Search

Reasoning is a central capability of human intelligence. In recent years, with the advent of large-scale datasets, pretrained large language models have emerged with new capabilities, including reasoning. However, these models still struggle with long-term, complex reasoning tasks, such as playing chess. Based on the observation that expert chess players employ a dual approach combining long-term strategic play with short-term tactical play along with language explanation, we propose improving the reasoning capability of large language models in chess by integrating annotated strategy and tactic. Specifically, we collect a dataset named MATE, which consists of 1 million chess positions with candidate moves annotated by chess experts for strategy and tactics. We finetune the LLaMA-3-8B model and compare it against state-of-the-art commercial language models in the task of selecting better chess moves. Our experiments show that our models perform better than GPT, Claude, and Gemini models. We find that language explanations can enhance the reasoning capability of large language models., Comment: submitted to NAACL2025

With the scale of vision Transformer-based models continuing to grow, finetuning these large-scale pretrained models for new tasks has become increasingly parameter-intensive. Visual prompt tuning is introduced as a parameter-efficient finetuning (PEFT) method to this trend. Despite its successes, a notable research challenge persists within almost all PEFT approaches: significant performance degradation is observed when there is a substantial disparity between the datasets applied in pretraining and finetuning phases. To address this challenge, we draw inspiration from human visual cognition, and propose the Visual Fourier Prompt Tuning (VFPT) method as a general and effective solution for adapting large-scale transformer-based models. Our approach innovatively incorporates the Fast Fourier Transform into prompt embeddings and harmoniously considers both spatial and frequency domain information. Apart from its inherent simplicity and intuitiveness, VFPT exhibits superior performance across all datasets, offering a general solution to dataset challenges, irrespective of data disparities. Empirical results demonstrate that our approach outperforms current state-of-the-art baselines on two benchmarks, with low parameter usage (e.g., 0.57% of model parameters on VTAB-1k) and notable performance enhancements (e.g., 73.20% of mean accuracy on VTAB-1k). Our code is avaliable at https://github.com/runtsang/VFPT., Comment: Conference on Neural Information Processing Systems (NeurIPS) 2024

In this work, we introduce an advanced acoustic leaky-wave antenna employing zero-refractive-index metamaterials (ZIMs) that significantly surpasses traditional designs in terms of radiation ef-ficiency and directivity. Our design features a novel space-coiling structure, which manipulates the Dirac-like dispersion based on accidental degeneracy to achieve double-zero-index metamaterials (DZIM). The newly developed acoustic Dirac leaky-wave antenna (ADLWA) achieves more than double the radiation efficiency of conventional antennas based on arrays with side holes and mem-branes. It exhibits superior directional control, allowing for precise beam scanning by adjusting the frequency. Additionally, the ADLWA functions effectively as a passive sonar system, capable of de-tecting the direction of moving sound sources. This breakthrough enhances acoustic wave control and promises significant advancements in sensing and communication technologies., Comment: 11 pages, 6 figures

Here we investigate the internal sublattice symmetry, and thus the enriched topological classification of bosonic Bogoliubov excitations of thermodynamically stable free-boson systems with non-vanishing particle-number-nonconserving terms. Specifically, we show that such systems well described by the bosonic Bogoliubov-de Gennes Hamiltonian can be in general reduced to particle-number-conserving (single-particle) ones. Building upon this observation, the sublattice symmetry is uncovered with respect to an excitation energy, which is usually hidden in the bosonic Bogoliubov-de Gennes Hamiltonian. Thus, we obtain an additional topological class, i.e., class AIII, which enriches the framework for the topological threefold way of free-boson systems. Moreover, a construction is proposed to show a category of systems respecting such a symmetry. For illustration, we resort to a one-dimensional (1D) prototypical model to demonstrate the topological excitation characterized by a winding number or symplectic polarization. By introducing the correlation function, we present an approach to measure the topological invariant. In addition, the edge excitation together with its robustness to symmetry-preserving disorders is also discussed., Comment: 18 pages, 4 figures

Advancements in reinforcement learning have led to the development of sophisticated models capable of learning complex decision-making tasks. However, efficiently integrating world models with decision transformers remains a challenge. In this paper, we introduce a novel approach that combines the Dreamer algorithm's ability to generate anticipatory trajectories with the adaptive learning strengths of the Online Decision Transformer. Our methodology enables parallel training where Dreamer-produced trajectories enhance the contextual decision-making of the transformer, creating a bidirectional enhancement loop. We empirically demonstrate the efficacy of our approach on a suite of challenging benchmarks, achieving notable improvements in sample efficiency and reward maximization over existing methods. Our results indicate that the proposed integrated framework not only accelerates learning but also showcases robustness in diverse and dynamic scenarios, marking a significant step forward in model-based reinforcement learning.

