Qian Yang

Yunfei Chu, Jin Xu, Qian Yang et al.

We introduce the latest progress of Qwen-Audio, a large-scale audio-language model called Qwen2-Audio, which is capable of accepting various audio signal inputs and performing audio analysis or direct textual responses with regard to speech instructions. In contrast to complex hierarchical tags, we have simplified the pre-training process by utilizing natural language prompts for different data and tasks, and have further expanded the data volume. We have boosted the instruction-following capability of Qwen2-Audio and implemented two distinct audio interaction modes for voice chat and audio analysis. In the voice chat mode, users can freely engage in voice interactions with Qwen2-Audio without text input. In the audio analysis mode, users could provide audio and text instructions for analysis during the interaction. Note that we do not use any system prompts to switch between voice chat and audio analysis modes. Qwen2-Audio is capable of intelligently comprehending the content within audio and following voice commands to respond appropriately. For instance, in an audio segment that simultaneously contains sounds, multi-speaker conversations, and a voice command, Qwen2-Audio can directly understand the command and provide an interpretation and response to the audio. Additionally, DPO has optimized the model's performance in terms of factuality and adherence to desired behavior. According to the evaluation results from AIR-Bench, Qwen2-Audio outperformed previous SOTAs, such as Gemini-1.5-pro, in tests focused on audio-centric instruction-following capabilities. Qwen2-Audio is open-sourced with the aim of fostering the advancement of the multi-modal language community.

Ziyue Jiang, Zhe Su, Zhou Zhao et al. · cmu

Polyphone disambiguation aims to capture accurate pronunciation knowledge from natural text sequences for reliable Text-to-speech (TTS) systems. However, previous approaches require substantial annotated training data and additional efforts from language experts, making it difficult to extend high-quality neural TTS systems to out-of-domain daily conversations and countless languages worldwide. This paper tackles the polyphone disambiguation problem from a concise and novel perspective: we propose Dict-TTS, a semantic-aware generative text-to-speech model with an online website dictionary (the existing prior information in the natural language). Specifically, we design a semantics-to-pronunciation attention (S2PA) module to match the semantic patterns between the input text sequence and the prior semantics in the dictionary and obtain the corresponding pronunciations; The S2PA module can be easily trained with the end-to-end TTS model without any annotated phoneme labels. Experimental results in three languages show that our model outperforms several strong baseline models in terms of pronunciation accuracy and improves the prosody modeling of TTS systems. Further extensive analyses demonstrate that each design in Dict-TTS is effective. The code is available at \url{https://github.com/Zain-Jiang/Dict-TTS}.

Qian Yang, Qian Chen, Wen Wang et al. · mila

Multi-modal multi-hop question answering involves answering a question by reasoning over multiple input sources from different modalities. Existing methods often retrieve evidences separately and then use a language model to generate an answer based on the retrieved evidences, and thus do not adequately connect candidates and are unable to model the interdependent relations during retrieval. Moreover, the pipelined approaches of retrieval and generation might result in poor generation performance when retrieval performance is low. To address these issues, we propose a Structured Knowledge and Unified Retrieval-Generation (SKURG) approach. SKURG employs an Entity-centered Fusion Encoder to align sources from different modalities using shared entities. It then uses a unified Retrieval-Generation Decoder to integrate intermediate retrieval results for answer generation and also adaptively determine the number of retrieval steps. Extensive experiments on two representative multi-modal multi-hop QA datasets MultimodalQA and WebQA demonstrate that SKURG outperforms the state-of-the-art models in both source retrieval and answer generation performance with fewer parameters. Our code is available at https://github.com/HITsz-TMG/SKURG.

Shengpeng Ji, Ziyue Jiang, Wen Wang et al.

Language models have been effectively applied to modeling natural signals, such as images, video, speech, and audio. A crucial component of these models is the codec tokenizer, which compresses high-dimensional natural signals into lower-dimensional discrete tokens. In this paper, we introduce WavTokenizer, which offers several advantages over previous SOTA acoustic codec models in the audio domain: 1)extreme compression. By compressing the layers of quantizers and the temporal dimension of the discrete codec, one-second audio of 24kHz sampling rate requires only a single quantizer with 40 or 75 tokens. 2)improved subjective quality. Despite the reduced number of tokens, WavTokenizer achieves state-of-the-art reconstruction quality with outstanding UTMOS scores and inherently contains richer semantic information. Specifically, we achieve these results by designing a broader VQ space, extended contextual windows, and improved attention networks, as well as introducing a powerful multi-scale discriminator and an inverse Fourier transform structure. We conducted extensive reconstruction experiments in the domains of speech, audio, and music. WavTokenizer exhibited strong performance across various objective and subjective metrics compared to state-of-the-art models. We also tested semantic information, VQ utilization, and adaptability to generative models. Comprehensive ablation studies confirm the necessity of each module in WavTokenizer. The related code, demos, and pre-trained models are available at https://github.com/jishengpeng/WavTokenizer.

Chandrayee Basu, Rosni Vasu, Michihiro Yasunaga et al.

Automatic medical text simplification can assist providers with patient-friendly communication and make medical texts more accessible, thereby improving health literacy. But curating a quality corpus for this task requires the supervision of medical experts. In this work, we present $\textbf{Med-EASi}$ ($\underline{\textbf{Med}}$ical dataset for $\underline{\textbf{E}}$laborative and $\underline{\textbf{A}}$bstractive $\underline{\textbf{Si}}$mplification), a uniquely crowdsourced and finely annotated dataset for supervised simplification of short medical texts. Its $\textit{expert-layman-AI collaborative}$ annotations facilitate $\textit{controllability}$ over text simplification by marking four kinds of textual transformations: elaboration, replacement, deletion, and insertion. To learn medical text simplification, we fine-tune T5-large with four different styles of input-output combinations, leading to two control-free and two controllable versions of the model. We add two types of $\textit{controllability}$ into text simplification, by using a multi-angle training approach: $\textit{position-aware}$, which uses in-place annotated inputs and outputs, and $\textit{position-agnostic}$, where the model only knows the contents to be edited, but not their positions. Our results show that our fine-grained annotations improve learning compared to the unannotated baseline. Furthermore, $\textit{position-aware}$ control generates better simplification than the $\textit{position-agnostic}$ one. The data and code are available at https://github.com/Chandrayee/CTRL-SIMP.

Ziyue Jiang, Yi Ren, Zhenhui Ye et al.

