Unverified50% confidenceBenchmarkExact time
SpatialASM yielded spatial reasoning performance improvements across four different LVLM backbone models
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/12/2026
First Seen
Valid until: 1/10/2027
Sources
Related Entities
Related Claims
UnverifiedThe Linear Representation Hypothesis (LRH) assumes that models encode high-level concepts as linear directions in the activation space.66% similarUnverifiedRL 环境通常遵循马尔可夫决策过程（MDP），由状态空间、动作空间、转移函数和奖励函数四个核心要素构成66% similarUnverified远距离概念融合在扩散模型中效果突出，因为模型被迫在特征空间中寻找新颖的插值路径65% similarUnverifiedExplicit ASM trajectories provide dedicated Chain-of-Thought supervision for spatial reasoning, demonstrating complete thinking paths63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1001973API
curl https://kongchang.com/api/v1/knowledge/claims/1001973MCP
get_claim(id=1001973)