As Large Language Models (LLMs) scale up and gain powerful Chain-of-Thoughts (CoTs) reasoning abilities, practical resource constraints drive efforts to distill these capabilities into more compact Smaller Language Models (SLMs). We find that CoTs consist mainly of simple reasoning forms, with a small proportion ($\approx 4.7\%$) of key reasoning steps that truly impact conclusions. However, previous distillation methods typically involve supervised fine-tuning student SLMs only on correct CoTs data produced by teacher LLMs, resulting in students struggling to learn the key reasoning steps, instead imitating the teacher's reasoning forms and making errors or omissions on these steps. To address these issues, drawing an analogy to human learning, where analyzing mistakes according to correct solutions often reveals the crucial steps leading to successes or failures, we propose mistak\textbf{E}-\textbf{D}riven key reason\textbf{I}ng step distilla\textbf{T}ion (\textbf{EDIT}), a novel method that further aids SLMs learning key reasoning steps rather than mere simple fine-tuning. Firstly, to expose these crucial steps in CoTs, we design specific prompts to generate dual CoTs data with similar reasoning paths but divergent conclusions. Then, we apply the minimum edit distance algorithm on the dual CoTs data to locate these key steps and optimize the likelihood of these steps. Extensive experiments validate the effectiveness of EDIT across both in-domain and out-of-domain benchmark reasoning datasets. Further analysis shows that EDIT can generate high-quality CoTs with more correct key reasoning steps. Notably, we also explore how different mistake patterns affect performance and find that EDIT benefits more from logical errors than from knowledge or mathematical calculation errors in dual CoTs\footnote{Code can be found at \url{https://github.com/C-W-D/EDIT}}.

Learning meaningful representations of complex objects that can be seen through multiple ($k\geq 3$) views or modalities is a core task in machine learning. Existing methods use losses originally intended for paired views, and extend them to $k$ views, either by instantiating $\tfrac12k(k-1)$ loss-pairs, or by using reduced embeddings, following a \textit{one vs. average-of-rest} strategy. We propose the multi-marginal matching gap (M3G), a loss that borrows tools from multi-marginal optimal transport (MM-OT) theory to simultaneously incorporate all $k$ views. Given a batch of $n$ points, each seen as a $k$-tuple of views subsequently transformed into $k$ embeddings, our loss contrasts the cost of matching these $n$ ground-truth $k$-tuples with the MM-OT polymatching cost, which seeks $n$ optimally arranged $k$-tuples chosen within these $n\times k$ vectors. While the exponential complexity $O(n^k$) of the MM-OT problem may seem daunting, we show in experiments that a suitable generalization of the Sinkhorn algorithm for that problem can scale to, e.g., $k=3\sim 6$ views using mini-batches of size $64~\sim128$. Our experiments demonstrate improved performance over multiview extensions of pairwise losses, for both self-supervised and multimodal tasks.

This paper introduces an interdisciplinary framework called Machine Psychology, which merges principles from operant learning psychology with a specific Artificial Intelligence model, the Non-Axiomatic Reasoning System (NARS), to enhance Artificial General Intelligence (AGI) research. The core premise of this framework is that adaptation is crucial to both biological and artificial intelligence and can be understood through operant conditioning principles. The study assesses this approach via three operant learning tasks using OpenNARS for Applications (ONA): simple discrimination, changing contingencies, and conditional discrimination tasks. In the simple discrimination task, NARS demonstrated rapid learning, achieving perfect accuracy during both training and testing phases. The changing contingencies task showcased NARS's adaptability, as it successfully adjusted its behavior when task conditions were reversed. In the conditional discrimination task, NARS handled complex learning scenarios effectively, achieving high accuracy by forming and utilizing intricate hypotheses based on conditional cues. These findings support the application of operant conditioning as a framework for creating adaptive AGI systems. NARS's ability to operate under conditions of insufficient knowledge and resources, coupled with its sensorimotor reasoning capabilities, establishes it as a robust model for AGI. The Machine Psychology framework, by incorporating elements of natural intelligence such as continuous learning and goal-driven behavior, offers a scalable and flexible approach for real-world applications. Future research should investigate using enhanced NARS systems, more advanced tasks, and applying this framework to diverse, complex challenges to further progress the development of human-level AI.

At the core of self-supervised learning for vision is the idea of learning invariant or equivariant representations with respect to a set of data transformations. This approach, however, introduces strong inductive biases, which can render the representations fragile in downstream tasks that do not conform to these symmetries. In this work, drawing insights from world models, we propose to instead learn a general representation that can adapt to be invariant or equivariant to different transformations by paying attention to context -- a memory module that tracks task-specific states, actions, and future states. Here, the action is the transformation, while the current and future states respectively represent the input's representation before and after the transformation. Our proposed algorithm, Contextual Self-Supervised Learning (ContextSSL), learns equivariance to all transformations (as opposed to invariance). In this way, the model can learn to encode all relevant features as general representations while having the versatility to tail down to task-wise symmetries when given a few examples as the context. Empirically, we demonstrate significant performance gains over existing methods on equivariance-related tasks, supported by both qualitative and quantitative evaluations.

