Qiuyuan Huang

Baolin Peng, Michel Galley, Pengcheng He et al. · microsoft-research

Large language models (LLMs), such as ChatGPT, are able to generate human-like, fluent responses for many downstream tasks, e.g., task-oriented dialog and question answering. However, applying LLMs to real-world, mission-critical applications remains challenging mainly due to their tendency to generate hallucinations and their inability to use external knowledge. This paper proposes a LLM-Augmenter system, which augments a black-box LLM with a set of plug-and-play modules. Our system makes the LLM generate responses grounded in external knowledge, e.g., stored in task-specific databases. It also iteratively revises LLM prompts to improve model responses using feedback generated by utility functions, e.g., the factuality score of a LLM-generated response. The effectiveness of LLM-Augmenter is empirically validated on two types of scenarios, task-oriented dialog and open-domain question answering. LLM-Augmenter significantly reduces ChatGPT's hallucinations without sacrificing the fluency and informativeness of its responses. We make the source code and models publicly available.

Liangke Gui, Yingshan Chang, Qiuyuan Huang et al. · cmu

Vision-Language Transformers can be learned without low-level human labels (e.g. class labels, bounding boxes, etc). Existing work, whether explicitly utilizing bounding boxes or patches, assumes that the visual backbone must first be trained on ImageNet class prediction before being integrated into a multimodal linguistic pipeline. We show that this is not necessary and introduce a new model Vision-Language from Captions (VLC) built on top of Masked Auto-Encoders that does not require this supervision. In fact, in a head-to-head comparison between ViLT, the current state-of-the-art patch-based vision-language transformer which is pretrained with supervised object classification, and our model, VLC, we find that our approach 1. outperforms ViLT on standard benchmarks, 2. provides more interpretable and intuitive patch visualizations, and 3. is competitive with many larger models that utilize ROIs trained on annotated bounding-boxes.

Ran Gong, Qiuyuan Huang, Xiaojian Ma et al.

Large Language Models (LLMs) have the capacity of performing complex scheduling in a multi-agent system and can coordinate these agents into completing sophisticated tasks that require extensive collaboration. However, despite the introduction of numerous gaming frameworks, the community has insufficient benchmarks towards building general multi-agents collaboration infrastructure that encompass both LLM and human-NPCs collaborations. In this work, we propose a novel infrastructure - MindAgent - to evaluate planning and coordination emergent capabilities for gaming interaction. In particular, our infrastructure leverages existing gaming framework, to i) require understanding of the coordinator for a multi-agent system, ii) collaborate with human players via un-finetuned proper instructions, and iii) establish an in-context learning on few-shot prompt with feedback. Furthermore, we introduce CUISINEWORLD, a new gaming scenario and related benchmark that dispatch a multi-agent collaboration efficiency and supervise multiple agents playing the game simultaneously. We conduct comprehensive evaluations with new auto-metric CoS for calculating the collaboration efficiency. Finally, our infrastructure can be deployed into real-world gaming scenarios in a customized VR version of CUISINEWORLD and adapted in existing broader Minecraft gaming domain. We hope our findings on LLMs and the new infrastructure for general-purpose scheduling and coordination can help shed light on how such skills can be obtained by learning from large language corpora.

Zane Durante, Qiuyuan Huang, Naoki Wake et al. · stanford

Multi-modal AI systems will likely become a ubiquitous presence in our everyday lives. A promising approach to making these systems more interactive is to embody them as agents within physical and virtual environments. At present, systems leverage existing foundation models as the basic building blocks for the creation of embodied agents. Embedding agents within such environments facilitates the ability of models to process and interpret visual and contextual data, which is critical for the creation of more sophisticated and context-aware AI systems. For example, a system that can perceive user actions, human behavior, environmental objects, audio expressions, and the collective sentiment of a scene can be used to inform and direct agent responses within the given environment. To accelerate research on agent-based multimodal intelligence, we define "Agent AI" as a class of interactive systems that can perceive visual stimuli, language inputs, and other environmentally-grounded data, and can produce meaningful embodied actions. In particular, we explore systems that aim to improve agents based on next-embodied action prediction by incorporating external knowledge, multi-sensory inputs, and human feedback. We argue that by developing agentic AI systems in grounded environments, one can also mitigate the hallucinations of large foundation models and their tendency to generate environmentally incorrect outputs. The emerging field of Agent AI subsumes the broader embodied and agentic aspects of multimodal interactions. Beyond agents acting and interacting in the physical world, we envision a future where people can easily create any virtual reality or simulated scene and interact with agents embodied within the virtual environment.

