Search papers, labs, and topics across Lattice.
5
0
8
Geometry-aware dataset condensation can dramatically enhance the fidelity of diffusion models, preserving essential distributional characteristics that traditional methods overlook.
Unleashing System 2 reasoning at System 1 speeds, SGA-MCTS lets frozen LLMs rival fine-tuned behemoths like GPT-4 on complex planning tasks.
Robots can now learn dexterous manipulation skills across different hand designs, thanks to a new Transformer architecture that treats actions as a flexible arrangement of joint movements, rather than a fixed sequence.
Achieve significant inference speedups in visual autoregressive models without retraining by pruning redundant tokens based on a novel structure-texture importance criterion.
By decoupling coarse action consistency from fine-grained variations, PF-DAG achieves state-of-the-art imitation learning performance in robotic manipulation tasks.