Scaling text-to-speech to a large and wild dataset has been proven to be highly effective in achieving timbre and speech style generalization, particularly in zero-shot TTS. However, previous works usually encode speech into latent using audio codec and use autoregressive language models or diffusion models to generate it, which ignores the intrinsic nature of speech and may lead to inferior or uncontrollable results. We argue that speech can be decomposed into several attributes (e.g., content, timbre, prosody, and phase) and each of them should be modeled using a module with appropriate inductive biases. From this perspective, we carefully design a novel and large zero-shot TTS system called Mega-TTS, which is trained with large-scale wild data and models different attributes in different ways: 1) Instead of using latent encoded by audio codec as the intermediate feature, we still choose spectrogram as it separates the phase and other attributes very well. Phase can be appropriately constructed by the GAN-based vocoder and does not need to be modeled by the language model. 2) We model the timbre using global vectors since timbre is a global attribute that changes slowly over time. 3) We further use a VQGAN-based acoustic model to generate the spectrogram and a latent code language model to fit the distribution of prosody, since prosody changes quickly over time in a sentence, and language models can capture both local and long-range dependencies. We scale Mega-TTS to multi-domain datasets with 20K hours of speech and evaluate its performance on unseen speakers. Experimental results demonstrate that Mega-TTS surpasses state-of-the-art TTS systems on zero-shot TTS, speech editing, and cross-lingual TTS tasks, with superior naturalness, robustness, and speaker similarity due to the proper inductive bias of each module. Audio samples are available at https://mega-tts.github.io/demo-page.

Yunfei Chu, Jin Xu, Xiaohuan Zhou et al.

Recently, instruction-following audio-language models have received broad attention for audio interaction with humans. However, the absence of pre-trained audio models capable of handling diverse audio types and tasks has hindered progress in this field. Consequently, most existing works have only been able to support a limited range of interaction capabilities. In this paper, we develop the Qwen-Audio model and address this limitation by scaling up audio-language pre-training to cover over 30 tasks and various audio types, such as human speech, natural sounds, music, and songs, to facilitate universal audio understanding abilities. However, directly co-training all tasks and datasets can lead to interference issues, as the textual labels associated with different datasets exhibit considerable variations due to differences in task focus, language, granularity of annotation, and text structure. To overcome the one-to-many interference, we carefully design a multi-task training framework by conditioning on a sequence of hierarchical tags to the decoder for encouraging knowledge sharing and avoiding interference through shared and specified tags respectively. Remarkably, Qwen-Audio achieves impressive performance across diverse benchmark tasks without requiring any task-specific fine-tuning, surpassing its counterparts. Building upon the capabilities of Qwen-Audio, we further develop Qwen-Audio-Chat, which allows for input from various audios and text inputs, enabling multi-turn dialogues and supporting various audio-central scenarios.

Qian Yang, Yunxin Li, Baotian Hu et al. · mila

Visual Entailment with natural language explanations aims to infer the relationship between a text-image pair and generate a sentence to explain the decision-making process. Previous methods rely mainly on a pre-trained vision-language model to perform the relation inference and a language model to generate the corresponding explanation. However, the pre-trained vision-language models mainly build token-level alignment between text and image yet ignore the high-level semantic alignment between the phrases (chunks) and visual contents, which is critical for vision-language reasoning. Moreover, the explanation generator based only on the encoded joint representation does not explicitly consider the critical decision-making points of relation inference. Thus the generated explanations are less faithful to visual-language reasoning. To mitigate these problems, we propose a unified Chunk-aware Alignment and Lexical Constraint based method, dubbed as CALeC. It contains a Chunk-aware Semantic Interactor (arr. CSI), a relation inferrer, and a Lexical Constraint-aware Generator (arr. LeCG). Specifically, CSI exploits the sentence structure inherent in language and various image regions to build chunk-aware semantic alignment. Relation inferrer uses an attention-based reasoning network to incorporate the token-level and chunk-level vision-language representations. LeCG utilizes lexical constraints to expressly incorporate the words or chunks focused by the relation inferrer into explanation generation, improving the faithfulness and informativeness of the explanations. We conduct extensive experiments on three datasets, and experimental results indicate that CALeC significantly outperforms other competitor models on inference accuracy and quality of generated explanations.

Lai Wei, Zhen Ying, Muyang He et al.

Diabetes is a chronic disease with a significant global health burden, requiring multi-stakeholder collaboration for optimal management. Large language models (LLMs) have shown promise in various healthcare scenarios, but their effectiveness across diverse diabetes tasks remains unproven. Our study introduced a framework to train and validate diabetes-specific LLMs. We first developed a comprehensive data processing pipeline that includes data collection, filtering, augmentation and refinement. This created a high-quality, diabetes-specific dataset and evaluation benchmarks from scratch. Fine-tuned on the collected training dataset, our diabetes-specific LLM family demonstrated state-of-the-art proficiency in processing various diabetes tasks compared to other LLMs. Furthermore, clinical studies revealed the potential applications of our models in diabetes care, including providing personalized healthcare, assisting medical education, and streamlining clinical tasks. Generally, our introduced framework helps develop diabetes-specific LLMs and highlights their potential to enhance clinical practice and provide personalized, data-driven support for diabetes management across different end users. Our codes, benchmarks and models are available at https://github.com/waltonfuture/Diabetica.

Gongbo Zhang, Qiao Jin, Denis Jered McInerney et al. · amazon-science, salesforce

Evidence-based medicine promises to improve the quality of healthcare by empowering medical decisions and practices with the best available evidence. The rapid growth of medical evidence, which can be obtained from various sources, poses a challenge in collecting, appraising, and synthesizing the evidential information. Recent advancements in generative AI, exemplified by large language models, hold promise in facilitating the arduous task. However, developing accountable, fair, and inclusive models remains a complicated undertaking. In this perspective, we discuss the trustworthiness of generative AI in the context of automated summarization of medical evidence.

Jacqueline R. M. A. Maasch, Hao Zhang, Qian Yang et al.

The cost of manual data labeling can be a significant obstacle in supervised learning. Data programming (DP) offers a weakly supervised solution for training dataset creation, wherein the outputs of user-defined programmatic labeling functions (LFs) are reconciled through unsupervised learning. However, DP can fail to outperform an unweighted majority vote in some scenarios, including low-data contexts. This work introduces a Bayesian extension of classical DP that mitigates failures of unsupervised learning by augmenting the DP objective with regularization terms. Regularized learning is achieved through maximum a posteriori estimation with informative priors. Majority vote is proposed as a proxy signal for automated prior parameter selection. Results suggest that regularized DP improves performance relative to maximum likelihood and majority voting, confers greater interpretability, and bolsters performance in low-data regimes.

Qian Yang, Ankur Sikarwar, Huy Le et al.

Cross-view spatial reasoning remains a weak spot for vision-language models (VLMs): they often reason in language and lose the fine-grained geometry needed for the task. Thinking with images aims to address this by generating an intermediate thinking image, but recent work shows that models often ignore the visual evidence in these traces. We therefore ask how to make visual thinking matter, and what kind of visual thinking works best. We study these questions in unified multimodal models (UMMs), which natively support interleaved image-text generation. For the first question, we propose View Dropout (VDrop), a training-time intervention that hides parts of one input view from the answer span while keeping them visible to the thinking-image tokens. This encourages the model to use the thinking image when answering, instead of relying only on the input views. Once the thinking image is used for answer prediction, we study which type of visual thinking is most effective. We frame this as a learnability-informativeness tradeoff and compare three thinking-image variants: top-down, panoramic, and point-matching renderings. Trained on synthetic scenes and evaluated on five real-world out-of-domain benchmarks, panoramic visual thinking with VDrop is the only configuration that is both informative and learnable, and it achieves the best out-of-domain generalization.

