Search

Sarcasm typically conveys emotions of contempt or criticism by expressing a meaning that is contrary to the speaker's true intent. Accurate detection of sarcasm aids in identifying and filtering undesirable information on the Internet, thereby reducing malicious defamation and rumor-mongering. Nonetheless, the task of automatic sarcasm detection remains highly challenging for machines, as it critically depends on intricate factors such as relational context. Most existing multimodal sarcasm detection methods focus on introducing graph structures to establish entity relationships between text and images while neglecting to learn the relational context between text and images, which is crucial evidence for understanding the meaning of sarcasm. In addition, the meaning of sarcasm changes with the evolution of different contexts, but existing methods may not be accurate in modeling such dynamic changes, limiting the generalization ability of the models. To address the above issues, we propose a relational context learning and multiplex fusion network (RCLMuFN) for multimodal sarcasm detection. Firstly, we employ four feature extractors to comprehensively extract features from raw text and images, aiming to excavate potential features that may have been previously overlooked. Secondly, we utilize the relational context learning module to learn the contextual information of text and images and capture the dynamic properties through shallow and deep interactions. Finally, we employ a multiplex feature fusion module to enhance the generalization of the model by penetratingly integrating multimodal features derived from various interaction contexts. Extensive experiments on two multimodal sarcasm detection datasets show that our proposed method achieves state-of-the-art performance.

The recent rapid development of large language models (LLMs) has sparked a new wave of technological revolution in medical artificial intelligence (AI). While LLMs are designed to understand and generate text like a human, autonomous agents that utilize LLMs as their "brain" have exhibited capabilities beyond text processing such as planning, reflection, and using tools by enabling their "bodies" to interact with the environment. We introduce a simulacrum of hospital called Agent Hospital that simulates the entire process of treating illness, in which all patients, nurses, and doctors are LLM-powered autonomous agents. Within the simulacrum, doctor agents are able to evolve by treating a large number of patient agents without the need to label training data manually. After treating tens of thousands of patient agents in the simulacrum (human doctors may take several years in the real world), the evolved doctor agents outperform state-of-the-art medical agent methods on the MedQA benchmark comprising US Medical Licensing Examination (USMLE) test questions. Our methods of simulacrum construction and agent evolution have the potential in benefiting a broad range of applications beyond medical AI.

Large language models (LLMs) exhibit powerful general intelligence across diverse scenarios, including their integration into chatbots. However, a vital challenge of LLM-based chatbots is that they may produce hallucinated content in responses, which significantly limits their applicability. Various efforts have been made to alleviate hallucination, such as retrieval augmented generation and reinforcement learning with human feedback, but most of them require additional training and data annotation. In this paper, we propose a novel post-hoc Citation-Enhanced Generation (CEG) approach combined with retrieval argumentation. Unlike previous studies that focus on preventing hallucinations during generation, our method addresses this issue in a post-hoc way. It incorporates a retrieval module to search for supporting documents relevant to the generated content, and employs a natural language inference-based citation generation module. Once the statements in the generated content lack of reference, our model can regenerate responses until all statements are supported by citations. Note that our method is a training-free plug-and-play plugin that is capable of various LLMs. Experiments on various hallucination-related datasets show our framework outperforms state-of-the-art methods in both hallucination detection and response regeneration on three benchmarks. Our codes and dataset will be publicly available.

Tactile signals collected by wearable electronics are essential in modeling and understanding human behavior. One of the main applications of tactile signals is action classification, especially in healthcare and robotics. However, existing tactile classification methods fail to capture the spatial and temporal features of tactile signals simultaneously, which results in sub-optimal performances. In this paper, we design Spatio-Temporal Aware tactility Transformer (STAT) to utilize continuous tactile signals for action classification. We propose spatial and temporal embeddings along with a new temporal pretraining task in our model, which aims to enhance the transformer in modeling the spatio-temporal features of tactile signals. Specially, the designed temporal pretraining task is to differentiate the time order of tubelet inputs to model the temporal properties explicitly. Experimental results on a public action classification dataset demonstrate that our model outperforms state-of-the-art methods in all metrics., Comment: Accepted by AAAI 2024

