· 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] Rethinking Generalized BCIs: Benchmarking 340,000+ Unique Algorithmic Configurations for EEG Mental Command Decoding
Robust decoding and classification of brain patterns measured with electroencephalography (EEG) remains a major challenge for real-world (i.e. outside scientifi...
- · ai
AWS launches new Nova AI models and a service that gives customers more control
Amazon Web Services announced four new AI models within its Nova model family and a frontier model service....
- · 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] Flexible Gravitational-Wave Parameter Estimation with Transformers
Gravitational-wave data analysis relies on accurate and efficient methods to extract physical information from noisy detector signals, yet the increasing rate a...
- · ai
[Paper] Pruning AMR: Efficient Visualization of Implicit Neural Representations via Weight Matrix Analysis
An implicit neural representation (INR) is a neural network that approximates a spatiotemporal function. Many memory-intensive visualization tasks, including mo...
- · ai
Leak reveals Apple Health app might soon connect to ChatGPT
AI chatbots have become a go-to source for many users’ health and fitness questions, and a new leak reveals that ChatGPT might soon be able to integrate your Ap...
- · ai
[Paper] Lumos: Let there be Language Model System Certification
We introduce the first principled framework, Lumos, for specifying and formally certifying Language Model System (LMS) behaviors. Lumos is an imperative probabi...
- · 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...