Abstract:Artificial intelligence generated content (AIGC) technologies, with a predominance of large language models (LLMs), have demonstrated remarkable performance improvements in various applications, which have attracted great interests from both academia and industry. Although some noteworthy advancements have been made in this area, a comprehensive exploration of the intricate relationship between AIGC and communication networks remains relatively limited. To address this issue, this paper conducts an exhaustive survey from dual standpoints: firstly, it scrutinizes the integration of LLMs and AIGC technologies within the domain of communication networks; secondly, it investigates how the communication networks can further bolster the capabilities of LLMs and AIGC. Additionally, this research explores the promising applications along with the challenges encountered during the incorporation of these AI technologies into communication networks. Through these detailed analyses, our work aims to deepen the understanding of how LLMs and AIGC can synergize with and enhance the development of advanced intelligent communication networks, contributing to a more profound comprehension of next-generation intelligent communication networks.
Abstract:In this paper, we propose a new framework for zero-shot object navigation. Existing zero-shot object navigation methods prompt LLM with the text of spatially closed objects, which lacks enough scene context for in-depth reasoning. To better preserve the information of environment and fully exploit the reasoning ability of LLM, we propose to represent the observed scene with 3D scene graph. The scene graph encodes the relationships between objects, groups and rooms with a LLM-friendly structure, for which we design a hierarchical chain-of-thought prompt to help LLM reason the goal location according to scene context by traversing the nodes and edges. Moreover, benefit from the scene graph representation, we further design a re-perception mechanism to empower the object navigation framework with the ability to correct perception error. We conduct extensive experiments on MP3D, HM3D and RoboTHOR environments, where SG-Nav surpasses previous state-of-the-art zero-shot methods by more than 10% SR on all benchmarks, while the decision process is explainable. To the best of our knowledge, SG-Nav is the first zero-shot method that achieves even higher performance than supervised object navigation methods on the challenging MP3D benchmark.
Abstract:Given a finite set of sample points, meta-learning algorithms aim to learn an optimal adaptation strategy for new, unseen tasks. Often, this data can be ambiguous as it might belong to different tasks concurrently. This is particularly the case in meta-regression tasks. In such cases, the estimated adaptation strategy is subject to high variance due to the limited amount of support data for each task, which often leads to sub-optimal generalization performance. In this work, we address the problem of variance reduction in gradient-based meta-learning and formalize the class of problems prone to this, a condition we refer to as \emph{task overlap}. Specifically, we propose a novel approach that reduces the variance of the gradient estimate by weighing each support point individually by the variance of its posterior over the parameters. To estimate the posterior, we utilize the Laplace approximation, which allows us to express the variance in terms of the curvature of the loss landscape of our meta-learner. Experimental results demonstrate the effectiveness of the proposed method and highlight the importance of variance reduction in meta-learning.
Abstract:This report evaluates the performance impact of enabling Trusted Execution Environments (TEE) on NVIDIA H100 GPUs for large language model (LLM) inference tasks. We benchmark the overhead introduced by TEE mode across various models and token lengths, focusing on the bottleneck caused by CPU-GPU data transfers via PCIe. Our results show that while there is minimal computational overhead within the GPU, the overall performance penalty is primarily due to data transfer. For most typical LLM queries, the overhead remains below 5%, with larger models and longer sequences experiencing near-zero overhead.
Abstract:The realm of textiles spans clothing, households, healthcare, sports, and industrial applications. The deformable nature of these objects poses unique challenges that prior work on rigid objects cannot fully address. The increasing interest within the community in textile perception and manipulation has led to new methods that aim to address challenges in modeling, perception, and control, resulting in significant progress. However, this progress is often tailored to one specific textile or a subcategory of these textiles. To understand what restricts these methods and hinders current approaches from generalizing to a broader range of real-world textiles, this review provides an overview of the field, focusing specifically on how and to what extent textile variations are addressed in modeling, perception, benchmarking, and manipulation of textiles. We finally conclude by identifying key open problems and outlining grand challenges that will drive future advancements in the field.