Quantum Spin Hall (QSH) insulators possess distinct helical in-gap states, enabling their edge states to act as one-dimensional conducting channels when backscattering is prohibited by time-reversal symmetry. However, it remains challenging to achieve high-performance combinations of nontrivial topological QSH states with superconductivity for applications and requires understanding of the complicated underlying mechanisms. Here, our experimental observations for a novel superconducting phase in the pressurized QSH insulator Ta2Pd3Te5 is reported, and the high-pressure phase maintains its original ambient pressure lattice symmetry up to 45 GPa. Our in-situ high-pressure synchrotron X-ray diffraction, electrical transport, infrared reflectance, and Raman spectroscopy measurements, in combination with rigorous theoretical calculations, provide compelling evidence for the association between the superconducting behavior and the abnormal densified phase. The isostructural transition was found to modify the topology of the Fermi surface directly, accompanied by a fivefold amplification of the density of states at 20 GPa compared to ambient pressure, which synergistically fosters the emergence of robust superconductivity. A profound comprehension of the fascinating properties exhibited by the compressed Ta2Pd3Te5 phase is achieved, highlighting the extraordinary potential of van der Waals (vdW) QSH insulators for exploring and investigating high-performance electronic advanced devices under extreme conditions., Comment: 16pages,4figures

The non-Hermitian skin effect is a distinctive phenomenon in non-Hermitian systems, which manifests as the anomalous localization of bulk states at the boundary. To understand the physical origin of the non-Hermitian skin effect, a bulk band characterization based on the dynamical degeneracy on an equal frequency contour is proposed, which reflects the strong anisotropy of the spectral function. In this paper, we report the experimental observation of both phenomena in a two-dimensional acoustic crystal, and reveal their remarkable correspondence by performing single-frequency excitation measurements. Our work not only provides a controllable experimental platform for studying the non-Hermitian physics, but also confirms the correspondence between the non-Hermitian skin effect and the dynamical degeneracy splitting, paving a new way to characterize the non-Hermitian skin effect., Comment: 14+3 pages, 4+4 figures

Topological insulators are a new phase of matter with the distinctive characteristics of an insulating bulk and conducting edge states. Recent theories indicate there even exist topological edge states in the fractal-dimensional lattices, which are fundamentally different from the current studies that rely on the integer dimensions. Here, we propose and experimentally demonstrate the squeezed Chern insulator in a fractal-dimensional acoustic lattice. First, through calculating the topological invariant of our topological fractal system, we find the topological phase diagram is squeezed by about 0.54 times, compared with that of the original Haldane model. Then by introducing synthetic gauge flux into an acoustic fractal lattice, we experimentally observe the one-way edge states that are protected by a robust mobility gap within the squeezed topological regimes. Our work demonstrates the first example of acoustic topological fractal insulators and provides new directions for the advanced control of sound waves.

Higher-order topological insulators, which support lower-dimensional topological boundary states than the first-order topological insulators, have been intensely investigated in the integer dimensional systems. Here, we provide a new paradigm by presenting experimentally a higher-order topological phase in a fractal-dimensional system. Through applying the Benalcazar, Bernevig, and Hughes model into a Sierpinski carpet fractal lattice, we uncover a squeezed higher-order phase diagram featuring the abundant corner states, which consist of zero-dimensional outer corner states and 1.89-dimensional inner corner states. As a result, the codimension is now 1.89 and our model can be classified into the fractional-order topological insulators. The non-zero fractional charges at the outer/inner corners indicate that all corner states in the fractal system are indeed topologically nontrivial. Finally, in a fabricated acoustic fractal lattice, we experimentally observe the outer/inner corner states with local acoustic measurements. Our work demonstrates a higher-order topological phase in an acoustic fractal lattice and may pave the way to the fractional-order topological insulators.