Search

Molecule discovery is a pivotal research field, impacting everything from the medicines we take to the materials we use. Recently, Large Language Models (LLMs) have been widely adopted in molecule understanding and generation, yet the alignments between molecules and their corresponding captions remain a significant challenge. Previous endeavours often treat the molecule as a general SMILES string or molecular graph, neglecting the fine-grained alignments between the molecular sub-structures and the descriptive textual phrases, which are crucial for accurate and explainable predictions. In this case, we introduce MolReFlect, a novel teacher-student framework designed to contextually perform the molecule-caption alignments in a fine-grained way. Our approach initially leverages a larger teacher LLM to label the detailed alignments by directly extracting critical phrases from molecule captions or SMILES strings and implying them to corresponding sub-structures or characteristics. To refine these alignments, we propose In-Context Selective Reflection, which retrieves previous extraction results as context examples for teacher LLM to reflect and lets a smaller student LLM select from in-context reflection and previous extraction results. Finally, we enhance the learning process of the student LLM through Chain-of-Thought In-Context Molecule Tuning, integrating the fine-grained alignments and the reasoning processes within the Chain-of-Thought format. Our experimental results demonstrate that MolReFlect enables LLMs like Mistral-7B to significantly outperform the previous baselines, achieving SOTA performance on the ChEBI-20 dataset. This advancement not only enhances the generative capabilities of LLMs in the molecule-caption translation task, but also contributes to a more explainable framework., Comment: 22 pages, 12 figures

We have demonstrated, for the first time to our knowledge, self-injection locking of a distributed feedback (DFB) diode laser to a multimode 4H-silicon carbide (4H-SiC) microring resonator, and observed resonant opto-mechanical oscillation in the cavity modes. While the fundamental transverse-electric mode family of the silicon carbide microring was optically pumped, Stokes light was generated in the adjacent fundamental transverse-magnetic resonant mode. The threshold of the process did not exceed 5~mW of light entering the cavity characterized with a loaded optical quality factor of $\smash{2\times10^6}$. These results mark a significant milestone in unlocking the potential of 4H-SiC through turnkey soliton microcomb generation and empowering future advancements in areas such as cavity optomechanics using this versatile and quantum-friendly material platform.

We report on optical studies of the Ruddlesden-Popper nickelates La$_{n+1}$Ni$_{n}$O$_{3n+1}$ with $n = 2$ (La$_{3}$Ni$_{2}$O$_{7}$), $n = 3$ (La$_{4}$Ni$_{3}$O$_{10}$) and $n = \infty$ (LaNiO$_{3}$). As the number of the NiO$_{6}$ octahedra layers $n$ grows, the ratio of the kinetic energy determined from the experimental optical conductivity and that from band theory $K_{\text{exp}}/K_{\text{band}}$ increases, suggesting a reduction of electronic correlations. While the strong electronic correlations in the bilayer La$_{3}$Ni$_{2}$O$_{7}$ place it on the verge of the Mott insulating phase, the trilayer La$_{4}$Ni$_{3}$O$_{10}$ and infinite-layer LaNiO$_{3}$ exhibit moderate electronic correlations, falling into the regime of correlated metals. The evolution of the electronic correlations in La$_{n+1}$Ni$_{n}$O$_{3n+1}$ is likely to be dominated by the Ni-$d_{z^2}$ orbital. Our results provide important information for understanding the superconductivity in Ruddlesden-Popper nickelates., Comment: 7 pages, 4 figures. Comments are welcome and appreciated

Recommender systems play a pivotal role across practical scenarios, showcasing remarkable capabilities in user preference modeling. However, the centralized learning paradigm predominantly used raises serious privacy concerns. The federated recommender system (FedRS) addresses this by updating models on clients, while a central server orchestrates training without accessing private data. Existing FedRS approaches, however, face unresolved challenges, including non-convex optimization, vulnerability, potential privacy leakage risk, and communication inefficiency. This paper addresses these challenges by reformulating the federated recommendation problem as a convex optimization issue, ensuring convergence to the global optimum. Based on this, we devise a novel method, RFRec, to tackle this optimization problem efficiently. In addition, we propose RFRecF, a highly efficient version that incorporates non-uniform stochastic gradient descent to improve communication efficiency. In user preference modeling, both methods learn local and global models, collaboratively learning users' common and personalized interests under the federated learning setting. Moreover, both methods significantly enhance communication efficiency, robustness, and privacy protection, with theoretical support. Comprehensive evaluations on four benchmark datasets demonstrate RFRec and RFRecF's superior performance compared to diverse baselines., Comment: CIKM 2024

Transformer models have achieved remarkable success in sequential recommender systems (SRSs). However, computing the attention matrix in traditional dot-product attention mechanisms results in a quadratic complexity with sequence lengths, leading to high computational costs for long-term sequential recommendation. Motivated by the above observation, we propose a novel L2-Normalized Linear Attention for the Transformer-based Sequential Recommender Systems (LinRec), which theoretically improves efficiency while preserving the learning capabilities of the traditional dot-product attention. Specifically, by thoroughly examining the equivalence conditions of efficient attention mechanisms, we show that LinRec possesses linear complexity while preserving the property of attention mechanisms. In addition, we reveal its latent efficiency properties by interpreting the proposed LinRec mechanism through a statistical lens. Extensive experiments are conducted based on two public benchmark datasets, demonstrating that the combination of LinRec and Transformer models achieves comparable or even superior performance than state-of-the-art Transformer-based SRS models while significantly improving time and memory efficiency., Comment: SIGIR 2023

