Programming robot behaviour in a complex world faces challenges on multiple levels, from dextrous low-level skills to high-level planning and reasoning. Recent pre-trained Large Language Models (LLMs) have shown remarkable reasoning ability in zero-shot robotic planning. However, it remains challenging to ground LLMs in multimodal sensory input and continuous action output, while enabling a robot to interact with its environment and acquire novel information as its policies unfold. We develop a robot interaction scenario with a partially observable state, which necessitates a robot to decide on a range of epistemic actions in order to sample sensory information among multiple modalities, before being able to execute the task correctly. An interactive perception framework is therefore proposed with an LLM as its backbone, whose ability is exploited to instruct epistemic actions and to reason over the resulting multimodal sensations (vision, sound, haptics, proprioception), as well as to plan an entire task execution based on the interactively acquired information. Our study demonstrates that LLMs can provide high-level planning and reasoning skills and control interactive robot behaviour in a multimodal environment, while multimodal modules with the context of the environmental state help ground the LLMs and extend their processing ability.
相關內容
IFIP TC13 Conference on Human-Computer Interaction是人機交互領域的研究者和實踐者展示其工作的重要平臺。多年來，這些會議吸引了來自幾個國家和文化的研究人員。官網鏈接： ·
Networking
·
語言模型化
·
INFORMS
·
多峰值
·
Training a Large Visual Language Model (LVLM) from scratch, like GPT-4, is resource-intensive. Our paper proposes an alternative method called LMEye, a play-plug-in Interactive Perception Network for Large Language Models (LLMs), aiming to improve the accuracy of image understanding for the LVLM. Previous methods that infuse visual information into LLMs utilize a static visual mapping network, but lack dynamic interaction between the LLMs and visual information. LMEye addresses this issue by allowing the LLM to incorporate the visual information that aligned with human instruction. Specifically, the LMEye network consists of a static visual mapping network to provide the basic perception of an image to LLMs. Then, it also contains additional linear layers responsible for acquiring requests from LLMs, decomposing image features, and transmitting the interleaved information to LLMs, respectively. In this way, LLMs act to be in charge of understanding human instructions, sending it to the interactive perception network, and generating the response based on the interleaved multimodal information. We evaluate LMEye through extensive experiments on multimodal question answering and reasoning tasks, demonstrating that it significantly improves the zero-shot performance of LLMs on multimodal tasks compared to previous methods.
Webpages have been a rich, scalable resource for vision-language and language only tasks. Yet only pieces of webpages are kept: image-caption pairs, long text articles, or raw HTML, never all in one place. Webpage tasks have resultingly received little attention and structured image-text data left underused. To study multimodal webpage understanding, we introduce the Wikipedia Webpage suite (WikiWeb2M) of 2M pages. We verify its utility on three generative tasks: page description generation, section summarization, and contextual image captioning. We design a novel attention mechanism Prefix Global, which selects the most relevant image and text content as global tokens to attend to the rest of the webpage for context. By using page structure to separate such tokens, it performs better than full attention with lower computational complexity. Experiments show that the new annotations from WikiWeb2M improve task performance compared to data from prior work. We also include ablations on sequence length, input features, and model size.
Semantic dimensions of sound have been playing a central role in understanding the nature of auditory sensory experience as well as the broader relation between perception, language, and meaning. Accordingly, and given the recent proliferation of large language models (LLMs), here we asked whether such models exhibit an organisation of perceptual semantics similar to those observed in humans. Specifically, we prompted ChatGPT, a chatbot based on a state-of-the-art LLM, to rate musical instrument sounds on a set of 20 semantic scales. We elicited multiple responses in separate chats, analogous to having multiple human raters. ChatGPT generated semantic profiles that only partially correlated with human ratings, yet showed robust agreement along well-known psychophysical dimensions of musical sounds such as brightness (bright-dark) and pitch height (deep-high). Exploratory factor analysis suggested the same dimensionality but different spatial configuration of a latent factor space between the chatbot and human ratings. Unexpectedly, the chatbot showed degrees of internal variability that were comparable in magnitude to that of human ratings. Our work highlights the potential of LLMs to capture salient dimensions of human sensory experience.
