Search papers, labs, and topics across Lattice.
University of London
5
0
10
Achieving high-fidelity avatar animation with just a single frame, SAGE revolutionizes the data requirements for dynamic facial expression modeling.
HarnessFix reveals that targeted, trace-guided repairs can significantly enhance LLM agent performance by addressing specific harness flaws rather than relying on broad modifications.
LLMs stumble in multi-turn conversations not just because of context length, but because they poison themselves with their own past mistakes – and you can fix it with self-distillation.
Current subject-driven text-to-image models struggle with specific subject categories and prompt scenarios, a problem exposed by a new benchmark that also offers actionable insights for improvement.
Forget MACs and parameters: accurately predict DL model energy and latency on MCUs with 3x and 6.5x lower error using just clock cycles.