A volumetric lattice Boltzmann (LB) method is developed for the particle-resolved direct numerical simulation of thermal particulate flows with conjugate heat transfer. This method is devised as a single-domain approach by applying the volumetric interpretation of the LB equation and introducing a solid fraction field to represent the particle. The volumetric LB scheme is employed to enforce the nonslip velocity condition in the solid domain, and a specialized momentum exchange scheme is proposed to calculate the hydrodynamic force and torque acting on the particle. To uniformly solve the temperature field over the entire domain with high numerical fidelity, an energy conservation equation is first derived by reformulating the convection term into a source term. A corresponding LB equation is then devised to automatically achieve the conjugate heat transfer condition and correctly handle the differences in thermophysical properties. Theoretical analysis of this LB equation is also performed to derive the constraints to preserve the numerical fidelity even near the solid-fluid interface. Numerical tests are first performed to validate the present volumetric LB method in various aspects. Then, the sedimentation of a cold particle with conjugate heat transfer in a long channel is investigated. It is found that the sedimentation process can be divided into the accelerating, decelerating, and equilibrium stages. As a further application to dense particulate flows, the sedimentation of 2048 cold particles with conjugate heat transfer in a square cavity is simulated. The particulate Rayleigh-B\'{e}nard convection is successfully captured in this particle-resolved simulation., Comment: 28 pages, 16 figures

Hyperbolic representation learning is well known for its ability to capture hierarchical information. However, the distance between samples from different levels of hierarchical classes can be required large. We reveal that the hyperbolic discriminant objective forces the backbone to capture this hierarchical information, which may inevitably increase the Lipschitz constant of the backbone. This can hinder the full utilization of the backbone's generalization ability. To address this issue, we introduce second-order pooling into hyperbolic representation learning, as it naturally increases the distance between samples without compromising the generalization ability of the input features. In this way, the Lipschitz constant of the backbone does not necessarily need to be large. However, current off-the-shelf low-dimensional bilinear pooling methods cannot be directly employed in hyperbolic representation learning because they inevitably reduce the distance expansion capability. To solve this problem, we propose a kernel approximation regularization, which enables the low-dimensional bilinear features to approximate the kernel function well in low-dimensional space. Finally, we conduct extensive experiments on graph-structured datasets to demonstrate the effectiveness of the proposed method.

We introduce a cutting-edge video compression framework tailored for the age of ubiquitous video data, uniquely designed to serve machine learning applications. Unlike traditional compression methods that prioritize human visual perception, our innovative approach focuses on preserving semantic information critical for deep learning accuracy, while efficiently reducing data size. The framework operates on a batch basis, capable of handling multiple video streams simultaneously, thereby enhancing scalability and processing efficiency. It features a dual reconstruction mode: lightweight for real-time applications requiring swift responses, and high-precision for scenarios where accuracy is crucial. Based on a designed deep learning algorithms, it adeptly segregates essential information from redundancy, ensuring machine learning tasks are fed with data of the highest relevance. Our experimental results, derived from diverse datasets including urban surveillance and autonomous vehicle navigation, showcase DMVC's superiority in maintaining or improving machine learning task accuracy, while achieving significant data compression. This breakthrough paves the way for smarter, scalable video analysis systems, promising immense potential across various applications from smart city infrastructure to autonomous systems, establishing a new benchmark for integrating video compression with machine learning.

Mobile deep vision systems play a vital role in numerous scenarios. However, deep learning applications in mobile vision scenarios face problems such as tight computing resources. With the development of edge computing, the architecture of edge clouds has mitigated some of the issues related to limited computing resources. However, it has introduced increased latency. To address these challenges, we designed CloudEye which consists of Fast Inference Module, Feature Mining Module and Quality Encode Module. CloudEye is a real-time, efficient mobile visual perception system that leverages content information mining on edge servers in a mobile vision system environment equipped with edge servers and coordinated with cloud servers. Proven by sufficient experiments, we develop a prototype system that reduces network bandwidth usage by 69.50%, increases inference speed by 24.55%, and improves detection accuracy by 67.30%

Large-scale quantum computation requires to be performed in the fault-tolerant manner. One crucial issue of fault-tolerant quantum computing (FTQC) is reducing the overhead of implementing logical gates. Recently proposed correlated decoding and ``algorithmic fault tolerance" achieve fast logical gates that enables universal quantum computation. However, for circuits involving mid-circuit measurements and feedback, this approach is incompatible with window-based decoding, which is a natural requirement for handling large-scale circuits. In this letter, we propose an alternative architecture that employs delayed fixup circuits, integrating window-based correlated decoding with fast transversal gates. This design significantly reduce both the frequency and duration of correlated decoding, while maintaining support for constant-time logical gates and universality across a broad class of quantum codes. More importantly, by spatial parallelism of windows, this architecture well adapts to time-optimal FTQC, making it particularly useful for large-scale computation. Using Shor's algorithm as an example, we explore the application of our architecture and reveals the promising potential of using fast transversal gates to perform large-scale quantum computing tasks with acceptable overhead on physical systems like ion traps., Comment: 11 pages, 9 figures