Controllable image captioning is an emerging multimodal topic that aims to describe the image with natural language following human purpose, $\textit{e.g.}$, looking at the specified regions or telling in a particular text style. State-of-the-art methods are trained on annotated pairs of input controls and output captions. However, the scarcity of such well-annotated multimodal data largely limits their usability and scalability for interactive AI systems. Leveraging unimodal instruction-following foundation models is a promising alternative that benefits from broader sources of data. In this paper, we present Caption AnyThing (CAT), a foundation model augmented image captioning framework supporting a wide range of multimodel controls: 1) visual controls, including points, boxes, and trajectories; 2) language controls, such as sentiment, length, language, and factuality. Powered by Segment Anything Model (SAM) and ChatGPT, we unify the visual and language prompts into a modularized framework, enabling the flexible combination between different controls. Extensive case studies demonstrate the user intention alignment capabilities of our framework, shedding light on effective user interaction modeling in vision-language applications. Our code is publicly available at //github.com/ttengwang/Caption-Anything.
Artificial neural networks (ANNs) are increasingly used as research models, but questions remain about their generalizability and representational invariance. Biological neural networks under social constraints evolved to enable communicable representations, demonstrating generalization capabilities. This study proposes a communication protocol between cooperative agents to analyze the formation of individual and shared abstractions and their impact on task performance. This communication protocol aims to mimic language features by encoding high-dimensional information through low-dimensional representation. Using grid-world mazes and reinforcement learning, teacher ANNs pass a compressed message to a student ANN for better task completion. Through this, the student achieves a higher goal-finding rate and generalizes the goal location across task worlds. Further optimizing message content to maximize student reward improves information encoding, suggesting that an accurate representation in the space of messages requires bi-directional input. This highlights the role of language as a common representation between agents and its implications on generalization capabilities.
The desired outcome for urban digital twins is an automatically generated detailed 3D model of a building from aerial imagery, footprints, LiDAR, or a fusion of these. Such 3D models have applications in architecture, civil engineering, urban planning, construction, real estate, GIS, and many others. Further, the visualization of large-scale data in conjunction with the generated 3D models is often a recurring and resource-intensive task. However, a completely automated end-to-end workflow is complex, requiring many steps to achieve a high-quality visualization. Methods for building reconstruction approaches have come a long way from previously manual approaches to semi-automatic or automatic approaches. The next step after reconstructing buildings is visualizing the buildings and their context. Advances in real-time rendering using game engines have enabled the extension of building reconstruction methods to procedurally generated context generation. This paper aims to complement existing methods of 3D building generation. First, we present a literature review covering different options for procedurally generated context generation and visualization methods in-depth, focusing on workflows and data pipelines. Next, we present a semi-automated workflow that extends the building reconstruction pipeline to include procedural context generation (terrain and vegetation) using Unreal Engine and, finally, the integration of various types of large-scale urban analysis data for visualization. We conclude with a series of challenges faced in achieving such pipelines and the limitations of the current approach. The steps for a complete, end-to-end solution involve developing robust systems for building detection, rooftop recognition, and geometry generation and importing and visualizing data in the same 3D environment.
Existing datasets for autonomous driving (AD) often lack diversity and long-range capabilities, focusing instead on 360{\deg} perception and temporal reasoning. To address this gap, we introduce Zenseact Open Dataset (ZOD), a large-scale and diverse multimodal dataset collected over two years in various European countries, covering an area 9x that of existing datasets. ZOD boasts the highest range and resolution sensors among comparable datasets, coupled with detailed keyframe annotations for 2D and 3D objects (up to 245m), road instance/semantic segmentation, traffic sign recognition, and road classification. We believe that this unique combination will facilitate breakthroughs in long-range perception and multi-task learning. The dataset is composed of Frames, Sequences, and Drives, designed to encompass both data diversity and support for spatio-temporal learning, sensor fusion, localization, and mapping. Frames consist of 100k curated camera images with two seconds of other supporting sensor data, while the 1473 Sequences and 29 Drives include the entire sensor suite for 20 seconds and a few minutes, respectively. ZOD is the only large-scale AD dataset released under a permissive license, allowing for both research and commercial use. The dataset is accompanied by an extensive development kit. Data and more information are available online (//zod.zenseact.com).
