Search papers, labs, and topics across Lattice.
100 papers published across 4 labs.
Bias detection in neural networks can be revolutionized by analyzing latent spaces and activations, revealing how biases are embedded in model architecture itself.
MF-VPD reduces model parameters by nearly 77% while boosting performance in visual perception tasks, making it a game-changer for efficient AI applications.
Small forward-marginal errors can mask significant numerical instability in diffusion sampling, leading to misleading conclusions about model performance.
BioModule transforms any 3D pose estimator into a tool for biomechanical analysis, bridging the gap between geometric accuracy and physical interpretability.
ProsMAE outperforms traditional methods by leveraging diverse histopathology datasets to significantly improve ISUP grade classification accuracy.
MF-VPD reduces model parameters by nearly 77% while boosting performance in visual perception tasks, making it a game-changer for efficient AI applications.
Small forward-marginal errors can mask significant numerical instability in diffusion sampling, leading to misleading conclusions about model performance.
BioModule transforms any 3D pose estimator into a tool for biomechanical analysis, bridging the gap between geometric accuracy and physical interpretability.
ProsMAE outperforms traditional methods by leveraging diverse histopathology datasets to significantly improve ISUP grade classification accuracy.
QR codes can now be secured against spoofing attacks with a dual-mode architecture that balances offline integrity and real-time validation.
SAM-MT decouples latency from target count, enabling real-time video segmentation that rivals single-target performance even with multiple objects in view.
PanoLOG's innovative partitioning strategy transforms panoramic 3D reconstruction, achieving top-tier rendering quality while slashing computational costs.
Event-based lip reading accuracy improves dramatically when leveraging viseme-aware temporal modeling, revealing the critical role of motion trajectories in distinguishing lip movements.
Fine-grained textual cues can dramatically improve face attack detection, revealing vulnerabilities in existing systems that rely solely on visual data.
UAV-OVVIS enables flexible target detection in UAV videos, outperforming traditional methods by allowing open-vocabulary queries for instance-level segmentation.
Canvas360 not only redefines panoramic generation with geometry-aware techniques but also delivers a dataset of 1 million samples that transforms how we approach in-context tasks.
By leveraging outdated DEMs, this framework achieves real-time, high-fidelity 3D terrain reconstruction, transforming wildfire hazard assessments.
A novel AI-driven approach reveals that targeted facial stimuli can significantly enhance the detection of perceptual differences between autistic and neurotypical individuals.
Surpassing larger models, this agent achieves 91.4% retrieval accuracy in long-horizon multimodal dialogues by leveraging episodic memory for efficient context management.
An ensemble approach combining U-Net and a geospatial model can accurately predict viticulture potential, outperforming traditional assessment methods.
A single DNN model can dynamically adjust input resolution for LiDAR object detection, achieving superior performance and efficiency in real-time applications.
A unified benchmark that evaluates federated learning in medical imaging across multiple organs reveals critical gaps in existing assessments and emphasizes the need for efficiency and privacy metrics.
Structured distribution shifts can significantly impair TWR HAR performance, but a new theoretical framework reveals how to enhance generalization across varying conditions.
ConRad boosts the efficiency of radiomic feature predictions by integrating segmentation boundary uncertainty, offering a game-changing approach to clinical imaging reliability.
Information restriction is the key to understanding how diffusion models can generalize rather than memorize, revealing a precise phase boundary that could transform generative AI practices.
Vision-language models struggle with safety-critical reasoning, but AUTOPILOT-VQA reveals their limitations in understanding real-world driving incidents.
Track2Map achieves real-time 3D reconstruction in robotic surgery, even when camera trajectory data is unreliable or missing.
VocaDet enables open-vocabulary object detection that evolves with user input, achieving high performance without retraining the model.
Roop's face-swapping model achieves a breakthrough in balancing pedestrian privacy and data usability, outperforming existing methods.
MobiDiff achieves a 5.3x speedup in generating synthetic mobility data while maintaining high fidelity to real-world patterns.
A novel hybrid approach boosts rare-class instance segmentation performance by up to 9.5 AP points by intelligently combining T2I generation with context-aware I2I editing.
State-of-the-art performance in endoscopic referring segmentation is now achievable through a novel attribute retrieval approach, transforming how we interpret complex medical imagery.
Classical symmetry scoring methods can rival deep learning approaches in performance while being orders of magnitude faster, challenging the assumption that deeper networks always outperform traditional techniques.
LightCrafter achieves superior video relighting by integrating PBR with diffusion models, enabling intricate lighting control and long-form temporal consistency without the need for extensive training data.