In this work, we propose a novel method named \textbf{Auto}mated Process Labeling via \textbf{C}onfidence \textbf{V}ariation (\textbf{\textsc{AutoCV}}) to enhance the reasoning capabilities of large language models (LLMs) by automatically annotating the reasoning steps. Our approach begins by training a verification model on the correctness of final answers, enabling it to generate automatic process annotations. This verification model assigns a confidence score to each reasoning step, indicating the probability of arriving at the correct final answer from that point onward. We detect relative changes in the verification's confidence scores across reasoning steps to automatically annotate the reasoning process. This alleviates the need for numerous manual annotations or the high computational costs associated with model-induced annotation approaches. We experimentally validate that the confidence variations learned by the verification model trained on the final answer correctness can effectively identify errors in the reasoning steps. Subsequently, we demonstrate that the process annotations generated by \textsc{AutoCV} can improve the accuracy of the verification model in selecting the correct answer from multiple outputs generated by LLMs. Notably, we achieve substantial improvements across five datasets in mathematics and commonsense reasoning. The source code of \textsc{AutoCV} is available at \url{https://github.com/rookie-joe/AUTOCV}.

Which transformer scaling regimes are able to perfectly solve different classes of algorithmic problems? While tremendous empirical advances have been attained by transformer-based neural networks, a theoretical understanding of their algorithmic reasoning capabilities in realistic parameter regimes is lacking. We investigate this question in terms of the network's depth, width, and number of extra tokens for algorithm execution. Our novel representational hierarchy separates 9 algorithmic reasoning problems into classes solvable by transformers in different realistic parameter scaling regimes. We prove that logarithmic depth is necessary and sufficient for tasks like graph connectivity, while single-layer transformers with small embedding dimensions can solve contextual retrieval tasks. We also support our theoretical analysis with ample empirical evidence using the GraphQA benchmark. These results show that transformers excel at many graph reasoning tasks, even outperforming specialized graph neural networks.

Intelligent vision control systems for surgical robots should adapt to unknown and diverse objects while being robust to system disturbances. Previous methods did not meet these requirements due to mainly relying on pose estimation and feature tracking. We propose a world-model-based deep reinforcement learning framework "Grasp Anything for Surgery" (GAS), that learns a pixel-level visuomotor policy for surgical grasping, enhancing both generality and robustness. In particular, a novel method is proposed to estimate the values and uncertainties of depth pixels for a rigid-link object's inaccurate region based on the empirical prior of the object's size; both depth and mask images of task objects are encoded to a single compact 3-channel image (size: 64x64x3) by dynamically zooming in the mask regions, minimizing the information loss. The learned controller's effectiveness is extensively evaluated in simulation and in a real robot. Our learned visuomotor policy handles: i) unseen objects, including 5 types of target grasping objects and a robot gripper, in unstructured real-world surgery environments, and ii) disturbances in perception and control. Note that we are the first work to achieve a unified surgical control system that grasps diverse surgical objects using different robot grippers on real robots in complex surgery scenes (average success rate: 69%). Our system also demonstrates significant robustness across 6 conditions including background variation, target disturbance, camera pose variation, kinematic control error, image noise, and re-grasping after the gripped target object drops from the gripper. Videos and codes can be found on our project page: https://linhongbin.github.io/gas/.

A Mitsubishi Electric machine has cracked the notoriously challenging Rubik's Cube puzzle in less than a third of a second. In the blink of an eye, computer-controlled components moved the squares of the 3 x 3 x 3 cube until each side of the block was a single color, thus completing the game. Humans present applauded the feat. Guinness World Records recognized the 0.305-second time achieved by the TOKUI Fast Accurate Synchronized Motion Testing Robot as a new world best, with it beating the previous record of 0.38 seconds. Mitsubishi Electric received a certificate from the records body on May 21. The fastest time by a human is 3.13 seconds, achieved in June 2023 by Max Park at an event in California.

Neuro-symbolic learning (NSL) models complex symbolic rule patterns into latent variable distributions by neural networks, which reduces rule search space and generates unseen rules to improve downstream task performance. Centralized NSL learning involves directly acquiring data from downstream tasks, which is not feasible for federated learning (FL). To address this limitation, we shift the focus from such a one-to-one interactive neuro-symbolic paradigm to one-to-many Federated Neuro-Symbolic Learning framework (FedNSL) with latent variables as the FL communication medium. Built on the basis of our novel reformulation of the NSL theory, FedNSL is capable of identifying and addressing rule distribution heterogeneity through a simple and effective Kullback-Leibler (KL) divergence constraint on rule distribution applicable under the FL setting. It further theoretically adjusts variational expectation maximization (V-EM) to reduce the rule search space across domains. This is the first incorporation of distribution-coupled bilevel optimization into FL. Extensive experiments based on both synthetic and real-world data demonstrate significant advantages of FedNSL compared to five state-of-the-art methods. It outperforms the best baseline by 17% and 29% in terms of unbalanced average training accuracy and unseen average testing accuracy, respectively.

We give a model-based agent that builds a Python program representing its knowledge of the world based on its interactions with the environment. The world model tries to explain its interactions, while also being optimistic about what reward it can achieve. We define this optimism as a logical constraint between a program and a planner. We study our agent on gridworlds, and on task planning, finding our approach is more sample-efficient compared to deep RL, more compute-efficient compared to ReAct-style agents, and that it can transfer its knowledge across environments by editing its code.