Energy band theory is a fundamental cornerstone of condensed matter physics. According to conventional wisdom, discrete translational symmetry is mandatory for defining energy bands. Here, we illustrate that, in fact, the concept of energy band can be generalized to incommensurate systems lacking such symmetry, thus transcending the traditional paradigm of energy band. The validity of our theory is verified by extensive numerical calculations in the celebrated Aubry-Andr\'e-Harper model and a two-dimensional incommensurate model of graphene. Building upon the proposed concept of incommensurate energy bands, we further develop a theory of angle-resolved photoemission spectroscopy (ARPES) for incommensurate systems, providing a clear physical picture for the incommensurate ARPES spectra. Our work establishes a comprehensive energy band theory for incommensurate systems., Comment: 8 pages, 3 figures

The cosmic distance duality relation (DDR), which links the angular diameter distance and the luminosity distance, is a cornerstone in modern cosmology. Any deviation from DDR may indicate new physics beyond the standard cosmological model. In this paper, we use four high-precision time-delayed strong gravitational lensing (SGL) systems provided by the H0LiCOW to test the validity of DDR. To this end, we directly compare the angular diameter distances from these SGL systems and the luminosity distances from the latest Pantheon+ compilation of SNe Ia. In order to reduce the statistical errors arising from redshift matching, the Gaussian process method is applied to reconstruct the distance-redshift relation from the Pantheon+ dataset. We parameterize the possible violation of DDR in three different models. It is found that all results confirm the validity of DDR at 1$\sigma$ confidence level. Additionally, Monte Carlo simulations based on the future LSST survey indicate that the precision of DDR could reach $10^{-2}$ level with 100 SGL systems., Comment: 11 pages, 6 figures

Gene expression is a cellular process that plays a fundamental role in human phenotypical variations and diseases. Despite advances of deep learning models for gene expression prediction, recent benchmarks have revealed their inability to learn distal regulatory grammar. Here, we address this challenge by leveraging a pretrained large language model to enhance gene expression prediction. We introduce Genetic sequence Token Alignment (GTA), which aligns genetic sequence features with natural language tokens, allowing for symbolic reasoning of genomic sequence features via the frozen language model. This cross-modal adaptation learns the regulatory grammar and allows us to further incorporate gene-specific human annotations as prompts, enabling in-context learning that is not possible with existing models. Trained on lymphoblastoid cells, GTA was evaluated on cells from the Geuvadis consortium and outperforms state-of-the-art models such as Enformer, achieving a Spearman correlation of 0.65, a 10\% improvement. Additionally, GTA offers improved interpretation of long-range interactions through the identification of the most meaningful sections of the input genetic context. GTA represents a powerful and novel cross-modal approach to gene expression prediction by utilizing a pretrained language model, in a paradigm shift from conventional gene expression models trained only on sequence data., Comment: 14 pages, 10 figures

We propose two distinct crosscap states for the two-dimensional (2D) Ising field theory. These two crosscap states, identifying Ising spins or dual spins (domain walls) at antipodal points, are shown to be related via the Kramers-Wannier duality transformation. We derive their Majorana free field representations and extend bosonization techniques to calculate correlation functions of the 2D Ising conformal field theory (CFT) with different crosscap boundaries. We further develop a conformal perturbation theory to calculate the Klein bottle entropy as a universal scaling function [Phys. Rev. Lett. 130, 151602 (2023)] in the 2D Ising field theory. The formalism developed in this work is applicable to many other 2D CFTs perturbed by relevant operators., Comment: 6+30 pages, 1+2 figures

Recent studies demonstrate that diffusion models can serve as a strong prior for solving inverse problems. A prominent example is Diffusion Posterior Sampling (DPS), which approximates the posterior distribution of data given the measure using Tweedie's formula. Despite the merits of being versatile in solving various inverse problems without re-training, the performance of DPS is hindered by the fact that this posterior approximation can be inaccurate especially for high noise levels. Therefore, we propose \textbf{D}iffusion \textbf{P}osterior \textbf{MC}MC (\textbf{DPMC}), a novel inference algorithm based on Annealed MCMC to solve inverse problems with pretrained diffusion models. We define a series of intermediate distributions inspired by the approximated conditional distributions used by DPS. Through annealed MCMC sampling, we encourage the samples to follow each intermediate distribution more closely before moving to the next distribution at a lower noise level, and therefore reduce the accumulated error along the path. We test our algorithm in various inverse problems, including super resolution, Gaussian deblurring, motion deblurring, inpainting, and phase retrieval. Our algorithm outperforms DPS with less number of evaluations across nearly all tasks, and is competitive among existing approaches.

This paper introduces a novel family of deep dynamical models designed to represent continuous-time sequence data. This family of models generates each data point in the time series by a neural emission model, which is a non-linear transformation of a latent state vector. The trajectory of the latent states is implicitly described by a neural ordinary differential equation (ODE), with the initial state following an informative prior distribution parameterized by an energy-based model. Furthermore, we can extend this model to disentangle dynamic states from underlying static factors of variation, represented as time-invariant variables in the latent space. We train the model using maximum likelihood estimation with Markov chain Monte Carlo (MCMC) in an end-to-end manner, without requiring additional assisting components such as an inference network. Our experiments on oscillating systems, videos and real-world state sequences (MuJoCo) illustrate that ODEs with the learnable energy-based prior outperform existing counterparts, and can generalize to new dynamic parameterization, enabling long-horizon predictions.