Zane Durante, Bidipta Sarkar, Ran Gong et al. · stanford

The development of artificial intelligence systems is transitioning from creating static, task-specific models to dynamic, agent-based systems capable of performing well in a wide range of applications. We propose an Interactive Agent Foundation Model that uses a novel multi-task agent training paradigm for training AI agents across a wide range of domains, datasets, and tasks. Our training paradigm unifies diverse pre-training strategies, including visual masked auto-encoders, language modeling, and next-action prediction, enabling a versatile and adaptable AI framework. We demonstrate the performance of our framework across three separate domains -- Robotics, Gaming AI, and Healthcare. Our model demonstrates its ability to generate meaningful and contextually relevant outputs in each area. The strength of our approach lies in its generality, leveraging a variety of data sources such as robotics sequences, gameplay data, large-scale video datasets, and textual information for effective multimodal and multi-task learning. Our approach provides a promising avenue for developing generalist, action-taking, multimodal systems.

Jae Sung Park, Jack Hessel, Khyathi Raghavi Chandu et al. · allen-ai, uw

Instruction following vision-language (VL) models offer a flexible interface that supports a broad range of multimodal tasks in a zero-shot fashion. However, interfaces that operate on full images do not directly enable the user to "point to" and access specific regions within images. This capability is important not only to support reference-grounded VL benchmarks, but also, for practical applications that require precise within-image reasoning. We build Localized Visual Commonsense models, which allow users to specify (multiple) regions as input. We train our model by sampling localized commonsense knowledge from a large language model (LLM): specifically, we prompt an LLM to collect commonsense knowledge given a global literal image description and a local literal region description automatically generated by a set of VL models. With a separately trained critic model that selects high-quality examples, we find that training on the localized commonsense corpus can successfully distill existing VL models to support a reference-as-input interface. Empirical results and human evaluations in a zero-shot setup demonstrate that our distillation method results in more precise VL models of reasoning compared to a baseline of passing a generated referring expression to an LLM.

Qiuyuan Huang, Naoki Wake, Bidipta Sarkar et al.

Recent advancements in large foundation models have remarkably enhanced our understanding of sensory information in open-world environments. In leveraging the power of foundation models, it is crucial for AI research to pivot away from excessive reductionism and toward an emphasis on systems that function as cohesive wholes. Specifically, we emphasize developing Agent AI -- an embodied system that integrates large foundation models into agent actions. The emerging field of Agent AI spans a wide range of existing embodied and agent-based multimodal interactions, including robotics, gaming, and healthcare systems, etc. In this paper, we propose a novel large action model to achieve embodied intelligent behavior, the Agent Foundation Model. On top of this idea, we discuss how agent AI exhibits remarkable capabilities across a variety of domains and tasks, challenging our understanding of learning and cognition. Furthermore, we discuss the potential of Agent AI from an interdisciplinary perspective, underscoring AI cognition and consciousness within scientific discourse. We believe that those discussions serve as a basis for future research directions and encourage broader societal engagement.

Qiuyuan Huang, Jae Sung Park, Abhinav Gupta et al.

Despite the growing adoption of mixed reality and interactive AI agents, it remains challenging for these systems to generate high quality 2D/3D scenes in unseen environments. The common practice requires deploying an AI agent to collect large amounts of data for model training for every new task. This process is costly, or even impossible, for many domains. In this study, we develop an infinite agent that learns to transfer knowledge memory from general foundation models (e.g. GPT4, DALLE) to novel domains or scenarios for scene understanding and generation in the physical or virtual world. The heart of our approach is an emerging mechanism, dubbed Augmented Reality with Knowledge Inference Interaction (ArK), which leverages knowledge-memory to generate scenes in unseen physical world and virtual reality environments. The knowledge interactive emergent ability (Figure 1) is demonstrated as the observation learns i) micro-action of cross-modality: in multi-modality models to collect a large amount of relevant knowledge memory data for each interaction task (e.g., unseen scene understanding) from the physical reality; and ii) macro-behavior of reality-agnostic: in mix-reality environments to improve interactions that tailor to different characterized roles, target variables, collaborative information, and so on. We validate the effectiveness of ArK on the scene generation and editing tasks. We show that our ArK approach, combined with large foundation models, significantly improves the quality of generated 2D/3D scenes, compared to baselines, demonstrating the potential benefit of incorporating ArK in generative AI for applications such as metaverse and gaming simulation.

