Despite recent advances demonstrating vision-language models' (VLMs) abilities to describe complex relationships in images using natural language, their capability to quantitatively reason about object sizes and distances remains underexplored. In this work, we introduce a manually annotated benchmark, Q-Spatial Bench, with 271 questions across five categories designed for quantitative spatial reasoning and systematically investigate the performance of state-of-the-art VLMs on this task. Our analysis reveals that reasoning about distances between objects is particularly challenging for SoTA VLMs; however, some VLMs significantly outperform others, with an over 40-point gap between the two best performing models. We also make the surprising observation that the success rate of the top-performing VLM increases by 19 points when a reasoning path using a reference object emerges naturally in the response. Inspired by this observation, we develop a zero-shot prompting technique, SpatialPrompt, that encourages VLMs to answer quantitative spatial questions using reference objects as visual cues. By instructing VLMs to use reference objects in their reasoning paths via SpatialPrompt, Gemini 1.5 Pro, Gemini 1.5 Flash, and GPT-4V improve their success rates by over 40, 20, and 30 points, respectively. We emphasize that these significant improvements are obtained without needing more data, model architectural modifications, or fine-tuning.

With the increasing demand for substantial amounts of high-quality data to train large language models (LLMs), efficiently filtering large web corpora has become a critical challenge. For this purpose, KenLM, a lightweight n-gram-based language model that operates on CPUs, is widely used. However, the traditional method of training KenLM utilizes only high-quality data and, consequently, does not explicitly learn the linguistic patterns of low-quality data. To address this issue, we propose an ensemble approach that leverages two contrasting KenLMs: (i) Good KenLM, trained on high-quality data; and (ii) Bad KenLM, trained on low-quality data. Experimental results demonstrate that our approach significantly reduces noisy content while preserving high-quality content compared to the traditional KenLM training method. This indicates that our method can be a practical solution with minimal computational overhead for resource-constrained environments.

Vision-language models (VLMs) such as CLIP are trained via contrastive learning between text and image pairs, resulting in aligned image and text embeddings that are useful for many downstream tasks. A notable drawback of CLIP, however, is that the resulting embedding space seems to lack some of the structure of their purely text-based alternatives. For instance, while text embeddings have been long noted to satisfy analogies in embedding space using vector arithmetic, CLIP has no such property. In this paper, we propose an approach to natively train CLIP in a contrastive manner to reason about differences in embedding space. We finetune CLIP so that the differences in image embedding space correspond to text descriptions of the image differences, which we synthetically generate with large language models on image-caption paired datasets. We first demonstrate that our approach yields significantly improved capabilities in ranking images by a certain attribute (e.g., elephants are larger than cats), which is useful in retrieval or constructing attribute-based classifiers, and improved zeroshot classification performance on many downstream image classification tasks. In addition, our approach enables a new mechanism for inference that we refer to as comparative prompting, where we leverage prior knowledge of text descriptions of differences between classes of interest, achieving even larger performance gains in classification. Finally, we illustrate that the resulting embeddings obey a larger degree of geometric properties in embedding space, such as in text-to-image generation. Vision-language models (VLMs) (Jia et al., 2021; Li et al., 2022a), and more specifically CLIP (Radford et al., 2021), leverage paired instances of images and corresponding text descriptions to produce a general-purpose joint embedding between images and language. These models have created a new paradigm of prompting (Radford et al., 2021; Li & Liang, 2021; Bach et al., 2022). In this new paradigm, we can easily design image classifiers through text descriptions of classes and by selecting which of our class descriptions most closely aligns with an image (in terms of cosine similarity in the multimodal embedding space). These models can also generate images corresponding to user-specified text prompts (Podell et al., 2023). Ultimately, this paradigm fundamentally relies on the accurate alignment of image and text modalities. While contrastive-based pretraining on large datasets aims to achieve this embedding alignment, a notable drawback of CLIP models is that they do not exhibit the structure of purely languagebased embeddings. For instance, text embeddings satisfy analogies in embedding space using vector arithmetic, e.g., Text("King") - Text("Man") + Text("Woman") Text ("Queen") (Mikolov et al., 2013), while CLIP has no such property.

Large language models (LLMs) are known for their exceptional performance across a range of natural language processing tasks, but their deployment comes at a high computational and financial cost. On the other hand, smaller language models (SLMs), which can be deployed on lower-cost edge devices, struggle to match the performance of their larger counterparts. This paper presents a novel hybrid inference approach that leverages the strengths of both model types while minimizing reliance on costly cloud-based LLMs. Unlike existing methods that route entire queries to either an SLM or a cloud LLM, our approach introduces a reward-based mechanism to dynamically determine the involvement of the cloud LLM during token generation. Specifically, each token predicted by the SLM is evaluated against a reward score, and only when this score falls below a certain threshold is the cloud LLM consulted for assistance in the next token prediction. This method not only reduces the traffic to the cloud LLM, thereby lowering costs, but also allows for flexible control over response quality depending on the reward score threshold. Experimental results demonstrate that our approach significantly reduces cloud LLM usage with minimal impact on overall response quality, offering a cost-effective solution for deploying high-performance language models.

Stance detection is a crucial NLP task with numerous applications in social science, from analyzing online discussions to assessing political campaigns. This paper investigates the optimal way to incorporate metadata into a political stance detection task. We demonstrate that previous methods combining metadata with language-based data for political stance detection have not fully utilized the metadata information; our simple baseline, using only party membership information, surpasses the current state-of-the-art. We then show that prepending metadata (e.g., party and policy) to political speeches performs best, outperforming all baselines, indicating that complex metadata inclusion systems may not learn the task optimally.

