Multimodal Chain of Thought (MCoT) is a popular prompting strategy for improving the performance of multimodal large language models (MLLMs) across a range of complex reasoning tasks. Despite its popularity, there is a notable absence of automated methods for evaluating the quality of reasoning steps in MCoT. To address this gap, we propose Multimodal Chain-of-Thought Evaluation (MiCEval), a framework designed to assess the correctness of reasoning chains by evaluating the quality of both the description and each reasoning step. The evaluation of the description component focuses on the accuracy of the image descriptions, while the reasoning step evaluates the quality of each step as it is conditionally generated based on the preceding steps. MiCEval is built upon a fine-grained dataset with annotations that rate each step according to correctness, relevance, and informativeness. Extensive experiments on four state-of-the-art MLLMs show that step-wise evaluations using MiCEval align more closely with human judgments compared to existing methods based on cosine similarity or fine-tuning approaches. MiCEval datasets and code can be found in https://github.com/alenai97/MiCEval.

Education is poised for a transformative shift with the advent of neurosymbolic artificial intelligence (NAI), which will redefine how we support deeply adaptive and personalized learning experiences. NAI-powered education systems will be capable of interpreting complex human concepts and contexts while employing advanced problem-solving strategies, all grounded in established pedagogical frameworks. This will enable a level of personalization in learning systems that to date has been largely unattainable at scale, providing finely tailored curricula that adapt to an individual's learning pace and accessibility needs, including the diagnosis of student understanding of subjects at a fine-grained level, identifying gaps in foundational knowledge, and adjusting instruction accordingly. In this paper, we propose a system that leverages the unique affordances of pedagogical agents -- embodied characters designed to enhance learning -- as critical components of a hybrid NAI architecture. To do so, these agents can thus simulate nuanced discussions, debates, and problem-solving exercises that push learners beyond rote memorization toward deep comprehension. We discuss the rationale for our system design and the preliminary findings of our work. We conclude that education in the era of NAI will make learning more accessible, equitable, and aligned with real-world skills. This is an era that will explore a new depth of understanding in educational tools.

Artificial Intelligence is rapidly embedding itself within militaries, economies, and societies, reshaping their very foundations. Given the depth and breadth of its consequences, it has never been more pressing to understand how to ensure that AI systems are safe, ethical, and have a positive societal impact. This book aims to provide a comprehensive approach to understanding AI risk. Our primary goals include consolidating fragmented knowledge on AI risk, increasing the precision of core ideas, and reducing barriers to entry by making content simpler and more comprehensible. The book has been designed to be accessible to readers from diverse backgrounds. You do not need to have studied AI, philosophy, or other such topics. The content is skimmable and somewhat modular, so that you can choose which chapters to read. We introduce mathematical formulas in a few places to specify claims more precisely, but readers should be able to understand the main points without these.

Existing open-source multimodal large language models (MLLMs) generally follow a training process involving pre-training and supervised fine-tuning. However, these models suffer from distribution shifts, which limit their multimodal reasoning, particularly in the Chain-of-Thought (CoT) performance. To address this, we introduce a preference optimization (PO) process to enhance the multimodal reasoning capabilities of MLLMs. Specifically, (1) on the data side, we design an automated preference data construction pipeline to create MMPR, a high-quality, large-scale multimodal reasoning preference dataset. and (2) on the model side, we explore integrating PO with MLLMs, developing a simple yet effective method, termed Mixed Preference Optimization (MPO), which boosts multimodal CoT performance. Our approach demonstrates improved performance across multiple benchmarks, particularly in multimodal reasoning tasks. Notably, our model, InternVL2-8B-MPO, achieves an accuracy of 67.0 on MathVista, outperforming InternVL2-8B by 8.7 points and achieving performance comparable to the 10x larger InternVL2-76B. We hope this study could inspire further advancements in MLLMs. Code, data, and model shall be publicly released.

Firing rate models are dynamical systems widely used in applied and theoretical neuroscience to describe local cortical dynamics in neuronal populations. By providing a macroscopic perspective of neuronal activity, these models are essential for investigating oscillatory phenomena, chaotic behavior, and associative memory processes. Despite their widespread use, the application of firing rate models to associative memory networks has received limited mathematical exploration, and most existing studies are focused on specific models. Conversely, well-established associative memory designs, such as Hopfield networks, lack key biologically-relevant features intrinsic to firing rate models, including positivity and interpretable synaptic matrices that reflect excitatory and inhibitory interactions. To address this gap, we propose a general framework that ensures the emergence of re-scaled memory patterns as stable equilibria in the firing rate dynamics. Furthermore, we analyze the conditions under which the memories are locally and globally asymptotically stable, providing insights into constructing biologically-plausible and robust systems for associative memory retrieval.

