Unverified50% confidenceBenchmarkExact time
Experimental results showed that the intervention directions identified by TR/TL-based optimization outperform the original task vectors in performance.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
11/2/2026
First Seen
Valid until: 1/31/2027
Sources
Related Entities
Related Claims
UnverifiedThe research team used Bayesian optimization to search over the TR and TL coefficients in order to find better intervention directions.77% similarUnverifiedSmall-step steering experiments show that attribution estimates closely match actual steering effects.73% similarUnverifiedOn difficult tasks (such as SST-2), the performance gain from intelligent sample pair selection is more pronounced.71% similarUnverifiedThe research team verified through controlled crop quality manipulation experiments that higher-quality crops lead to better downstream task transfer performance.71% similarUnverifiedOutcome-aware likelihood comparison evaluates skill utility by computing the log-likelihood of the model reproducing the trajectory under the two conditions of carrying and not carrying the candidate skill, and weighting and comparing the likelihood difference according to the trajectory outcome label.69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1124972API
curl https://kongchang.com/api/v1/knowledge/claims/1124972MCP
get_claim(id=1124972)