Fernando Delgado, Stephen Yang, Michael Madaio et al.

Despite the growing consensus that stakeholders affected by AI systems should participate in their design, enormous variation and implicit disagreements exist among current approaches. For researchers and practitioners who are interested in taking a participatory approach to AI design and development, it remains challenging to assess the extent to which any participatory approach grants substantive agency to stakeholders. This article thus aims to ground what we dub the "participatory turn" in AI design by synthesizing existing theoretical literature on participation and through empirical investigation and critique of its current practices. Specifically, we derive a conceptual framework through synthesis of literature across technology design, political theory, and the social sciences that researchers and practitioners can leverage to evaluate approaches to participation in AI design. Additionally, we articulate empirical findings concerning the current state of participatory practice in AI design based on an analysis of recently published research and semi-structured interviews with 12 AI researchers and practitioners. We use these empirical findings to understand the current state of participatory practice and subsequently provide guidance to better align participatory goals and methods in a way that accounts for practical constraints.

Qian Yang, Weixiang Yan, Aishwarya Agrawal

Despite tremendous advancements, current state-of-the-art Vision-Language Models (VLMs) are still far from perfect. They tend to hallucinate and may generate biased responses. In such circumstances, having a way to assess the reliability of a given response generated by a VLM is quite useful. Existing methods, such as estimating uncertainty using answer likelihoods or prompt-based confidence generation, often suffer from overconfidence. Other methods use self-consistency comparison but are affected by confirmation biases. To alleviate these, we propose Decompose and Compare Consistency (DeCC) for reliability measurement. By comparing the consistency between the direct answer generated using the VLM's internal reasoning process, and the indirect answers obtained by decomposing the question into sub-questions and reasoning over the sub-answers produced by the VLM, DeCC measures the reliability of VLM's direct answer. Experiments across six vision-language tasks with three VLMs show DeCC's reliability estimation achieves better correlation with task accuracy compared to the existing methods.

Meituan LongCat Team, Bairui Wang, Bayan et al.

We introduce LongCat-Flash-Omni, a state-of-the-art open-source omni-modal model with 560 billion parameters, excelling at real-time audio-visual interaction. By adopting a curriculum-inspired progressive training strategy that transitions from simpler to increasingly complex modality sequence modeling tasks, LongCat-Flash-Omni attains comprehensive multimodal capabilities while maintaining strong unimodal capability. Building upon LongCat-Flash, which adopts a high-performance Shortcut-connected Mixture-of-Experts (MoE) architecture with zero-computation experts, LongCat-Flash-Omni integrates efficient multimodal perception and speech reconstruction modules. Despite its immense size of 560B parameters (with 27B activated), LongCat-Flash-Omni achieves low-latency real-time audio-visual interaction. For training infrastructure, we developed a modality-decoupled parallelism scheme specifically designed to manage the data and model heterogeneity inherent in large-scale multimodal training. This innovative approach demonstrates exceptional efficiency by sustaining over 90% of the throughput achieved by text-only training. Extensive evaluations show that LongCat-Flash-Omni achieves state-of-the-art performance on omni-modal benchmarks among open-source models. Furthermore, it delivers highly competitive results across a wide range of modality-specific tasks, including text, image, and video understanding, as well as audio understanding and generation. We provide a comprehensive overview of the model architecture design, training procedures, and data strategies, and open-source the model to foster future research and development in the community.

Shengpeng Ji, Yifu Chen, Minghui Fang et al.

Recent advancements in spoken dialogue models, exemplified by systems like GPT-4o, have captured significant attention in the speech domain. Compared to traditional three-tier cascaded spoken dialogue models that comprise speech recognition (ASR), large language models (LLMs), and text-to-speech (TTS), modern spoken dialogue models exhibit greater intelligence. These advanced spoken dialogue models not only comprehend audio, music, and other speech-related features, but also capture stylistic and timbral characteristics in speech. Moreover, they generate high-quality, multi-turn speech responses with low latency, enabling real-time interaction through simultaneous listening and speaking capability. Despite the progress in spoken dialogue systems, there is a lack of comprehensive surveys that systematically organize and analyze these systems and the underlying technologies. To address this, we have first compiled existing spoken dialogue systems in the chronological order and categorized them into the cascaded and end-to-end paradigms. We then provide an in-depth overview of the core technologies in spoken dialogue models, covering aspects such as speech representation, training paradigm, streaming, duplex, and interaction capabilities. Each section discusses the limitations of these technologies and outlines considerations for future research. Additionally, we present a thorough review of relevant datasets, evaluation metrics, and benchmarks from the perspectives of training and evaluating spoken dialogue systems. We hope this survey will contribute to advancing both academic research and industrial applications in the field of spoken dialogue systems. The related material is available at https://github.com/jishengpeng/WavChat.

Qian Yang, Jessie Jia, Elaine Tsai et al.

Interactive, multi-agent social simulation systems have shown promise for helping users practice navigating various complex social situations across domains. This paper asks: To what extent can such systems help young adult (YA) bystanders speak up publicly against cyberbullying, a task often thwarted by complex, multi-party social dynamics? We created Upstanders' Practicum, a multi-AI-agent social media simulation powered by Large Language Models (LLMs), as a probe and observed 34 YAs freely practicing public bystander intervention across three iteratively refined versions. We found that practicing public bystander intervention in the simulation was helpful, but after participants made three attention shifts: (1) from inattention to paying true attention, (2) from self-focus ("I don't usually do this'') to attending to those directly involved, and (3) from resolving the private conflict between bully and victim ("maybe I could set up the meeting between them'') to addressing the broader audience online ("public comment is about norm-setting"). Only after these shifts did practice in the simulation start to help: participants then saw a reason to speak up publicly and, through continued practice, crafted tactful public messages without explicit instruction. These findings illuminate new design and research opportunities for bystander education beyond social skill instruction, namely, designing for true attention, for fostering a vocal upstander identity, and for seeing bystander intervention as public norm setting. In addition, we open-source Truman Agents (cornell-design-aigroup.github.io/TrumanAgents/), the first-of-its-kind multi-LLM-agent social media simulation platform that Upstanders' Practicum builds upon, for future cyberbullying and social media research.