Sam Altman has told OpenAI staff members during their weekly meeting that the company is changing its rather convoluted non-profit corporate structure next year, according to Fortune. The CEO said OpenAI will move away from being controlled by a non-profit entity and will transition into a more traditional for-profit organization. He didn't delve into the specifics of how the company will achieve that goal and what OpenAI's corporate structure will look like exactly. A spokesperson only told Fortune that it remains "focused on building AI that benefits everyone" and that non-profit is "core to [its] mission and will continue to exist." OpenAI started as a non-profit organization in 2015 that relied on money from donors.

It used to go by at least two different names -- Oculus Connect and then Facebook Connect -- but whatever the moniker, Meta's fall event is still a big showcase for the company's latest and greatest achievements in the virtual reality and mixed reality space. Much like last year, we can likely predict the biggest news coming out of Meta Connect 2024 with just two acronyms: AI and AR. Like every other big tech firm this year, Meta will be desperate to demonstrate how it plans to stay relevant in a future powered by AI. And now that we're seven months beyond the launch of Apple's Vision Pro, which arrived alongside a short-lived spike in interest in augmented reality (AR), Meta CEO Mark Zuckerberg is likely eager to show off his own plans to make AR a reality. While Zuckerberg isn't as hot on the metaverse as he was when he renamed his company, the union of AI and AR is one way he can still make the dream of persistent virtual worlds come true.

In massive multiple-input multiple-output (MIMO) systems, how to reliably acquire downlink channel state information (CSI) with low overhead is challenging. In this work, by integrating the generative pre-trained Transformer (GPT) with federated-tuning, we propose a CSI-GPT approach to realize efficient downlink CSI acquisition. Specifically, we first propose a Swin Transformer-based channel acquisition network (SWTCAN) to acquire downlink CSI, where pilot signals, downlink channel estimation, and uplink CSI feedback are jointly designed. Furthermore, to solve the problem of insufficient training data, we propose a variational auto-encoder-based channel sample generator (VAE-CSG), which can generate sufficient CSI samples based on a limited number of high-quality CSI data obtained from the current cell. The CSI dataset generated from VAE-CSG will be used for pre-training SWTCAN. To fine-tune the pre-trained SWTCAN for improved performance, we propose an online federated-tuning method, where only a small amount of SWTCAN parameters are unfrozen and updated using over-the-air computation, avoiding the high communication overhead caused by aggregating the complete CSI samples from user equipment (UEs) to the BS for centralized fine-tuning. Simulation results verify the advantages of the proposed SWTCAN and the communication efficiency of the proposed federated-tuning method. Our code is publicly available at https://github.com/BIT-ZY/CSI-GPT

Recently advancements in large multimodal models have led to significant strides in image comprehension capabilities. Despite these advancements, there is a lack of the robust benchmark specifically for assessing the Image-to-Web conversion proficiency of these large models. Primarily, it is essential to ensure the integrity of the web elements generated. These elements comprise visible and invisible categories. Previous evaluation methods (e.g., BLEU) are notably susceptible to significant alterations due to the presence of invisible elements in Web. Furthermore, it is crucial to measure the layout information of web pages, referring to the positional relationships between elements, which is overlooked by previous work. To address challenges, we have curated and aligned a benchmark of images and corresponding web codes (IW-Bench). Specifically, we propose the Element Accuracy, which tests the completeness of the elements by parsing the Document Object Model (DOM) tree. Layout Accuracy is also proposed to analyze the positional relationships of elements by converting DOM tree into a common subsequence. Besides, we design a five-hop multimodal Chain-of-Thought Prompting for better performance, which contains five hop: 1) SoM prompt injection. 2) Inferring Elements. 3) Inferring Layout. 4) Inferring Web code. 5) Reflection. Our benchmark comprises 1200 pairs of images and web codes with varying levels of difficulty. We have conducted extensive experiments on existing large multimodal models, offering insights into their performance and areas for improvement in image-to-web domain.

Automatic scene generation is an essential area of research with applications in robotics, recreation, visual representation, training and simulation, education, and more. This survey provides a comprehensive review of the current state-of-the-arts in automatic scene generation, focusing on techniques that leverage machine learning, deep learning, embedded systems, and natural language processing (NLP). We categorize the models into four main types: Variational Autoencoders (VAEs), Generative Adversarial Networks (GANs), Transformers, and Diffusion Models. Each category is explored in detail, discussing various sub-models and their contributions to the field. We also review the most commonly used datasets, such as COCO-Stuff, Visual Genome, and MS-COCO, which are critical for training and evaluating these models. Methodologies for scene generation are examined, including image-to-3D conversion, text-to-3D generation, UI/layout design, graph-based methods, and interactive scene generation. Evaluation metrics such as Frechet Inception Distance (FID), Kullback-Leibler (KL) Divergence, Inception Score (IS), Intersection over Union (IoU), and Mean Average Precision (mAP) are discussed in the context of their use in assessing model performance. The survey identifies key challenges and limitations in the field, such as maintaining realism, handling complex scenes with multiple objects, and ensuring consistency in object relationships and spatial arrangements. By summarizing recent advances and pinpointing areas for improvement, this survey aims to provide a valuable resource for researchers and practitioners working on automatic scene generation.