We introduce a novel method for pre-training of large-scale vision encoders. Building on recent advancements in autoregressive pre-training of vision models, we extend this framework to a multimodal setting, i.e., images and text. In this paper, we present AIMV2, a family of generalist vision encoders characterized by a straightforward pre-training process, scalability, and remarkable performance across a range of downstream tasks. This is achieved by pairing the vision encoder with a multimodal decoder that autoregressively generates raw image patches and text tokens. Our encoders excel not only in multimodal evaluations but also in vision benchmarks such as localization, grounding, and classification. Notably, our AIMV2-3B encoder achieves 89.5% accuracy on ImageNet-1k with a frozen trunk. Furthermore, AIMV2 consistently outperforms state-of-the-art contrastive models (e.g., CLIP, SigLIP) in multimodal image understanding across diverse settings.

Building a generalist model for user interface (UI) understanding is challenging due to various foundational issues, such as platform diversity, resolution variation, and data limitation. In this paper, we introduce Ferret-UI 2, a multimodal large language model (MLLM) designed for universal UI understanding across a wide range of platforms, including iPhone, Android, iPad, Webpage, and AppleTV. Building on the foundation of Ferret-UI, Ferret-UI 2 introduces three key innovations: support for multiple platform types, high-resolution perception through adaptive scaling, and advanced task training data generation powered by GPT-4o with set-of-mark visual prompting. These advancements enable Ferret-UI 2 to perform complex, user-centered interactions, making it highly versatile and adaptable for the expanding diversity of platform ecosystems. Extensive empirical experiments on referring, grounding, user-centric advanced tasks (comprising 9 subtasks $\times$ 5 platforms), GUIDE next-action prediction dataset, and GUI-World multi-platform benchmark demonstrate that Ferret-UI 2 significantly outperforms Ferret-UI, and also shows strong cross-platform transfer capabilities.

Machine unlearning has emerged as an effective strategy for forgetting specific information in the training data. However, with the increasing integration of visual data, privacy concerns in Vision Language Models (VLMs) remain underexplored. To address this, we introduce Facial Identity Unlearning Benchmark (FIUBench), a novel VLM unlearning benchmark designed to robustly evaluate the effectiveness of unlearning algorithms under the Right to be Forgotten setting. Specifically, we formulate the VLM unlearning task via constructing the Fictitious Facial Identity VQA dataset and apply a two-stage evaluation pipeline that is designed to precisely control the sources of information and their exposure levels. In terms of evaluation, since VLM supports various forms of ways to ask questions with the same semantic meaning, we also provide robust evaluation metrics including membership inference attacks and carefully designed adversarial privacy attacks to evaluate the performance of algorithms. Through the evaluation of four baseline VLM unlearning algorithms within FIUBench, we find that all methods remain limited in their unlearning performance, with significant trade-offs between model utility and forget quality. Furthermore, our findings also highlight the importance of privacy attacks for robust evaluations. We hope FIUBench will drive progress in developing more effective VLM unlearning algorithms.

Existing automatic evaluation on text-to-image synthesis can only provide an image-text matching score, without considering the object-level compositionality, which results in poor correlation with human judgments. In this work, we propose LLMScore, a new framework that offers evaluation scores with multi-granularity compositionality. LLMScore leverages the large language models (LLMs) to evaluate text-to-image models. Initially, it transforms the image into image-level and object-level visual descriptions. Then an evaluation instruction is fed into the LLMs to measure the alignment between the synthesized image and the text, ultimately generating a score accompanied by a rationale. Our substantial analysis reveals the highest correlation of LLMScore with human judgments on a wide range of datasets (Attribute Binding Contrast, Concept Conjunction, MSCOCO, DrawBench, PaintSkills). Notably, our LLMScore achieves Kendall's tau correlation with human evaluations that is 58.8% and 31.2% higher than the commonly-used text-image matching metrics CLIP and BLIP, respectively.

This paper presents a detailed study of improving visual representations for vision language (VL) tasks and develops an improved object detection model to provide object-centric representations of images. Compared to the most widely used bottom-up and top-down model [2], the new model is bigger, better-designed for VL tasks, and pre-trained on much larger training corpora that combine multiple public annotated object detection datasets. Therefore, it can generate representations of a richer collection of visual objects and concepts. While previous VL research focuses mainly on improving the vision-language fusion model and leaves the object detection model improvement untouched, we show that visual features matter significantly in VL models. In our experiments we feed the visual features generated by the new object detection model into a Transformer-based VL fusion model OSCAR [20], and utilize an improved approach OSCAR+ to pre-train the VL model and fine-tune it on a wide range of downstream VL tasks. Our results show that the new visual features significantly improve the performance across all VL tasks, creating new state-of-the-art results on seven public benchmarks. Code, models and pre-extracted features are released at https://github.com/pzzhang/VinVL.

