Search papers, labs, and topics across Lattice.
100 papers published across 9 labs.
Achieving over 4600x speedup in OTA design without sacrificing accuracy could revolutionize circuit modeling practices.
CanvasAgent can adapt its tool decisions in real-time, significantly improving the quality and coherence of complex image creations.
Light-Omni achieves a remarkable 12.1× speedup in video understanding while enhancing accuracy, redefining efficiency in agentic video processing.
SynCity 3000 can generate intricate 3D scenes from a single image, overcoming the limitations of traditional methods in scene coherence and detail.
Cortex outperforms traditional models by enabling zero-shot execution of complex long-horizon tasks, bridging the gap between high-level planning and low-level execution.
Achieving over 4600x speedup in OTA design without sacrificing accuracy could revolutionize circuit modeling practices.
CanvasAgent can adapt its tool decisions in real-time, significantly improving the quality and coherence of complex image creations.
Light-Omni achieves a remarkable 12.1× speedup in video understanding while enhancing accuracy, redefining efficiency in agentic video processing.
SynCity 3000 can generate intricate 3D scenes from a single image, overcoming the limitations of traditional methods in scene coherence and detail.
Cortex outperforms traditional models by enabling zero-shot execution of complex long-horizon tasks, bridging the gap between high-level planning and low-level execution.
A unified pixel-space approach in PixWorld achieves superior 3D scene generation and reconstruction without the pitfalls of latent encoding.
Merging image tokens intelligently can cut storage costs by over 16 times while boosting retrieval accuracy, challenging the notion that less data always means less context.
Boundary-centric pretraining can dramatically enhance depth estimation, a critical capability for embodied AI systems.
Robots can now autonomously adapt to camera changes without needing explicit calibration, significantly improving deployment flexibility.
Non-contact video monitoring can detect apnoea-related breathing cessation in pre-term infants with surprising accuracy, outperforming traditional methods.
Hyperbolic vision-language models fail to leverage their geometric potential, operating instead in near-Euclidean space, which undermines their hierarchical claims.
FUSE resolves complex parameter degeneracies in exoplanet orbital estimation, outperforming state-of-the-art methods and closely matching ground-truth MCMC results.
SSL representations of satellite imagery can reveal hidden environmental associations that significantly impact downstream task performance.
Unimodal deep ensembles can outperform late-fusion networks in multimodal classification, even under severe modality imbalance.
KinEMbed achieves unprecedented accuracy in decoding hand kinematics from EMG, outperforming established methods and paving the way for advanced prosthetic control.
No existing model editing method consistently outperforms others in the complex landscape of medical VLMs, revealing significant trade-offs in reliability and generalizability.
TacReasoner outperforms larger models in tactile reasoning tasks, achieving competitive results with fewer parameters.
Memory-augmented pose estimation can dramatically improve generalization across diverse object instances, outperforming traditional methods by leveraging accumulated geometric knowledge.
DSWAM bridges the gap between coarse user commands and fine-grained robot actions, outperforming traditional models in real-world task execution.
A new dataset, SynSFX, reveals that existing audio deepfake detectors struggle with generalization to synthetic sound effects, highlighting a critical gap in current research.
EventCoT achieves state-of-the-art RTL performance with fewer visual tokens, revolutionizing how we approach temporal reasoning in videos.
Learning motion latents through geometric prediction enables robots to manipulate objects robustly in cluttered environments with minimal prior demonstrations.
Even the best multimodal models struggle to reconstruct complex interactive dashboards, revealing a critical gap in current capabilities.
RABBiT can accurately predict brain responses to speech with just 10 minutes of participant data, outperforming traditional models and enabling scalable population-level studies.
Faithful reasoning in VLA models can boost policy responsiveness to rare scenarios by 1.6x compared to state-of-the-art approaches, revealing a critical gap in current alignment strategies.
Local-Preserving Supervised Fine-Tuning can enhance model performance without sacrificing the rich diversity of pretrained knowledge, achieving superior results in both accuracy and diversity metrics.
Routing a teacher's knowledge across model components can outperform traditional encoder-based approaches in audio captioning.
Pre-generation signals can predict failure sources in vision-language models, enabling targeted interventions before answers are generated.
Observation-Aligned supervision reveals that traditional chart-to-code training often leads to hallucinations, and aligning targets with identifiable quantities can dramatically improve model performance.
Relationship-aware 3D scene understanding can significantly enhance open-vocabulary segmentation, outperforming traditional methods that ignore object relationships.
Unaudited labels can inflate VLM accuracy by up to 17 percentage points, revealing critical flaws in current evaluation practices for industrial AI systems.