Fractional quantum Hall states have been observed at filling factor $\nu=3/4$ in three platforms. General theoretical analysis of topological orders at $\nu=3/4$ revealed that four types of non-Abelian states with Ising anyons have ground state degeneracy $12$ on the torus. The properties of $\nu=3/4$ states can be analyzed using two complementary approaches. In the first one, they are treated as particle-hole conjugate of $\nu=1/4$ Moore-Read types states. In the second one, they are mapped to composite fermions with reverse flux attachment at effective filling factor $3/2$, whose integral part realizes an integer quantum Hall state and the fractional part realizes $\nu=1/2$ Moore-Read type states. For the specific case of bilayer graphene, numerical calculations demonstrate that strong Landau level mixing could generate a gapped state at $\nu=3/4$ with 12 fold ground state degeneracy on the torus. Its chiral graviton spectral functions has one low energy peak with negative chirality and one high energy peak with positive chirality. This points to a specific member of the Moore-Read type states and agrees with the deduction based on daughter states., Comment: 6 pages, 2 figures

Achieving human-level intelligence requires refining cognitive distinctions between System 1 and System 2 thinking. While contemporary AI, driven by large language models, demonstrates human-like traits, it falls short of genuine cognition. Transitioning from structured benchmarks to real-world scenarios presents challenges for visual agents, often leading to inaccurate and overly confident responses. To address the challenge, we introduce FaST, which incorporates the Fast and Slow Thinking mechanism into visual agents. FaST employs a switch adapter to dynamically select between System 1/2 modes, tailoring the problem-solving approach to different task complexity. It tackles uncertain and unseen objects by adjusting model confidence and integrating new contextual data. With this novel design, we advocate a flexible system, hierarchical reasoning capabilities, and a transparent decision-making pipeline, all of which contribute to its ability to emulate human-like cognitive processes in visual intelligence. Empirical results demonstrate that FaST outperforms various well-known baselines, achieving 80.8% accuracy over VQA^{v2} for visual question answering and 48.7% GIoU score over ReasonSeg for reasoning segmentation, demonstrate FaST's superior performance. Extensive testing validates the efficacy and robustness of FaST's core components, showcasing its potential to advance the development of cognitive visual agents in AI systems. The code is available at ttps://github.com/GuangyanS/Sys2-LLaVA.

The rapid development of AI highlights the pressing need for sustainable energy, a critical global challenge for decades. Nuclear fusion, generally seen as an ultimate solution, has been the focus of intensive research for nearly a century, with investments reaching hundreds of billions of dollars. Recent advancements in Inertial Confinement Fusion have drawn significant attention to fusion research, in which Laser-Plasma Interaction (LPI) is critical for ensuring fusion stability and efficiency. However, the complexity of LPI upon fusion ignition makes analytical approaches impractical, leaving researchers depending on extremely computation-demanding Particle-in-Cell (PIC) simulations to generate data, presenting a significant bottleneck to advancing fusion research. In response, this work introduces Diff-PIC, a novel framework that leverages conditional diffusion models as a computationally efficient alternative to PIC simulations for generating high-fidelity scientific LPI data. In this work, physical patterns captured by PIC simulations are distilled into diffusion models associated with two tailored enhancements: (1) To effectively capture the complex relationships between physical parameters and corresponding outcomes, the parameters are encoded in a physically-informed manner. (2) To further enhance efficiency while maintaining high fidelity and physical validity, the rectified flow technique is employed to transform our model into a one-step conditional diffusion model. Experimental results show that Diff-PIC achieves 16,200$\times$ speedup compared to traditional PIC on a 100 picosecond simulation, with an average reduction in MAE / RMSE / FID of 59.21% / 57.15% / 39.46% with respect to two other SOTA data generation approaches.

Fermionic Gaussian states are eigenstates of quadratic Hamiltonians and widely used in quantum many-body problems. We propose a highly efficient algorithm that converts fermionic Gaussian states to matrix product states. It can be formulated for finite-size systems without translation invariance, but becomes particularly appealing when applied to infinite systems with translation invariance. If the ground states of a topologically ordered system on infinite cylinders are expressed as matrix product states, then the fixed points of the transfer matrix can be harnessed to filter out the anyon eigenbasis, also known as minimally entangled states. This allows for efficient computation of universal properties such as entanglement spectrum and modular matrices. The potential of our method is demonstrated by numerical calculations in two chiral spin liquids that have the same topological orders as the bosonic Laughlin and Moore-Read states, respectively. The anyon eigenbasis for the first one has been worked out before and serves as a useful benchmark. The anyon eigenbasis of the second one is, however, not transparent and its successful construction provides a nontrivial corroboration of our method., Comment: 13 pages, 7 figures