Learning to generate text with a given label is a challenging task because natural language sentences are highly variable and ambiguous. It renders difficulties in trade-off between sentence quality and label fidelity. In this paper, we present CARA to alleviate the issue, where two auxiliary classifiers work simultaneously to ensure that (1) the encoder learns disentangled features and (2) the generator produces label-related sentences. Two practical techniques are further proposed to improve the performance, including annealing the learning signal from the auxiliary classifier, and enhancing the encoder with pre-trained language models. To establish a comprehensive benchmark fostering future research, we consider a suite of four datasets, and systematically reproduce three representative methods. CARA shows consistent improvement over the previous methods on the task of label-conditional text generation, and achieves state-of-the-art on the task of attribute transfer.

Learning to navigate in a visual environment following natural-language instructions is a challenging task, because the multimodal inputs to the agent are highly variable, and the training data on a new task is often limited. In this paper, we present the first pre-training and fine-tuning paradigm for vision-and-language navigation (VLN) tasks. By training on a large amount of image-text-action triplets in a self-supervised learning manner, the pre-trained model provides generic representations of visual environments and language instructions. It can be easily used as a drop-in for existing VLN frameworks, leading to the proposed agent PREVALENT. It learns more effectively in new tasks and generalizes better in a previously unseen environment. The performance is validated on three VLN tasks. On the Room-to-Room benchmark, our model improves the state-of-the-art from 47\% to 51\% on success rate weighted by path length. Further, the learned representation is transferable to other VLN tasks. On two recent tasks, vision-and-dialog navigation and ``Help, Anna!'', the proposed PREVALENT leads to significant improvement over existing methods, achieving a new state of the art.

When trained effectively, the Variational Autoencoder (VAE) (Kingma and Welling, 2013;Bowman et al., 2016) can be both a powerful generative model and an effective representation learning framework for natural language.In this paper, we propose the first large-scale language VAE model OPTIMUS 1 .A universal latent embedding space for sentences is first pre-trained on large text corpus, and then fine-tuned for various language generation and understanding tasks.Compared with GPT-2, OPTIMUS enables guided language generation from an abstract level using the latent vectors.Compared with BERT, OPTIMUS can generalize better on low-resource language understanding tasks due to the smooth latent space structure.Extensive experimental results on a wide range of language tasks demonstrate the effectiveness of OPTIMUS.It achieves new state-of-the-art on VAE language modeling benchmarks.Encoder

Training task-completion dialogue agents with reinforcement learning usually requires a large number of real user experiences. The Dyna-Q algorithm extends Q-learning by integrating a world model, and thus can effectively boost training efficiency using simulated experiences generated by the world model. The effectiveness of Dyna-Q, however, depends on the quality of the world model - or implicitly, the pre-specified ratio of real vs. simulated experiences used for Q-learning. To this end, we extend the recently proposed Deep Dyna-Q (DDQ) framework by integrating a switcher that automatically determines whether to use a real or simulated experience for Q-learning. Furthermore, we explore the use of active learning for improving sample efficiency, by encouraging the world model to generate simulated experiences in the stateaction space where the agent has not (fully) explored. Our results show that by combining switcher and active learning, the new framework named as Switch-based Active Deep Dyna-Q (Switch-DDQ), leads to significant improvement over DDQ and Q-learning baselines in both simulation and human evaluations.1

Given a text description, most existing semantic parsers synthesize a program in one shot. However, it is quite challenging to produce a correct program solely based on the description, which in reality is often ambiguous or incomplete. In this paper, we investigate interactive semantic parsing, where the agent can ask the user clarification questions to resolve ambiguities via a multi-turn dialogue, on an important type of programs called “If-Then recipes.” We develop a hierarchical reinforcement learning (HRL) based agent that significantly improves the parsing performance with minimal questions to the user. Results under both simulation and human evaluation show that our agent substantially outperforms non-interactive semantic parsers and rule-based agents.1

This paper presents a new approach that extends Deep Dyna-Q (DDQ) by incorporating a Budget-Conscious Scheduling (BCS) to best utilize a fixed, small amount of user interactions (budget) for learning task-oriented dialogue agents.BCS consists of (1) a Poissonbased global scheduler to allocate budget over different stages of training; (2) a controller to decide at each training step whether the agent is trained using real or simulated experiences;(3) a user goal sampling module to generate the experiences that are most effective for policy learning.Experiments on a movie-ticket booking task with simulated and real users show that our approach leads to significant improvements in success rate over the state-ofthe-art baselines given the fixed budget.

