Search

This paper addresses the need for improved precision in existing Retrieval-Augmented Generation (RAG) methods that primarily focus on enhancing recall. We propose a multi-layer knowledge pyramid approach within the RAG framework to achieve a better balance between precision and recall. The knowledge pyramid consists of three layers: Ontologies, Knowledge Graphs (KGs), and chunk-based raw text. We employ cross-layer augmentation techniques for comprehensive knowledge coverage and dynamic updates of the Ontology schema and instances. To ensure compactness, we utilize cross-layer filtering methods for knowledge condensation in KGs. Our approach, named PolyRAG, follows a waterfall model for retrieval, starting from the top of the pyramid and progressing down until a confident answer is obtained. We introduce two benchmarks for domain-specific knowledge retrieval, one in the academic domain and the other in the financial domain. The effectiveness of the methods has been validated through comprehensive experiments by outperforming 19 SOTA methods. An encouraging observation is that the proposed method has augmented the GPT-4, providing 395\% F1 gain by improving its performance from 0.1636 to 0.8109.

Accurate human localization is crucial for various applications, especially in the Metaverse era. Existing high precision solutions rely on expensive, tag-dependent hardware, while vision-based methods offer a cheaper, tag-free alternative. However, current vision solutions based on stereo vision face limitations due to rigid perspective transformation principles and error propagation in multi-stage SVD solvers. These solutions also require multiple high-resolution cameras with strict setup constraints. To address these limitations, we propose a probabilistic approach that considers all points on the human body as observations generated by a distribution centered around the body's geometric center. This enables us to improve sampling significantly, increasing the number of samples for each point of interest from hundreds to billions. By modeling the relation between the means of the distributions of world coordinates and pixel coordinates, leveraging the Central Limit Theorem, we ensure normality and facilitate the learning process. Experimental results demonstrate human localization accuracy of 95% within a 0.3m range and nearly 100% accuracy within a 0.5m range, achieved at a low cost of only 10 USD using two web cameras with a resolution of 640x480 pixels.

Recent advancements in generative models have significantly impacted content creation, leading to the emergence of Personalized Content Synthesis (PCS). With a small set of user-provided examples, PCS aims to customize the subject of interest to specific user-defined prompts. Over the past two years, more than 150 methods have been proposed. However, existing surveys mainly focus on text-to-image generation, with few providing up-to-date summaries on PCS. This paper offers a comprehensive survey of PCS, with a particular focus on the diffusion models. Specifically, we introduce the generic frameworks of PCS research, which can be broadly classified into optimization-based and learning-based approaches. We further categorize and analyze these methodologies, discussing their strengths, limitations, and key techniques. Additionally, we delve into specialized tasks within the field, such as personalized object generation, face synthesis, and style personalization, highlighting their unique challenges and innovations. Despite encouraging progress, we also present an analysis of the challenges such as overfitting and the trade-off between subject fidelity and text alignment. Through this detailed overview and analysis, we propose future directions to advance the development of PCS.

This paper extends the valuation and optimal surrender framework for variable annuities with guaranteed minimum benefits in a L\'evy equity market environment by incorporating a stochastic interest rate described by the Hull-White model. This approach frames a more dynamic and realistic financial setting compared to previous literature. We exploit a robust valuation mechanism employing a hybrid numerical method that merges tree methods for interest rate modeling with finite difference techniques for the underlying asset price. This method is particularly effective for addressing the complexities of variable annuities, where periodic fees and mortality risks are significant factors. Our findings reveal the influence of stochastic interest rates on the strategic decision-making process concerning the surrender of these financial instruments. Through comprehensive numerical experiments, and by comparing our results with those obtained through the Longstaff-Schwartz Monte Carlo method, we illustrate how our refined model can guide insurers in designing contracts that equitably balance the interests of both parties. This is particularly relevant in discouraging premature surrenders while adapting to the realistic fluctuations of financial markets. Lastly, a comparative statics analysis with varying interest rate parameters underscores the impact of interest rates on the cost of the optimal surrender strategy, emphasizing the importance of accurately modeling stochastic interest rates.

This paper presents a pilot study that explores the application of active learning, traditionally studied in the context of discriminative models, to generative models. We specifically focus on image synthesis personalization tasks. The primary challenge in conducting active learning on generative models lies in the open-ended nature of querying, which differs from the closed form of querying in discriminative models that typically target a single concept. We introduce the concept of anchor directions to transform the querying process into a semi-open problem. We propose a direction-based uncertainty sampling strategy to enable generative active learning and tackle the exploitation-exploration dilemma. Extensive experiments are conducted to validate the effectiveness of our approach, demonstrating that an open-source model can achieve superior performance compared to closed-source models developed by large companies, such as Google's StyleDrop. The source code is available at https://github.com/zhangxulu1996/GAL4Personalization.