Yuchen Tian, Weixiang Yan, Qian Yang et al. · berkeley, mila

Large Language Models (LLMs) have made significant progress in code generation, offering developers groundbreaking automated programming support. However, LLMs often generate code that is syntactically correct and even semantically plausible, but may not execute as expected or fulfill specified requirements. This phenomenon of hallucinations in the code domain has not been systematically explored. To advance the community's understanding and research on this issue, we introduce the concept of code hallucinations and propose a classification method for code hallucination based on execution verification. We categorize code hallucinations into four main types: mapping, naming, resource, and logic hallucinations, with each category further divided into different subcategories to understand and address the unique challenges faced by LLMs in code generation with finer granularity. Additionally, we present a dynamic detection algorithm called CodeHalu designed to detect and quantify code hallucinations. We also introduce the CodeHaluEval benchmark, which includes 8,883 samples from 699 tasks, to systematically and quantitatively evaluate code hallucinations. By evaluating 17 popular LLMs using this benchmark, we reveal significant differences in their accuracy and reliability in code generation, offering detailed insights for further improving the code generation capabilities of LLMs. The CodeHalu benchmark and code are publicly available at https://github.com/yuchen814/CodeHalu.

Le Zhang, Qian Yang, Aishwarya Agrawal · mila

How well are unimodal vision and language models aligned? Although prior work have approached answering this question, their assessment methods do not directly translate to how these models are used in practical vision-language tasks. In this paper, we propose a direct assessment method, inspired by linear probing, to assess vision-language alignment. We identify that the degree of alignment of the SSL vision models depends on their SSL training objective, and we find that the clustering quality of SSL representations has a stronger impact on alignment performance than their linear separability. Next, we introduce Swift Alignment of Image and Language (SAIL), a efficient transfer learning framework that aligns pretrained unimodal vision and language models for downstream vision-language tasks. Since SAIL leverages the strengths of pretrained unimodal models, it requires significantly fewer (6%) paired image-text data for the multimodal alignment compared to models like CLIP which are trained from scratch. SAIL training only requires a single A100 GPU, 5 hours of training and can accommodate a batch size up to 32,768. SAIL achieves 73.4% zero-shot accuracy on ImageNet (vs. CLIP's 72.7%) and excels in zero-shot retrieval, complex reasoning, and semantic segmentation. Additionally, SAIL improves the language-compatibility of vision encoders that in turn enhance the performance of multimodal large language models. The entire codebase and model weights are open-source: https://lezhang7.github.io/sail.github.io/

Yushuo Niu, Ethan Chadwick, Anson W. K. Ma et al.

Automatic defect detection for 3D printing processes, which shares many characteristics with change detection problems, is a vital step for quality control of 3D printed products. However, there are some critical challenges in the current state of practice. First, existing methods for computer vision-based process monitoring typically work well only under specific camera viewpoints and lighting situations, requiring expensive pre-processing, alignment, and camera setups. Second, many defect detection techniques are specific to pre-defined defect patterns and/or print schematics. In this work, we approach the defect detection problem using a novel Semi-Siamese deep learning model that directly compares a reference schematic of the desired print and a camera image of the achieved print. The model then solves an image segmentation problem, precisely identifying the locations of defects of different types with respect to the reference schematic. Our model is designed to enable comparison of heterogeneous images from different domains while being robust against perturbations in the imaging setup such as different camera angles and illumination. Crucially, we show that our simple architecture, which is easy to pre-train for enhanced performance on new datasets, outperforms more complex state-of-the-art approaches based on generative adversarial networks and transformers. Using our model, defect localization predictions can be made in less than half a second per layer using a standard MacBook Pro while achieving an F1-score of more than 0.9, demonstrating the efficacy of using our method for in-situ defect detection in 3D printing.

Jianping Zhao, Qiong Zhou, Tian Wang et al.

MolProphecy is a human-in-the-loop (HITL) multi-modal framework designed to integrate chemists' domain knowledge into molecular property prediction models. While molecular pre-trained models have enabled significant gains in predictive accuracy, they often fail to capture the tacit, interpretive reasoning central to expert-driven molecular design. To address this, MolProphecy employs ChatGPT as a virtual chemist to simulate expert-level reasoning and decision-making. The generated chemist knowledge is embedded by the large language model (LLM) as a dedicated knowledge representation and then fused with graph-based molecular features through a gated cross-attention mechanism, enabling joint reasoning over human-derived and structural features. Evaluated on four benchmark datasets (FreeSolv, BACE, SIDER, and ClinTox), MolProphecy outperforms state-of-the-art (SOTA) models, achieving a 15.0 percent reduction in RMSE on FreeSolv and a 5.39 percent improvement in AUROC on BACE. Analysis reveals that chemist knowledge and structural features provide complementary contributions, improving both accuracy and interpretability. MolProphecy offers a practical and generalizable approach for collaborative drug discovery, with the flexibility to incorporate real chemist input in place of the current simulated proxy--without the need for model retraining. The implementation is publicly available at https://github.com/zhangruochi/MolProphecy.

Qian Yang, Jin Xu, Wenrui Liu et al.

Recently, instruction-following audio-language models have received broad attention for human-audio interaction. However, the absence of benchmarks capable of evaluating audio-centric interaction capabilities has impeded advancements in this field. Previous models primarily focus on assessing different fundamental tasks, such as Automatic Speech Recognition (ASR), and lack an assessment of the open-ended generative capabilities centered around audio. Thus, it is challenging to track the progression in the Large Audio-Language Models (LALMs) domain and to provide guidance for future improvement. In this paper, we introduce AIR-Bench (\textbf{A}udio \textbf{I}nst\textbf{R}uction \textbf{Bench}mark), the first benchmark designed to evaluate the ability of LALMs to understand various types of audio signals (including human speech, natural sounds, and music), and furthermore, to interact with humans in the textual format. AIR-Bench encompasses two dimensions: \textit{foundation} and \textit{chat} benchmarks. The former consists of 19 tasks with approximately 19k single-choice questions, intending to inspect the basic single-task ability of LALMs. The latter one contains 2k instances of open-ended question-and-answer data, directly assessing the comprehension of the model on complex audio and its capacity to follow instructions. Both benchmarks require the model to generate hypotheses directly. We design a unified framework that leverages advanced language models, such as GPT-4, to evaluate the scores of generated hypotheses given the meta-information of the audio. Experimental results demonstrate a high level of consistency between GPT-4-based evaluation and human evaluation. By revealing the limitations of existing LALMs through evaluation results, AIR-Bench can provide insights into the direction of future research.

Qian Yang, Zhouyuan Huo, Wenlin Wang et al.

Language models are essential for natural language processing (NLP) tasks, such as machine translation and text summarization. Remarkable performance has been demonstrated recently across many NLP domains via a Transformer-based language model with over a billion parameters, verifying the benefits of model size. Model parallelism is required if a model is too large to fit in a single computing device. Current methods for model parallelism either suffer from backward locking in backpropagation or are not applicable to language models. We propose the first model-parallel algorithm that speeds the training of Transformer-based language models. We also prove that our proposed algorithm is guaranteed to converge to critical points for non-convex problems. Extensive experiments on Transformer and Transformer-XL language models demonstrate that the proposed algorithm obtains a much faster speedup beyond data parallelism, with comparable or better accuracy. Code to reproduce experiments is to be found at \url{https://github.com/LaraQianYang/Ouroboros}.