Vision Transformers outperform CNNs in modeling human texture perception, revealing a fundamental shift in how we understand visual processing in AI.
ARGUS achieves up to 97% tracking accuracy in under a minute, revolutionizing automated cell tracking without the need for training data or GPU support.
Integrating geographical encoding with a robust data quality assessment reduces poverty prediction errors by nearly 19% in satellite imagery analysis.
Traditional generative models struggle with subtle neurodegenerative changes, but Latent Drift captures clinically relevant progression by focusing on compressed semantic representations.
Multimodal queries in UAV imagery can significantly reduce visual-query ambiguity and improve target localization across diverse scenarios.
Multi-deformation modeling can be achieved more effectively by choosing the right integration strategy, impacting the robustness of dynamic scene reconstruction.
HSA achieves up to 41.5% improvement in scene decomposition accuracy by leveraging hierarchical semantic understanding with minimal labeled data.
Adapting pretrained models on-the-fly to ever-changing data distributions could redefine how we deploy AI in dynamic environments.
SkelGen4D achieves high-quality text-driven mesh animation without the burden of extensive skeleton annotations, outperforming fully supervised models.
StatLUT achieves artifact-free photorealistic style transfer by decoupling color and structure, outperforming state-of-the-art methods in visual fidelity.
GRE-Diff enables users to create and refine apartment layouts interactively, merging AI efficiency with human creativity in unprecedented ways.
LUMI revolutionizes lossless image compression by decoupling it from tokenizer behavior, achieving superior performance with a unified approach across different LLM architectures.
Performance claims in colonoscopy polyp segmentation may be misleading, with a single metric shift altering the perceived best model.
Achieving a superior balance between domain consistency and information preservation in joint distribution modeling could redefine approaches to unpaired data scenarios.
Achieving state-of-the-art accuracy in RGB-Thermal video object detection, DHNet tackles spatial misalignment with innovative dual-correlation learning.
EVIS bridges the gap between simulation and real-world event-camera data, enabling rapid prototyping and testing for robotics without the costly data collection process.
SAGA boosts temporal stability in autoregressive video generation, achieving a remarkable increase in temporal quality from 97.30 to 97.91 without retraining.
Textual prompts can revolutionize object detection in aerial imagery, enabling models to adaptively focus on complex scenes with unprecedented accuracy.
RadLoc achieves unprecedented speed and robustness in radar-based global localization, outperforming state-of-the-art methods while using the smallest descriptor size.
Traditional tetrahedralization is error-prone, but HoloTetSphere achieves a unified, coherent mesh that enhances physical simulation accuracy.
ZipDepth achieves real-time monocular depth estimation on resource-constrained devices while rivaling the accuracy of much larger models.
Wat3R achieves superior underwater 3D geometry estimation without any annotated data, leveraging unlabeled footage to overcome the challenges of light attenuation and scattering.
A frozen CT-CLIP model can outperform traditional clinical baselines in lung cancer survival prediction, even with limited data.
Higher input resolution can hinder segmentation performance for larger diabetic retinopathy lesions, challenging the assumption that more detail is always better.
Models trained with hand-object masked strategies can achieve superior HOI recognition by effectively isolating and utilizing hand- and object-centric cues.
Whareformer outperforms prior models in tracking occluded objects in egocentric videos, achieving state-of-the-art results with minimal training data.
GenRes++ not only detects AI-generated images but also adapts to multiple transformations, outperforming existing methods by focusing on the most informative features.
HumanForge reveals that existing benchmarks fall short in capturing the complexities of human interactions in video forensics, exposing critical gaps in current detection capabilities.
Long-term identity preservation in multi-object tracking is far more challenging than previously understood, with all tested methods exhibiting substantial fragmentation in trajectories.
LongE2V achieves unprecedented temporal coherence in video reconstruction from sparse event data, outperforming all existing methods.
OPSD-V enhances video generation by leveraging real video data for on-policy self-distillation, leading to superior visual quality and motion dynamics.
Diverse temporal supervision can dramatically enhance video reasoning capabilities, outperforming traditional methods by leveraging the Chain-of-Frame approach.
Integrating physics into deep learning models can dramatically boost fuel density prediction accuracy and stability, outperforming conventional data-driven approaches.
PET-guided MRI translation can achieve unprecedented accuracy in lesion detection and representation, transforming clinical imaging practices.
Bridging satellite imagery with street-level semantics boosts urban carbon emission predictions, achieving superior accuracy without needing ground-level data at inference.
Radiology's Vision Foundation Models show promise, but their clinical impact is stymied by inconsistent evaluation practices and data limitations.