This paper presents a pilot study aimed at introducing multi-agent debate into multimodal reasoning. The study addresses two key challenges: the trivialization of opinions resulting from excessive summarization and the diversion of focus caused by distractor concepts introduced from images. These challenges stem from the inductive (bottom-up) nature of existing debating schemes. To address the issue, we propose a deductive (top-down) debating approach called Blueprint Debate on Graphs (BDoG). In BDoG, debates are confined to a blueprint graph to prevent opinion trivialization through world-level summarization. Moreover, by storing evidence in branches within the graph, BDoG mitigates distractions caused by frequent but irrelevant concepts. Extensive experiments validate that BDoG is able to achieve state-of-the-art results in ScienceQA and MMBench with significant improvements over previous methods. The source code can be accessed at https://github.com/thecharm/BDoG., Comment: Accepted by ACM Multimedia 2024

Negative refractive index (NRI) of the mescopic dissipative left-handed transmission line (LHTL) is manipulated by the displaced squeezed Fock state (DSFS) and the dissipation presented by the resistance and conductance. Comparing to the classical LHTL, some specific quantum characteristics are shown in the LHTL because of quantum effect, which will be significant to its miniaturization application in microwave frequency., Comment: 5 pages, 4 figures

We prove that the Drinfeld center centralized by a symmetric fusion category is a symmetric monoidal functor if we choose proper domain and codomain categories. We also compute the factorization homology of stratified surfaces with coefficients satisfying certain anomaly-free conditions.

Left-handedness signifies negative permittivity ($\varepsilon_r$) and permeability ((\mu_r)) in the same frequency band. The $\varepsilon_r$ and $\mu_r$ are evaluated in a quantized composite right-left handed transmission line (CRLH-TL), and the frequency band for left-handedness is also valuated in the balanced resonance ($ L_r C_l = L_l C_r $) and unbalanced resonance($L_l C_r \neq L_r C_l$) cases in the displaced squeezed Fock state. The results show that the balanced resonance plays an important role in bandwidth and achieving for left-handedness. These displays some quantum mechanical behaviors and proposes a new potential approach to wider frequency band left-handedness for the quantized CRLH-TL., Comment: 10 pages, 3 figures

Tuning language models for dialogue generation has been a prevalent paradigm for building capable dialogue agents. Yet, traditional tuning narrowly views dialogue generation as resembling other language generation tasks, ignoring the role disparities between two speakers and the multi-round interactive process that dialogues ought to be. Such a manner often leads to unsatisfactory chat consistency for the built agent. In this work, we emphasize the interactive, communicative nature of dialogue and argue that it is more feasible to model the speaker roles of agent and user separately, enabling the agent to adhere to its role consistently. With this in mind, we propose an efficient Multi-round Interactive Dialogue Tuning (Midi-Tuning) framework. It models the agent and user individually with two adapters built upon large language models. The adapters make use of respective utterances round by round in alternating order and they are tuned via a round-level memory caching mechanism. Extensive experiments demonstrate that, our framework performs superior to traditional fine-tuning and harbors the tremendous potential for improving dialogue consistency., Comment: Accepted by ACL 2024

According to the Mermin Wagner theorem, two-dimensional material is difficult to have the Curie temperature above room temperature. By using the method of band engineering, we design a promising two-dimensional ferromagnetic semiconductor Cr2XP (X=P, As, Sb) with large magnetization, high Curie temperature and sizable band gap. The formation of gap is discussed in terms of the hybridizations, occupation and distribution of electronic states and charge transfer. Large magnetic moments about 6.16~6.37uB origin from the occupation of Cr-d electrons in crystal field.Competition and cooperation between d-d (Cr-d~Cr-d) and d-p-d (Cr-d~X-p~Cr-d) exchange interactions lead to the emergence of ferromagnetic ordering phase. Furthermore, Curie temperatures, approaching to 269 K, 332 K and 400 K for Cr2P2, Cr2AsP and Cr2SbP, are estimated by employing Monte Carlo simulation based on the Heisenberg model. Magnetic anisotropy energy of Cr2XP is determined by calculating the total energy dependence on the angle along different directions, and the origin is also discussed by the second-order perturbation theory. In addition, the Cr2XP possesses excellent thermodynamical, dynamical and mechanical stabilities, and can overcome their own gravity to keep their planar structure without the support of substrate. These above-mentioned advantages will offer some valuable hints for two-dimensional ferromagnetic semiconductor Cr2XP in spintronic devices.