Higgs and Goldstone modes manifest as fluctuations in the order parameter of system, offering insights into its phase transitions and symmetry properties. Exploring the dynamics of these collective excitations in a Rydberg atoms system advances various branches of condensed matter, particle physics, and cosmology. Here, we report an experimental signature of Higgs and Goldstone modes in a U(1) symmetry-broken Rydberg atomic gases. By constructing two probe fields to excite atoms, we observe the distinct phase and amplitude fluctuations of Rydberg atoms collective excitations under the particle-hole symmetry. Due to the van der Waals interactions between the Rydberg atoms, we detect a symmetric variance spectrum divided by the divergent regime and phase boundary, capturing the full dynamics of the additional Higgs and Goldstone modes. Studying the Higgs and Goldstone modes in Rydberg atoms allows us to explore fundamental aspects of quantum phase transitions and symmetry breaking phenomena, while leveraging the unique properties of these highly interacting systems to uncover new physics and potential applications in quantum simulation.

In this study, we present a detailed investigation of kagome superconductors CsV3Sb5 single crystal and its Ta-doped variant, Cs(V0.86Ta0.14)3Sb5, through specific heat measurements. Our results show a clear suppression of the charge density wave (CDW) and notable increase in the superconducting transition temperature (Tc) from 2.8 K to 4.6 K upon Ta doping. The electronic specific heat of the pristine CsV3Sb5 sample can be fitted with a model comprising an s-wave gap and a highly anisotropic extended s-wave gap, where the ratio 2{\Delta}/k_B T_c is smaller than the weak coupling limit of 3.5. For the doped sample Cs(V0.86Ta0.14)3Sb5, it exhibits two isotropic s-wave gaps, yielding the larger gap of 2{\Delta}/k_B T_c=5.04, which indicates a significant enhancement in superconducting coupling. This evolution is attributed to the increased density of states (DOS) near the Fermi level released through the suppression of the CDW gap. Our results demonstrate enhanced superconducting coupling and variation of gap structure in CsV3Sb5 due to Ta doping.

We explore the feasibility and potential of building a ground-truth-free evaluation model to assess the quality of segmentations generated by the Segment Anything Model (SAM) and its variants in medical imaging. This evaluation model estimates segmentation quality scores by analyzing the coherence and consistency between the input images and their corresponding segmentation predictions. Based on prior research, we frame the task of training this model as a regression problem within a supervised learning framework, using Dice scores (and optionally other metrics) along with mean squared error to compute the training loss. The model is trained utilizing a large collection of public datasets of medical images with segmentation predictions from SAM and its variants. We name this model EvanySeg (Evaluation of Any Segmentation in Medical Images). Our exploration of convolution-based models (e.g., ResNet) and transformer-based models (e.g., ViT) suggested that ViT yields better performance for this task. EvanySeg can be employed for various tasks, including: (1) identifying poorly segmented samples by detecting low-percentile segmentation quality scores; (2) benchmarking segmentation models without ground truth by averaging quality scores across test samples; (3) alerting human experts to poor-quality segmentation predictions during human-AI collaboration by applying a threshold within the score space; and (4) selecting the best segmentation prediction for each test sample at test time when multiple segmentation models are available, by choosing the prediction with the highest quality score. Models and code will be made available at https://github.com/ahjolsenbics/EvanySeg., Comment: 17 pages, 15 figures

Recently, large language models (LLMs) have shown strong potential in facilitating human-robotic interaction and collaboration. However, existing LLM-based systems often overlook the misalignment between human and robot perceptions, which hinders their effective communication and real-world robot deployment. To address this issue, we introduce SYNERGAI, a unified system designed to achieve both perceptual alignment and human-robot collaboration. At its core, SYNERGAI employs 3D Scene Graph (3DSG) as its explicit and innate representation. This enables the system to leverage LLM to break down complex tasks and allocate appropriate tools in intermediate steps to extract relevant information from the 3DSG, modify its structure, or generate responses. Importantly, SYNERGAI incorporates an automatic mechanism that enables perceptual misalignment correction with users by updating its 3DSG with online interaction. SYNERGAI achieves comparable performance with the data-driven models in ScanQA in a zero-shot manner. Through comprehensive experiments across 10 real-world scenes, SYNERGAI demonstrates its effectiveness in establishing common ground with humans, realizing a success rate of 61.9% in alignment tasks. It also significantly improves the success rate from 3.7% to 45.68% on novel tasks by transferring the knowledge acquired during alignment., Comment: Project page: https://synerg-ai.github.io

Study of phase transitions provide insights into how a many-body system behaves under different conditions, enabling us to understand the symmetry breaking, critical phenomena, and topological properties. Strong long-range interactions in highly excited Rydberg atoms create a versatile platform for exploring exotic emergent topological phases. Here, we report the experimental observation of dynamical topological phase transitions in cold Rydberg atomic gases under a microwave field driving. By measuring the system transmission curves while varying the probe intensity, we observe complex hysteresis trajectories characterized by distinct winding numbers as they cross the critical point. At the transition state, where the winding number flips, the topology of these hysteresis trajectories evolves into more non-trivial structures. The topological trajectories are shown to be robust against noise, confirming their rigidity in dynamic conditions. These findings contribute to the insights of emergence of complex dynamical topological phases in many-body systems.

