During collaboration in XR (eXtended Reality), users typically share and interact with virtual objects in a common, shared virtual environment. Specifically, collaboration among users in Mixed Reality (MR) requires knowing their position, movement, and understanding of the visual scene surrounding their physical environments. Otherwise, one user could move an important virtual object to a position blocked by the physical environment for others. However, even for a single physical environment, 3D reconstruction takes a long time and the produced 3D data is typically very large in size. Also, these large amounts of 3D data take a long time to be streamed to receivers making real-time updates on the rendered scene challenging. Furthermore, many collaboration systems in MR require multiple devices, which take up space and make setup difficult. To address these challenges, in this paper, we describe a single-device system called Collaborative Adaptive Mixed Reality Environment (CAMRE). We build CAMRE using the scene understanding capabilities of HoloLens 2 devices to create shared MR virtual environments for each connected user and demonstrate using a Leader-Follower(s) paradigm: faster reconstruction and scene update times due to smaller data. Consequently, multiple users can receive shared, synchronized, and close-to-real-time latency virtual scenes from a chosen Leader, based on their physical position and movement. We also illustrate other expanded features of CAMRE MR virtual environment such as navigation using a real-time virtual mini-map and X-ray vision for handling adaptive wall opacity. We share several experimental results that evaluate the performance of CAMRE in terms of the network latency in sharing virtual objects and other capabilities.
相關內容
Learning from human feedback is a prominent technique to align the output of large language models (LLMs) with human expectations. Reinforcement learning from human feedback (RLHF) leverages human preference signals that are in the form of ranking of response pairs to perform this alignment. However, human preference on LLM outputs can come in much richer forms including natural language, which may provide detailed feedback on strengths and weaknesses of a given response. In this work we investigate data efficiency of modeling human feedback that is in natural language. Specifically, we fine-tune an open-source LLM, e.g., Falcon-40B-Instruct, on a relatively small amount (1000 records or even less) of human feedback in natural language in the form of critiques and revisions of responses. We show that this model is able to improve the quality of responses from even some of the strongest LLMs such as ChatGPT, BARD, and Vicuna, through critique and revision of those responses. For instance, through one iteration of revision of ChatGPT responses, the revised responses have 56.6% win rate over the original ones, and this win rate can be further improved to 65.9% after applying the revision for five iterations.
The ability to understand spatial-temporal patterns for crowds of people is crucial for achieving long-term autonomy of mobile robots deployed in human environments. However, traditional historical data-driven memory models are inadequate for handling anomalies, resulting in poor reasoning by robot in estimating the crowd spatial distribution. In this article, a Receding Horizon Optimization (RHO) formulation is proposed that incorporates a Probability-related Partially Updated Memory (PPUM) for robot path planning in crowded environments with uncertainties. The PPUM acts as a memory layer that combines real-time sensor observations with historical knowledge using a weighted evidence fusion theory to improve robot's adaptivity to the dynamic environments. RHO then utilizes the PPUM as a informed knowledge to generate a path that minimizes the likelihood of encountering dense crowds while reducing the cost of local motion planning. The proposed approach provides an innovative solution to the problem of robot's long-term safe interaction with human in uncertain crowded environments. In simulation, the results demonstrate the superior performance of our approach compared to benchmark methods in terms of crowd distribution estimation accuracy, adaptability to anomalies and path planning efficiency.
In the domain of 3D Human Pose Estimation, which finds widespread daily applications, the requirement for convenient acquisition equipment continues to grow. To satisfy this demand, we set our sights on a short-baseline binocular setting that offers both portability and a geometric measurement property that radically mitigates depth ambiguity. However, as the binocular baseline shortens, two serious challenges emerge: first, the robustness of 3D reconstruction against 2D errors deteriorates; and second, occlusion reoccurs due to the limited visual differences between two views. To address the first challenge, we propose the Stereo Co-Keypoints Estimation module to improve the view consistency of 2D keypoints and enhance the 3D robustness. In this module, the disparity is utilized to represent the correspondence of binocular 2D points and the Stereo Volume Feature is introduced to contain binocular features across different disparities. Through the regression of SVF, two-view 2D keypoints are simultaneously estimated in a collaborative way which restricts their view consistency. Furthermore, to deal with occlusions, a Pre-trained Pose Transformer module is introduced. Through this module, 3D poses are refined by perceiving pose coherence, a representation of joint correlations. This perception is injected by the Pose Transformer network and learned through a pre-training task that recovers iterative masked joints. Comprehensive experiments carried out on H36M and MHAD datasets, complemented by visualizations, validate the effectiveness of our approach in the short-baseline binocular 3D Human Pose Estimation and occlusion handling.
The ability to collect a large dataset of human preferences from text-to-image users is usually limited to companies, making such datasets inaccessible to the public. To address this issue, we create a web app that enables text-to-image users to generate images and specify their preferences. Using this web app we build Pick-a-Pic, a large, open dataset of text-to-image prompts and real users' preferences over generated images. We leverage this dataset to train a CLIP-based scoring function, PickScore, which exhibits superhuman performance on the task of predicting human preferences. Then, we test PickScore's ability to perform model evaluation and observe that it correlates better with human rankings than other automatic evaluation metrics. Therefore, we recommend using PickScore for evaluating future text-to-image generation models, and using Pick-a-Pic prompts as a more relevant dataset than MS-COCO. Finally, we demonstrate how PickScore can enhance existing text-to-image models via ranking.
