Search papers, labs, and topics across Lattice.
CGVQ achieves a remarkable 20% reduction in bits per pixel while maintaining visual quality, revolutionizing Gaussian-based image compression.
Current avatar systems are more diverse than ever, yet foundational prior learning is often overlooked in discussions of photorealistic digital humans.
Current VLMs struggle with specialized domains, failing to adapt effectively in both zero-shot and ICL scenarios, revealing critical gaps in their spatio-temporal reasoning abilities.
Dynamic token editing in image synthesis could redefine how we approach high-resolution generative models.
NeuMatEx outperforms PBR techniques by extracting complex neural materials with unprecedented visual fidelity and precision from multi-view images.
Achieving up to 1.90X speedup in video generation without sacrificing fidelity, ScalingAttention redefines efficiency in Diffusion Transformers.
Self-correcting models can achieve unprecedented fidelity and plausibility in generative tasks by actively learning from their own alignment errors.
A single-line code change can restore diversity and fidelity in video generation models, outperforming even the original teacher models.
Combining learning and geometric optimization, this framework achieves a 60.9% grasp success rate, outperforming traditional methods by a significant margin.
Real-time multi-view 3D tracking can now be achieved at scale without the computational burdens of centralized systems, thanks to a fully distributed approach.
Achieving zero-shot generalization in robotic grasping across diverse gripper designs could revolutionize how robots interact with their environments.
Grounding boosts spatial reasoning in VLMs: explicitly linking language to 2D and 3D scene elements lets models decompose complex spatial problems and improve performance even on non-grounded tasks.
Forget scaling laws: a single looped transformer block, iterated explicitly, crushes billion-parameter feed-forward networks at multi-view 3D reconstruction.
Masking just 5% of attention heads in vision-language models tanks performance on long-context tasks, revealing a surprisingly sparse and critical set of "multimodal retrieval heads" that attend to both text and images.
Get up to 1.79x faster ViT inference on high-resolution images without sacrificing accuracy by surgically replacing full-attention blocks with cheaper alternatives *after* pre-training.
Ditch slow, token-by-token box generation: LocateAnything's Parallel Box Decoding (PBD) boosts VLM grounding speed and accuracy by decoding entire bounding boxes at once.
Ditch the clunky tool-use pipelines: STORM teaches video-language models to reason about space and time using *internalized* latent trajectories, slashing inference costs while boosting accuracy.
Relight 3D assets 25x faster with a feed-forward network that distills relightable representations from large reconstruction models, sidestepping expensive per-scene optimization.
Near-field lighting? No problem: 8DNA pre-bakes complex light transport into neural representations, outperforming prior methods with faster inference and lower training costs.
Forget clunky animation pipelines – MotionBricks lets you assemble real-time, high-quality character motions like LEGOs, even controlling robots.
Open-vocabulary 3D instance segmentation just got 100x faster, thanks to a new transformer architecture that ditches region proposals and fragmented masks.
Finally, a method disentangles dynamic egocentric scenes into background, hand, and object components, enabling fine-grained understanding and editing.
Unlock the power of cutting-edge photon-counting CT imaging on your existing routine chest CT scans, boosting lesion detection by 10-15%.
Finally, a video generation model lets you puppeteer objects and their reactions independently, all while freely moving the camera.
Serving both image and video diffusion models on the same hardware? GENSERVE's step-level preemption and dynamic resource allocation can boost your service level agreement (SLA) attainment by up to 44%.
Gaussian Splatting gets a high-frequency boost: Neural Harmonic Textures unlock significantly more detail in primitive-based 3D reconstructions without sacrificing speed.
Achieve 49% and 19% better Chamfer distance than state-of-the-art dynamic surface reconstruction methods on Hi4D and CMU Panoptic datasets, respectively, by enforcing temporal consistency in Gaussian Splatting.
A hybrid cuVSLAM-based visual SLAM system achieves superior mapping accuracy in real-world logistics environments, outperforming other VO/VSLAM approaches.
Forget monolithic LoRAs: LoRWeB dynamically mixes a basis set of LoRAs to unlock SOTA generalization in visual analogy tasks.
Achieve state-of-the-art depth completion by adapting 3D foundation models at test time with minimal parameter updates, outperforming task-specific encoders that often overfit.
Forget tedious manual segmentation: ArtisanGS lets you lasso objects in 3D Gaussian Splats with AI-powered 2D selections that propagate into 3D, giving you unprecedented control over editing.
Current NVS evaluation metrics are misleading, so this paper introduces a task-aware framework using Zero123 features that actually aligns with human perception of quality and faithfulness.
Flipping just *two* sign bits in a large neural network can obliterate its performance, revealing a surprising fragility in even state-of-the-art models.