Memory is the foundation of all human activities; without memory, it would be nearly impossible for people to perform any task in daily life. With the development of Large Language Models (LLMs), their language capabilities are becoming increasingly comparable to those of humans. But do LLMs have memory? Based on current performance, LLMs do appear to exhibit memory. So, what is the underlying mechanism of this memory? Previous research has lacked a deep exploration of LLMs' memory capabilities and the underlying theory. In this paper, we use Universal Approximation Theorem (UAT) to explain the memory mechanism in LLMs. We also conduct experiments to verify the memory capabilities of various LLMs, proposing a new method to assess their abilities based on these memory ability. We argue that LLM memory operates like Schr\"odinger's memory, meaning that it only becomes observable when a specific memory is queried. We can only determine if the model retains a memory based on its output in response to the query; otherwise, it remains indeterminate. Finally, we expand on this concept by comparing the memory capabilities of the human brain and LLMs, highlighting the similarities and differences in their operational mechanisms.

In this paper, we propose a Q-learning based decision-making framework to improve the safety and efficiency of Autonomous Vehicles when they encounter other maliciously behaving vehicles while passing through unsignalized intersections. In Autonomous Vehicles, conventional reward signals are set as regular rewards regarding feedback factors such as safety and efficiency. In this paper, safety gains are modulated by variable weighting parameters to ensure that safety can be emphasized more in emergency situations. The framework proposed in this paper introduces first-order theory of mind inferences on top of conventional rewards, using first-order beliefs as additional reward signals. The decision framework enables Autonomous Vehicles to make informed decisions when encountering vehicles with potentially malicious behaviors at unsignalized intersections, thereby improving the overall safety and efficiency of Autonomous Vehicle transportation systems. In order to verify the performance of the decision framework, this paper uses Prescan/Simulink co-simulations for simulation, and the results show that the performance of the decision framework can meet the set requirements.

Sequential recommendation methods are crucial in modern recommender systems for their remarkable capability to understand a user's changing interests based on past interactions. However, a significant challenge faced by current methods (e.g., RNN- or Transformer-based models) is to effectively and efficiently capture users' preferences by modeling long behavior sequences, which impedes their various applications like short video platforms where user interactions are numerous. Recently, an emerging architecture named Mamba, built on state space models (SSM) with efficient hardware-aware designs, has showcased the tremendous potential for sequence modeling, presenting a compelling avenue for addressing the challenge effectively. Inspired by this, we propose a novel generic and efficient sequential recommendation backbone, SSD4Rec, which explores the seamless adaptation of Mamba for sequential recommendations. Specifically, SSD4Rec marks the variable- and long-length item sequences with sequence registers and processes the item representations with bidirectional Structured State Space Duality (SSD) blocks. This not only allows for hardware-aware matrix multiplication but also empowers outstanding capabilities in variable-length and long-range sequence modeling. Extensive evaluations on four benchmark datasets demonstrate that the proposed model achieves state-of-the-art performance while maintaining near-linear scalability with user sequence length. Our code is publicly available at https://github.com/ZhangYifeng1995/SSD4Rec.

Graph Contrastive Learning (GCL) is a potent paradigm for self-supervised graph learning that has attracted attention across various application scenarios. However, GCL for learning on Text-Attributed Graphs (TAGs) has yet to be explored. Because conventional augmentation techniques like feature embedding masking cannot directly process textual attributes on TAGs. A naive strategy for applying GCL to TAGs is to encode the textual attributes into feature embeddings via a language model and then feed the embeddings into the following GCL module for processing. Such a strategy faces three key challenges: I) failure to avoid information loss, II) semantic loss during the text encoding phase, and III) implicit augmentation constraints that lead to uncontrollable and incomprehensible results. In this paper, we propose a novel GCL framework named LATEX-GCL to utilize Large Language Models (LLMs) to produce textual augmentations and LLMs' powerful natural language processing (NLP) abilities to address the three limitations aforementioned to pave the way for applying GCL to TAG tasks. Extensive experiments on four high-quality TAG datasets illustrate the superiority of the proposed LATEX-GCL method. The source codes and datasets are released to ease the reproducibility, which can be accessed via this link: https://anonymous.4open.science/r/LATEX-GCL-0712.

