Search papers, labs, and topics across Lattice.
Xiamen University
3
0
6
Fine-tuning the exploration-exploitation balance can dramatically boost LLM reasoning capabilities, as shown by our novel perplexity-guided strategy.
Forget semantic trickery – the key to spotting AI-generated fakes lies in subtle physical fingerprints like Laplacian variance and residual noise, offering near-perfect detection accuracy.
Existing 3D visual grounding methods crumble in complex scenes, but PC-CrossDiff's dual-level attention unlocks a +10% accuracy boost by parsing subtle spatial cues.