Abstract:We investigate the entity alignment problem with unlabeled dangling cases, meaning that there are entities in the source or target graph having no counterparts in the other, and those entities remain unlabeled. The problem arises when the source and target graphs are of different scales, and it is much cheaper to label the matchable pairs than the dangling entities. To solve the issue, we propose a novel GNN-based dangling detection and entity alignment framework. While the two tasks share the same GNN and are trained together, the detected dangling entities are removed in the alignment. Our framework is featured by a designed entity and relation attention mechanism for selective neighborhood aggregation in representation learning, as well as a positive-unlabeled learning loss for an unbiased estimation of dangling entities. Experimental results have shown that each component of our design contributes to the overall alignment performance which is comparable or superior to baselines, even if the baselines additionally have 30\% of the dangling entities labeled as training data.
Abstract:Knowledge graphs contain informative factual knowledge but are considered incomplete. To answer complex queries under incomplete knowledge, learning-based Complex Query Answering (CQA) models are proposed to directly learn from the query-answer samples to avoid the direct traversal of incomplete graph data. Existing works formulate the training of complex query answering models as multi-task learning and require a large number of training samples. In this work, we explore the compositional structure of complex queries and argue that the different logical operator types, rather than the different complex query types, are the key to improving generalizability. Accordingly, we propose a meta-learning algorithm to learn the meta-operators with limited data and adapt them to different instances of operators under various complex queries. Empirical results show that learning meta-operators is more effective than learning original CQA or meta-CQA models.
Abstract:Dance typically involves professional choreography with complex movements that follow a musical rhythm and can also be influenced by lyrical content. The integration of lyrics in addition to the auditory dimension, enriches the foundational tone and makes motion generation more amenable to its semantic meanings. However, existing dance synthesis methods tend to model motions only conditioned on audio signals. In this work, we make two contributions to bridge this gap. First, we propose LM2D, a novel probabilistic architecture that incorporates a multimodal diffusion model with consistency distillation, designed to create dance conditioned on both music and lyrics in one diffusion generation step. Second, we introduce the first 3D dance-motion dataset that encompasses both music and lyrics, obtained with pose estimation technologies. We evaluate our model against music-only baseline models with objective metrics and human evaluations, including dancers and choreographers. The results demonstrate LM2D is able to produce realistic and diverse dance matching both lyrics and music. A video summary can be accessed at: https://youtu.be/4XCgvYookvA.
Abstract:We present BEHAVIOR-1K, a comprehensive simulation benchmark for human-centered robotics. BEHAVIOR-1K includes two components, guided and motivated by the results of an extensive survey on "what do you want robots to do for you?". The first is the definition of 1,000 everyday activities, grounded in 50 scenes (houses, gardens, restaurants, offices, etc.) with more than 9,000 objects annotated with rich physical and semantic properties. The second is OMNIGIBSON, a novel simulation environment that supports these activities via realistic physics simulation and rendering of rigid bodies, deformable bodies, and liquids. Our experiments indicate that the activities in BEHAVIOR-1K are long-horizon and dependent on complex manipulation skills, both of which remain a challenge for even state-of-the-art robot learning solutions. To calibrate the simulation-to-reality gap of BEHAVIOR-1K, we provide an initial study on transferring solutions learned with a mobile manipulator in a simulated apartment to its real-world counterpart. We hope that BEHAVIOR-1K's human-grounded nature, diversity, and realism make it valuable for embodied AI and robot learning research. Project website: https://behavior.stanford.edu.
Abstract:Interactive perception enables robots to manipulate the environment and objects to bring them into states that benefit the perception process. Deformable objects pose challenges to this due to significant manipulation difficulty and occlusion in vision-based perception. In this work, we address such a problem with a setup involving both an active camera and an object manipulator. Our approach is based on a sequential decision-making framework and explicitly considers the motion regularity and structure in coupling the camera and manipulator. We contribute a method for constructing and computing a subspace, called Dynamic Active Vision Space (DAVS), for effectively utilizing the regularity in motion exploration. The effectiveness of the framework and approach are validated in both a simulation and a real dual-arm robot setup. Our results confirm the necessity of an active camera and coordinative motion in interactive perception for deformable objects.