Controlled fusion energy is deemed pivotal for the advancement of human civilization. In this study, we introduce $\textbf{LPI-LLM}$, a novel integration of Large Language Models (LLMs) with classical reservoir computing paradigms tailored to address a critical challenge, Laser-Plasma Instabilities ($\texttt{LPI}$), in Inertial Confinement Fusion ($\texttt{ICF}$). Our approach offers several key contributions: Firstly, we propose the $\textit{LLM-anchored Reservoir}$, augmented with a $\textit{Fusion-specific Prompt}$, enabling accurate forecasting of $\texttt{LPI}$-generated-hot electron dynamics during implosion. Secondly, we develop $\textit{Signal-Digesting Channels}$ to temporally and spatially describe the driver laser intensity across time, capturing the unique characteristics of $\texttt{ICF}$ inputs. Lastly, we design the $\textit{Confidence Scanner}$ to quantify the confidence level in forecasting, providing valuable insights for domain experts to design the $\texttt{ICF}$ process. Extensive experiments demonstrate the superior performance of our method, achieving 1.90 CAE, 0.14 $\texttt{top-1}$ MAE, and 0.11 $\texttt{top-5}$ MAE in predicting Hard X-ray ($\texttt{HXR}$) energies emitted by the hot electrons in $\texttt{ICF}$ implosions, which presents state-of-the-art comparisons against concurrent best systems. Additionally, we present $\textbf{LPI4AI}$, the first $\texttt{LPI}$ benchmark based on physical experiments, aimed at fostering novel ideas in $\texttt{LPI}$ research and enhancing the utility of LLMs in scientific exploration. Overall, our work strives to forge an innovative synergy between AI and $\texttt{ICF}$ for advancing fusion energy.

The use of trajectory data with abundant spatial-temporal information is pivotal in Intelligent Transport Systems (ITS) and various traffic system tasks. Location-Based Services (LBS) capitalize on this trajectory data to offer users personalized services tailored to their location information. However, this trajectory data contains sensitive information about users' movement patterns and habits, necessitating confidentiality and protection from unknown collectors. To address this challenge, privacy-preserving methods like K-anonymity and Differential Privacy have been proposed to safeguard private information in the dataset. Despite their effectiveness, these methods can impact the original features by introducing perturbations or generating unrealistic trajectory data, leading to suboptimal performance in downstream tasks. To overcome these limitations, we propose a Federated Variational AutoEncoder (FedVAE) approach, which effectively generates a new trajectory dataset while preserving the confidentiality of private information and retaining the structure of the original features. In addition, FedVAE leverages Variational AutoEncoder (VAE) to maintain the original feature space and generate new trajectory data, and incorporates Federated Learning (FL) during the training stage, ensuring that users' data remains locally stored to protect their personal information. The results demonstrate its superior performance compared to other existing methods, affirming FedVAE as a promising solution for enhancing data privacy and utility in location-based applications., Comment: 2023 IEEE 98th Vehicular Technology Conference

Genuine multipartite entanglement (GME) is not only fundamental interesting for the study of quantum-to-classical transition, but also is essential for realizing universal quantum computing and quantum networks. Here we investigate the multipartite entanglement (ME) dynamics in a linear chain of N LC resonators interacting optomechanically with a common thermal acoustic reservoir. By presenting the exact analytical solutions of system evolution, we predict the periodic generation of non-Gaussian ME, including the discrete and continuous variables entanglement. Interestingly, the GME is obtained even though the system is in a heat bath. The mechanism relies on the special acoustic environment featuring frequency comb structure. More importantly, our proposed model also allows the periodic generation of entangled multipartite cat states (MCSs), i.e., a typical GHZ state, with high fidelity. This work fundamentally broadens the fields of ME, and have wide applications in implementing thermal-noise-resistant quantum information processing and many-body quantum simulation., Comment: 25 pages, 9 figures

The realization of correlated multi-photon processes usually depends on the interaction between nonlinear media and atoms. However, the nonlinearity of optical materials is generally weak, making it still very challenging to achieve correlated multi-photon dynamics at the few-photon level. Meanwhile, giant atoms, with their capability for multi-point coupling, which is a novel paradigm in quantum optics, mostly focus on the single photon field. In this work, using the method described in Phys. Rev. Res. 6. 013279 (2024), we reveal that the ladder-type three-level giant atom spontaneously emits strongly correlated photon pairs with high efficiency by designing and optimizing the target function. In addition, by encoding local phases into the optimal coupling sequence, directional two-photon correlated transfer can be achieved. This method does not require a nonlinear waveguide and can be realized in the conventional environment. We show that the photon pairs emitted in both the bidirectional and the chiral case exhibit strong correlation properties in both time and space. Such correlated photon pairs have great potential applications for quantum information processing. For example, numerical results show that our proposal can realize the two-photon mediated cascaded quantum system., Comment: 12 pages; 10 figures