Qian Yang, Miaomiao Wang, Abdelhamid Tayebi

This paper proposes a model predictive trajectory tracking approach for quadrotors subject to input constraints. Our proposed approach relies on a hierarchical control strategy with an outer-loop feedback generating the required thrust and desired attitude and an inner-loop feedback regulating the actual attitude to the desired one. For the outer-loop translational dynamics, the generation of the virtual control input is formulated as a constrained model predictive control problem with time-varying input constraints and a control strategy, endowed with uniform global asymptotic stability guarantees, is proposed. For the inner-loop rotational dynamics, a hybrid geometric controller is adopted, achieving semi-global exponential tracking of the desired attitude. Finally, we prove that the overall cascaded system is semi-globally asymptotically stable. Simulation results illustrate the effectiveness of the proposed approach.

Michael A. Hedderich, Natalie N. Bazarova, Wenting Zou et al.

Cyberbullying harms teenagers' mental health, and teaching them upstanding intervention is crucial. Wizard-of-Oz studies show chatbots can scale up personalized and interactive cyberbullying education, but implementing such chatbots is a challenging and delicate task. We created a no-code chatbot design tool for K-12 teachers. Using large language models and prompt chaining, our tool allows teachers to prototype bespoke dialogue flows and chatbot utterances. In offering this tool, we explore teachers' distinctive needs when designing chatbots to assist their teaching, and how chatbot design tools might better support them. Our findings reveal that teachers welcome the tool enthusiastically. Moreover, they see themselves as playwrights guiding both the students' and the chatbot's behaviors, while allowing for some improvisation. Their goal is to enable students to rehearse both desirable and undesirable reactions to cyberbullying in a safe environment. We discuss the design opportunities LLM-Chains offer for empowering teachers and the research opportunities this work opens up.

Jose A. Guridi, Cristobal Cheyre, Qian Yang

Natural language processing (NLP) tools have the potential to boost civic participation and enhance democratic processes because they can significantly increase governments' capacity to gather and analyze citizen opinions. However, their adoption in government remains limited, and harnessing their benefits while preventing unintended consequences remains a challenge. While prior work has focused on improving NLP performance, this work examines how different internal government stakeholders influence NLP tools' thoughtful adoption. We interviewed seven politicians (politically appointed officials as heads of government institutions) and thirteen public servants (career government employees who design and administrate policy interventions), inquiring how they choose whether and how to use NLP tools to support civic participation processes. The interviews suggest that policymakers across both groups focused on their needs for career advancement and the need to showcase the legitimacy and fairness of their work when considering NLP tool adoption and use. Because these needs vary between politicians and public servants, their preferred NLP features and tool designs also differ. Interestingly, despite their differing needs and opinions, neither group clearly identifies who should advocate for NLP adoption to enhance civic participation or address the unintended consequences of a poorly considered adoption. This lack of clarity in responsibility might have caused the governments' low adoption of NLP tools. We discuss how these findings reveal new insights for future HCI research. They inform the design of NLP tools for increasing civic participation efficiency and capacity, the design of other tools and methods that ensure thoughtful adoption of AI tools in government, and the design of NLP tools for collaborative use among users with different incentives and needs.

Kanishk Jain, Qian Yang, Shravan Nayak et al.

Vision-language Models (VLMs), despite achieving strong performance on multimodal benchmarks, often misinterpret straightforward visual concepts that humans identify effortlessly, such as counting, spatial reasoning, and viewpoint understanding. Previous studies manually identified these weaknesses and found that they often stem from deficits in specific skills. However, such manual efforts are costly, unscalable, and subject to human bias, which often overlooks subtle details in favor of salient objects, resulting in an incomplete understanding of a model's vulnerabilities. To address these limitations, we propose a Reinforcement Learning (RL)-based framework to automatically discover the failure modes or blind spots of any candidate VLM on a given data distribution without human intervention. Our framework trains a questioner agent that adaptively generates queries based on the candidate VLM's responses to elicit incorrect answers. Our approach increases question complexity by focusing on fine-grained visual details and distinct skill compositions as training progresses, consequently identifying 36 novel failure modes in which VLMs struggle. We demonstrate the broad applicability of our framework by showcasing its generalizability across various model combinations.

Tao Long, Sitong Wang, Émilie Fabre et al.

UIST researchers develop tools to address user challenges. However, user interactions with AI evolve over time through learning, adaptation, and repurposing, making one time evaluations insufficient. Capturing these dynamics requires longer-term studies, but challenges in deployment, evaluation design, and data collection have made such longitudinal research difficult to implement. Our workshop aims to tackle these challenges and prepare researchers with practical strategies for longitudinal studies. The workshop includes a keynote, panel discussions, and interactive breakout groups for discussion and hands-on protocol design and tool prototyping sessions. We seek to foster a community around longitudinal system research and promote it as a more embraced method for designing, building, and evaluating UIST tools.

Shivam Chandhok, Qian Yang, Oscar Manas et al.

Instruction tuning has been central to the success of recent vision-language models (VLMs), but it remains expensive-requiring large-scale datasets, high-quality annotations, and large compute budgets. We propose PRioritized cOncept learninG via Relative Error-driven Sample Selection (PROGRESS), a data- and compute-efficient framework that enables VLMs to dynamically select what to learn next based on their evolving needs during training. At each stage, the model tracks its learning progress across skills and selects the most informative samples-those it has not already mastered and that are not too difficult to learn at the current stage of training. This strategy effectively controls skill acquisition and the order in which skills are learned. Specifically, we sample from skills showing the highest learning progress, prioritizing those with the most rapid improvement. Unlike prior methods, PROGRESS requires no upfront answer annotations, queries answers only on a need basis, avoids reliance on additional supervision from auxiliary VLMs, and does not require compute-heavy gradient computations for data selection. Experiments across multiple instruction-tuning datasets of varying scales demonstrate that PROGRESS consistently outperforms state-of-the-art baselines with much less data and supervision. Additionally, we show strong cross-architecture generalization and transferability to larger models, validating PROGRESS as a scalable solution for efficient learning.

Hauke Sandhaus, Angel Hsing-Chi Hwang, Wendy Ju et al.

Safety-critical data, such as crash and near-crash records, are crucial to improving autonomous vehicle (AV) design and development. Sharing such data across AV companies, academic researchers, regulators, and the public can help make all AVs safer. However, AV companies rarely share safety-critical data externally. This paper aims to pinpoint why AV companies are reluctant to share safety-critical data, with an eye on how these barriers can inform new approaches to promote sharing. We interviewed twelve AV company employees who actively work with such data in their day-to-day work. Findings suggest two key, previously unknown barriers to data sharing: (1) Datasets inherently embed salient knowledge that is key to improving AV safety and are resource-intensive. Therefore, data sharing, even within a company, is fraught with politics. (2) Interviewees believed AV safety knowledge is private knowledge that brings competitive edges to their companies, rather than public knowledge for social good. We discuss the implications of these findings for incentivizing and enabling safety-critical AV data sharing, specifically, implications for new approaches to (1) debating and stratifying public and private AV safety knowledge, (2) innovating data tools and data sharing pipelines that enable easier sharing of public AV safety data and knowledge; (3) offsetting costs of curating safety-critical data and incentivizing data sharing.