Human-centric perception plays a vital role in vision and graphics. But their data annotations are prohibitively expensive. Therefore, it is desirable to have a versatile pre-train model that serves as a foundation for data-efficient downstream tasks transfer. To this end, we propose the Human-Centric Multi-Modal Contrastive Learning framework HCMoCo that leverages the multi-modal nature of human data (e.g. RGB, depth, 2D keypoints) for effective representation learning. The objective comes with two main challenges: dense pre-train for multi-modality data, efficient usage of sparse human priors. To tackle the challenges, we design the novel Dense Intra-sample Contrastive Learning and Sparse Structure-aware Contrastive Learning targets by hierarchically learning a modal-invariant latent space featured with continuous and ordinal feature distribution and structure-aware semantic consistency. HCMoCo provides pre-train for different modalities by combining heterogeneous datasets, which allows efficient usage of existing task-specific human data. Extensive experiments on four downstream tasks of different modalities demonstrate the effectiveness of HCMoCo, especially under data-efficient settings (7.16% and 12% improvement on DensePose Estimation and Human Parsing). Moreover, we demonstrate the versatility of HCMoCo by exploring cross-modality supervision and missing-modality inference, validating its strong ability in cross-modal association and reasoning.
UniViLM: A Unified Video and Language Pre-Training Model for Multimodal Understanding and Generation
We propose UniViLM: a Unified Video and Language pre-training Model for multimodal understanding and generation. Motivated by the recent success of BERT based pre-training technique for NLP and image-language tasks, VideoBERT and CBT are proposed to exploit BERT model for video and language pre-training using narrated instructional videos. Different from their works which only pre-train understanding task, we propose a unified video-language pre-training model for both understanding and generation tasks. Our model comprises of 4 components including two single-modal encoders, a cross encoder and a decoder with the Transformer backbone. We first pre-train our model to learn the universal representation for both video and language on a large instructional video dataset. Then we fine-tune the model on two multimodal tasks including understanding task (text-based video retrieval) and generation task (multimodal video captioning). Our extensive experiments show that our method can improve the performance of both understanding and generation tasks and achieves the state-of-the art results.
Meta-reinforcement learning algorithms can enable robots to acquire new skills much more quickly, by leveraging prior experience to learn how to learn. However, much of the current research on meta-reinforcement learning focuses on task distributions that are very narrow. For example, a commonly used meta-reinforcement learning benchmark uses different running velocities for a simulated robot as different tasks. When policies are meta-trained on such narrow task distributions, they cannot possibly generalize to more quickly acquire entirely new tasks. Therefore, if the aim of these methods is to enable faster acquisition of entirely new behaviors, we must evaluate them on task distributions that are sufficiently broad to enable generalization to new behaviors. In this paper, we propose an open-source simulated benchmark for meta-reinforcement learning and multi-task learning consisting of 50 distinct robotic manipulation tasks. Our aim is to make it possible to develop algorithms that generalize to accelerate the acquisition of entirely new, held-out tasks. We evaluate 6 state-of-the-art meta-reinforcement learning and multi-task learning algorithms on these tasks. Surprisingly, while each task and its variations (e.g., with different object positions) can be learned with reasonable success, these algorithms struggle to learn with multiple tasks at the same time, even with as few as ten distinct training tasks. Our analysis and open-source environments pave the way for future research in multi-task learning and meta-learning that can enable meaningful generalization, thereby unlocking the full potential of these methods.
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