gradient cosine similarity on WikiText-2 from 0.670 to 0.755.73% similarUnverifiedQ4_K_M采用分组量化策略，将权重张量划分为64或256维子块并独立计算缩放因子与零点，能将困惑度损失控制在1–3%以内64% similarVerifiedQ4量化将每个权重参数从16位压缩到4位，理论上可将模型体积缩小约75%64% similarUnverifiedOn Llama-3.2-3B, fine-tuning a brand-new dense model with the 5% of data selected by CACTUS reached 49.44% accuracy on BIG-Bench Hard; selecting data directly with the dense model gave 49.54%; data selected by the ALPS method could only reach 47.22%.64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1022896API
curl https://kongchang.com/api/v1/knowledge/claims/1022896MCP
get_claim(id=1022896)