A new typology reveals that the coherence of chart-image pairs in scientific communication can significantly impact how experts and non-experts interpret data.
FlowMark achieves robust video watermarking without user input, embedding messages seamlessly even through common video edits and social media re-encoding.
UNIVERSE achieves a remarkable 4.3× speedup in trajectory inference while maintaining planning accuracy, revolutionizing how video dynamics inform autonomous driving actions.
Achieving over 42% recall in semantic video communication could redefine how we transmit meaning in bandwidth-limited networks.
AI-driven sperm analysis could revolutionize male infertility diagnostics by providing objective, reproducible results that surpass traditional methods.
Interactive visualizations of LLM outputs can transform how users engage with complex information, allowing for targeted exploration without the need to sift through dense text.
Collateral damage in concept erasure is significantly reduced, allowing for precise edits without compromising related visual information.
GUSH3R achieves real-time dynamic human-scene reconstruction with photorealistic quality, outperforming traditional optimization methods in efficiency.
FSDC-DETR boosts small object detection performance by over 6 AP points, leveraging a unique frequency-spatial collaborative approach that preserves high-frequency details.
FressDet achieves state-of-the-art multispectral object detection while using 93% fewer parameters, revolutionizing efficiency in the field.
Integrating semantic guidance into BEV instance prediction significantly boosts performance, proving that understanding object-specific behavior is crucial for autonomous driving.
Decoupling geometry from semantics in surgical scene understanding leads to unprecedented robustness in 4D reconstruction, even amidst drastic tissue changes.
Anticipatory driving capabilities in autonomous vehicles can now be achieved without compromising safety, thanks to a new framework that adapts to real-time road conditions.
RADIANCE boosts the success rate of synthesizing rare concepts in text-to-image models by effectively rebalancing denoising trajectories without additional training.
LangLoc achieves unprecedented accuracy in indoor localization from natural language, closing the gap between coarse scene retrieval and precise pose estimation.
Visual grounding can cut waypoint error by up to 44% in VLA navigation, especially for longer instructions, without the need for model retraining.
Achieving a harmonious balance between temporal consistency and editability in video editing could redefine standards in text-guided video manipulation.
Achieving superior anatomical consistency in multi-view spine imaging without explicit 3D reconstruction could revolutionize diagnostic practices.
A hybrid deep learning approach boosts slate tile classification accuracy by over 10%, revolutionizing quality control in the industry.
Structural preservation in low-light image enhancement can be dramatically improved by leveraging depth cues, as shown by DMSA-Net's superior performance on benchmark datasets.
3DMPE reconstructs 3D point clouds from incomplete 2D views without the need for training data, setting a new standard for geometric reconstruction methods.
Composing concepts as separate image layers in LILAC eliminates identity confusion in multi-concept diffusion models, achieving superior results without joint retraining.
Achieving a 6.37x speedup in inference while expanding OCR capabilities across long-tail tasks sets a new benchmark for lightweight models.
Model merging can drastically enhance continual learning for survival analysis, outperforming traditional methods while preserving privacy and reducing costs.
Explicitly modeling relational interactions in visual representations boosts weakly supervised referring expression comprehension to new heights.
High-CFG diffusion inversion can fail dramatically depending on the prompt-latent pairing, revealing a nuanced landscape of reconstruction success that challenges existing assumptions.
Achieving superior spatio-temporal action detection with a lightweight framework that outperforms heavy transformer models while reducing computational costs.
A single LoRA can achieve superior style transfer results by effectively integrating content and style without the conflicts of multiple adapters.
TAO transforms the way we handle overconfident visual recognition failures, ensuring robust performance in real-time robotic applications.
Transforming image generation into a dynamic feedback system yields up to 25.36% better facial similarity and significant spatial error reductions without any training.
Role-aware training can boost video diffusion models' physical consistency by up to 39.4% without sacrificing visual fidelity.
Incorporating device-specific viewing conditions can dramatically enhance the accuracy of video quality assessments, bridging the gap between lab results and real-world experiences.
Modern video generation models can inherently estimate dynamic lighting, producing HDR environment maps that are both temporally coherent and physically plausible.
Direct composition learning in DiCE-CIR achieves state-of-the-art zero-shot image retrieval without the overhead of projection methods, streamlining the process significantly.
PixelPilot redefines trajectory prediction in autonomous driving by transforming it into scalable 2D tasks, leading to unprecedented generalization across heterogeneous datasets.
