Graphs have been widely adopted to denote structural connections between entities. The relations are in many cases heterogeneous, but entangled together and denoted merely as a single edge between a pair of nodes. For example, in a social network graph, users in different latent relationships like friends and colleagues, are usually connected via a bare edge that conceals such intrinsic connections. In this paper, we introduce a novel graph convolutional network (GCN), termed as factorizable graph convolutional network (FactorGCN), that explicitly disentangles such intertwined relations encoded in a graph. FactorGCN takes a simple graph as input, and disentangles it into several factorized graphs, each of which represents a latent and disentangled relation among nodes. The features of the nodes are then aggregated separately in each factorized latent space to produce disentangled features, which further leads to better performances for downstream tasks. We evaluate the proposed FactorGCN both qualitatively and quantitatively on the synthetic and real-world datasets, and demonstrate that it yields truly encouraging results in terms of both disentangling and feature aggregation.

University of Toronto professor Geoffrey Hinton, center, and graduate students Ilya Sutskever, left, and Alex Krizhevsky, right, in 2013. There are many stories of how artificial intelligence came to take over the world, but one of the most important developments is the emergence in 2012 of AlexNet, a neural network that, for the first time, demonstrated a huge jump in a computer's ability to recognize images. Thursday, the Computer History Museum (CHM), in collaboration with Google, released for the first time the AlexNet source code written by University of Toronto graduate student Alex Krizhevsky, placing it on GitHub for all to peruse and download. "CHM is proud to present the source code to the 2012 version of Alex Krizhevsky, Ilya Sutskever, and Geoffery Hinton's AlexNet, which transformed the field of artificial intelligence," write the Museum organizers in the readme file on GitHub. Krizhevsky's creation would lead to a flood of innovation in the ensuing years, and tons of capital, based on proof that with sufficient data and computing, neural networks could achieve breakthroughs previously viewed as mainly theoretical.

Active learning effectively collects data instances for training deep learning models when the labeled dataset is limited and the annotation cost is high. Data augmentation is another effective technique to enlarge the limited amount of labeled instances. The scarcity of labeled dataset leads us to consider the integration of data augmentation and active learning. One possible approach is a pipelined combination, which selects informative instances via the acquisition function and generates virtual instances from the selected instances via augmentation. However, this pipelined approach would not guarantee the informativeness of the virtual instances. This paper proposes Look-Ahead Data Acquisition via augmentation, or LADA framework, that looks ahead the effect of data augmentation in the process of acquisition. LADA jointly considers both 1) unlabeled data instance to be selected and 2) virtual data instance to be generated by data augmentation, to construct the acquisition function. Moreover, to generate maximally informative virtual instances, LADA optimizes the data augmentation policy to maximize the predictive acquisition score, resulting in the proposal of InfoSTN and InfoMixup. The experimental results of LADA show a significant improvement over the recent augmentation and acquisition baselines that were independently applied.

Cinematographers adeptly capture the essence of the world, crafting compelling visual narratives through intricate camera movements. Witnessing the strides made by large language models in perceiving and interacting with the 3D world, this study explores their capability to control cameras with human language guidance. We introduce ChatCam, a system that navigates camera movements through conversations with users, mimicking a professional cinematographer's workflow. To achieve this, we propose CineGPT, a GPT-based autoregressive model for text-conditioned camera trajectory generation. We also develop an Anchor Determinator to ensure precise camera trajectory placement. ChatCam understands user requests and employs our proposed tools to generate trajectories, which can be used to render high-quality video footage on radiance field representations. Our experiments, including comparisons to state-of-the-art approaches and user studies, demonstrate our approach's ability to interpret and execute complex instructions for camera operation, showing promising applications in real-world production settings. We will release the codebase upon paper acceptance.

The detailed description of each data point's entries is as follows. " query ": " What is the weather in Palo Alto?", In this example, the query asks about the current weather in Palo Alto. Here's an example JSON data for the parallel function-calling category, i.e., the user's query contains " query ": " Find the sum of all the multiples of 3 and 5 " description ": " Find the sum of all multiples of " description ": " The numbers to find multiples of.", " description ": " Find the product of the first n prime This step helps to filter out poorly formatted or incomplete data points. B.1 Generator LLM Prompt Example Prompt for the Generator to Generate Parallel Function-Calling Data """ You are a data labeler.

The advancement of function-calling agent models requires diverse, reliable, and high-quality datasets. This paper presents APIGen, an automated data generation pipeline designed to synthesize high-quality datasets for function-calling applications. We leverage APIGen and collect 3,673 executable APIs across 21 different categories to generate diverse function-calling datasets in a scalable and structured manner. Each data in our dataset is verified through three hierarchical stages: format checking, actual function executions, and semantic verification, improving its reliability and correctness. We demonstrate that models trained with our curated datasets, even with only 7B parameters, can achieve state-of-the-art performance on the Berkeley Function-Calling Benchmark, outperforming multiple GPT-4 models. Moreover, our 1B model achieves exceptional performance, surpassing GPT-3.5-Turbo and Claude-3 Haiku. We release a dataset containing 60,000 high-quality entries, aiming to advance the field of function-calling agent domains.

Many reinforcement learning (RL) environments consist of independent entities that interact sparsely. In such environments, RL agents have only limited influence over other entities in any particular situation. Our idea in this work is that learning can be efficiently guided by knowing when and what the agent can influence with its actions. To achieve this, we introduce a measure of situation-dependent causal influence based on conditional mutual information and show that it can reliably detect states of influence. We then propose several ways to integrate this measure into RL algorithms to improve exploration and off-policy learning. All modified algorithms show strong increases in data efficiency on robotic manipulation tasks.

Here we provide proofs for all the results in Section 4 that were excluded in the main paper. For each of these results we dedicate a subsection that provides further details. Combining all these results from different subsections, in Appendix A.4 we provide the proof for our main result (Theorem 2.1). A.1 Properties of Convex Program and Proof of Lemma 4.3 Here we prove important properties of our convex program. In the remainder we prove and state interesting properties of this function that helps us construct sparse approximate solutions.