A balanced-test score can mislead operational performance assessments by over 60%, revealing a critical need for prior-matched evaluation in rare-event detection.
Mixed-state quantum diffusion can effectively bridge the gap between classical data and quantum generative models, enabling efficient image generation with reduced qubit requirements.
In the most challenging crowd scenarios, a point-based counter outperforms traditional detection and segmentation methods, revealing a critical insight for real-world applications in crowd management.
Agentic AI struggles with computational imaging tasks, revealing a stark divide between visual plausibility and physical fidelity.
Occluded content in image editing can be accurately restored by grounding preservation in historical context, rather than just the current frame.
Self-supervised pretraining not only boosts segmentation accuracy but also enables consistent performance across diverse forest types and scales.
LoCA achieves state-of-the-art performance in vision tasks while preserving spatial priors, revolutionizing how we adapt convolutional models without full fine-tuning.
SAR-derived textures are the game-changer for accurately mapping informal settlements, achieving over 81% accuracy even in challenging conditions.
Rectifying off-manifold samples to a stable semantic manifold can dramatically enhance object detection performance in unseen domains.
Adaptive weighting of shape and texture features in cardiac video classification leads to state-of-the-art performance and enhanced interpretability of critical cardiac phases.
VCDP transforms semi-supervised medical image segmentation by aligning voxel embeddings with both global organ identities and local anatomical variations, leading to superior performance on challenging segmentation tasks.
Over 1,100 submissions reveal groundbreaking advancements in sports video understanding, with new methods pushing the boundaries of action prediction and localization.
EP-SAM outperforms traditional SAM methods by effectively addressing contour ambiguity in ultrasound images through innovative edge-aware supervision.
Bias detection in neural networks can be revolutionized by analyzing latent spaces and activations, revealing how biases are embedded in model architecture itself.
Achieving accurate video object segmentation without manual labels, this framework outperforms traditional methods by maintaining both spatial and temporal coherence.
Uncovering the hidden semantic vocabulary of deepfake detectors transforms our understanding of how these models differentiate between real and fake content.
EditVerse3D achieves high-fidelity 3D object edits using only coarse region specifications, outperforming traditional methods that require precise inputs.
Achieving clinical-grade segmentation accuracy on standard CPU workstations in under 45 seconds could revolutionize body composition analysis in healthcare settings.
Personalized text-to-image generation can achieve unprecedented quality by combining stage-aware adaptation with intelligent candidate selection, revealing a nuanced trade-off between identity consistency and representation diversity.
Achieving over 96% of fully supervised segmentation performance with less than 0.6% of annotated data could revolutionize the efficiency of material screening in research.
Explicitly coupling geometry and appearance can dramatically enhance the robustness of 3D reconstruction against pose drift in long sequences.
ASFR-Net not only bridges the gap between different imaging modalities but also sets a new benchmark for heterogeneous change detection with its innovative spatio-frequency processing.
Traditional segmentation methods fail to preserve topological integrity, but a new approach focusing on connectivity bottlenecks boosts accuracy by over 7 percentage points.
Achieving over 98% accuracy in squint and cataract detection, this system could revolutionize accessibility in web interfaces for the visually impaired.
ColorFM achieves a breakthrough in color transfer by seamlessly integrating optimization with learning, delivering unmatched visual quality and semantic fidelity.
Rethinking intraoperative imaging from "data completeness" to "data sufficiency" could revolutionize how we balance image quality, procedure time, and radiation exposure in clinical settings.
HPR-SAM outperforms existing methods by effectively capturing complex anatomical representations, achieving state-of-the-art results in medical image segmentation without the need for prompts.
Context-sensitive failures in glioma segmentation models can be identified and quantified, revealing vulnerabilities that standard metrics miss.
SHTA achieves significant improvements in segmentation accuracy by ensuring semantic consistency in challenging regions, all without increasing inference costs.
Achieving precise 3D heart reconstructions from sparse MRI data, Bi-PT redefines the potential for cardiac imaging in clinical settings.
SpiS-GAN generates highly authentic handwriting that preserves original styles while significantly improving recognition accuracy across languages.
Multi-view analysis of μUS data can dramatically enhance prostate cancer detection, outperforming traditional methods and expert assessments.
High-resolution chest X-ray perception can be achieved without inflating token counts, leading to better diagnostic accuracy and report generation.
Combining audio and visual analysis in a unified ensemble model boosts deepfake detection accuracy and generalization across diverse manipulations.
Current dense predictors can deviate by over 3x from accurate predictions when faced with unsupported edge cues, revealing a fundamental flaw in their design.