Realizing precise control over multiquanta emission is crucial for quantum information processing, especially when integrated with advanced techniques of manipulating quantum states. Here, by spinning the resonator to induce the Sagnac effect, we can obtain nonreciprocal photon-phonon and photon-magnon super-Rabi oscillations under conditions of optically driving resonance transitions. Opening dissipative channels for such super-Rabi oscillations enables the realization of directional bundle emissions of entangled photon-phonon pairs and photon-magnon pairs by transferring pure multiquanta state to bundled multiquanta outside of the system. This nonreciprocal emission is a flexible switch that can be controlled with precision, and simultaneous emissions of different entangled pairs (such as photon-phonon or photon-magnon pairs) can even emerge but in opposite directions by driving the resonator from different directions. This ability to flexibly manipulate the system allows us to achieve directional entangled multiquanta emitters, and has also potential applications for building hybrid quantum networks and on-chip quantum communications., Comment: 16 pages, 4 figures, accepted by Physical Review Letters

Learning abstract state representations and knowledge is crucial for long-horizon robot planning. We present InterPreT, an LLM-powered framework for robots to learn symbolic predicates from language feedback of human non-experts during embodied interaction. The learned predicates provide relational abstractions of the environment state, facilitating the learning of symbolic operators that capture action preconditions and effects. By compiling the learned predicates and operators into a PDDL domain on-the-fly, InterPreT allows effective planning toward arbitrary in-domain goals using a PDDL planner. In both simulated and real-world robot manipulation domains, we demonstrate that InterPreT reliably uncovers the key predicates and operators governing the environment dynamics. Although learned from simple training tasks, these predicates and operators exhibit strong generalization to novel tasks with significantly higher complexity. In the most challenging generalization setting, InterPreT attains success rates of 73% in simulation and 40% in the real world, substantially outperforming baseline methods., Comment: RSS 2024; https://interpret-robot.github.io

Generative models based on flow matching have attracted significant attention for their simplicity and superior performance in high-resolution image synthesis. By leveraging the instantaneous change-of-variables formula, one can directly compute image likelihoods from a learned flow, making them enticing candidates as priors for downstream tasks such as inverse problems. In particular, a natural approach would be to incorporate such image probabilities in a maximum-a-posteriori (MAP) estimation problem. A major obstacle, however, lies in the slow computation of the log-likelihood, as it requires backpropagating through an ODE solver, which can be prohibitively slow for high-dimensional problems. In this work, we propose an iterative algorithm to approximate the MAP estimator efficiently to solve a variety of linear inverse problems. Our algorithm is mathematically justified by the observation that the MAP objective can be approximated by a sum of $N$ ``local MAP'' objectives, where $N$ is the number of function evaluations. By leveraging Tweedie's formula, we show that we can perform gradient steps to sequentially optimize these objectives. We validate our approach for various linear inverse problems, such as super-resolution, deblurring, inpainting, and compressed sensing, and demonstrate that we can outperform other methods based on flow matching. Code is available at https://github.com/YasminZhang/ICTM., Comment: Accepted to NeurIPS 2024

Existing diffusion-based text-to-3D generation methods primarily focus on producing visually realistic shapes and appearances, often neglecting the physical constraints necessary for downstream tasks. Generated models frequently fail to maintain balance when placed in physics-based simulations or 3D printed. This balance is crucial for satisfying user design intentions in interactive gaming, embodied AI, and robotics, where stable models are needed for reliable interaction. Additionally, stable models ensure that 3D-printed objects, such as figurines for home decoration, can stand on their own without requiring additional supports. To fill this gap, we introduce Atlas3D, an automatic and easy-to-implement method that enhances existing Score Distillation Sampling (SDS)-based text-to-3D tools. Atlas3D ensures the generation of self-supporting 3D models that adhere to physical laws of stability under gravity, contact, and friction. Our approach combines a novel differentiable simulation-based loss function with physically inspired regularization, serving as either a refinement or a post-processing module for existing frameworks. We verify Atlas3D's efficacy through extensive generation tasks and validate the resulting 3D models in both simulated and real-world environments.

This paper investigates the conformal isometry hypothesis as a potential explanation for hexagonal periodic patterns in grid cell response maps. The hypothesis posits that grid cell activity forms a high-dimensional vector in neural space, encoding the agent's position in 2D physical space. As the agent moves, this vector rotates within a 2D manifold in the neural space, driven by a recurrent neural network. The conformal hypothesis suggests that this neural manifold is a conformally isometric embedding of physical space, where local displacements in neural space are proportional to those in physical space. In this paper, we conduct numerical experiments to show that this hypothesis leads to the hexagon periodic patterns of grid cells, agnostic to the choice of transformation models. Furthermore, we present a theoretical understanding that hexagon patterns emerge by minimizing our loss function because hexagon flat torus exhibits minimal deviation from local conformal isometry. In addition, we propose a conformal modulation of the agent's input velocity, enabling the recurrent neural network of grid cells to satisfy the conformal isometry hypothesis automatically., Comment: arXiv admin note: text overlap with arXiv:2310.19192

