Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
Affiliation:
7
0
8
Source-validation accuracy is a poor proxy for out-of-distribution reliability; re-ranking checkpoints by aggregated source reliability metrics significantly boosts target probability quality without needing target data.
Video segmenters suffer from persistent identity drift because they blindly write noisy observations to memory; gating state transitions through propose-verify graph reasoning preserves object history through extended occlusions without altering the underlying base model.
AAPT boosts GUI agent success rates by 58% in decision-critical moments, eliminating delays without sacrificing accuracy.
Over 15% of benchmark failures for computer-use agents are misclassified, revealing critical flaws in current evaluation methods.
By decoupling semantic reasoning from spatial grounding, AnchorSeg achieves unprecedented accuracy in reasoning segmentation tasks.
Forget brute-force search: CoT2-Meta shows that strategically controlling reasoning trajectories with metacognition yields significant gains in accuracy and compute efficiency across a wide range of reasoning tasks.