Film-maker James Cameron and Disney are being sued by an actress who has accused the director of using her likeness as the basis for one of the lead characters in his hit film series Avatar. German-born US actress Q'orianka Kilcher, who is of indigenous Peruvian descent, alleged that in 2005 - when she was 14 - Cameron extracted her facial features from a photograph of her portraying Pocahontas in another film, The New World. In court documents filed on Tuesday in California, her team claimed Cameron directed his design team to use it as the foundation for the character of Neytiri, depicted on screen by Zoe Saldaña. BBC News has contacted Cameron and Disney for a comment. The Avatar movies contain a hybrid of live-action performance mixed with computer-generated characters.

Evaluating large language models (LLMs) is challenging.

Our insight is that satellite's earth observation photos are not just images

Neural Information Processing Systems http://nips.cc/

In this paper, we propose SAPipe, a performant system that pushes the training speed ofdata parallelism toitsfullest extent.

Data parallelism across multiple machines is widely adopted for accelerating distributed deep learning, but it is hard to achieve linear speedup due to the heavy communication. In this paper, we propose SAPipe, a performant system that pushes the training speed of data parallelism to its fullest extent.

Machine unlearning aims to remove the influence of specific data points from a trained model to satisfy privacy, copyright, and safety requirements. In real deployments, providers distribute a global model to many edge devices, where each client personalizes the model using private data. When a deletion request is issued, clients may ignore it or falsely claim compliance, and providers cannot check their parameters or data. This makes verification difficult, especially because personalized models must forget the targeted samples while preserving local utility, and verification must remain lightweight on edge devices. We introduce ZK APEX, a zero-shot personalized unlearning method that operates directly on the personalized model without retraining. ZK APEX combines sparse masking on the provider side with a small Group OBS compensation step on the client side, using a blockwise empirical Fisher matrix to create a curvature-aware update designed for low overhead. Paired with Halo2 zero-knowledge proofs, it enables the provider to verify that the correct unlearning transformation was applied without revealing any private data or personalized parameters. On Vision Transformer classification tasks, ZK APEX recovers nearly all personalization accuracy while effectively removing the targeted information. Applied to the OPT125M generative model trained on code data, it recovers around seventy percent of the original accuracy. Proof generation for the ViT case completes in about two hours, more than ten million times faster than retraining-based checks, with less than one gigabyte of memory use and proof sizes around four hundred megabytes. These results show the first practical framework for verifiable personalized unlearning on edge devices.