Yanru Wu
1 indexed paper
Recent (6 mo)
1With code
0Influential cites
0Benchmarked
0Publications per year
126
Top categories
Vision×1ML×1
Frequent co-authors
Research Timeline
2026
CORE-MTL: Rethinking Gradient Balancing via Causal Orthogonal Representations
CORE-MTL proposes a representation-centric framework that uses causal orthogonal representations to disentangle task-relevant structure from nuisance variation in multi-task learning, achieving superior generalization.
Highlighted terms show continued research focus across papers