Recent advances in text-to-image personalization have enabled high-quality and controllable image synthesis for user-provided concepts. However, existing methods still struggle to balance identity preservation with text alignment. Our approach is based on the fact that generating prompt-aligned images requires a precise semantic understanding of the prompt, which involves accurately processing the interactions between the new concept and its surrounding context tokens within the CLIP text encoder. To address this, we aim to embed the new concept properly into the input embedding space of the text encoder, allowing for seamless integration with existing tokens. We introduce Context Regularization (CoRe), which enhances the learning of the new concept's text embedding by regularizing its context tokens in the prompt. This is based on the insight that appropriate output vectors of the text encoder for the context tokens can only be achieved if the new concept's text embedding is correctly learned. CoRe can be applied to arbitrary prompts without requiring the generation of corresponding images, thus improving the generalization of the learned text embedding. Additionally, CoRe can serve as a test-time optimization technique to further enhance the generations for specific prompts. Comprehensive experiments demonstrate that our method outperforms several baseline methods in both identity preservation and text alignment. Code will be made publicly available.

Topic taxonomy discovery aims at uncovering topics of different abstraction levels and constructing hierarchical relations between them. Unfortunately, most of prior work can hardly model semantic scopes of words and topics by holding the Euclidean embedding space assumption. What's worse, they infer asymmetric hierarchical relations by symmetric distances between topic embeddings. As a result, existing methods suffer from problems of low-quality topics at high abstraction levels and inaccurate hierarchical relations. To alleviate these problems, this paper develops a Box embedding-based Topic Model (BoxTM) that maps words and topics into the box embedding space, where the asymmetric metric is defined to properly infer hierarchical relations among topics. Additionally, our BoxTM explicitly infers upper-level topics based on correlation between specific topics through recursive clustering on topic boxes. Finally, extensive experiments validate high-quality of the topic taxonomy learned by BoxTM., Comment: to be published in TACL

The recently discovered spin-triplet superconductor candidate UTe2 with Tc = 2 K has attracted enormous attention because it possesses many interesting properties, such as the extremely high upper critical field Hc2(0), chiral superconductivity and spontaneous time-reversal symmetry breaking, etc., all these suggest that it may be the long-sought spin-triplet superconductor. Here we report the discovery of superconductivity up to Tc = 4K in one of its siblings, i.e., UAs2 under high pressures. Interestingly, the UAs2 shows metallic behavior with an antiferromagnetic (AFM) transition at about 274 K under ambient pressure. Upon applying pressure, this transition is pushed down to lower temperatures with improved electric conductivity. When the pressure rises to about 20-22 GPa, superconductivity occurs together with the emergence of a linear temperature dependence of normal state resistance, the latter is a hallmark of the strange-metal state. The superconductivity with the highest Tc = 4 K is reached under a pressure of about 26.8 GPa, and it is robust against magnetic field with the upper critical field {\mu}0Hc2(0) ~ 12 T, far beyond the Pauli limit. Higher pressures will suppress the superconductivity and bring back the Fermi liquid behavior, showing a clear signature of quantum criticality. Our results open a new avenue for investigating the unconventional superconductivity concerning the mysterious 5f-band electrons in this uranium-based system., Comment: 16 pages of main text, 4 figures + 7 extended data figures

This paper tackles the challenge of multi-sensor multi-object tracking by proposing various decentralised Variational Inference (VI) schemes that match the tracking performance of centralised sensor fusion with only local message exchanges among neighboring sensors. We first establish a centralised VI sensor fusion scheme as a benchmark and analyse the limitations of its decentralised counterpart, which requires sensors to await consensus at each VI iteration. Therefore, we propose a decentralised gradient-based VI framework that optimises the Locally Maximised Evidence Lower Bound (LM-ELBO) instead of the standard ELBO, which reduces the parameter search space and enables faster convergence, making it particularly beneficial for decentralised tracking.This proposed framework is inherently self-evolving, improving with advancements in decentralised optimisation techniques for convergence guarantees and efficiency. Further, we enhance the convergence speed of proposed decentralised schemes using natural gradients and gradient tracking strategies. Results verify that our decentralised VI schemes are empirically equivalent to centralised fusion in tracking performance. Notably, the decentralised natural gradient VI method is the most communication-efficient, with communication costs comparable to suboptimal decentralised strategies while delivering notably higher tracking accuracy.

Large language models (LLMs) have made remarkable progress in various natural language processing tasks as a benefit of their capability to comprehend and reason with factual knowledge. However, a significant amount of factual knowledge is stored in structured data, which possesses unique characteristics that differ from the unstructured texts used for pretraining. This difference can introduce imperceptible inference parameter deviations, posing challenges for LLMs in effectively utilizing and reasoning with structured data to accurately infer factual knowledge. To this end, we propose a benchmark named StructFact, to evaluate the structural reasoning capabilities of LLMs in inferring factual knowledge. StructFact comprises 8,340 factual questions encompassing various tasks, domains, timelines, and regions. This benchmark allows us to investigate the capability of LLMs across five factual tasks derived from the unique characteristics of structural facts. Extensive experiments on a set of LLMs with different training strategies reveal the limitations of current LLMs in inferring factual knowledge from structured data. We present this benchmark as a compass to navigate the strengths and weaknesses of LLMs in reasoning with structured data for knowledge-sensitive tasks, and to encourage advancements in related real-world applications. Please find our code at https://github.com/EganGu/StructFact.