Khonzoda Umarova, Talia Wise, Zhuoer Lyu et al.

Writing about a subject enriches writers' understanding of that subject. This cognitive benefit of writing -- known as constructive learning -- is essential to how students learn in various disciplines. However, does this benefit persist when students write with generative AI writing assistants? Prior research suggests the answer varies based on the type of AI, e.g., auto-complete systems tend to hinder ideation, while assistants that pose Socratic questions facilitate it. This paper adds an additional perspective. Through a case study, we demonstrate that the impact of genAI on students' idea development depends not only on the AI but also on the students and, crucially, their interactions in between. Students who proactively explored ideas gained new ideas from writing, regardless of whether they used auto-complete or Socratic AI assistants. Those who engaged in prolonged, mindless copyediting developed few ideas even with a Socratic AI. These findings suggest opportunities in designing AI writing assistants, not merely by creating more thought-provoking AI, but also by fostering more thought-provoking writer-AI interactions.

Soumyashree Sahoo, Chinmaey Shende, Md. Zakir Hossain et al.

Currently, depression treatment relies on closely monitoring patients response to treatment and adjusting the treatment as needed. Using self-reported or physician-administrated questionnaires to monitor treatment response is, however, burdensome, costly and suffers from recall bias. In this paper, we explore using location sensory data collected passively on smartphones to predict treatment outcome. To address heterogeneous data collection on Android and iOS phones, the two predominant smartphone platforms, we explore using domain adaptation techniques to map their data to a common feature space, and then use the data jointly to train machine learning models. Our results show that this domain adaptation approach can lead to significantly better prediction than that with no domain adaptation. In addition, our results show that using location features and baseline self-reported questionnaire score can lead to F1 score up to 0.67, comparable to that obtained using periodic self-reported questionnaires, indicating that using location data is a promising direction for predicting depression treatment outcome.

Li Yi, Qian Yang

Liquid scintillation triple-to-doubly coincident ratio (TDCR) spectroscopy is widely adopted as a standard method for radionuclide quantification because of its inherent advantages such as high precision, self-calibrating capability, and independence from radioactive reference sources. However, multiradionuclide analysis via TDCR faces the challenges of limited automation and reliance on mixture-specific standards, which may not be easily available. Here, we present an Artificial Intelligence (AI) framework that combines numerical spectral simulation and deep learning for standard-free automated analysis. $β$ spectra for model training were generated using Geant4 simulations coupled with statistically modeled detector response sampling. A tailored neural network architecture, trained on this dataset covering various nuclei mix ratio and quenching scenarios, enables autonomous resolution of individual radionuclide activities and detecting efficiency through end-to-end learning paradigms. The model delivers consistent high accuracy across tasks: activity proportions (mean absolute error = 0.009), detection efficiencies (mean absolute error = 0.002), and spectral reconstruction (Structural Similarity Index = 0.9998), validating its physical plausibility for quenched $β$ spectroscopy. This AI-driven methodology exhibits significant potential for automated safety-compliant multiradionuclide analysis with robust generalization, real-time processing capabilities, and engineering feasibility, particularly in scenarios where reference materials are unavailable or rapid field analysis is required.

Yushuo Niu, Tianyu Li, Yuanyuan Zhu et al.

Transforming in-situ transmission electron microscopy (TEM) imaging into a tool for spatially-resolved operando characterization of solid-state reactions requires automated, high-precision semantic segmentation of dynamically evolving features. However, traditional deep learning methods for semantic segmentation often encounter limitations due to the scarcity of labeled data, visually ambiguous features of interest, and small-object scenarios. To tackle these challenges, we introduce MultiTaskDeltaNet (MTDN), a novel deep learning architecture that creatively reconceptualizes the segmentation task as a change detection problem. By implementing a unique Siamese network with a U-Net backbone and using paired images to capture feature changes, MTDN effectively utilizes minimal data to produce high-quality segmentations. Furthermore, MTDN utilizes a multi-task learning strategy to leverage correlations between physical features of interest. In an evaluation using data from in-situ environmental TEM (ETEM) videos of filamentous carbon gasification, MTDN demonstrated a significant advantage over conventional segmentation models, particularly in accurately delineating fine structural features. Notably, MTDN achieved a 10.22% performance improvement over conventional segmentation models in predicting small and visually ambiguous physical features. This work bridges several key gaps between deep learning and practical TEM image analysis, advancing automated characterization of nanomaterials in complex experimental settings.

Kiarash Naghavi Khanghah, Zhiling Chen, Lela Romeo et al.

Additive manufacturing enables the fabrication of complex designs while minimizing waste, but faces challenges related to defects and process anomalies. This study presents a novel multimodal Retrieval-Augmented Generation-based framework that automates anomaly detection across various Additive Manufacturing processes leveraging retrieved information from literature, including images and descriptive text, rather than training datasets. This framework integrates text and image retrieval from scientific literature and multimodal generation models to perform zero-shot anomaly identification, classification, and explanation generation in a Laser Powder Bed Fusion setting. The proposed framework is evaluated on four L-PBF manufacturing datasets from Oak Ridge National Laboratory, featuring various printer makes, models, and materials. This evaluation demonstrates the framework's adaptability and generalizability across diverse images without requiring additional training. Comparative analysis using Qwen2-VL-2B and GPT-4o-mini as MLLM within the proposed framework highlights that GPT-4o-mini outperforms Qwen2-VL-2B and proportional random baseline in manufacturing anomalies classification. Additionally, the evaluation of the RAG system confirms that incorporating retrieval mechanisms improves average accuracy by 12% by reducing the risk of hallucination and providing additional information. The proposed framework can be continuously updated by integrating emerging research, allowing seamless adaptation to the evolving landscape of AM technologies. This scalable, automated, and zero-shot-capable framework streamlines AM anomaly analysis, enhancing efficiency and accuracy.

Ruochi Zhang, Qian Yang, Xiaoyang Wang et al.

The rapid accumulation of Electronic Health Records (EHRs) has transformed healthcare by providing valuable data that enhance clinical predictions and diagnoses. While conventional machine learning models have proven effective, they often lack robust representation learning and depend heavily on expert-crafted features. Although deep learning offers powerful solutions, it is often criticized for its lack of interpretability. To address these challenges, we propose DeepSelective, a novel end to end deep learning framework for predicting patient prognosis using EHR data, with a strong emphasis on enhancing model interpretability. DeepSelective combines data compression techniques with an innovative feature selection approach, integrating custom-designed modules that work together to improve both accuracy and interpretability. Our experiments demonstrate that DeepSelective not only enhances predictive accuracy but also significantly improves interpretability, making it a valuable tool for clinical decision-making. The source code is freely available at http://www.healthinformaticslab.org/supp/resources.php .

