Researchers at the University of Oxford have introduced DynPoint, an artificial intelligence algorithm that enables the rapid synthesis of novel views for unconstrained monocular videos. DynPoint employs explicit estimation of consistent depth and scene flow for surface points, creating a hierarchical neural point cloud to generate views of the target frame. The proposed model demonstrates…

This research paper introduces a method called “codebook features” that aims to enhance the interpretability and control of neural networks. By leveraging vector quantization, the method transforms the dense and continuous computations of neural networks into a more interpretable form by discretizing the network’s hidden states. The experiments conducted demonstrate the effectiveness of codebook features…

Researchers from the University of Tokyo have developed a deep learning model called 3D-Memory In Memory (3D-MIM) to accurately predict the expansion of supernova (SN) shells in galaxy simulations. By combining the model with the Hamiltonian splitting method, the researchers can integrate SN-affected particles separately. The 3D-MIM model shows strong generalization capabilities and offers a…

Big language models (LLMs) are becoming skilled in programming and refactoring code to create libraries for software developers. Researchers from MIT CSAIL, MIT Brain and Cognitive Sciences, and Harvey Mudd College present LILO, a neurosymbolic framework that integrates LLMs with automatic refactoring to learn libraries of reusable function abstractions. LILO demonstrates improved performance compared to…

The ControlLLM framework, developed by researchers from The Hong Kong University of Science and Technology, OpenGVLab, Shanghai AI Laboratory, Tsinghua University, and SenseTime, enables large language models (LLMs) to utilize multi-modal tools for solving complex real-world tasks. ControlLLM excels in accuracy, efficiency, and versatility, surpassing existing methods in various tasks involving image, audio, and video…

Cohere’s Embed v3 model is a valuable solution for finding relevant and informative content in text data. It outperforms other models in benchmark tests and offers efficient navigation through vast amounts of information. Supporting over 100 languages, Embed v3 enhances search applications and retrieval-augmented generative AI systems.

AI-generated counterfeit nudes of students from Westfield High School in New Jersey, US, were distributed among peers. The school has not disclosed specific details or taken disciplinary action, citing confidentiality concerns. Similar incidents have occurred in Spain and involved public figures and online influencers. New Jersey lacks legislation to penalize the creation and distribution of…

Hollywood’s Screen Actors Guild-American Federation of Television and Radio Artists (SAG-AFTRA) is dissatisfied with the latest proposal from the Alliance of Motion Picture and Television Producers (AMPTP) in ongoing labor discussions. The sticking point is the use of AI in the industry. SAG-AFTRA remains uncertain if AMPTP will re-enter negotiations or cease discussions entirely. The…

Researchers have developed a framework called Language Models for Motion Control (LaMo) that incorporates Large Language Models (LLMs) for offline reinforcement learning. LaMo combines pre-trained LLMs with Decision Transformers (DT) and introduces innovations like LoRA fine-tuning and auxiliary language loss. It outperforms existing methods in sparse-reward tasks and narrows the gap between value-based offline RL…