Search papers, labs, and topics across Lattice.
6
0
11
0
Selectively repeating only the most informative tokens can dramatically enhance reasoning in LLMs while slashing computational costs.
FacePlex achieves real-time, synchronized speech and facial motion generation, outperforming existing models in lip-sync quality and motion fidelity.
Simulated environments can revolutionize forecasting by providing immediate resolutions to complex probabilistic questions that are often elusive in the real world.
SPARC achieves superior control performance in robotic applications by dynamically allocating bitrate based on the task relevance of visual information, outperforming traditional codecs.
LLMs get *worse* at forecasting high-stakes events like epidemics and financial crises as they get more capable, because they aggressively extrapolate growth and overestimate tail risk.
Achieve near-FP32 image restoration performance with an Int8 model that runs at 442 FPS on NVIDIA Jetson Orin, all thanks to a quantization-aware distillation framework that avoids decoder distillation.
