Search papers, labs, and topics across Lattice.
12
0
9
15
Strong 3D perception and competitive motion planning in autonomous driving are achieved without sacrificing general vision-language understanding.
SimWAM achieves state-of-the-art performance in autonomous driving while eliminating the need for future video generation at inference, drastically reducing latency.
TurboVLA achieves 97.7% success in robotic manipulation while using less than 1 GB of VRAM, challenging the dominance of LLM-centric approaches.
CMAM revolutionizes text-based person retrieval by achieving granularity-aware matching that significantly outperforms state-of-the-art methods across diverse query levels.
Wat3R achieves superior underwater 3D geometry estimation without any annotated data, leveraging unlabeled footage to overcome the challenges of light attenuation and scattering.
Visual updates in DeltaV cut token generation by over half while boosting reasoning accuracy, challenging the need for full-image outputs in multimodal models.
HERMES++ achieves state-of-the-art performance in both future point cloud prediction and 3D scene understanding by unifying these tasks within a single driving world model.
DINO, not CLIP, might be the better foundation for open-set 3D object retrieval, especially when paired with dynamic view integration and virtual feature synthesis to avoid overfitting.
Doc-V* demonstrates that an agentic approach to multi-page document VQA, using active navigation and structured memory, can significantly outperform retrieval-augmented generation, especially in out-of-domain scenarios.
Text-to-video diffusion models can now count (more accurately) without retraining, thanks to a clever attention-based guidance method.
Achieve state-of-the-art 3D scene understanding by dynamically adapting network parameters at test time, proving that input-aware adjustments can significantly boost performance with minimal overhead.
World models can now remember and realistically regenerate dynamic objects that temporarily disappear from view, thanks to a novel hybrid memory architecture.