We present the Frontier Aware Search with backTracking (FAST) Navigator, a general framework for action decoding, that achieves state-of-the-art results on the Room-to-Room (R2R) Vision-and-Language navigation challenge of Anderson et. al. (2018). Given a natural language instruction and photo-realistic image views of a previously unseen environment, the agent was tasked with navigating from source to target location as quickly as possible. While all current approaches make local action decisions or score entire trajectories using beam search, ours balances local and global signals when exploring an unobserved environment. Importantly, this lets us act greedily but use global signals to backtrack when necessary. Applying FAST framework to existing state-of-the-art models achieved a 17% relative gain, an absolute 6% gain on Success rate weighted by Path Length (SPL)1.

Xiujun Li, Chunyuan Li, Qiaolin Xia, Yonatan Bisk, Asli Celikyilmaz, Jianfeng Gao, Noah A. Smith, Yejin Choi. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). 2019.

We present a new algorithm that significantly improves the efficiency of exploration for deep Q-learning agents in dialogue systems. Our agents explore via Thompson sampling, drawing Monte Carlo samples from a Bayes-by-Backprop neural network. Our algorithm learns much faster than common exploration strategies such as ε-greedy, Boltzmann, bootstrapping, and intrinsic-reward-based ones. Additionally, we show that spiking the replay buffer with experiences from just a few successful episodes can make Q-learning feasible when it might otherwise fail.

Training a task-completion dialogue agent via reinforcement learning (RL) is costly because it requires many interactions with real users.One common alternative is to use a user simulator.However, a user simulator usually lacks the language complexity of human interlocutors and the biases in its design may tend to degrade the agent.To address these issues, we present Deep Dyna-Q, which to our knowledge is the first deep RL framework that integrates planning for task-completion dialogue policy learning.We incorporate into the dialogue agent a model of the environment, referred to as the world model, to mimic real user response and generate simulated experience.During dialogue policy learning, the world model is constantly updated with real user experience to approach real user behavior, and in turn, the dialogue agent is optimized using both real experience and simulated experience.The effectiveness of our approach is demonstrated on a movie-ticket booking task in both simulated and human-in-theloop settings 1 .

This paper presents a Discriminative Deep Dyna-Q (D3Q) approach to improving the effectiveness and robustness of Deep Dyna-Q (DDQ), a recently proposed framework that extends the Dyna-Q algorithm to integrate planning for task-completion dialogue policy learning.To obviate DDQ's high dependency on the quality of simulated experiences, we incorporate an RNN-based discriminator in D3Q to differentiate simulated experience from real user experience in order to control the quality of training data.Experiments show that D3Q significantly outperforms DDQ by controlling the quality of simulated experience used for planning.The effectiveness and robustness of D3Q is further demonstrated in a domain extension setting, where the agent's capability of adapting to a changing environment is tested. 1

Developing agents to engage in complex goaloriented dialogues is challenging partly because the main learning signals are very sparse in long conversations.In this paper, we propose a divide-and-conquer approach that discovers and exploits the hidden structure of the task to enable efficient policy learning.First, given successful example dialogues, we propose the Subgoal Discovery Network (SDN) to divide a complex goal-oriented task into a set of simpler subgoals in an unsupervised fashion.We then use these subgoals to learn a multi-level policy by hierarchical reinforcement learning.We demonstrate our method by building a dialogue agent for the composite task of travel planning.Experiments with simulated and real users show that our approach performs competitively against a state-of-theart method that requires human-defined subgoals.Moreover, we show that the learned subgoals are often human comprehensible.

This paper presents a new method - adversarial advantage actor-critic (Adversarial A2C), which significantly improves the efficiency of dialogue policy learning in task-completion dialogue systems. Inspired by generative adversarial networks (GAN), we train a discriminator to differentiate responses/actions generated by dialogue agents from responses/actions by experts. Then, we incorporate the discriminator as another critic into the advantage actor-critic (A2C) framework, to encourage the dialogue agent to explore state-action within the regions where the agent takes actions similar to those of the experts. Experimental results in a movie-ticket booking domain show that the proposed Adversarial A2C can accelerate policy exploration efficiently.