While diffusion models can learn complex distributions, sampling requires a computationally expensive iterative process. Existing distillation methods enable efficient sampling, but have notable limitations, such as performance degradation with very few sampling steps, reliance on training data access, or mode-seeking optimization that may fail to capture the full distribution. We propose EM Distillation (EMD), a maximum likelihood-based approach that distills a diffusion model to a one-step generator model with minimal loss of perceptual quality. Our approach is derived through the lens of Expectation-Maximization (EM), where the generator parameters are updated using samples from the joint distribution of the diffusion teacher prior and inferred generator latents. We develop a reparametrized sampling scheme and a noise cancellation technique that together stabilizes the distillation process. We further reveal an interesting connection of our method with existing methods that minimize mode-seeking KL. EMD outperforms existing one-step generative methods in terms of FID scores on ImageNet-64 and ImageNet-128, and compares favorably with prior work on distilling text-to-image diffusion models.

Offline Black-Box Optimization (BBO) aims at optimizing a black-box function using the knowledge from a pre-collected offline dataset of function values and corresponding input designs. However, the high-dimensional and highly-multimodal input design space of black-box function pose inherent challenges for most existing methods that model and operate directly upon input designs. These issues include but are not limited to high sample complexity, which relates to inaccurate approximation of black-box function; and insufficient coverage and exploration of input design modes, which leads to suboptimal proposal of new input designs. In this work, we consider finding a latent space that serves as a compressed yet accurate representation of the design-value joint space, enabling effective latent exploration of high-value input design modes. To this end, we formulate an learnable energy-based latent space, and propose Noise-intensified Telescoping density-Ratio Estimation (NTRE) scheme for variational learning of an accurate latent space model without costly Markov Chain Monte Carlo. The optimization process is then exploration of high-value designs guided by the learned energy-based model in the latent space, formulated as gradient-based sampling from a latent-variable-parameterized inverse model. We show that our particular parameterization encourages expanded exploration around high-value design modes, motivated by inversion thinking of a fundamental result of conditional covariance matrix typically used for variance reduction. We observe that our method, backed by an accurately learned informative latent space and an expanding-exploration model design, yields significant improvements over strong previous methods on both synthetic and real world datasets such as the design-bench suite.

We theoretically predict a kind of power-law-exponential (PLE) dipole-dipole interaction between quantum emitters in a 1D waveguide QED system. This unconventional long-range interaction is the combination of power-law growth and exponential decay couplings. Applying PLE interaction to a spin model, we uncover the rich many-body phases. Most remarkably, we find that PLE interaction can induce the ordered and critical spiral phases. These spiral phases emerge from the strong frustration generated by the power-law factor of PLE interaction, hence they are absent for other types of long-range interaction, e.g., pure exponential and power-law decay interactions. Our work is also applicable for the higher dimensional systems. It fundamentally broadens the realm of many-body physics and has the significant applications in quantum simulation of strong correlated matters., Comment: 16 pages, 12 figures

Feature extraction is a critical technology to realize the automatic transmission of feature information throughout product life cycles. As CAD models primarily capture the 3D geometry of products, feature extraction heavily relies on geometric information. However, existing feature extraction methods often yield inaccurate outcomes due to the diverse interpretations of geometric information. This report presents a set-based feature extraction approach to address this uncertainty issue. Unlike existing methods that seek accurate feature results, our approach aims to transform the uncertainty of geometric information into a set of feature subgraphs. First, we define the convexity of basic geometric entities and introduce the concept of two-level attributed adjacency graphs. Second, a feature extraction workflow is designed to determine feature boundaries and identify feature subgraphs from CAD models. This set of feature subgraphs can be used for further feature recognition. A feature extraction system is programmed using C++ and UG/Open to demonstrate the feasibility of our proposed approach., Comment: 13 pages

In this paper, we introduce a simple yet effective tabular data watermarking mechanism with statistical guarantees. We show theoretically that the proposed watermark can be effectively detected, while faithfully preserving the data fidelity, and also demonstrates appealing robustness against additive noise attack. The general idea is to achieve the watermarking through a strategic embedding based on simple data binning. Specifically, it divides the feature's value range into finely segmented intervals and embeds watermarks into selected ``green list" intervals. To detect the watermarks, we develop a principled statistical hypothesis-testing framework with minimal assumptions: it remains valid as long as the underlying data distribution has a continuous density function. The watermarking efficacy is demonstrated through rigorous theoretical analysis and empirical validation, highlighting its utility in enhancing the security of synthetic and real-world datasets.

The proliferation and refinement of affordable virtual reality (VR) technologies and wearable sensors have opened new frontiers in cognitive and behavioral neuroscience. This chapter offers a broad overview of VR for anyone interested in leveraging it as a research tool. In the first section, it examines the fundamental functionalities of VR and outlines important considerations that inform the development of immersive content that stimulates the senses. In the second section, the focus of the discussion shifts to the implementation of VR in the context of the neuroscience lab. Practical advice is offered on adapting commercial, off-theshelf devices to specific research purposes. Further, methods are explored for recording, synchronizing, and fusing heterogeneous forms of data obtained through the VR system or add-on sensors, as well as for labeling events and capturing game play.