Liangke Gui, Borui Wang, Qiuyuan Huang et al.

The primary focus of recent work with largescale transformers has been on optimizing the amount of information packed into the model's parameters. In this work, we ask a different question: Can multimodal transformers leverage explicit knowledge in their reasoning? Existing, primarily unimodal, methods have explored approaches under the paradigm of knowledge retrieval followed by answer prediction, but leave open questions about the quality and relevance of the retrieved knowledge used, and how the reasoning processes over implicit and explicit knowledge should be integrated. To address these challenges, we propose a novel model - Knowledge Augmented Transformer (KAT) - which achieves a strong state-of-the-art result (+6 points absolute) on the open-domain multimodal task of OK-VQA. Our approach integrates implicit and explicit knowledge in an end to end encoder-decoder architecture, while still jointly reasoning over both knowledge sources during answer generation. An additional benefit of explicit knowledge integration is seen in improved interpretability of model predictions in our analysis.

Kezhen Chen, Qiuyuan Huang, Hamid Palangi et al.

Generating formal-language programs represented by relational tuples, such as Lisp programs or mathematical operations, to solve problems stated in natural language is a challenging task because it requires explicitly capturing discrete symbolic structural information implicit in the input. However, most general neural sequence models do not explicitly capture such structural information, limiting their performance on these tasks. In this paper, we propose a new encoder-decoder model based on a structured neural representation, Tensor Product Representations (TPRs), for mapping Natural-language problems to Formal-language solutions, called TP-N2F. The encoder of TP-N2F employs TPR `binding' to encode natural-language symbolic structure in vector space and the decoder uses TPR `unbinding' to generate, in symbolic space, a sequential program represented by relational tuples, each consisting of a relation (or operation) and a number of arguments. TP-N2F considerably outperforms LSTM-based seq2seq models on two benchmarks and creates new state-of-the-art results. Ablation studies show that improvements can be attributed to the use of structured TPRs explicitly in both the encoder and decoder. Analysis of the learned structures shows how TPRs enhance the interpretability of TP-N2F.

Ming Jiang, Junjie Hu, Qiuyuan Huang et al.

Popular metrics used for evaluating image captioning systems, such as BLEU and CIDEr, provide a single score to gauge the system's overall effectiveness. This score is often not informative enough to indicate what specific errors are made by a given system. In this study, we present a fine-grained evaluation method REO for automatically measuring the performance of image captioning systems. REO assesses the quality of captions from three perspectives: 1) Relevance to the ground truth, 2) Extraness of the content that is irrelevant to the ground truth, and 3) Omission of the elements in the images and human references. Experiments on three benchmark datasets demonstrate that our method achieves a higher consistency with human judgments and provides more intuitive evaluation results than alternative metrics.

Ming Jiang, Qiuyuan Huang, Lei Zhang et al.

This paper presents a new metric called TIGEr for the automatic evaluation of image captioning systems. Popular metrics, such as BLEU and CIDEr, are based solely on text matching between reference captions and machine-generated captions, potentially leading to biased evaluations because references may not fully cover the image content and natural language is inherently ambiguous. Building upon a machine-learned text-image grounding model, TIGEr allows to evaluate caption quality not only based on how well a caption represents image content, but also on how well machine-generated captions match human-generated captions. Our empirical tests show that TIGEr has a higher consistency with human judgments than alternative existing metrics. We also comprehensively assess the metric's effectiveness in caption evaluation by measuring the correlation between human judgments and metric scores.

Wenbo Li, Pengchuan Zhang, Lei Zhang et al.

