In the rapidly evolving landscape of AI research and application, Multimodal Large Language Models (MLLMs) have emerged as a transformative force, adept at interpreting and integrating information from diverse modalities such as text, images, and Graphical User Interfaces (GUIs). Despite these advancements, the nuanced interaction and understanding of GUIs pose a significant challenge, limiting the potential of existing models to enhance automation levels. To bridge this gap, this paper presents V-Zen, an innovative Multimodal Large Language Model (MLLM) meticulously crafted to revolutionise the domain of GUI understanding and grounding. Equipped with dual-resolution image encoders, V-Zen establishes new benchmarks in efficient grounding and next-action prediction, thereby laying the groundwork for self-operating computer systems. Complementing V-Zen is the GUIDE dataset, an extensive collection of real-world GUI elements and task-based sequences, serving as a catalyst for specialised fine-tuning. The successful integration of V-Zen and GUIDE marks the dawn of a new era in multimodal AI research, opening the door to intelligent, autonomous computing experiences. This paper extends an invitation to the research community to join this exciting journey, shaping the future of GUI automation. In the spirit of open science, our code, data, and model will be made publicly available, paving the way for multimodal dialogue scenarios with intricate and precise interactions.

Modern large language models (LLMs) represent a paradigm shift in what can plausibly be expected of machine learning models. The fact that LLMs can effectively generate sensible answers to a diverse range of queries suggests that they would be useful in customer support applications. While powerful, LLMs have been observed to be prone to hallucination which unfortunately makes their near term use in customer support applications challenging. To address this issue we present a system that allows us to use an LLM to augment our customer support advocates by re-framing the language modeling task as a discriminative classification task. In this framing, we seek to present the top-K best template responses for a customer support advocate to use when responding to a customer. We present the result of both offline and online experiments where we observed offline gains and statistically significant online lifts for our experimental system. Along the way, we present observed scaling curves for validation loss and top-K accuracy, resulted from model parameter ablation studies. We close by discussing the space of trade-offs with respect to model size, latency, and accuracy as well as and suggesting future applications to explore.

The rapid advancement of Generative Artificial Intelligence (AI), such as Large Language Models (LLMs) and Multimodal Large Language Models (MLLM), has the potential to revolutionize the way we work and interact with digital systems across various industries. However, the current state of software automation, such as Robotic Process Automation (RPA) frameworks, often requires domain expertise and lacks visibility and intuitive interfaces, making it challenging for users to fully leverage these technologies. This position paper argues for the emerging area of Human-Centered Automation (HCA), which prioritizes user needs and preferences in the design and development of automation systems. Drawing on empirical evidence from human-computer interaction research and case studies, we highlight the importance of considering user perspectives in automation and propose a framework for designing human-centric automation solutions. The paper discusses the limitations of existing automation approaches, the challenges in integrating AI and RPA, and the benefits of human-centered automation for productivity, innovation, and democratizing access to these technologies. We emphasize the importance of open-source solutions and provide examples of how HCA can empower individuals and organizations in the era of rapidly progressing AI, helping them remain competitive. The paper also explores pathways to achieve more advanced and context-aware automation solutions. We conclude with a call to action for researchers and practitioners to focus on developing automation technologies that adapt to user needs, provide intuitive interfaces, and leverage the capabilities of high-end AI to create a more accessible and user-friendly future of automation.

To bridge the gap between vision and language modalities, Multimodal Large Language Models (MLLMs) usually learn an adapter that converts visual inputs to understandable tokens for Large Language Models (LLMs). However, most adapters generate consistent visual tokens, regardless of the specific objects of interest mentioned in the prompt. Since these adapters distribute equal attention to every detail in the image and focus on the entire scene, they may increase the cognitive load for LLMs, particularly when processing complex scenes. To alleviate this problem, we propose prompt-aware adapters. These adapters are designed with the capability to dynamically embed visual inputs based on the specific focus of the prompt. Specifically, prompt-aware adapters utilize both global and local textual features to capture the most relevant visual clues from the prompt at both coarse and fine granularity levels. This approach significantly enhances the ability of LLMs to understand and interpret visual content. Experiments on various visual question answering tasks, such as counting and position reasoning, demonstrate the effectiveness of prompt-aware adapters.

While large multimodal models excel in broad vision-language benchmarks, they often struggle with tasks requiring precise perception of low-level visual details, such as comparing line lengths or solving simple mazes. In particular, this failure mode persists in question-answering tasks about vector graphics -- images composed purely of 2D objects and shapes. To address this challenge, we propose the Visually Descriptive Language Model (VDLM), which performs text-based reasoning about vector graphics. VDLM leverages Scalable Vector Graphics (SVG) for a more precise visual description and first uses an off-the-shelf raster-to-SVG algorithm for encoding. Since existing language models cannot understand raw SVGs in a zero-shot setting, VDLM then bridges SVG with pretrained language models through a newly introduced intermediate symbolic representation, Primal Visual Description (PVD), comprising primitive attributes (e.g., shape, position, measurement) with their corresponding predicted values. PVD is task-agnostic and represents visual primitives that are universal across all vector graphics. It can be learned with procedurally generated (SVG, PVD) pairs and also enables the direct use of LLMs for generalization to complex reasoning tasks. By casting an image to a text-based representation, we can leverage the power of language models to learn alignment from SVG to visual primitives and generalize to unseen question-answering tasks. Empirical results show that VDLM achieves stronger zero-shot performance compared to state-of-the-art LMMs, such as GPT-4V, in various low-level multimodal perception and reasoning tasks on vector graphics. We additionally present extensive analyses on VDLM's performance, demonstrating that our framework offers better interpretability due to its disentangled perception and reasoning processes. Project page: https://mikewangwzhl.github.io/VDLM/

