In this paper, we study the problem of 3D scene geometry decomposition and manipulation from 2D views. By leveraging the recent implicit neural representation techniques, particularly the appealing neural radiance fields, we introduce an object field component to learn unique codes for all individual objects in 3D space only from 2D supervision. The key to this component is a series of carefully designed loss functions to enable every 3D point, especially in non-occupied space, to be effectively optimized even without 3D labels. In addition, we introduce an inverse query algorithm to freely manipulate any specified 3D object shape in the learned scene representation. Notably, our manipulation algorithm can explicitly tackle key issues such as object collisions and visual occlusions. Our method, called DM-NeRF, is among the first to simultaneously reconstruct, decompose, manipulate and render complex 3D scenes in a single pipeline. Extensive experiments on three datasets clearly show that our method can accurately decompose all 3D objects from 2D views, allowing any interested object to be freely manipulated in 3D space such as translation, rotation, size adjustment, and deformation.

The extent to which text-only language models (LMs) learn to represent features of the non-linguistic world is an open question. Prior work has shown that pretrained LMs can be taught to caption images when a vision model's parameters are optimized to encode images in the language space. We test a stronger hypothesis: that the conceptual representations learned by frozen text-only models and vision-only models are similar enough that this can be achieved with a linear map. We show that the image representations from vision models can be transferred as continuous prompts to frozen LMs by training only a single linear projection. Using these to prompt the LM achieves competitive performance on captioning and visual question answering tasks compared to models that tune both the image encoder and text decoder (such as the MAGMA model). We compare three image encoders with increasing amounts of linguistic supervision seen during pretraining: BEIT (no linguistic information), NF-ResNET (lexical category information), and CLIP (full natural language descriptions). We find that all three encoders perform equally well at transferring visual property information to the language model (e.g., whether an animal is large or small), but that image encoders pretrained with linguistic supervision more saliently encode category information (e.g., distinguishing hippo vs. elephant) and thus perform significantly better on benchmark language-and-vision tasks. Our results indicate that LMs encode conceptual information structurally similarly to vision-based models, even those that are solely trained on images. Code is available here: https://github.com/jmerullo/limber

Chain-of-thought prompting combined with pre-trained large language models has achieved encouraging results on complex reasoning tasks. In this paper, we propose a new decoding strategy, self-consistency, to replace the naive greedy decoding used in chain-of-thought prompting. It first samples a diverse set of reasoning paths instead of only taking the greedy one, and then selects the most consistent answer by marginalizing out the sampled reasoning paths. Self-consistency leverages the intuition that a complex reasoning problem typically admits multiple different ways of thinking leading to its unique correct answer. Our extensive empirical evaluation shows that self-consistency boosts the performance of chain-of-thought prompting with a striking margin on a range of popular arithmetic and commonsense reasoning benchmarks, including GSM8K (+17.9%), Although language models have demonstrated remarkable success across a range of NLP tasks, their ability to demonstrate reasoning is ...

Polanyi's paradox, named in honor of the philosopher and polymath Michael Polanyi, states that "we know more than we can tell."[1] He means that most of our knowledge is tacit and cannot be easily formalized with words.[2] In The Tacit Dimension, Polanyi gives the example of recognizing a face without being able to tell what facial features humans use to make such a distinction. The example describes Gestalt psychology which emerged in the early twentieth century as a theory of perception that rejected the basic principles of elementalist and structuralist psychology as well as functionalist and behavioralist theories of the mind. Gestalt theory emphasizes that conscious humans perceive entire patterns or configurations, not individual components, and cannot always explain what they know. Consider the ancient Chinese game Go, where nobody can define a good move.

A #worldmodel is generally viewed as "an abstract representation of the spatial or temporal dimensions of our world". Humans develop a mental model of the world based on what they are able to perceive with their limited senses. The decisions and actions we make are based on this internal model and what we perceive at any given moment is governed by our brain's prediction of the future based on our internal model. This guides model-based ML NNs models aimed to learn condensed/compressed spatial and temporal representations of data for real-life interactions with the environment, like Vision (V), Memory (M), and Controller (C) VAE (V) agent model. The role of the V model is to learn an abstract, compressed representation of each observed input frame, the role of the M model is to predict the future.

Recent advancements in visiolinguistic (VL) learning have allowed the development of multiple models and techniques that offer several impressive implementations, able to currently resolve a variety of tasks that require the collaboration of vision and language. Current datasets used for VL pre-training only contain a limited amount of visual and linguistic knowledge, thus significantly limiting the generalization capabilities of many VL models. External knowledge sources such as knowledge graphs (KGs) and Large Language Models (LLMs) are able to cover such generalization gaps by filling in missing knowledge, resulting in the emergence of hybrid architectures. In the current survey, we analyze tasks that have benefited from such hybrid approaches.

