Large language models (LLMs) and large multimodal models (LMMs) have shown great potential in automating complex tasks like web browsing and gaming. However, their ability to generalize across diverse applications remains limited, hindering broader utility. To address this challenge, we present OSCAR: Operating System Control via state-Aware reasoning and Re-planning. OSCAR is a generalist agent designed to autonomously navigate and interact with various desktop and mobile applications through standardized controls, such as mouse and keyboard inputs, while processing screen images to fulfill user commands. OSCAR translates human instructions into executable Python code, enabling precise control over graphical user interfaces (GUIs). To enhance stability and adaptability, OSCAR operates as a state machine, equipped with error-handling mechanisms and dynamic task re-planning, allowing it to efficiently adjust to real-time feedback and exceptions. We demonstrate OSCAR’s effectiveness through extensive experiments on diverse benchmarks across desktop and mobile platforms, where it transforms complex workflows into simple natural language commands, significantly boosting user productivity. Our code will be open-source upon publication.

Chain-of-thought (CoT) reasoning enables large language models (LLMs) to move beyond fast System-1 responses and engage in deliberative System-2 reasoning. However, this comes at the cost of significant inefficiency due to verbose intermediate output. Recent latent-space reasoning methods improve efficiency by operating on hidden states without decoding into language, yet they treat all steps uniformly, failing to distinguish critical deductions from auxiliary steps and resulting in suboptimal use of computational resources. In this paper, we propose System-1.5 Reasoning, an adaptive reasoning framework that dynamically allocates computation across reasoning steps through shortcut paths in latent space.Specifically, System-1.5 Reasoning introduces two types of dynamic shortcuts. The model depth shortcut (DS) adaptively reasons along the vertical depth by early exiting non-critical tokens through lightweight adapter branches, while allowing critical tokens to continue through deeper Transformer layers. The step shortcut (SS) reuses hidden states across the decoding steps to skip trivial steps and reason horizontally in latent space. Training System-1.5 Reasoning involves a two-stage self-distillation process: first distilling natural language CoT into latent-space continuous thought, and then distilling full-path System-2 latent reasoning into adaptive shortcut paths (System-1.5 Reasoning).Experiments on reasoning tasks demonstrate the superior performance of our method. For example, on GSM8K, System-1.5 Reasoning achieves reasoning performance comparable to traditional CoT fine-tuning methods while accelerating inference by over 20× and reducing token generation by 91.0\% on average.

Large language models (LLMs) are primarily evaluated by overall performance on various text understanding and generation tasks.However, such a paradigm fails to comprehensively differentiate the fine-grained language and cognitive skills, rendering the lack of sufficient interpretation to LLMs' capabilities.In this paper, we present FAC 2 E, a framework for Fine-grAined and Cognition-grounded LLMs' Capability Evaluation.Specifically, we formulate LLMs' evaluation in a multi-dimensional and explainable manner by dissociating the language-related capabilities and the cognitionrelated ones.Besides, through extracting the intermediate reasoning from LLMs, we further break down the process of applying a specific capability into three sub-steps: recalling relevant knowledge, utilizing knowledge, and solving problems.Finally, FAC 2 E evaluates each sub-step of each fine-grained capability, providing a two-faceted diagnosis for LLMs.Utilizing FAC 2 E, we identify a common shortfall in knowledge utilization among models and propose a straightforward, knowledge-enhanced method to mitigate this issue.Our results not only showcase promising performance enhancements but also highlight a direction for future LLM advancements.

Machine Learning is often challenged by insufficient labeled data. Previous methods employing implicit commonsense knowledge of pre-trained language models (PLMs) or pattern-based symbolic knowledge have achieved great success in mitigating manual annotation efforts. In this paper, we focus on the collaboration among different knowledge sources and present KICE, a Knowledge-evolving framework by Iterative Consolidation and Expansion with the guidance of PLMs and rule-based patterns. Specifically, starting with limited labeled data as seeds, KICE first builds a Rule Generator by prompt-tuning to stimulate the rich knowledge distributed in PLMs, generate seed rules, and initialize the rules set. Afterwards, based on the rule-labeled data, the task model is trained in a self-training pipeline where the knowledge in rules set is consolidated with self-learned high-confidence rules. Finally, for the low-confidence rules, KICE solicits human-enlightened understanding and expands the knowledge coverage for better task model training. Our framework is verified on relation extraction (RE) task, and the experiments on TACRED show that the model performance (F1) grows from 33.24% to 79.84% with the enrichment of knowledge, outperforming all the baselines including other knowledgeable methods.

