Search papers, labs, and topics across Lattice.
Affiliation:
3
0
6
3
Negative Self-Distillation (NSD) is introduced, a new framework that optimizes LLMs by diverging from flawed reasoning rather than imitating privileged solutions, and consistently outperforms OPSD and other label-free, self-bootstrapping reinforcement learning (RL) baselines.
Achieving state-of-the-art RFOV extraction, DragRoof reduces inference steps while enhancing accuracy in correcting geometric displacements in urban imagery.
Even the best MLLMs struggle to meet user requirements, achieving only 66% coverage of essential task functions.
