· ai
[Paper] In-Context Sync-LoRA for Portrait Video Editing
Editing portrait videos is a challenging task that requires flexible yet precise control over a wide range of modifications, such as appearance changes, express...
-
- · ai
[Paper] U4D: Uncertainty-Aware 4D World Modeling from LiDAR Sequences
Modeling dynamic 3D environments from LiDAR sequences is central to building reliable 4D worlds for autonomous driving and embodied AI. Existing generative fram...
- · ai
[Paper] InEx: Hallucination Mitigation via Introspection and Cross-Modal Multi-Agent Collaboration
Hallucination remains a critical challenge in large language models (LLMs), hindering the development of reliable multimodal LLMs (MLLMs). Existing solutions of...
- · ai
[Paper] Contextual Image Attack: How Visual Context Exposes Multimodal Safety Vulnerabilities
While Multimodal Large Language Models (MLLMs) show remarkable capabilities, their safety alignments are susceptible to jailbreak attacks. Existing attack metho...
- · ai
[Paper] BEVDilation: LiDAR-Centric Multi-Modal Fusion for 3D Object Detection
Integrating LiDAR and camera information in the bird's eye view (BEV) representation has demonstrated its effectiveness in 3D object detection. However, because...
- · ai
[Paper] A Lightweight Real-Time Low-Light Enhancement Network for Embedded Automotive Vision Systems
In low-light environments like nighttime driving, image degradation severely challenges in-vehicle camera safety. Since existing enhancement algorithms are ofte...
- · ai
[Paper] Layout Anything: One Transformer for Universal Room Layout Estimation
We present Layout Anything, a transformer-based framework for indoor layout estimation that adapts the OneFormer's universal segmentation architecture to geomet...
- · ai
[Paper] Benchmarking Scientific Understanding and Reasoning for Video Generation using VideoScience-Bench
The next frontier for video generation lies in developing models capable of zero-shot reasoning, where understanding real-world scientific laws is crucial for a...
- · ai
[Paper] EGGS: Exchangeable 2D/3D Gaussian Splatting for Geometry-Appearance Balanced Novel View Synthesis
Novel view synthesis (NVS) is crucial in computer vision and graphics, with wide applications in AR, VR, and autonomous driving. While 3D Gaussian Splatting (3D...
- · ai
The Great Equaliser
The corner shop that predicts your shopping habits better than Amazon. The local restaurant that automates its supply chain with the precision of McDonald's. Th...
- · ai
[Paper] Real-Time Multimodal Data Collection Using Smartwatches and Its Visualization in Education
Wearable sensors, such as smartwatches, have become increasingly prevalent across domains like healthcare, sports, and education, enabling continuous monitoring...
- · software
How to Fix Crooked Documents Before OCR Runs
!Cover image for How to Fix Croanged Documents Before OCR Runshttps://media2.dev.to/dynamic/image/width=1000,height=420,fit=cover,gravity=auto,format=auto/https...