Eva is a multimodal conversational system that helps users to accomplish their domain goals through collaborative dialogue. The system does this by inferring users' intentions and plans to achieve those goals, detects whether obstacles are present, finds plans to overcome them or to achieve higher-level goals, and plans its actions, including speech acts,to help users accomplish those goals. In doing so, the system maintains and reasons with its own beliefs, goals and intentions, and explicitly reasons about those of its user. Belief reasoning is accomplished with a modal Horn-clause meta-interpreter. The planning and reasoning subsystems obey the principles of persistent goals and intentions, including the formation and decomposition of intentions to perform complex actions, as well as the conditions under which they can be given up. In virtue of its planning process, the system treats its speech acts just like its other actions -- physical acts affect physical states, digital acts affect digital states, and speech acts affect mental and social states. This general approach enables Eva to plan a variety of speech acts including requests, informs, questions, confirmations, recommendations, offers, acceptances, greetings, and emotive expressions. Each of these has a formally specified semantics which is used during the planning and reasoning processes. Because it can keep track of different users' mental states, it can engage in multi-party dialogues. Importantly, Eva can explain its utterances because it has created a plan standing behind each of them. Finally, Eva employs multimodal input and output, driving an avatar that can perceive and employ facial and head movements along with emotive speech acts.

Mathematical reasoning, a core ability of human intelligence, presents unique challenges for machines in abstract thinking and logical reasoning. Recent large pre-trained language models such as GPT-3 have achieved remarkable progress on mathematical reasoning tasks written in text form, such as math word problems (MWP). However, it is unknown if the models can handle more complex problems that involve math reasoning over heterogeneous information, such as tabular data. To fill the gap, we present Tabular Math Word Problems (TabMWP), a new dataset containing 38,431 open-domain grade-level problems that require mathematical reasoning on both textual and tabular data. Each question in TabMWP is aligned with a tabular context, which is presented as an image, semi-structured text, and a structured table. There are two types of questions: free-text and multi-choice, and each problem is annotated with gold solutions to reveal the multi-step reasoning process. We evaluate different pre-trained models on TabMWP, including the GPT-3 model in a few-shot setting. As earlier studies suggest, since few-shot GPT-3 relies on the selection of in-context examples, its performance is unstable and can degrade to near chance. The unstable issue is more severe when handling complex problems like TabMWP. To mitigate this, we further propose a novel approach, PromptPG, which utilizes policy gradient to learn to select in-context examples from a small amount of training data and then constructs the corresponding prompt for the test example. Experimental results show that our method outperforms the best baseline by 5.31% on the accuracy metric and reduces the prediction variance significantly compared to random selection, which verifies its effectiveness in selecting in-context examples.

A big convergence of language, multimodal perception, action, and world modeling is a key step toward artificial general intelligence. In this work, we introduce Kosmos-1, a Multimodal Large Language Model (MLLM) that can perceive general modalities, learn in context (i.e., few-shot), and follow instructions (i.e., zero-shot). Specifically, we train Kosmos-1 from scratch on web-scale multimodal corpora, including arbitrarily interleaved text and images, image-caption pairs, and text data. We evaluate various settings, including zero-shot, few-shot, and multimodal chain-of-thought prompting, on a wide range of tasks without any gradient updates or finetuning. Experimental results show that Kosmos-1 achieves impressive performance on (i) language understanding, generation, and even OCR-free NLP (directly fed with document images), (ii) perception-language tasks, including multimodal dialogue, image captioning, visual question answering, and (iii) vision tasks, such as image recognition with descriptions (specifying classification via text instructions). We also show that MLLMs can benefit from cross-modal transfer, i.e., transfer knowledge from language to multimodal, and from multimodal to language. In addition, we introduce a dataset of Raven IQ test, which diagnoses the nonverbal reasoning capability of MLLMs.

Many popular machine learning models scale poorly when deployed on CPUs. In this paper we explore the reasons why and propose a simple, yet effective approach based on the well-known Divide-and-Conquer Principle to tackle this problem of great practical importance. Given an inference job, instead of using all available computing resources (i.e., CPU cores) for running it, the idea is to break the job into independent parts that can be executed in parallel, each with the number of cores according to its expected computational cost. We implement this idea in the popular OnnxRuntime framework and evaluate its effectiveness with several use cases, including the well-known models for optical character recognition (PaddleOCR) and natural language processing (BERT).