Inversion methods, such as Textual Inversion, generate personalized images by incorporating concepts of interest provided by user images. However, existing methods often suffer from overfitting issues, where the dominant presence of inverted concepts leads to the absence of other desired concepts. It stems from the fact that during inversion, the irrelevant semantics in the user images are also encoded, forcing the inverted concepts to occupy locations far from the core distribution in the embedding space. To address this issue, we propose a method that guides the inversion process towards the core distribution for compositional embeddings. Additionally, we introduce a spatial regularization approach to balance the attention on the concepts being composed. Our method is designed as a post-training approach and can be seamlessly integrated with other inversion methods. Experimental results demonstrate the effectiveness of our proposed approach in mitigating the overfitting problem and generating more diverse and balanced compositions of concepts in the synthesized images. The source code is available at https://github.com/zhangxulu1996/Compositional-Inversion., Comment: This paper was accepted by AAAI 2024

The rise of online social networks has facilitated the evolution of social recommender systems, which incorporate social relations to enhance users' decision-making process. With the great success of Graph Neural Networks (GNNs) in learning node representations, GNN-based social recommendations have been widely studied to model user-item interactions and user-user social relations simultaneously. Despite their great successes, recent studies have shown that these advanced recommender systems are highly vulnerable to adversarial attacks, in which attackers can inject well-designed fake user profiles to disrupt recommendation performances. While most existing studies mainly focus on argeted attacks to promote target items on vanilla recommender systems, untargeted attacks to degrade the overall prediction performance are less explored on social recommendations under a black-box scenario. To perform untargeted attacks on social recommender systems, attackers can construct malicious social relationships for fake users to enhance the attack performance. However, the coordination of social relations and item profiles is challenging for attacking black-box social recommendations. To address this limitation, we first conduct several preliminary studies to demonstrate the effectiveness of cross-community connections and cold-start items in degrading recommendations performance. Specifically, we propose a novel framework MultiAttack based on multi-agent reinforcement learning to coordinate the generation of cold-start item profiles and cross-community social relations for conducting untargeted attacks on black-box social recommendations. Comprehensive experiments on various real-world datasets demonstrate the effectiveness of our proposed attacking framework under the black-box setting., Comment: Accepted by ACM TOIS

The evolution of entanglement in a non-Hermitian quantum system may behave differently compared to its Hermitian counterpart. In this paper, we investigate the entanglement dynamics of two coupled and driven non-Hermitian qubits. Through calculating the concurrence of the system, we find that the evolution of the bipartite entanglement manifests two distinct patterns in the parameter space. In the low non-Hermiticity regime, the concurrence oscillates significantly, while in the opposite regime the same quantity would trend to a stable value. We attribute this phenomenon to parity-time ($ \mathcal{PT}$) symmetry phase transition. In addition, we have also studied the effect of decoherence on the entanglement dynamics. Our research provides a method to stabilize entanglement by exploiting non-Hermiticity., Comment: 6 pages, 5 figures

Molecule discovery plays a crucial role in various scientific fields, advancing the design of tailored materials and drugs. However, most of the existing methods heavily rely on domain experts, require excessive computational cost, or suffer from sub-optimal performance. On the other hand, Large Language Models (LLMs), like ChatGPT, have shown remarkable performance in various cross-modal tasks due to their powerful capabilities in natural language understanding, generalization, and in-context learning (ICL), which provides unprecedented opportunities to advance molecule discovery. Despite several previous works trying to apply LLMs in this task, the lack of domain-specific corpus and difficulties in training specialized LLMs still remain challenges. In this work, we propose a novel LLM-based framework (MolReGPT) for molecule-caption translation, where an In-Context Few-Shot Molecule Learning paradigm is introduced to empower molecule discovery with LLMs like ChatGPT to perform their in-context learning capability without domain-specific pre-training and fine-tuning. MolReGPT leverages the principle of molecular similarity to retrieve similar molecules and their text descriptions from a local database to enable LLMs to learn the task knowledge from context examples. We evaluate the effectiveness of MolReGPT on molecule-caption translation, including molecule understanding and text-based molecule generation. Experimental results show that compared to fine-tuned models, MolReGPT outperforms MolT5-base and is comparable to MolT5-large without additional training. To the best of our knowledge, MolReGPT is the first work to leverage LLMs via in-context learning in molecule-caption translation for advancing molecule discovery. Our work expands the scope of LLM applications, as well as providing a new paradigm for molecule discovery and design., Comment: Accepted by IEEE TKDE. Our implementation is available at: https://github.com/phenixace/MolReGPT