Responses generated by neural conversational models tend to lack informativeness and diversity. We present Adversarial Information Maximization (AIM), an adversarial learning framework that addresses these two related but distinct problems. To foster response diversity, we leverage adversarial training that allows distributional matching of synthetic and real responses. To improve informativeness, our framework explicitly optimizes a variational lower bound on pairwise mutual information between query and response. Empirical results from automatic and human evaluations demonstrate that our methods significantly boost informativeness and diversity.

Bhuwan Dhingra, Lihong Li, Xiujun Li, Jianfeng Gao, Yun-Nung Chen, Faisal Ahmed, Li Deng. Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2017.

Building a dialogue agent to fulfill complex tasks, such as travel planning, is challenging because the agent has to learn to collectively complete multiple subtasks.For example, the agent needs to reserve a hotel and book a flight so that there leaves enough time for commute between arrival and hotel check-in.This paper addresses this challenge by formulating the task in the mathematical framework of options over Markov Decision Processes (MDPs), and proposing a hierarchical deep reinforcement learning approach to learning a dialogue manager that operates at different temporal scales.The dialogue manager consists of: (1) a top-level dialogue policy that selects among subtasks or options, (2) a low-level dialogue policy that selects primitive actions to complete the subtask given by the top-level policy, and (3) a global state tracker that helps ensure all cross-subtask constraints be satisfied.Experiments on a travel planning task with simulated and real users show that our approach leads to significant improvements over three baselines, two based on handcrafted rules and the other based on flat deep reinforcement learning.

Natural language understanding and dialogue policy learning are both essential in conversational systems that predict the next system actions in response to a current user utterance. Conventional approaches aggregate separate models of natural language understanding (NLU) and system action prediction (SAP) as a pipeline that is sensitive to noisy outputs of error-prone NLU. To address the issues, we propose an end-to-end deep recurrent neural network with limited contextual dialogue memory by jointly training NLU and SAP on DSTC4 multi-domain human-human dialogues. Experiments show that our proposed model significantly outperforms the state-of-the-art pipeline models for both NLU and SAP, which indicates that our joint model is capable of mitigating the affects of noisy NLU outputs, and NLU model can be refined by error flows backpropagating from the extra supervised signals of system actions.

One of the major drawbacks of modularized task-completion dialogue systems is that each module is trained individually, which presents several challenges. For example, downstream modules are affected by earlier modules, and the performance of the entire system is not robust to the accumulated errors. This paper presents a novel end-to-end learning framework for task-completion dialogue systems to tackle such issues. Our neural dialogue system can directly interact with a structured database to assist users in accessing information and accomplishing certain tasks. The reinforcement learning based dialogue manager offers robust capabilities to handle noises caused by other components of the dialogue system. Our experiments in a movie-ticket booking domain show that our end-to-end system not only outperforms modularized dialogue system baselines for both objective and subjective evaluation, but also is robust to noises as demonstrated by several systematic experiments with different error granularity and rates specific to the language understanding module.

While it is generally held that network management is tedious and error-prone, it is not well understood which specific management practices increase the risk of failures. Indeed, our survey of 51 network operators reveals a significant diversity of opinions, and our characterization of the management practices in the 850+ networks of a large online service provider shows significant diversity in prevalent practices. Motivated by these observations, we develop a management plane analytics (MPA) framework that an organization can use to: (i) infer which management practices impact network health, and (ii) develop a predictive model of health, based on observed practices, to improve network management. We overcome the challenges of sparse and skewed data by aggregating data from many networks, reducing data dimensionality, and oversampling minority cases. Our learned models predict network health with an accuracy of 76-89%, and our causal analysis uncovers some high impact practices that operators thought had a low impact on network health. Our tool is publicly available, so organizations can analyze their own management practices.

Point-of-care (POC) diagnostics is playing an increasingly important role in public health, environmental monitoring, and food safety analysis. Smartphones, alone or in conjunction with add-on devices, have shown great capability of data collection, analysis, display, and transmission, making them popular in POC diagnostics. In this article, the state-of-the-art advances in smartphone-based POC diagnostic technologies and their applications in the past few years are outlined, ranging fromin vivotests that use smartphone's built-in/external sensors to detect biological signals toin vitrotests that involves complicated biochemical reactions. Novel techniques are illustrated by a number of attractive examples, followed by a brief discussion of the smartphone's role in telemedicine. The challenges and perspectives of smartphone-based POC diagnostics are also provided.