Federated Learning (FL) has garnered significant attention for its potential to protect user privacy while enhancing model training efficiency. However, recent research has demonstrated that FL protocols can be easily compromised by active reconstruction attacks executed by dishonest servers. These attacks involve the malicious modification of global model parameters, allowing the server to obtain a verbatim copy of users' private data by inverting their gradient updates. Tackling this class of attack remains a crucial challenge due to the strong threat model. In this paper, we propose OASIS, a defense mechanism based on image augmentation that effectively counteracts active reconstruction attacks while preserving model performance. We first uncover the core principle of gradient inversion that enables these attacks and theoretically identify the main conditions by which the defense can be robust regardless of the attack strategies. We then construct OASIS with image augmentation showing that it can undermine the attack principle. Comprehensive evaluations demonstrate the efficacy of OASIS highlighting its feasibility as a solution.
Most large language models (LLMs) are trained once and never updated; thus, they lack the ability to dynamically adapt to our ever-changing world. In this work, we perform a detailed study of the factuality of LLM-generated text in the context of answering questions that test current world knowledge. Specifically, we introduce FreshQA, a novel dynamic QA benchmark encompassing a diverse range of question and answer types, including questions that require fast-changing world knowledge as well as questions with false premises that need to be debunked. We benchmark a diverse array of both closed and open-source LLMs under a two-mode evaluation procedure that allows us to measure both correctness and hallucination. Through human evaluations involving more than 50K judgments, we shed light on limitations of these models and demonstrate significant room for improvement: for instance, all models (regardless of model size) struggle on questions that involve fast-changing knowledge and false premises. Motivated by these results, we present FreshPrompt, a simple few-shot prompting method that substantially boosts the performance of an LLM on FreshQA by incorporating relevant and up-to-date information retrieved from a search engine into the prompt. Our experiments show that FreshPrompt outperforms both competing search engine-augmented prompting methods such as Self-Ask (Press et al., 2022) as well as commercial systems such as Perplexity.AI. Further analysis of FreshPrompt reveals that both the number of retrieved evidences and their order play a key role in influencing the correctness of LLM-generated answers. Additionally, instructing the LLM to generate concise and direct answers helps reduce hallucination compared to encouraging more verbose answers. To facilitate future work, we release FreshQA at github.com/freshllms/freshqa and commit to updating it at regular intervals.
In response to legislation mandating companies to honor the \textit{right to be forgotten} by erasing user data, it has become imperative to enable data removal in Vertical Federated Learning (VFL) where multiple parties provide private features for model training. In VFL, data removal, i.e., \textit{machine unlearning}, often requires removing specific features across all samples under privacy guarentee in federated learning. To address this challenge, we propose \methname, a novel Gradient Boosting Decision Tree (GBDT) framework that effectively enables both \textit{instance unlearning} and \textit{feature unlearning} without the need for retraining from scratch. Leveraging a robust GBDT structure, we enable effective data deletion while reducing degradation of model performance. Extensive experimental results on popular datasets demonstrate that our method achieves superior model utility and forgetfulness compared to \textit{state-of-the-art} methods. To our best knowledge, this is the first work that investigates machine unlearning in VFL scenarios.
The emergence of large language models (LLMs) has substantially influenced natural language processing, demonstrating exceptional results across various tasks. In this study, we employ ``Introspective Tips" to facilitate LLMs in self-optimizing their decision-making. By introspectively examining trajectories, LLM refines its policy by generating succinct and valuable tips. Our method enhances the agent's performance in both few-shot and zero-shot learning situations by considering three essential scenarios: learning from the agent's past experiences, integrating expert demonstrations, and generalizing across diverse games. Importantly, we accomplish these improvements without fine-tuning the LLM parameters; rather, we adjust the prompt to generalize insights from the three aforementioned situations. Our framework not only supports but also emphasizes the advantage of employing LLM in in-contxt decision-making. Experiments involving over 100 games in TextWorld illustrate the superior performance of our approach.
Existing recommender systems extract the user preference based on learning the correlation in data, such as behavioral correlation in collaborative filtering, feature-feature, or feature-behavior correlation in click-through rate prediction. However, regretfully, the real world is driven by causality rather than correlation, and correlation does not imply causation. For example, the recommender systems can recommend a battery charger to a user after buying a phone, in which the latter can serve as the cause of the former, and such a causal relation cannot be reversed. Recently, to address it, researchers in recommender systems have begun to utilize causal inference to extract causality, enhancing the recommender system. In this survey, we comprehensively review the literature on causal inference-based recommendation. At first, we present the fundamental concepts of both recommendation and causal inference as the basis of later content. We raise the typical issues that the non-causality recommendation is faced. Afterward, we comprehensively review the existing work of causal inference-based recommendation, based on a taxonomy of what kind of problem causal inference addresses. Last, we discuss the open problems in this important research area, along with interesting future works.
Sentiment analysis is a widely studied NLP task where the goal is to determine opinions, emotions, and evaluations of users towards a product, an entity or a service that they are reviewing. One of the biggest challenges for sentiment analysis is that it is highly language dependent. Word embeddings, sentiment lexicons, and even annotated data are language specific. Further, optimizing models for each language is very time consuming and labor intensive especially for recurrent neural network models. From a resource perspective, it is very challenging to collect data for different languages. In this paper, we look for an answer to the following research question: can a sentiment analysis model trained on a language be reused for sentiment analysis in other languages, Russian, Spanish, Turkish, and Dutch, where the data is more limited? Our goal is to build a single model in the language with the largest dataset available for the task, and reuse it for languages that have limited resources. For this purpose, we train a sentiment analysis model using recurrent neural networks with reviews in English. We then translate reviews in other languages and reuse this model to evaluate the sentiments. Experimental results show that our robust approach of single model trained on English reviews statistically significantly outperforms the baselines in several different languages.
小貼士
登錄享
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191