Search papers, labs, and topics across Lattice.
Harbin Institute of Technology
4
0
7
Current coding agents falter in preserving content integrity while reconstructing UI regions, revealing critical gaps in their iterative coding capabilities.
Closing the sim-to-real gap in vision-language navigation requires benchmarks grounded in realistic 3D reconstructions, not just generated scenes.
Steer LVLMs' attention with caption guidance and watch object hallucinations drop by 6%鈥攏o training required.
STRATAGEM reveals that selectively reinforcing reasoning trajectories can dramatically enhance a model's ability to transfer reasoning skills across diverse tasks, especially in complex mathematical scenarios.
