Search papers, labs, and topics across Lattice.
University of Science and Technology of China
4
0
9
3
Achieve state-of-the-art results in agentic knowledge base question answering by distilling gold-action policies into on-policy student rollouts, bridging the gap between sparse rewards and weakly supervised intermediate actions.
Forget training loops and labels: this method selects high-value reasoning examples for RL using only a single forward pass through the model.
TabEmbed leapfrogs existing text embedding models to achieve SOTA performance on tabular data by reformulating tasks as semantic matching problems and using contrastive learning.
RLVR models exhibit "Early Correctness Coherence" under noisy supervision, suggesting a surprising opportunity for self-correction via dynamic label refinement.