The interactions between Rydberg atoms and microwave fields provide a valuable framework for studying the complex dynamics out of equilibrium, exotic phases, and critical phenomena in many-body physics. This unique interplay allows us to explore various regimes of nonlinearity and phase transitions. Here, we observe a phase transition from the state in the regime of bistability to that in multistability in strongly interacting Rydberg atoms by varying the microwave field intensity, accompanying with the breaking of Z3-symmetry. During the phase transition, the system experiences a hidden critical point, in which the multistable states are difficult to be identified. Through changing the initial state of system, we can identify a hidden multistable state and reveal a hidden trajectory of phase transition, allowing us to track to a hidden critical point. In addition, we observe multiple phase transitions in spectra, suggesting higher-order symmetry breaking. The reported results shed light on manipulating multistability in dissipative Rydberg atoms systems and hold promise in the applications of non-equilibrium many-body physics., Comment: 10 pages, 5 figures

Test-time adaptation (TTA) effectively addresses distribution shifts between training and testing data by adjusting models on test samples, which is crucial for improving model inference in real-world applications. However, traditional TTA methods typically follow a fixed pattern to address the dynamic data patterns (low-diversity or high-diversity patterns) often leading to performance degradation and consequently a decline in Quality of Experience (QoE). The primary issues we observed are:Different scenarios require different normalization methods (e.g., Instance Normalization is optimal in mixed domains but not in static domains). Model fine-tuning can potentially harm the model and waste time.Hence, it is crucial to design strategies for effectively measuring and managing distribution diversity to minimize its negative impact on model performance. Based on these observations, this paper proposes a new general method, named Diversity Adaptive Test-Time Adaptation (DATTA), aimed at improving QoE. DATTA dynamically selects the best batch normalization methods and fine-tuning strategies by leveraging the Diversity Score to differentiate between high and low diversity score batches. It features three key components: Diversity Discrimination (DD) to assess batch diversity, Diversity Adaptive Batch Normalization (DABN) to tailor normalization methods based on DD insights, and Diversity Adaptive Fine-Tuning (DAFT) to selectively fine-tune the model. Experimental results show that our method achieves up to a 21% increase in accuracy compared to state-of-the-art methodologies, indicating that our method maintains good model performance while demonstrating its robustness. Our code will be released soon., Comment: 16 pages, 2 figures

Large vision-language models (LVLMs) have made significant progress in recent years. While LVLMs exhibit excellent ability in language understanding, question answering, and conversations of visual inputs, they are prone to producing hallucinations. While several methods are proposed to evaluate the hallucinations in LVLMs, most are reference-based and depend on external tools, which complicates their practical application. To assess the viability of alternative methods, it is critical to understand whether the reference-free approaches, which do not rely on any external tools, can efficiently detect hallucinations. Therefore, we initiate an exploratory study to demonstrate the effectiveness of different reference-free solutions in detecting hallucinations in LVLMs. In particular, we conduct an extensive study on three kinds of techniques: uncertainty-based, consistency-based, and supervised uncertainty quantification methods on four representative LVLMs across two different tasks. The empirical results show that the reference-free approaches are capable of effectively detecting non-factual responses in LVLMs, with the supervised uncertainty quantification method outperforming the others, achieving the best performance across different settings.

Attributed networks containing entity-specific information in node attributes are ubiquitous in modeling social networks, e-commerce, bioinformatics, etc. Their inherent network topology ranges from simple graphs to hypergraphs with high-order interactions and multiplex graphs with separate layers. An important graph mining task is node clustering, aiming to partition the nodes of an attributed network into k disjoint clusters such that intra-cluster nodes are closely connected and share similar attributes, while inter-cluster nodes are far apart and dissimilar. It is highly challenging to capture multi-hop connections via nodes or attributes for effective clustering on multiple types of attributed networks. In this paper, we first present AHCKA as an efficient approach to attributed hypergraph clustering (AHC). AHCKA includes a carefully-crafted K-nearest neighbor augmentation strategy for the optimized exploitation of attribute information on hypergraphs, a joint hypergraph random walk model to devise an effective AHC objective, and an efficient solver with speedup techniques for the objective optimization. The proposed techniques are extensible to various types of attributed networks, and thus, we develop ANCKA as a versatile attributed network clustering framework, capable of attributed graph clustering (AGC), attributed multiplex graph clustering (AMGC), and AHC. Moreover, we devise ANCKA with algorithmic designs tailored for GPU acceleration to boost efficiency. We have conducted extensive experiments to compare our methods with 19 competitors on 8 attributed hypergraphs, 16 competitors on 6 attributed graphs, and 16 competitors on 3 attributed multiplex graphs, all demonstrating the superb clustering quality and efficiency of our methods., Comment: 25 pages, 15 figures

Grounding natural language in physical 3D environments is essential for the advancement of embodied artificial intelligence. Current datasets and models for 3D visual grounding predominantly focus on identifying and localizing objects from static, object-centric descriptions. These approaches do not adequately address the dynamic and sequential nature of task-oriented grounding necessary for practical applications. In this work, we propose a new task: Task-oriented Sequential Grounding in 3D scenes, wherein an agent must follow detailed step-by-step instructions to complete daily activities by locating a sequence of target objects in indoor scenes. To facilitate this task, we introduce SG3D, a large-scale dataset containing 22,346 tasks with 112,236 steps across 4,895 real-world 3D scenes. The dataset is constructed using a combination of RGB-D scans from various 3D scene datasets and an automated task generation pipeline, followed by human verification for quality assurance. We adapted three state-of-the-art 3D visual grounding models to the sequential grounding task and evaluated their performance on SG3D. Our results reveal that while these models perform well on traditional benchmarks, they face significant challenges with task-oriented sequential grounding, underscoring the need for further research in this area., Comment: website: https://sg-3d.github.io/