Objective: To investigate the effects of different approaches to EEG preprocessing, channel montage selection, and model architecture on the performance of an online-capable stress detection algorithm in a classroom scenario. Methods: This analysis used EEG data from a longitudinal stress and fatigue study conducted among university students. Their self-reported stress ratings during each class session were the basis for classifying EEG recordings into either normal or elevated stress states. We used a data-processing pipeline that combined Artifact Subspace Reconstruction (ASR)and an Independent Component Analysis (ICA)-based method to achieve online artifact removal. We compared the performance of a Linear Discriminant Analysis (LDA) and a 4-layer neural network as classifiers. We opted for accuracy, balanced accuracy, and F1 score as the metrics for assessing performance. We examined the impact of varying numbers of input channels using different channel montages. Additionally, we explored different window lengths and step sizes during online evaluation. Results: Our online artifact removal method achieved performance comparable to the offline ICA method in both offline and online evaluations. A balanced accuracy of 77% and 78% in an imbalanced binary classification were observed when using the 11-frontal-channel LDA model with the proposed artifact removal method. Moreover, the model performance remained intact when changing the channel montage from 30 full-scalp channels to just 11 frontal channels. During the online evaluation, we achieved the highest balanced accuracy (78%) with a window length of 20 seconds and a step size of 1 second. Significance: This study comprehensively investigates the deployment of stress detection in real-world scenarios. The findings of this study provide insight into the development of daily mental stress monitoring.

Fragile topology, akin to twisted bilayer graphene and the exotic phases therein, is a notable topological class with intriguing properties. However, due to its unique nature and the lack of bulk-edge correspondence, the experimental signature of fragile topology has been under debated since its birth. Here, we demonstrate experimentally that fragile topological phases with filling anomaly can be probed via screw dislocations, despite that they do not support gapless edge states. Using a designer hexagonal phononic crystal with a fragile topological band gap, we find that 1D gapless bound modes can emerge at a screw dislocation due to the bulk fragile topology. We then establish a connection between our system and the twisted boundary condition via the gauge invariance principle and illustrate that such an emergent phenomenon is an intrinsic property of fragile topological phases with filling anomaly. We observe experimentally the 1D topological bound states using the pump-probe measurements of their dispersion and wavefunctions, which unveils a novel bulk-defect correspondence of fragile topology and a powerful tool for probing fragile topological phases and materials., Comment: Submitted to Science Bulletin

We present an approach to designing 3D Iterated Function Systems (IFS) within the Unity Editor and rendered to VR in real-time. Objects are modeled as a hierarchical tree of primitive shapes and operators, editable using a graphical user interface allowing artists to develop psychedelic scenes with little to no coding knowledge, and is easily extensible for more advanced users to add their own primitive shapes and operators., Comment: 4 pages, 5 figures. Submitted to IEEE VIS 2024

Text-to-image diffusion models have shown great success in generating high-quality text-guided images. Yet, these models may still fail to semantically align generated images with the provided text prompts, leading to problems like incorrect attribute binding and/or catastrophic object neglect. Given the pervasive object-oriented structure underlying text prompts, we introduce a novel object-conditioned Energy-Based Attention Map Alignment (EBAMA) method to address the aforementioned problems. We show that an object-centric attribute binding loss naturally emerges by approximately maximizing the log-likelihood of a $z$-parameterized energy-based model with the help of the negative sampling technique. We further propose an object-centric intensity regularizer to prevent excessive shifts of objects attention towards their attributes. Extensive qualitative and quantitative experiments, including human evaluation, on several challenging benchmarks demonstrate the superior performance of our method over previous strong counterparts. With better aligned attention maps, our approach shows great promise in further enhancing the text-controlled image editing ability of diffusion models., Comment: Accepted to ECCV 2024

Autonomous vehicle (AV) systems rely on robust perception models as a cornerstone of safety assurance. However, objects encountered on the road exhibit a long-tailed distribution, with rare or unseen categories posing challenges to a deployed perception model. This necessitates an expensive process of continuously curating and annotating data with significant human effort. We propose to leverage recent advances in vision-language and large language models to design an Automatic Data Engine (AIDE) that automatically identifies issues, efficiently curates data, improves the model through auto-labeling, and verifies the model through generation of diverse scenarios. This process operates iteratively, allowing for continuous self-improvement of the model. We further establish a benchmark for open-world detection on AV datasets to comprehensively evaluate various learning paradigms, demonstrating our method's superior performance at a reduced cost., Comment: Accepted by CVPR-2024