Knowledge representation and reasoning systems represent knowledge as collections of facts and rules. KRRs can represent complex concepts and relations, and they can query and manipulate information in sophisticated ways. Unfortunately, the KRR technology has been hindered by the fact that specifying the requisite knowledge requires skills that most domain experts do not have, and professional knowledge engineers are hard to find. Some recent CNL-based approaches, such as the Knowledge Authoring Logic Machine (KALM), have shown to have very high accuracy compared to others, and a natural question is to what extent the CNL restrictions can be lifted. Besides the CNL restrictions, KALM has limitations in terms of the types of knowledge it can represent. To address these issues, we propose an extension of KALM called KALM for Factual Language (KALMF). KALMF uses a neural parser for natural language, MS, to parse what we call factual English sentences, which require little grammar training to use. Building upon KALMF, we propose KALM for Rules and Actions (KALMR), to represent and reason with rules and actions. Furthermore, we identify the reasons behind the slow speed of KALM and make optimizations to address this issue. Our evaluation using multiple benchmarks shows that our approaches achieve a high level of correctness on fact and query authoring (95%) and on rule authoring (100%). When used for authoring and reasoning with actions, our approach achieves more than 99.3% correctness, demonstrating its effectiveness in enabling more sophisticated knowledge representation and reasoning. We also illustrate the logical reasoning capabilities of our approach by drawing attention to the problems faced by the famous AI, ChatGPT. Finally, the evaluation of the newly proposed speed optimization points not only to a 68% runtime improvement but also yields better accuracy of the overall system.

How many moves does it take to solve a Rubik's cube if it is quantum? A quantum Rubik's cube would be infinitely more complex than the traditional puzzle, but mathematical modelling shows it wouldn't be unsolvable. In the summer of 2022, Noah Lordi and Maedée Trank-Greene at the University of Colorado Boulder and their colleagues made a bet: how many possible states would a quantum Rubik's cube have? To even make their guesses, they first had to define what a quantum Rubik's cube would entail.

World models play a crucial role in decision-making within embodied environments, enabling cost-free explorations that would otherwise be expensive in the real world. To facilitate effective decision-making, world models must be equipped with strong generalizability to support faithful imagination in out-of-distribution (OOD) regions and provide reliable uncertainty estimation to assess the credibility of the simulated experiences, both of which present significant challenges for prior scalable approaches. This paper introduces WHALE, a framework for learning generalizable world models, consisting of two key techniques: behavior-conditioning and retracing-rollout. Behavior-conditioning addresses the policy distribution shift, one of the primary sources of the world model generalization error, while retracing-rollout enables efficient uncertainty estimation without the necessity of model ensembles. These techniques are universal and can be combined with any neural network architecture for world model learning. Incorporating these two techniques, we present Whale-ST, a scalable spatial-temporal transformer-based world model with enhanced generalizability. We demonstrate the superiority of Whale-ST in simulation tasks by evaluating both value estimation accuracy and video generation fidelity. Additionally, we examine the effectiveness of our uncertainty estimation technique, which enhances model-based policy optimization in fully offline scenarios. Furthermore, we propose Whale-X, a 414M parameter world model trained on 970K trajectories from Open X-Embodiment datasets. We show that Whale-X exhibits promising scalability and strong generalizability in real-world manipulation scenarios using minimal demonstrations.

Large Multimodal Models (LMMs) have achieved strong performance across a range of vision and language tasks. However, their spatial reasoning capabilities are under-investigated. In this paper, we construct a novel VQA dataset, Spatial-MM, to comprehensively study LMMs' spatial understanding and reasoning capabilities. Our analyses on object-relationship and multi-hop reasoning reveal several important findings. Firstly, bounding boxes and scene graphs, even synthetic ones, can significantly enhance LMMs' spatial reasoning. Secondly, LMMs struggle more with questions posed from the human perspective than the camera perspective about the image. Thirdly, chain of thought (CoT) prompting does not improve model performance on complex multi-hop questions involving spatial relations. % Moreover, spatial reasoning steps are much less accurate than non-spatial ones across MLLMs. Lastly, our perturbation analysis on GQA-spatial reveals that LMMs are much stronger at basic object detection than complex spatial reasoning. We believe our benchmark dataset and in-depth analyses can spark further research on LMMs spatial reasoning. Spatial-MM benchmark is available at: https://github.com/FatemehShiri/Spatial-MM

Game solving is the process of finding the theoretical outcome for a game, assuming that all player choices are optimal. This paper focuses on a technique that can reduce the heuristic search space significantly for 7x7 Killall-Go. In Go and Killall-Go, live patterns are stones that are protected from opponent capture. Mutual life, also referred to as seki, is when both players' stones achieve life by sharing liberties with their opponent. Whichever player attempts to capture the opponent first will leave their own stones vulnerable. Therefore, it is critical to recognize seki patterns to avoid putting oneself in jeopardy. Recognizing seki can reduce the search depth significantly. In this paper, we enumerate all seki patterns up to a predetermined area size, then store these patterns into a seki table. This allows us to recognize seki during search, which significantly improves solving efficiency for the game of Killall-Go. Experiments show that a day-long, unsolvable position can be solved in 482 seconds with the addition of a seki table. For general positions, a 10% to 20% improvement in wall clock time and node count is observed.