The interplay between strong long-range interactions and the coherent driving contribute to the formation of complex patterns, symmetry, and novel phases of matter in many-body systems. However, long-range interactions may induce an additional dissipation channel, resulting in non-Hermitian many-body dynamics and the emergence of exceptional points in spectrum. Here, we report experimental observation of interaction-induced exceptional points in cold Rydberg atomic gases, revealing the breaking of charge-conjugation parity symmetry. By measuring the transmission spectrum under increasing and decreasing probe intensity, the interaction-induced hysteresis trajectories are observed, which give rise to non-Hermitian dynamics. We record the area enclosed by hysteresis loops and investigate the dynamics of hysteresis loops. The reported exceptional points and hysteresis trajectories in cold Rydberg atomic gases provide valuable insights into the underlying non-Hermitian physics in many-body systems, allowing us to study the interplay between long-range interactions and non-Hermiticity.

Cross-view geo-localization in GNSS-denied environments aims to determine an unknown location by matching drone-view images with the correct geo-tagged satellite-view images from a large gallery. Recent research shows that learning discriminative image representations under specific weather conditions can significantly enhance performance. However, the frequent occurrence of unseen extreme weather conditions hinders progress. This paper introduces MCGF, a Multi-weather Cross-view Geo-localization Framework designed to dynamically adapt to unseen weather conditions. MCGF establishes a joint optimization between image restoration and geo-localization using denoising diffusion models. For image restoration, MCGF incorporates a shared encoder and a lightweight restoration module to help the backbone eliminate weather-specific information. For geo-localization, MCGF uses EVA-02 as a backbone for feature extraction, with cross-entropy loss for training and cosine distance for testing. Extensive experiments on University160k-WX demonstrate that MCGF achieves competitive results for geo-localization in varying weather conditions., Comment: Accepted by ACM MM24 workshop

Previous studies in quantum information have recognized that specific types of noise can encode information in certain applications. However, the role of noise in Quantum Hypothesis Testing (QHT), traditionally assumed to undermine performance and reduce success probability, has not been thoroughly explored. Our study bridges this gap by establishing sufficient conditions for noisy dynamics that can surpass the success probabilities achievable under noiseless (unitary) dynamics within certain time intervals. We then devise and experimentally implement a noise-assisted QHT protocol in the setting of ultralow-field nuclear magnetic resonance spin systems. Our experimental results demonstrate that the success probability of QHT under the noisy dynamics can indeed surpass the ceiling set by unitary evolution alone. Moreover, we have shown that in cases where noise initially hampers the performance, strategic application of coherent controls on the system can transform these previously detrimental noises into advantageous factors. This transformative approach demonstrates the potential to harness and leverage noise in QHT, which pushes the boundaries of QHT and general quantum information processing.

Deep neural networks (DNNs) have significantly boosted the performance of many challenging tasks. Despite the great development, DNNs have also exposed their vulnerability. Recent studies have shown that adversaries can manipulate the predictions of DNNs by adding a universal adversarial perturbation (UAP) to benign samples. On the other hand, increasing efforts have been made to help users understand and explain the inner working of DNNs by highlighting the most informative parts (i.e., attribution maps) of samples with respect to their predictions. Moreover, we first empirically find that such attribution maps between benign and adversarial examples have a significant discrepancy, which has the potential to detect universal adversarial perturbations for defending against adversarial attacks. This finding motivates us to further investigate a new research problem: whether there exist universal adversarial perturbations that are able to jointly attack DNNs classifier and its interpretation with malicious desires. It is challenging to give an explicit answer since these two objectives are seemingly conflicting. In this paper, we propose a novel attacking framework to generate joint universal adversarial perturbations (JUAP), which can fool the DNNs model and misguide the inspection from interpreters simultaneously. Comprehensive experiments on various datasets demonstrate the effectiveness of the proposed method JUAP for joint attacks. To the best of our knowledge, this is the first effort to study UAP for jointly attacking both DNNs and interpretations.