SAYRE's innovative approach to synthesizing KIE training data leads to substantial performance gains for on-device models, particularly in challenging extraction scenarios.
Compact imaging systems can now achieve full-resolution 5D spectral light field recovery without the bulk of traditional camera arrays.
Policies trained on PRISM-generated datasets achieve unprecedented success rates in real-world tasks, outperforming traditional dataset methods by a wide margin.
HIEVI-RAG's innovative four-stage reasoning pipeline significantly boosts accuracy in long-document understanding, outperforming existing methods by over 8%.
Achieving 89% constraint satisfaction in graphic design edits, StructuredEdit outperforms existing models while drastically reducing editing time and correction iterations.
Achieving state-of-the-art lensless image reconstruction, IFIN leverages a unique bidirectional coupling of forward and inverse processes to enhance data fidelity and adaptability.
Achieving 96.3% accuracy in texture recognition with a neuromorphic system that consumes just 19.6 mW challenges the conventional power-performance trade-offs in robotic perception.
Heading estimation can now be dynamically refined in challenging environments, drastically reducing drift and improving accuracy during GNSS outages.
Extracting interaction cues from a frozen video model enables robots to achieve up to 90.6% success in manipulation tasks without costly rollout processes.
SEAM reduces boundary jerk by 28% and transition discontinuity by 27%, all while preserving task success and computational efficiency.
Context-gated latent-action conditioning enables VLA models to achieve unprecedented success rates in robot manipulation tasks without relying on separate action-generation modules.
Generators can dramatically improve their performance on long-tailed visual requests by leveraging a teach-then-search co-training approach, overcoming a critical knowledge boundary.
TimeThink revolutionizes video reasoning by enabling models to pinpoint relevant temporal evidence with unprecedented accuracy, outperforming existing approaches.
VLMs struggle with raw medical data, achieving only a 48.6% success rate in standardization, revealing a critical gap in their clinical applicability.
SCALA achieves human-level sample efficiency by mimicking cognitive selectivity, allowing models to excel in visual recognition with minimal data.
Prompt-based continual learning can now capture diverse image distributions, overcoming the limitations of prompt collapse that hinder performance across tasks.
CuRe transforms video captioning reward design by shifting from holistic evaluations to precise claim-level verification, significantly boosting factual accuracy and diversity in generated captions.
Dynamic gating allows DGSeg to filter out noise and ambiguity in segmentation cues, leading to superior performance in reasoning segmentation tasks.
Surpassing human performance in gaze estimation, PaGE closes the human-AI gap by over 60% while remaining lightweight for real-world applications.
WildSplat achieves state-of-the-art novel view synthesis from unposed images by effectively decoupling geometry and appearance, even under challenging lighting conditions.
Unsupervised learning can achieve high-quality pixel-level semantic left-right predictions in images, even for entirely unseen object categories.
CLIPix transforms CLIP's image-level capabilities into precise pixel-level localization, achieving state-of-the-art segmentation performance on benchmark datasets.
Self-supervised learning from monocular videos can now achieve superior stereo video generation by directly computing disocclusion masks, eliminating reliance on expensive stereo datasets.
M-agents harbor 158 unique implementation bugs that could lead to critical failures in real-world applications, and a new tool can identify over 60% of these issues automatically.
Audex achieves state-of-the-art audio understanding and generation while maintaining the reasoning prowess of its text-only foundation, all through a unified architecture.
MV-Forcing enables the generation of long, multi-view videos with geometric consistency, overcoming the limitations of current video synthesis methods.
By preserving the semantics of pretrained models while achieving superior compositional generalization, InternVLA-A1.5 redefines how robots can learn and execute complex tasks.
Vandalism attacks can cripple AV perception, but the REVIVE framework restores detection performance to near-original levels, even under severe occlusion.
IFGRVFL-MV achieves superior classification accuracy by effectively integrating intuitionistic fuzzy logic and graph embeddings, challenging traditional RVFL limitations.
Hierarchical multi-label classification techniques can boost CXR diagnostic accuracy by over 12%, transforming automated disease detection in radiology.
Hierarchical modeling of 3D facial geometry reveals significant insights into phenotype classification, but struggles with rare conditions highlight critical gaps in current methodologies.
Current MLLMs struggle with Bangla form comprehension, missing key granular details that could hinder their real-world application in low-resource languages.
Achieving a COMET score of 0.781 in EN-ZH speech translation highlights the effectiveness of synthetic data in enhancing instruction-following capabilities in multimodal models.
Transforming malware binaries into images using Hilbert curves and entropy features leads to state-of-the-art detection performance, even in few-shot learning scenarios.