This work introduces a novel Text-Guided Time Series Forecasting (TGTSF) task. By integrating textual cues, such as channel descriptions and dynamic news, TGTSF addresses the critical limitations of traditional methods that rely purely on historical data. To support this task, we propose TGForecaster, a robust baseline model that fuses textual cues and time series data using cross-attention mechanisms. We then present four meticulously curated benchmark datasets to validate the proposed framework, ranging from simple periodic data to complex, event-driven fluctuations. Our comprehensive evaluations demonstrate that TGForecaster consistently achieves state-of-the-art performance, highlighting the transformative potential of incorporating textual information into time series forecasting. This work not only pioneers a novel forecasting task but also establishes a new benchmark for future research, driving advancements in multimodal data integration for time series models.

Advances in large language models raise the question of how alignment techniques will adapt as models become increasingly complex and humans will only be able to supervise them weakly. Weak-to-Strong mimics such a scenario where weak model supervision attempts to harness the full capabilities of a much stronger model. This work extends Weak-to-Strong to WeakS-to-Strong by exploring an ensemble of weak models which simulate the variability in human opinions. Confidence scores are estimated using a Bayesian approach to guide the WeakS-to-Strong generalization. Furthermore, we extend the application of WeakS-to-Strong from text classification tasks to text generation tasks where more advanced strategies are investigated for supervision. Moreover, direct preference optimization is applied to advance the student model's preference learning, beyond the basic learning framework of teacher forcing. Results demonstrate the effectiveness of the proposed approach for the reliability of a strong student model, showing potential for superalignment.

Standard cells are essential components of modern digital circuit designs. With process technologies advancing toward 2nm, more routability issues have arisen due to the decreasing number of routing tracks, increasing number and complexity of design rules, and strict patterning rules. The state-of-the-art standard cell design automation framework is able to automatically design standard cell layouts in advanced nodes, but it is still struggling to generate highly competitive Performance-Power-Area (PPA) and routable cell layouts for complex sequential cell designs. Consequently, a novel and efficient methodology incorporating the expertise of experienced human designers to incrementally optimize the PPA of cell layouts is highly necessary and essential. High-quality device clustering, with consideration of netlist topology, diffusion sharing/break and routability in the layouts, can reduce complexity and assist in finding highly competitive PPA, and routable layouts faster. In this paper, we leverage the natural language and reasoning ability of Large Language Model (LLM) to generate high-quality cluster constraints incrementally to optimize the cell layout PPA and debug the routability with ReAct prompting. On a benchmark of sequential standard cells in 2nm, we demonstrate that the proposed method not only achieves up to 19.4% smaller cell area, but also generates 23.5% more LVS/DRC clean cell layouts than previous work. In summary, the proposed method not only successfully reduces cell area by 4.65% on average, but also is able to fix routability in the cell layout designs.

Multimodal contrastive learning methods (e.g., CLIP) have shown impressive zero-shot classification performance due to their strong ability to joint representation learning for visual and textual modalities. However, recent research revealed that multimodal contrastive learning on poisoned pre-training data with a small proportion of maliciously backdoored data can induce backdoored CLIP that could be attacked by inserted triggers in downstream tasks with a high success rate. To defend against backdoor attacks on CLIP, existing defense methods focus on either the pre-training stage or the fine-tuning stage, which would unfortunately cause high computational costs due to numerous parameter updates. In this paper, we provide the first attempt at a computationally efficient backdoor detection method to defend against backdoored CLIP in the inference stage. We empirically find that the visual representations of backdoored images are insensitive to both benign and malignant changes in class description texts. Motivated by this observation, we propose BDetCLIP, a novel test-time backdoor detection method based on contrastive prompting. Specifically, we first prompt the language model (e.g., GPT-4) to produce class-related description texts (benign) and class-perturbed random texts (malignant) by specially designed instructions. Then, the distribution difference in cosine similarity between images and the two types of class description texts can be used as the criterion to detect backdoor samples. Extensive experiments validate that our proposed BDetCLIP is superior to state-of-the-art backdoor detection methods, in terms of both effectiveness and efficiency.

The increasing prevalence of Large Language Models (LMs) in critical applications highlights the need for controlled language generation strategies that are not only computationally efficient but that also enjoy performance guarantees. To achieve this, we use a common model of concept semantics as linearly represented in an LM's latent space. In particular, we take the view that natural language generation traces a trajectory in this continuous semantic space, realized by the language model's hidden activations. This view permits a control-theoretic treatment of text generation in latent space, in which we propose a lightweight, gradient-free intervention that dynamically steers trajectories away from regions corresponding to undesired meanings. Crucially, we show that this intervention, which we compute in closed form, is guaranteed (in probability) to steer the output into the allowed region. Finally, we demonstrate on a toxicity avoidance objective that the intervention steers language away from undesired content while maintaining text quality.