Search papers, labs, and topics across Lattice.
Imperial College London
5
0
9
Synthesizing realistic hand-object interactions is now possible with HO-Flow, a framework that leverages masked flow matching and interaction-aware VAEs to achieve state-of-the-art results in motion diversity and physical plausibility.
MLLMs can now better understand your pointing with Hand Intent Tokens (HINT), boosting accuracy on egocentric video question answering by 6.6% on a new benchmark.
Unlock scalable CAD generation from unannotated 3D meshes with DreamCAD, a framework that directly produces editable BREPs from point-level supervision, outperforming existing methods and achieving over 75% user preference.
Smart glasses powered by web-native AI agents can now outperform commercial solutions in assistive tasks, offering a practical path to always-on, context-aware help for users navigating daily life.
By stitching together the best reasoning steps from multiple diffusion-generated trajectories, this method achieves significant accuracy gains and latency reductions in math and coding tasks, outperforming traditional diffusion models and unified architectures.