Conventional Task and Motion Planning (TAMP) approaches rely on manually crafted interfaces connecting symbolic task planning with continuous motion generation. These domain-specific and labor-intensive modules are limited in addressing emerging tasks in real-world settings. Here, we present LLM^3, a novel Large Language Model (LLM)-based TAMP framework featuring a domain-independent interface. Specifically, we leverage the powerful reasoning and planning capabilities of pre-trained LLMs to propose symbolic action sequences and select continuous action parameters for motion planning. Crucially, LLM^3 incorporates motion planning feedback through prompting, allowing the LLM to iteratively refine its proposals by reasoning about motion failure. Consequently, LLM^3 interfaces between task planning and motion planning, alleviating the intricate design process of handling domain-specific messages between them. Through a series of simulations in a box-packing domain, we quantitatively demonstrate the effectiveness of LLM^3 in solving TAMP problems and the efficiency in selecting action parameters. Ablation studies underscore the significant contribution of motion failure reasoning to the success of LLM^3. Furthermore, we conduct qualitative experiments on a physical manipulator, demonstrating the practical applicability of our approach in real-world settings., Comment: IROS 2024. Codes available: https://github.com/AssassinWS/LLM-TAMP

Real-world datasets commonly exhibit noisy labels and class imbalance, such as long-tailed distributions. While previous research addresses this issue by differentiating noisy and clean samples, reliance on information from predictions based on noisy long-tailed data introduces potential errors. To overcome the limitations of prior works, we introduce an effective two-stage approach by combining soft-label refurbishing with multi-expert ensemble learning. In the first stage of robust soft label refurbishing, we acquire unbiased features through contrastive learning, making preliminary predictions using a classifier trained with a carefully designed BAlanced Noise-tolerant Cross-entropy (BANC) loss. In the second stage, our label refurbishment method is applied to obtain soft labels for multi-expert ensemble learning, providing a principled solution to the long-tail noisy label problem. Experiments conducted across multiple benchmarks validate the superiority of our approach, Label Refurbishment considering Label Rarity (LR^2), achieving remarkable accuracies of 94.19% and 77.05% on simulated noisy CIFAR-10 and CIFAR-100 long-tail datasets, as well as 77.74% and 81.40% on real-noise long-tail datasets, Food-101N and Animal-10N, surpassing existing state-of-the-art methods.

It has been recently established that a nonlinear valley current could be generated through traveling a surface acoustic wave (SAW) in two-dimensional Dirac materials. So far, the SAW-driven valley currents have been attributed to warping Fermi surface or Berry phase effect. Here, we demonstrate that tilt mechanism can also lead to a nonlinear valley Hall current (VHC) when propagating SAW in materials with the tilted Dirac cone placed on a piezoelectric substrate. It's found that the nonlinear VHC exhibits a $\sin\theta$ dependence on the orientation of tilt with respect to SAW. In addition, this tilt-induced nonlinear acoustic VHC shows independence on the relaxation time, distinguishing from the contributions from the Berry phase or trigonal warping. Remarkably, the magnitude of the nonlinear acoustic VHC from tilt mechanism in the uniaxially strained graphene is two orders larger than those reported in MoS$_2$ stemmed from the Berry phase effect and the warping effect., Comment: 6 pages, 2 figures, Accepted by PRB letter

The low-energy physics of Tomonaga-Luttinger liquids (TLLs) is controlled by the Luttinger parameter. We demonstrate that this parameter can be extracted from a single wave function for one-component TLLs with periodic boundary condition. This method relies on the fact that TLLs are described by conformal field theory in which crosscap states can be constructed. The overlaps between the crosscap states and the ground state as well as some excited states are proved to be universal numbers that directly reveal the Luttinger parameter. In microscopic lattice models, crosscap states are formed by putting each pair of antipodal sites into a maximally entangled state. Analytical and numerical calculations are performed in a few representative models to substantiate the conformal field theory prediction. The extracted Luttinger parameters are generally quite accurate in finite-size systems with moderate lengths, so there is no need to perform data fitting and/or finite-size scaling., Comment: 6+9 pages, 2 figures

This work explores the challenging problem of molecule design by framing it as a conditional generative modeling task, where target biological properties or desired chemical constraints serve as conditioning variables. We propose the Latent Prompt Transformer (LPT), a novel generative model comprising three components: (1) a latent vector with a learnable prior distribution modeled by a neural transformation of Gaussian white noise; (2) a molecule generation model based on a causal Transformer, which uses the latent vector as a prompt; and (3) a property prediction model that predicts a molecule's target properties and/or constraint values using the latent prompt. LPT can be learned by maximum likelihood estimation on molecule-property pairs. During property optimization, the latent prompt is inferred from target properties and constraints through posterior sampling and then used to guide the autoregressive molecule generation. After initial training on existing molecules and their properties, we adopt an online learning algorithm to progressively shift the model distribution towards regions that support desired target properties. Experiments demonstrate that LPT not only effectively discovers useful molecules across single-objective, multi-objective, and structure-constrained optimization tasks, but also exhibits strong sample efficiency.