RGB-D salient object detection aims to detect visually distinctive objects or regions from a pair of the RGB image and the depth image. State-of-the-art RGB-D saliency detectors are mainly based on convolutional neural networks but almost suffer from an intrinsic limitation relying on the labeled data, thus degrading detection accuracy in complex cases. In this work, we present a self-supervised self-ensembling network (S$^3$Net) for semi-supervised RGB-D salient object detection by leveraging the unlabeled data and exploring a self-supervised learning mechanism. To be specific, we first build a self-guided convolutional neural network (SG-CNN) as a baseline model by developing a series of three-layer cross-model feature fusion (TCF) modules to leverage complementary information among depth and RGB modalities and formulating an auxiliary task that predicts a self-supervised image rotation angle. After that, to further explore the knowledge from unlabeled data, we assign SG-CNN to a student network and a teacher network, and encourage the saliency predictions and self-supervised rotation predictions from these two networks to be consistent on the unlabeled data. Experimental results on seven widely-used benchmark datasets demonstrate that our network quantitatively and qualitatively outperforms the state-of-the-art methods.

Machine Reading Comprehension (MRC) reveals the ability to understand a given text passage and answer questions based on it.Existing research works in MRC rely heavily on large-size models and corpus to improve the performance evaluated by metrics such as Exact Match (EM ) and F 1 .However, such a paradigm lacks sufficient interpretation to model capability and can not efficiently train a model with a large corpus.In this paper, we argue that a deep understanding of model capabilities and data properties can help us feed a model with appropriate training data based on its learning status.Specifically, we design an MRC capability assessment framework that assesses model capabilities in an explainable and multi-dimensional manner.Based on it, we further uncover and disentangle the connections between various data properties and model performance.Finally, to verify the effectiveness of the proposed MRC capability assessment framework, we incorporate it into a curriculum learning pipeline and devise a Capability Boundary Breakthrough Curriculum (CBBC) strategy, which performs a model capability-based training to maximize the data value and improve training efficiency.Extensive experiments demonstrate that our approach significantly improves performance, achieving up to an 11.22% / 8.71% improvement of EM / F 1 on MRC tasks.

Existing metrics for assessing question generation not only require costly human reference but also fail to take into account the input context of generation, rendering the lack of deep understanding of the relevance between the generated questions and input contexts.As a result, they may wrongly penalize a legitimate and reasonable candidate question when it (i) involves complicated reasoning with the context or (ii) can be grounded by multiple evidences in the context.In this paper, we propose QRelScore, a context-aware Relevance evaluation metric for Question Generation.Based on off-the-shelf language models such as BERT and GPT2, QRelScore employs both word-level hierarchical matching and sentence-level prompt-based generation to cope with the complicated reasoning and diverse generation from multiple evidences, respectively.Compared with existing metrics, our experiments demonstrate that QRelScore is able to achieve a higher correlation with human judgments while being much more robust to adversarial samples.

Training deep models for RGB-D salient object detection (SOD) often requires a large number of labeled RGB-D images. However, RGB-D data is not easily acquired, which limits the development of RGB-D SOD techniques. To alleviate this issue, we present a Dual-Semi RGB-D Salient Object Detection Network (DS-Net) to leverage unlabeled RGB images for boosting RGB-D saliency detection. We first devise a depth decoupling convolutional neural network (DDCNN), which contains a depth estimation branch and a saliency detection branch. The depth estimation branch is trained with RGB-D images and then used to estimate the pseudo depth maps for all unlabeled RGB images to form the paired data. The saliency detection branch is used to fuse the RGB feature and depth feature to predict the RGB-D saliency. Then, the whole DDCNN is assigned as the backbone in a teacher-student framework for semi-supervised learning. Moreover, we also introduce a consistency loss on the intermediate attention and saliency maps for the unlabeled data, as well as a supervised depth and saliency loss for labeled data. Experimental results on seven widely-used benchmark datasets demonstrate that our DDCNN outperforms state-of-the-art methods both quantitatively and qualitatively. We also demonstrate that our semi-supervised DS-Net can further improve the performance, even when using an RGB image with the pseudo depth map.