Yuanxin Wang

Yuanxin Wang, Pawel Filipczuk, Anisha Garg et al.

Modern LLM reasoning relies on extensive test-time computation, driven by internal model training and external agentic orchestration. However, this synergy is often inefficient, as model verbosity and poor instruction following lead to wasted compute. We analyze this capability-cost trade-off and introduce an optimized reasoning workflow (\cepo) that empowers smaller open-source models to outperform models multiple times their size. We will open-source this workflow to enable further research. Our work demonstrates a clear path toward co-designing orchestration frameworks with the underlying model capabilities to unlock powerful reasoning in small-to-medium sized models.

Xu Liu, Tong Zhou, Yuanxin Wang et al.

The advent of foundation models, which are pre-trained on vast datasets, has ushered in a new era of computer vision, characterized by their robustness and remarkable zero-shot generalization capabilities. Mirroring the transformative impact of foundation models like large language models (LLMs) in natural language processing, visual foundation models (VFMs) have become a catalyst for groundbreaking developments in computer vision. This review paper delineates the pivotal trajectories of VFMs, emphasizing their scalability and proficiency in generative tasks such as text-to-image synthesis, as well as their adeptness in discriminative tasks including image segmentation. While generative and discriminative models have historically charted distinct paths, we undertake a comprehensive examination of the recent strides made by VFMs in both domains, elucidating their origins, seminal breakthroughs, and pivotal methodologies. Additionally, we collate and discuss the extensive resources that facilitate the development of VFMs and address the challenges that pave the way for future research endeavors. A crucial direction for forthcoming innovation is the amalgamation of generative and discriminative paradigms. The nascent application of generative models within discriminative contexts signifies the early stages of this confluence. This survey aspires to be a contemporary compendium for scholars and practitioners alike, charting the course of VFMs and illuminating their multifaceted landscape.

Yuanxin Wang, Ganesh Venkatesh

Large Language Models (LLMs) have demonstrated remarkable proficiency in understanding text and generating high-quality responses. However, a critical distinction from human cognition is their typical lack of a distinct internal `reading' or deliberation phase before `speaking' (i.e., generating text). Humans often engage in silent reading to comprehend context and formulate thoughts prior to articulation. This paper investigates methods to imbue LLMs with a similar capacity for internal processing. We introduce and evaluate techniques that encourage LLMs to `read silently.' Our findings indicate that even a straightforward approach, such as providing the model with an initial contextual prompt or `reading space' before it begins predicting subsequent tokens for the final output, can yield significant performance improvements. We further enhance this concept by developing a `reading buddy' architecture, where an auxiliary component silently processes the input and provides refined contextual insights to the primary generation model. These approaches aim to foster deeper understanding from LLMs so that they can produce better reasoned responses, moving them one step closer to more human-like text processing. Our results indicate that these simple techniques can provide surprisingly strong impact on accuracy with multiple point accuracy boost.

Maoyuan Sun, Yue Ma, Yuanxin Wang et al.

Data-driven decision making has been a common task in today's big data era, from simple choices such as finding a fast way to drive home, to complex decisions on medical treatment. It is often supported by visual analytics. For various reasons (e.g., system failure, interrupted network, intentional information hiding, or bias), visual analytics for sensemaking of data involves missingness (e.g., data loss and incomplete analysis), which impacts human decisions. For example, missing data can cost a business millions of dollars, and failing to recognize key evidence can put an innocent person in jail. Being aware of missingness is critical to avoid such catastrophes. To fulfill this, as an initial step, we consider missingness in visual analytics from two aspects: data-centric and human-centric. The former emphasizes missingness in three data-related categories: data composition, data relationship, and data usage. The latter focuses on the human-perceived missingness at three levels: observed-level, inferred-level, and ignored-level. Based on them, we discuss possible roles of visualizations for handling missingness, and conclude our discussion with future research opportunities.

Xingjun Li, Yuanxin Wang, Hong Wang et al.

Code search is an important and frequent activity for developers using computational notebooks (e.g., Jupyter). The flexibility of notebooks brings challenges for effective code search, where classic search interfaces for traditional software code may be limited. In this paper, we propose, NBSearch, a novel system that supports semantic code search in notebook collections and interactive visual exploration of search results. NBSearch leverages advanced machine learning models to enable natural language search queries and intuitive visualizations to present complicated intra- and inter-notebook relationships in the returned results. We developed NBSearch through an iterative participatory design process with two experts from a large software company. We evaluated the models with a series of experiments and the whole system with a controlled user study. The results indicate the feasibility of our analytical pipeline and the effectiveness of NBSearch to support code search in large notebook collections.

George Michalopoulos, Yuanxin Wang, Hussam Kaka et al.

Contextual word embedding models, such as BioBERT and Bio_ClinicalBERT, have achieved state-of-the-art results in biomedical natural language processing tasks by focusing their pre-training process on domain-specific corpora. However, such models do not take into consideration expert domain knowledge. In this work, we introduced UmlsBERT, a contextual embedding model that integrates domain knowledge during the pre-training process via a novel knowledge augmentation strategy. More specifically, the augmentation on UmlsBERT with the Unified Medical Language System (UMLS) Metathesaurus was performed in two ways: i) connecting words that have the same underlying `concept' in UMLS, and ii) leveraging semantic group knowledge in UMLS to create clinically meaningful input embeddings. By applying these two strategies, UmlsBERT can encode clinical domain knowledge into word embeddings and outperform existing domain-specific models on common named-entity recognition (NER) and clinical natural language inference clinical NLP tasks.

Tianwei Yue, Yuanxin Wang, Longxiang Zhang et al.

Advancements in genomic research such as high-throughput sequencing techniques have driven modern genomic studies into "big data" disciplines. This data explosion is constantly challenging conventional methods used in genomics. In parallel with the urgent demand for robust algorithms, deep learning has succeeded in a variety of fields such as vision, speech, and text processing. Yet genomics entails unique challenges to deep learning since we are expecting from deep learning a superhuman intelligence that explores beyond our knowledge to interpret the genome. A powerful deep learning model should rely on insightful utilization of task-specific knowledge. In this paper, we briefly discuss the strengths of different deep learning models from a genomic perspective so as to fit each particular task with a proper deep architecture, and remark on practical considerations of developing modern deep learning architectures for genomics. We also provide a concise review of deep learning applications in various aspects of genomic research, as well as pointing out potential opportunities and obstacles for future genomics applications.