This research introduces DISCIPL, a novel framework where language models dictate their own reasoning process for complex tasks. By having a Planner LM generate inference programs, DISCIPL orchestrates Follower LMs to solve problems, offering a more efficient and automated approach compared to existing methods like chain-of-thought or structured inference. The framework supports various inference patterns, including constrained generation and self-correction, and achieves significant performance gains on challenging tasks requiring structured reasoning and constraint satisfaction, as demonstrated through evaluations on diverse datasets. This work presents a new way to integrate code generation and probabilistic inference, enabling improved test-time adaptability for language models.

The provided text introduces Amazon Q Developer in SageMaker Canvas, a new AI tool that allows users to build and deploy machine learning models using natural language. This tool, powered by generative AI, simplifies the ML development process by automating tasks like data preparation, model selection, and training, thus requiring no specialized expertise. The article details the functionality of this agentic system, highlighting its chatbot interface and ability to guide users through the entire ML workflow, from data input to model deployment and explanation. Additionally, the source includes various job postings for Applied Scientists across different Amazon divisions, indicating active research and development in areas like machine learning, agentic AI, and personalization within the company.

This research addresses the challenge of catastrophic forgetting in large language models during continual learning, where adapting to new tasks degrades performance on old ones. To overcome this, the authors introduce a novel approach that utilizes adaptive singular value decomposition (SVD) to identify and preserve important knowledge while allowing flexible learning of new information. Their method dynamically determines task-specific low-rank parameter subspaces for updates, ensuring these updates remain orthogonal to critical directions learned from prior tasks. This constrained full fine-tuning technique achieves state-of-the-art results on various benchmarks, demonstrating effective knowledge retention and adaptation without increasing the model's parameter count or requiring storage of past gradients.

Meta AI has introduced its Llama 4 family of large language models, highlighting two new open-weight models: Llama 4 Scout and Llama 4 Maverick, along with a powerful, still-training model called Llama 4 Behemoth. These multimodal models feature innovations like Mixture-of-Experts architecture and significantly expanded context windows, outperforming previous Llama iterations and competing with or exceeding the capabilities of other leading models on various benchmarks. The release emphasizes open access, with the new models available for download and integration, aiming to foster innovation and the development of personalized AI experiences. Meta also details their approach to pre-training, post-training, and safety measures implemented in the Llama 4 series, underscoring their commitment to responsible AI development.

This paper introduces UniOcc, a new benchmark for 3D occupancy forecasting and prediction in autonomous driving. It unifies data from real-world datasets like nuScenes and Waymo with synthetic data from CARLA and OpenCOOD, providing 2D/3D occupancy labels and voxel-level flow. UniOcc also offers novel evaluation metrics that don't rely solely on imperfect ground truth and includes a toolkit for object segmentation and tracking within the voxel space, aiming to standardize and advance research in this critical area.

This research introduces a novel method for generating counterfactual explanations for graph-based predictions.The approach utilizes a permutation equivariant graph variational autoencoder (PEGVAE) to create a meaningful latent space representation of graphs. By traversing this latent space guided by the classifier, the method identifies minimally altered graphs with a different classification. This technique addresses the challenges posed by the discrete nature and permutation invariance of graphs. Experiments on molecular datasets demonstrate the method's ability to produce robust and high-performing counterfactual explanations compared to baseline approaches. The work offers a way to understand how to change a graph to alter its predicted outcome without explicitly defining a graph distance metric.

The provided research paper explores the novel problem of continual forgetting in pre-trained vision models, where the goal is to sequentially remove specific unwanted knowledge while retaining the model's performance on other tasks. To address this, the authors introduce Group Sparse LoRA (GS-LoRA++), a parameter-efficient fine-tuning approach that uses low-rank adaptation with a group sparsity regularization to selectively modify the model's feed-forward networks. Furthermore, to handle practical scenarios like scarce forgetting data, they incorporate prototype regularization to guide the forgetting process. Extensive experiments across various vision tasks demonstrate the effectiveness and efficiency of their proposed method in achieving selective and continual knowledge erasure with minimal impact on remaining knowledge.

The provided research explores optimizing communication and sensing for autonomous vehicles using millimeter wave technology and orthogonal frequency-division multiplexing. Facing dynamic environments and the impact of wireless conditions on mmWave, the authors propose an adaptive system. This system employs reinforcement learning, considering queue state and channel state information. The goal is to achieve reliable communication and accurate velocity estimation of surrounding objects. To improve performance, they introduce adaptive OFDM and a reward function that utilizes the age of updates. Simulation results using A2C and PPO algorithms demonstrate the superiority of their approach over existing designs.

Recent progress in video generation still struggles with issues like motion instability and prompt alignment. To address this, the study explores incorporating human preferences into advanced flow-based video generation models. The authors introduce a large, new dataset of human-annotated video preferences across visual quality, motion quality, and text alignment. They also develop a multi-dimensional reward model to quantify these preferences and propose three alignment algorithms for flow-based models, demonstrating that a modified Direct Preference Optimization method yields the most effective results in aligning video generation with human expectations.

This research paper introduces AnimeGamer, a novel method for creating infinite anime life simulation games. Unlike previous work limited to static images or finite gameplay, AnimeGamer uses a multimodal large language model to process user instructions and predict subsequent game states. These states include dynamic animation shots and updated character attributes, aiming for a more immersive and consistent gaming experience. The paper details the model's architecture, training process, and evaluation, demonstrating its superior performance in generating coherent and interactive anime game worlds compared to baseline methods.