Search papers, labs, and topics across Lattice.
9
0
12
3
Ghosting artifacts are dramatically reduced and rendering quality improved in UAV scene reconstructions through adaptive feature aggregation tailored to local dynamics.
SlimSearcher cuts tool-call rounds by up to 58% without sacrificing accuracy, redefining efficiency in web agent training.
Freezing most of your critic network and only training a tiny LoRA adapter can dramatically improve off-policy RL performance and stability.
Jointly modeling need prediction and service recommendation in an LLM framework dramatically improves local life service recommendations, outperforming traditional isolated approaches.
VLMs struggle to connect the dots between dynamic drone footage and satellite imagery, highlighting a critical gap in their spatial reasoning abilities.
By recognizing that CLIP features aren't monolithic, DR-Seg unlocks targeted structural enhancements that dramatically improve open-vocabulary remote sensing segmentation.
Generate detailed 3D indoor scenes from short text descriptions with SDesc3D, a framework that leverages multi-view structural priors and regional functionality to overcome the limitations of explicit semantic cues.
Forget expensive video diffusion: Resonance4D unlocks high-fidelity 4D dynamic simulations by cleverly supervising motion in the frequency domain.
Stop guessing affordances from static scenes: A3R's agentic approach leverages cross-dimensional evidence acquisition to significantly outperform one-shot methods in complex 3D environments.
