William Li

Jinming Zhang, Xuanru Zhou, Jiachen Lian et al.

Speech dysfluency detection is crucial for clinical diagnosis and language assessment, but existing methods are limited by the scarcity of high-quality annotated data. Although recent advances in TTS model have enabled synthetic dysfluency generation, existing synthetic datasets suffer from unnatural prosody and limited contextual diversity. To address these limitations, we propose LLM-Dys -- the most comprehensive dysfluent speech corpus with LLM-enhanced dysfluency simulation. This dataset captures 11 dysfluency categories spanning both word and phoneme levels. Building upon this resource, we improve an end-to-end dysfluency detection framework. Experimental validation demonstrates state-of-the-art performance. All data, models, and code are open-sourced at https://github.com/Berkeley-Speech-Group/LLM-Dys.

Hongyang Wei, Baixin Xu, Hongbo Liu et al.

Recent advances in multimodal models have demonstrated impressive capabilities in unified image generation and editing. However, many prominent open-source models prioritize scaling model parameters over optimizing training strategies, limiting their efficiency and performance. In this work, we present UniPic2-SD3.5M-Kontext, a 2B-parameter DiT model based on SD3.5-Medium, which achieves state-of-the-art image generation and editing while extending seamlessly into a unified multimodal framework. Our approach begins with architectural modifications to SD3.5-Medium and large-scale pre-training on high-quality data, enabling joint text-to-image generation and editing capabilities. To enhance instruction following and editing consistency, we propose a novel Progressive Dual-Task Reinforcement strategy (PDTR), which effectively strengthens both tasks in a staged manner. We empirically validate that the reinforcement phases for different tasks are mutually beneficial and do not induce negative interference. After pre-training and reinforcement strategies, UniPic2-SD3.5M-Kontext demonstrates stronger image generation and editing capabilities than models with significantly larger generation parameters-including BAGEL (7B) and Flux-Kontext (12B). Furthermore, following the MetaQuery, we connect the UniPic2-SD3.5M-Kontext and Qwen2.5-VL-7B via a connector and perform joint training to launch a unified multimodal model UniPic2-Metaquery. UniPic2-Metaquery integrates understanding, generation, and editing, achieving top-tier performance across diverse tasks with a simple and scalable training paradigm. This consistently validates the effectiveness and generalizability of our proposed training paradigm, which we formalize as Skywork UniPic 2.0.

Yihang Guo, Tianyuan Yu, Liang Bai et al.

Multi-task learning (MTL) aims to build general-purpose vision systems by training a single network to perform multiple tasks jointly. While promising, its potential is often hindered by "unbalanced optimization", where task interference leads to subpar performance compared to single-task models. To facilitate research in MTL, this paper presents a systematic experimental analysis to dissect the factors contributing to this persistent problem. Our investigation confirms that the performance of existing optimization methods varies inconsistently across datasets, and advanced architectures still rely on costly grid-searched loss weights. Furthermore, we show that while powerful Vision Foundation Models (VFMs) provide strong initialization, they do not inherently resolve the optimization imbalance, and merely increasing data quantity offers limited benefits. A crucial finding emerges from our analysis: a strong correlation exists between the optimization imbalance and the norm of task-specific gradients. We demonstrate that this insight is directly applicable, showing that a straightforward strategy of scaling task losses according to their gradient norms can achieve performance comparable to that of an extensive and computationally expensive grid search. Our comprehensive analysis suggests that understanding and controlling gradient dynamics is a more direct path to stable MTL than developing increasingly complex methods.

William Li, Lei Hamilton, Kaise Al-natour et al.

This paper focuses on evaluating the effectiveness of Large Language Models at solving embodied robotic tasks using the Meta PARTNER benchmark. Meta PARTNR provides simplified environments and robotic interactions within randomized indoor kitchen scenes. Each randomized kitchen scene is given a task where two robotic agents cooperatively work together to solve the task. We evaluated multiple frontier models on Meta PARTNER environments. Our results indicate that reasoning models like OpenAI o3-mini outperform non-reasoning models like OpenAI GPT-4o and Llama 3 when operating in PARTNR's robotic embodied environments. o3-mini displayed outperform across centralized, decentralized, full observability, and partial observability configurations. This provides a promising avenue of research for embodied robotic development.

David Q. Sun, Hadas Kotek, Christopher Klein et al.

This paper develops and implements a scalable methodology for (a) estimating the noisiness of labels produced by a typical crowdsourcing semantic annotation task, and (b) reducing the resulting error of the labeling process by as much as 20-30% in comparison to other common labeling strategies. Importantly, this new approach to the labeling process, which we name Dynamic Automatic Conflict Resolution (DACR), does not require a ground truth dataset and is instead based on inter-project annotation inconsistencies. This makes DACR not only more accurate but also available to a broad range of labeling tasks. In what follows we present results from a text classification task performed at scale for a commercial personal assistant, and evaluate the inherent ambiguity uncovered by this annotation strategy as compared to other common labeling strategies.

Xuan Bi, Gediminas Adomavicius, William Li et al.

Due to accessible big data collections from consumers, products, and stores, advanced sales forecasting capabilities have drawn great attention from many companies especially in the retail business because of its importance in decision making. Improvement of the forecasting accuracy, even by a small percentage, may have a substantial impact on companies' production and financial planning, marketing strategies, inventory controls, supply chain management, and eventually stock prices. Specifically, our research goal is to forecast the sales of each product in each store in the near future. Motivated by tensor factorization methodologies for personalized context-aware recommender systems, we propose a novel approach called the Advanced Temporal Latent-factor Approach to Sales forecasting (ATLAS), which achieves accurate and individualized prediction for sales by building a single tensor-factorization model across multiple stores and products. Our contribution is a combination of: tensor framework (to leverage information across stores and products), a new regularization function (to incorporate demand dynamics), and extrapolation of tensor into future time periods using state-of-the-art statistical (seasonal auto-regressive integrated moving-average models) and machine-learning (recurrent neural networks) models. The advantages of ATLAS are demonstrated on eight product category datasets collected by the Information Resource, Inc., where a total of 165 million weekly sales transactions from more than 1,500 grocery stores over 15,560 products are analyzed.

Junmei Zhong, William Li

Auto dealerships receive thousands of calls daily from customers who are interested in sales, service, vendors and jobseekers. With so many calls, it is very important for auto dealers to understand the intent of these calls to provide positive customer experiences that ensure customer satisfaction, deep customer engagement to boost sales and revenue, and optimum allocation of agents or customer service representatives across the business. In this paper, we define the problem of customer phone call intent as a multi-class classification problem stemming from the large database of recorded phone call transcripts. To solve this problem, we develop a convolutional neural network (CNN)-based supervised learning model to classify the customer calls into four intent categories: sales, service, vendor and jobseeker. Experimental results show that with the thrust of our scalable data labeling method to provide sufficient training data, the CNN-based predictive model performs very well on long text classification according to the quantitative metrics of F1-Score, precision, recall, and accuracy.