In this paper, we propose Object-driven Attentive Generative Adversarial Newtorks (Obj-GANs) that allow object-centered text-to-image synthesis for complex scenes. Following the two-step (layout-image) generation process, a novel object-driven attentive image generator is proposed to synthesize salient objects by paying attention to the most relevant words in the text description and the pre-generated semantic layout. In addition, a new Fast R-CNN based object-wise discriminator is proposed to provide rich object-wise discrimination signals on whether the synthesized object matches the text description and the pre-generated layout. The proposed Obj-GAN significantly outperforms the previous state of the art in various metrics on the large-scale COCO benchmark, increasing the Inception score by 27% and decreasing the FID score by 11%. A thorough comparison between the traditional grid attention and the new object-driven attention is provided through analyzing their mechanisms and visualizing their attention layers, showing insights of how the proposed model generates complex scenes in high quality.

Xin Wang, Qiuyuan Huang, Asli Celikyilmaz et al.

Vision-language navigation (VLN) is the task of navigating an embodied agent to carry out natural language instructions inside real 3D environments. In this paper, we study how to address three critical challenges for this task: the cross-modal grounding, the ill-posed feedback, and the generalization problems. First, we propose a novel Reinforced Cross-Modal Matching (RCM) approach that enforces cross-modal grounding both locally and globally via reinforcement learning (RL). Particularly, a matching critic is used to provide an intrinsic reward to encourage global matching between instructions and trajectories, and a reasoning navigator is employed to perform cross-modal grounding in the local visual scene. Evaluation on a VLN benchmark dataset shows that our RCM model significantly outperforms previous methods by 10% on SPL and achieves the new state-of-the-art performance. To improve the generalizability of the learned policy, we further introduce a Self-Supervised Imitation Learning (SIL) method to explore unseen environments by imitating its own past, good decisions. We demonstrate that SIL can approximate a better and more efficient policy, which tremendously minimizes the success rate performance gap between seen and unseen environments (from 30.7% to 11.7%).

Qiuyuan Huang, Zhe Gan, Asli Celikyilmaz et al.

We propose a hierarchically structured reinforcement learning approach to address the challenges of planning for generating coherent multi-sentence stories for the visual storytelling task. Within our framework, the task of generating a story given a sequence of images is divided across a two-level hierarchical decoder. The high-level decoder constructs a plan by generating a semantic concept (i.e., topic) for each image in sequence. The low-level decoder generates a sentence for each image using a semantic compositional network, which effectively grounds the sentence generation conditioned on the topic. The two decoders are jointly trained end-to-end using reinforcement learning. We evaluate our model on the visual storytelling (VIST) dataset. Empirical results from both automatic and human evaluations demonstrate that the proposed hierarchically structured reinforced training achieves significantly better performance compared to a strong flat deep reinforcement learning baseline.

Qiuyuan Huang, Pengchuan Zhang, Dapeng Wu et al.

We study in this paper the problems of both image captioning and text-to-image generation, and present a novel turbo learning approach to jointly training an image-to-text generator (a.k.a. CaptionBot) and a text-to-image generator (a.k.a. DrawingBot). The key idea behind the joint training is that image-to-text generation and text-to-image generation as dual problems can form a closed loop to provide informative feedback to each other. Based on such feedback, we introduce a new loss metric by comparing the original input with the output produced by the closed loop. In addition to the old loss metrics used in CaptionBot and DrawingBot, this extra loss metric makes the jointly trained CaptionBot and DrawingBot better than the separately trained CaptionBot and DrawingBot. Furthermore, the turbo-learning approach enables semi-supervised learning since the closed loop can provide pseudo-labels for unlabeled samples. Experimental results on the COCO dataset demonstrate that the proposed turbo learning can significantly improve the performance of both CaptionBot and DrawingBot by a large margin.

Dianqi Li, Qiuyuan Huang, Xiaodong He et al.

We study how to generate captions that are not only accurate in describing an image but also discriminative across different images. The problem is both fundamental and interesting, as most machine-generated captions, despite phenomenal research progresses in the past several years, are expressed in a very monotonic and featureless format. While such captions are normally accurate, they often lack important characteristics in human languages - distinctiveness for each caption and diversity for different images. To address this problem, we propose a novel conditional generative adversarial network for generating diverse captions across images. Instead of estimating the quality of a caption solely on one image, the proposed comparative adversarial learning framework better assesses the quality of captions by comparing a set of captions within the image-caption joint space. By contrasting with human-written captions and image-mismatched captions, the caption generator effectively exploits the inherent characteristics of human languages, and generates more discriminative captions. We show that our proposed network is capable of producing accurate and diverse captions across images.

Qiuyuan Huang, Li Deng, Dapeng Wu et al.

