Search papers, labs, and topics across Lattice.
Thanks:
5
0
6
0
FAR-DPO boosts the success rate of cyclic peptide design by over 10% while ensuring robust performance across challenging targets.
Output extrapolation in STEP-OPD enables a unified student model to surpass the performance of its specialized teachers across all evaluated tasks.
Rarity-aware sampling and spatial consistency techniques enable discrete diffusion to achieve high-quality image super-resolution with fewer decoding steps than traditional methods.
Transforming image generation into a dynamic feedback system yields up to 25.36% better facial similarity and significant spatial error reductions without any training.
A unified framework reveals that existing LLM policy optimization methods often overlook compound failures that require simultaneous adjustments to both trajectory and reward components.
