Search papers, labs, and topics across Lattice.
Simple ensemble methods leveraging rich textual context can outperform state-of-the-art multimodal forecasting approaches on a new benchmark, TimesX, revealing hidden vulnerabilities in existing evaluations.
Gemma 4's unified architecture and reasoning mode enable it to outperform larger models in human-rated tasks while maintaining high efficiency.
Task-specific audio perturbations can boost model accuracy by over 6% and reduce hallucinations in large audio-language models.
Triangle splats from video diffusion latents yield superior geometric accuracy and visual quality, challenging the dominance of volumetric 3D Gaussians in scene generation.
WEQA achieves a 24% accuracy boost in wearable health question answering by dynamically adapting to the complexities of sensor data and user queries.
VisualClaw slashes API costs by 98% while boosting accuracy, transforming how VLMs can operate in real-time environments.
No single model dominates video embedding tasks, revealing stark contrasts in performance based on modality and task type.
Autoregressive policies can achieve real-time execution with superior performance and speed, challenging the dominance of diffusion-based approaches.
VLMs struggle with procedural 3D modeling, often producing flawed outputs due to API mismatches and geometric disconnections, but performance can be significantly boosted through iterative refinement.
Ditch the brittle code synthesis and noisy gradients: LiveSVG unlocks high-quality SVG animations by directly fitting vector graphics to reference videos generated from motion prompts.
PARCEL redefines visual tokenization, achieving superior efficiency and performance by dynamically anchoring feature extraction to spatial pool tokens.
Imagine telepresence where your avatar convincingly blends into any environment, relit in real-time based on the scene's actual lighting, all from a single headset.
Forget handcrafted prompts: a hierarchical multi-agent framework turns diffusion models into coherent storytelling engines by globally optimizing for semantic coherence.
Current remote sensing change captioning datasets miss fine-grained localized semantic reasoning, but RSRCC fills this gap with 126k change-specific questions.
LVLMs can self-detect and correct object hallucinations by focusing on specific image regions, offering a simple, training-free fix.
Generating consistent visual narratives is now possible: CANVAS outperforms existing methods by explicitly planning character, background, and scene continuity across multiple shots.
Achieve world-consistent video generation by directly optimizing geometry in the latent space of pre-trained video diffusion models, sidestepping costly RGB-space operations and architectural changes.
MLLMs are surprisingly prone to hallucinating subtle details, especially when asked about the absence of specific attributes or relationships within an image.
Imagine an XR experience where you can selectively isolate and enhance individual sound sources in real-time, making chaotic audio environments crystal clear.
Forget local semantic alignment: CAST unlocks temporally coherent video retrieval and generation by explicitly modeling visual state transitions.
AI-generated videos can now respect physics, thanks to a framework that uses a physical simulator to guide diffusion models, resulting in more realistic and coherent motion.
Multimodal web agents are surprisingly vulnerable to cross-modal attacks, but a novel adversarial training approach can double task completion efficiency while mitigating these risks.
Existing deforestation monitoring maps misclassify smallholder agroforestry as "forest," risking unfair penalties under regulations like the EUDR.
