Recognizing the physical states of objects and their transformations within videos is crucial for structured video understanding and enabling robust real-world applications, such as robotic manipulation. However, pretrained vision-language models often struggle to capture these nuanced dynamics and their temporal context, and specialized object state recognition frameworks may not generalize to unseen actions or objects. We introduce SAGE (State-Action Graph Embeddings), a novel framework that offers a unified model of physical state transitions by decomposing states into fine-grained, language-described visual concepts that are sharable across different objects and actions. SAGE initially leverages Large Language Models to construct a State-Action Graph, which is then multimodally refined using Vision-Language Models. Extensive experiments show that our method significantly outperforms baselines, generalizes effectively to unseen objects and actions in open-world settings. SAGE improves the prior state-of-the-art by as much as 14.6% on novel state recognition with less than 5% of its inference time.

Oriented to the position tracking and attitude control problem of quadrotors, an analytic optimal strategy is proposed based on iterative sequential action control, considering the applicability and computing efficiency. To begin with, the nonlinear dynamics of quadrotors are described using quaternions. Then, the iterative sequential optimization strategy generates candidate actions based on the coupled 6-Degree-of-Freedom (6-DoF) model. Each action is a triplet consisting of the amplitude, application occasion and duration. After selection and synthesis, the optimal sequences in the flight are determined. The advantages of the proposed strategy are energy conservation and accurate tracking, owing to the application of discrete signals. Finally, forward simulations of the quadrotor are conducted in various, with detailed analysis, to demonstrate the efficiency of the strategy.

Adversarial attacks are carried out to reveal the vulnerability of deep neural networks.Textual adversarial attacking is challenging because text is discrete and a small perturbation can bring significant change to the original input.Word-level attacking, which can be regarded as a combinatorial optimization problem, is a well-studied class of textual attack methods.However, existing word-level attack models are far from perfect, largely because unsuitable search space reduction methods and inefficient optimization algorithms are employed.In this paper, we propose a novel attack model, which incorporates the sememebased word substitution method and particle swarm optimization-based search algorithm to solve the two problems separately.We conduct exhaustive experiments to evaluate our attack model by attacking BiLSTM and BERT on three benchmark datasets.Experimental results demonstrate that our model consistently achieves much higher attack success rates and crafts more high-quality adversarial examples as compared to baseline methods.Also, further experiments show our model has higher transferability and can bring more robustness enhancement to victim models by adversarial training.

Word sense disambiguation (WSD) is a fundamental natural language processing task.Unsupervised knowledge-based WSD only relies on a lexical knowledge base as the sense inventory and has wider practical use than supervised WSD that requires a mass of sense-annotated data.HowNet is the most widely used lexical knowledge base in Chinese WSD.Because of its uniqueness, however, most of existing unsupervised WSD methods cannot work for HowNetbased WSD, and the tailor-made methods have not obtained satisfying results.In this paper, we propose a new unsupervised method for HowNet-based Chinese WSD, which exploits the masked language model task of pre-trained language models.In experiments, considering existing evaluation dataset is small and out-of-date, we build a new and larger HowNet-based WSD dataset.Experimental results demonstrate that our model achieves significantly better performance than all the baseline methods.All the code and data of this paper are available at https://github.com/thunlp/SememeWSD.