Qian Yang, Calbert Graham

Voice conversion (VC) modifies voice characteristics while preserving linguistic content. This paper presents the Stepback network, a novel model for converting speaker identity using non-parallel data. Unlike traditional VC methods that rely on parallel data, our approach leverages deep learning techniques to enhance disentanglement completion and linguistic content preservation. The Stepback network incorporates a dual flow of different domain data inputs and uses constraints with self-destructive amendments to optimize the content encoder. Extensive experiments show that our model significantly improves VC performance, reducing training costs while achieving high-quality voice conversion. The Stepback network's design offers a promising solution for advanced voice conversion tasks.

Mina Lee, Percy Liang, Qian Yang

Large language models (LMs) offer unprecedented language generation capabilities and exciting opportunities for interaction design. However, their highly context-dependent capabilities are difficult to grasp and are often subjectively interpreted. In this paper, we argue that by curating and analyzing large interaction datasets, the HCI community can foster more incisive examinations of LMs' generative capabilities. Exemplifying this approach, we present CoAuthor, a dataset designed for revealing GPT-3's capabilities in assisting creative and argumentative writing. CoAuthor captures rich interactions between 63 writers and four instances of GPT-3 across 1445 writing sessions. We demonstrate that CoAuthor can address questions about GPT-3's language, ideation, and collaboration capabilities, and reveal its contribution as a writing "collaborator" under various definitions of good collaboration. Finally, we discuss how this work may facilitate a more principled discussion around LMs' promises and pitfalls in relation to interaction design. The dataset and an interface for replaying the writing sessions are publicly available at https://coauthor.stanford.edu.

Maryam Pardakhti, Nila Mandal, Anson W. K. Ma et al.

Active learning is of great interest for many practical applications, especially in industry and the physical sciences, where there is a strong need to minimize the number of costly experiments necessary to train predictive models. However, there remain significant challenges for the adoption of active learning methods in many practical applications. One important challenge is that many methods assume a fixed model, where model hyperparameters are chosen a priori. In practice, it is rarely true that a good model will be known in advance. Existing methods for active learning with model selection typically depend on a medium-sized labeling budget. In this work, we focus on the case of having a very small labeling budget, on the order of a few dozen data points, and develop a simple and fast method for practical active learning with model selection. Our method is based on an underlying pool-based active learner for binary classification using support vector classification with a radial basis function kernel. First we show empirically that our method is able to find hyperparameters that lead to the best performance compared to an oracle model on less separable, difficult to classify datasets, and reasonable performance on datasets that are more separable and easier to classify. Then, we demonstrate that it is possible to refine our model selection method using a weighted approach to trade-off between achieving optimal performance on datasets that are easy to classify, versus datasets that are difficult to classify, which can be tuned based on prior domain knowledge about the dataset.

Fernando Delgado, Stephen Yang, Michael Madaio et al.

There is a growing consensus in HCI and AI research that the design of AI systems needs to engage and empower stakeholders who will be affected by AI. However, the manner in which stakeholders should participate in AI design is unclear. This workshop paper aims to ground what we dub a 'participatory turn' in AI design by synthesizing existing literature on participation and through empirical analysis of its current practices via a survey of recent published research and a dozen semi-structured interviews with AI researchers and practitioners. Based on our literature synthesis and empirical research, this paper presents a conceptual framework for analyzing participatory approaches to AI design and articulates a set of empirical findings that in ensemble detail out the contemporary landscape of participatory practice in AI design. These findings can help bootstrap a more principled discussion on how PD of AI should move forward across AI, HCI, and other research communities.

Bojian Hou, Hao Zhang, Gur Ladizhinsky et al.

Abstruse learning algorithms and complex datasets increasingly characterize modern clinical decision support systems (CDSS). As a result, clinicians cannot easily or rapidly scrutinize the CDSS recommendation when facing a difficult diagnosis or treatment decision in practice. Over-trust or under-trust are frequent. Prior research has explored supporting such assessments by explaining DST data inputs and algorithmic mechanisms. This paper explores a different approach: Providing precisely relevant, scientific evidence from biomedical literature. We present a proof-of-concept system, Clinical Evidence Engine, to demonstrate the technical and design feasibility of this approach across three domains (cardiovascular diseases, autism, cancer). Leveraging Clinical BioBERT, the system can effectively identify clinical trial reports based on lengthy clinical questions (e.g., "risks of catheter infection among adult patients in intensive care unit who require arterial catheters, if treated with povidone iodine-alcohol"). This capability enables the system to identify clinical trials relevant to diagnostic/treatment hypotheses -- a clinician's or a CDSS's. Further, Clinical Evidence Engine can identify key parts of a clinical trial abstract, including patient population (e.g., adult patients in intensive care unit who require arterial catheters), intervention (povidone iodine-alcohol), and outcome (risks of catheter infection). This capability opens up the possibility of enabling clinicians to 1) rapidly determine the match between a clinical trial and a clinical question, and 2) understand the result and contexts of the trial without extensive reading. We demonstrate this potential by illustrating two example use scenarios of the system. We discuss the idea of designing DST explanations not as specific to a DST or an algorithm, but as a domain-agnostic decision support infrastructure.

Dakuo Wang, Michael Muller, Qian Yang et al.

Geographically distributed teams often face challenges in coordination and collaboration, lowering their productivity. Understanding the relationship between team dispersion and productivity is critical for supporting such teams. Extensive prior research has studied these relations in lab settings or using qualitative measures. This paper extends prior work by contributing an empirical case study in a real-world organization, using quantitative measures. We studied 117 new research project teams from the same discipline within an industrial research lab for 6 months. During this time, all teams shared one goal: submitting research papers to the same target conference. We analyzed these teams' dispersion-related characteristics as well as team productivity. Interestingly, we found little statistical evidence that geographic and time differences relate to team productivity. However, organizational and functional distances are predictive of the productivity of the dispersed teams we studied. We discuss the open research questions these findings revealed and their implications for future research.

Yunxin Li, Qian Yang, Qingcai Chen et al.

Single online handwritten Chinese character recognition~(single OLHCCR) has achieved prominent performance. However, in real application scenarios, users always write multiple Chinese characters to form one complete sentence and the contextual information within these characters holds the significant potential to improve the accuracy, robustness and efficiency of sentence-level OLHCCR. In this work, we first propose a simple and straightforward end-to-end network, namely vanilla compositional network~(VCN) to tackle the sentence-level OLHCCR. It couples convolutional neural network with sequence modeling architecture to exploit the handwritten character's previous contextual information. Although VCN performs much better than the state-of-the-art single OLHCCR model, it exposes high fragility when confronting with not well written characters such as sloppy writing, missing or broken strokes. To improve the robustness of sentence-level OLHCCR, we further propose a novel deep spatial-temporal fusion network~(DSTFN). It utilizes a pre-trained autoregresssive framework as the backbone component, which projects each Chinese character into word embeddings, and integrates the spatial glyph features of handwritten characters and their contextual information multiple times at multi-layer fusion module. We also construct a large-scale sentence-level handwriting dataset, named as CSOHD to evaluate models. Extensive experiment results demonstrate that DSTFN achieves the state-of-the-art performance, which presents strong robustness compared with VCN and exiting single OLHCCR models. The in-depth empirical analysis and case studies indicate that DSTFN can significantly improve the efficiency of handwriting input, with the handwritten Chinese character with incomplete strokes being recognized precisely.