This paper proposes a new architecture - Attentive Tensor Product Learning (ATPL) - to represent grammatical structures in deep learning models. ATPL is a new architecture to bridge this gap by exploiting Tensor Product Representations (TPR), a structured neural-symbolic model developed in cognitive science, aiming to integrate deep learning with explicit language structures and rules. The key ideas of ATPL are: 1) unsupervised learning of role-unbinding vectors of words via TPR-based deep neural network; 2) employing attention modules to compute TPR; and 3) integration of TPR with typical deep learning architectures including Long Short-Term Memory (LSTM) and Feedforward Neural Network (FFNN). The novelty of our approach lies in its ability to extract the grammatical structure of a sentence by using role-unbinding vectors, which are obtained in an unsupervised manner. This ATPL approach is applied to 1) image captioning, 2) part of speech (POS) tagging, and 3) constituency parsing of a sentence. Experimental results demonstrate the effectiveness of the proposed approach.

Pratik Prabhanjan Brahma, Qiuyuan Huang, Dapeng Wu

While deep learning has pushed the boundaries in various machine learning tasks, the current models are still far away from replicating many functions that a normal human brain can do. Explicit memorization based deep architecture have been recently proposed with the objective to understand and predict better. In this work, we design a system that involves a primary learner and an adjacent representational memory bank which is organized using a comparative learner. This spatially forked deep architecture with a structured memory can simultaneously predict and reason about the nature of an input, which may even belong to a category never seen in the training data, by relating it with the memorized past representations at the higher layers. Characterizing images of unseen object classes in both synthetic and real world datasets is used as an example to showcase the operational success of the proposed framework.

Tao Xu, Pengchuan Zhang, Qiuyuan Huang et al.

In this paper, we propose an Attentional Generative Adversarial Network (AttnGAN) that allows attention-driven, multi-stage refinement for fine-grained text-to-image generation. With a novel attentional generative network, the AttnGAN can synthesize fine-grained details at different subregions of the image by paying attentions to the relevant words in the natural language description. In addition, a deep attentional multimodal similarity model is proposed to compute a fine-grained image-text matching loss for training the generator. The proposed AttnGAN significantly outperforms the previous state of the art, boosting the best reported inception score by 14.14% on the CUB dataset and 170.25% on the more challenging COCO dataset. A detailed analysis is also performed by visualizing the attention layers of the AttnGAN. It for the first time shows that the layered attentional GAN is able to automatically select the condition at the word level for generating different parts of the image.

Qiuyuan Huang, Paul Smolensky, Xiaodong He et al.

CAPTCHAs based on reading text are susceptible to machine-learning-based attacks due to recent significant advances in deep learning (DL). To address this, this paper promotes image/visual captioning based CAPTCHAs, which is robust against machine-learning-based attacks. To develop image/visual-captioning-based CAPTCHAs, this paper proposes a new image captioning architecture by exploiting tensor product representations (TPR), a structured neural-symbolic framework developed in cognitive science over the past 20 years, with the aim of integrating DL with explicit language structures and rules. We call it the Tensor Product Generation Network (TPGN). The key ideas of TPGN are: 1) unsupervised learning of role-unbinding vectors of words via a TPR-based deep neural network, and 2) integration of TPR with typical DL architectures including Long Short-Term Memory (LSTM) models. The novelty of our approach lies in its ability to generate a sentence and extract partial grammatical structure of the sentence by using role-unbinding vectors, which are obtained in an unsupervised manner. Experimental results demonstrate the effectiveness of the proposed approach.

Qiuyuan Huang, Paul Smolensky, Xiaodong He et al.

We present a new approach to the design of deep networks for natural language processing (NLP), based on the general technique of Tensor Product Representations (TPRs) for encoding and processing symbol structures in distributed neural networks. A network architecture --- the Tensor Product Generation Network (TPGN) --- is proposed which is capable in principle of carrying out TPR computation, but which uses unconstrained deep learning to design its internal representations. Instantiated in a model for image-caption generation, TPGN outperforms LSTM baselines when evaluated on the COCO dataset. The TPR-capable structure enables interpretation of internal representations and operations, which prove to contain considerable grammatical content. Our caption-generation model can be interpreted as generating sequences of grammatical categories and retrieving words by their categories from a plan encoded as a distributed representation.