Qian Yang, Jianyi Zhang, Weituo Hao et al.

The outbreak of COVID-19 Disease due to the novel coronavirus has caused a shortage of medical resources. To aid and accelerate the diagnosis process, automatic diagnosis of COVID-19 via deep learning models has recently been explored by researchers across the world. While different data-driven deep learning models have been developed to mitigate the diagnosis of COVID-19, the data itself is still scarce due to patient privacy concerns. Federated Learning (FL) is a natural solution because it allows different organizations to cooperatively learn an effective deep learning model without sharing raw data. However, recent studies show that FL still lacks privacy protection and may cause data leakage. We investigate this challenging problem by proposing a simple yet effective algorithm, named \textbf{F}ederated \textbf{L}earning \textbf{o}n Medical Datasets using \textbf{P}artial Networks (FLOP), that shares only a partial model between the server and clients. Extensive experiments on benchmark data and real-world healthcare tasks show that our approach achieves comparable or better performance while reducing the privacy and security risks. Of particular interest, we conduct experiments on the COVID-19 dataset and find that our FLOP algorithm can allow different hospitals to collaboratively and effectively train a partially shared model without sharing local patients' data.

Guoyin Wang, Chunyuan Li, Jianqiao Li et al.

Neural language models are often trained with maximum likelihood estimation (MLE), where the next word is generated conditioned on the ground-truth word tokens. During testing, however, the model is instead conditioned on previously generated tokens, resulting in what is termed exposure bias. To reduce this gap between training and testing, we propose using optimal transport (OT) to match the sequences generated in these two modes. An extension is further proposed to improve the OT learning, based on the structural and contextual information of the text sequences. The effectiveness of the proposed method is validated on machine translation, text summarization, and text generation tasks.

Chen Lin, Si Chen, Hui Li et al.

Recommendation Systems (RS) have become an essential part of many online services. Due to its pivotal role in guiding customers towards purchasing, there is a natural motivation for unscrupulous parties to spoof RS for profits. In this paper, we study the shilling attack: a subsistent and profitable attack where an adversarial party injects a number of user profiles to promote or demote a target item. Conventional shilling attack models are based on simple heuristics that can be easily detected, or directly adopt adversarial attack methods without a special design for RS. Moreover, the study on the attack impact on deep learning based RS is missing in the literature, making the effects of shilling attack against real RS doubtful. We present a novel Augmented Shilling Attack framework (AUSH) and implement it with the idea of Generative Adversarial Network. AUSH is capable of tailoring attacks against RS according to budget and complex attack goals, such as targeting a specific user group. We experimentally show that the attack impact of AUSH is noticeable on a wide range of RS including both classic and modern deep learning based RS, while it is virtually undetectable by the state-of-the-art attack detection model.

Zhouyuan Huo, Qian Yang, Bin Gu et al.

Mobile crowdsensing has gained significant attention in recent years and has become a critical paradigm for emerging Internet of Things applications. The sensing devices continuously generate a significant quantity of data, which provide tremendous opportunities to develop innovative intelligent applications. To utilize these data to train machine learning models while not compromising user privacy, federated learning has become a promising solution. However, there is little understanding of whether federated learning algorithms are guaranteed to converge. We reconsider model averaging in federated learning and formulate it as a gradient-based method with biased gradients. This novel perspective assists analysis of its convergence rate and provides a new direction for more acceleration. We prove for the first time that the federated averaging algorithm is guaranteed to converge for non-convex problems, without imposing additional assumptions. We further propose a novel accelerated federated learning algorithm and provide a convergence guarantee. Simulated federated learning experiments are conducted to train deep neural networks on benchmark datasets, and experimental results show that our proposed method converges faster than previous approaches.

Wenlin Wang, Hongteng Xu, Zhe Gan et al.

We propose a novel graph-driven generative model, that unifies multiple heterogeneous learning tasks into the same framework. The proposed model is based on the fact that heterogeneous learning tasks, which correspond to different generative processes, often rely on data with a shared graph structure. Accordingly, our model combines a graph convolutional network (GCN) with multiple variational autoencoders, thus embedding the nodes of the graph i.e., samples for the tasks) in a uniform manner while specializing their organization and usage to different tasks. With a focus on healthcare applications (tasks), including clinical topic modeling, procedure recommendation and admission-type prediction, we demonstrate that our method successfully leverages information across different tasks, boosting performance in all tasks and outperforming existing state-of-the-art approaches.

Qian Yang

Throughout the course of my Ph.D., I have been designing the user experience (UX) of various machine learning (ML) systems. In this workshop, I share two projects as case studies in which people engage with ML in much more complicated and nuanced ways than the technical HCML work might assume. The first case study describes how cardiology teams in three hospitals used a clinical decision-support system that helps them decide whether and when to implant an artificial heart to a heart failure patient. I demonstrate that physicians cannot draw on their decision-making experience by seeing only patient data on paper. They are also confused by some fundamental premises upon which ML operates. For example, physicians asked: Are ML predictions made based on clinicians' best efforts? Is it ethical to make decisions based on previous patients' collective outcomes? In the second case study, my collaborators and I designed an intelligent text editor, with the goal of improving authors' writing experience with NLP (Natural Language Processing) technologies. We prototyped a number of generative functionalities where the system provides phrase-or-sentence-level writing suggestions upon user request. When writing with the prototype, however, authors shared that they need to "see where the sentence is going two paragraphs later" in order to decide whether the suggestion aligns with their writing; Some even considered adopting machine suggestions as plagiarism, therefore "is simply wrong". By sharing these unexpected and intriguing responses from these real-world ML users, I hope to start a discussion about such previously-unknown complexities and nuances of -- as the workshop proposal states -- "putting ML at the service of people in a way that is accessible, useful, and trustworthy to all".

Wenlin Wang, Chenyang Tao, Zhe Gan et al.

The performance of many network learning applications crucially hinges on the success of network embedding algorithms, which aim to encode rich network information into low-dimensional vertex-based vector representations. This paper considers a novel variational formulation of network embeddings, with special focus on textual networks. Different from most existing methods that optimize a discriminative objective, we introduce Variational Homophilic Embedding (VHE), a fully generative model that learns network embeddings by modeling the semantic (textual) information with a variational autoencoder, while accounting for the structural (topology) information through a novel homophilic prior design. Homophilic vertex embeddings encourage similar embedding vectors for related (connected) vertices. The proposed VHE promises better generalization for downstream tasks, robustness to incomplete observations, and the ability to generalize to unseen vertices. Extensive experiments on real-world networks, for multiple tasks, demonstrate that the proposed method consistently achieves superior performance relative to competing state-of-the-art approaches.