As one of the most representative DL techniques, Transformer architecture has empowered numerous advanced models, especially the large language models (LLMs) that comprise billions of parameters, becoming a cornerstone in deep learning. Despite the impressive achievements, Transformers still face inherent limitations, particularly the time-consuming inference resulting from the quadratic computation complexity of attention calculation. Recently, a novel architecture named Mamba, drawing inspiration from classical state space models (SSMs), has emerged as a promising alternative for building foundation models, delivering comparable modeling abilities to Transformers while preserving near-linear scalability concerning sequence length. This has sparked an increasing number of studies actively exploring Mamba's potential to achieve impressive performance across diverse domains. Given such rapid evolution, there is a critical need for a systematic review that consolidates existing Mamba-empowered models, offering a comprehensive understanding of this emerging model architecture. In this survey, we therefore conduct an in-depth investigation of recent Mamba-associated studies, covering three main aspects: the advancements of Mamba-based models, the techniques of adapting Mamba to diverse data, and the applications where Mamba can excel. Specifically, we first review the foundational knowledge of various representative deep learning models and the details of Mamba-1&2 as preliminaries. Then, to showcase the significance of Mamba for AI, we comprehensively review the related studies focusing on Mamba models' architecture design, data adaptability, and applications. Finally, we present a discussion of current limitations and explore various promising research directions to provide deeper insights for future investigations.

Despite the photorealistic novel view synthesis (NVS) performance achieved by the original 3D Gaussian splatting (3DGS), its rendering quality significantly degrades with sparse input views. This performance drop is mainly caused by the limited number of initial points generated from the sparse input, insufficient supervision during the training process, and inadequate regularization of the oversized Gaussian ellipsoids. To handle these issues, we propose the LoopSparseGS, a loop-based 3DGS framework for the sparse novel view synthesis task. In specific, we propose a loop-based Progressive Gaussian Initialization (PGI) strategy that could iteratively densify the initialized point cloud using the rendered pseudo images during the training process. Then, the sparse and reliable depth from the Structure from Motion, and the window-based dense monocular depth are leveraged to provide precise geometric supervision via the proposed Depth-alignment Regularization (DAR). Additionally, we introduce a novel Sparse-friendly Sampling (SFS) strategy to handle oversized Gaussian ellipsoids leading to large pixel errors. Comprehensive experiments on four datasets demonstrate that LoopSparseGS outperforms existing state-of-the-art methods for sparse-input novel view synthesis, across indoor, outdoor, and object-level scenes with various image resolutions., Comment: 13 pages, 10 figures

Neural networks are increasingly evolving towards training large models with big data, a method that has demonstrated superior performance across many tasks. However, this approach introduces an urgent problem: current deep learning models are predominantly serial, meaning that as the number of network layers increases, so do the training and inference times. This is unacceptable if deep learning is to continue advancing. Therefore, this paper proposes a deep learning parallelization strategy based on the Universal Approximation Theorem (UAT). From this foundation, we designed a parallel network called Para-Former to test our theory. Unlike traditional serial models, the inference time of Para-Former does not increase with the number of layers, significantly accelerating the inference speed of multi-layer networks. Experimental results validate the effectiveness of this network.

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.

Human cognition significantly influences expressed behavior and is intrinsically tied to authentic personality traits. Personality assessment plays a pivotal role in various fields, including psychology, education, social media, etc. However, traditional self-report questionnaires can only provide data based on what individuals are willing and able to disclose, thereby lacking objective. Moreover, automated measurements and peer assessments demand significant human effort and resources. In this paper, given the advantages of the Virtual Reality (VR) technique, we develop a VR simulator -- PersonalityScanner, to stimulate cognitive processes and simulate daily behaviors based on an immersive and interactive simulation environment, in which participants carry out a battery of engaging tasks that formulate a natural story of first-day at work. Through this simulator, we collect a synchronous multi-modal dataset with ten modalities, including first/third-person video, audio, text, eye tracking, facial microexpression, pose, depth data, log, and inertial measurement unit. By systematically examining the contributions of different modalities on revealing personality, we demonstrate the superior performance and effectiveness of PersonalityScanner., Comment: Accepted to COGSCI 2024

Financial risks trend to spread from one entity to another, ultimately leading to systemic risks. The key to preventing such risks lies in understanding the causal chains behind risk contagion. Despite this, prevailing approaches primarily emphasize identifying risks, overlooking the underlying causal analysis of risk. To address such an issue, we propose a Risk Contagion Causal Reasoning model called RC2R, which uses the logical reasoning capabilities of large language models (LLMs) to dissect the causal mechanisms of risk contagion grounded in the factual and expert knowledge embedded within financial knowledge graphs (KGs). At the data level, we utilize financial KGs to construct causal instructions, empowering LLMs to perform formal causal reasoning on risk propagation and tackle the "causal parrot" problem of LLMs. In terms of model architecture, we integrate a fusion module that aligns tokens and nodes across various granularities via multi-scale contrastive learning, followed by the amalgamation of textual and graph-structured data through soft prompt with cross multi-head attention mechanisms. To quantify risk contagion, we introduce a risk pathway inference module for calculating risk scores for each node in the graph. Finally, we visualize the risk contagion pathways and their intensities using Sankey diagrams, providing detailed causal explanations. Comprehensive experiments on financial KGs and supply chain datasets demonstrate that our model outperforms several state-of-the-art models in prediction performance and out-of-distribution (OOD) generalization capabilities. We will make our dataset and code publicly accessible to encourage further research and development in this field.

In this paper, we investigate the feasibility of leveraging large language models (LLMs) for integrating general knowledge and incorporating pseudo-events as priors for temporal content distribution in video moment retrieval (VMR) models. The motivation behind this study arises from the limitations of using LLMs as decoders for generating discrete textual descriptions, which hinders their direct application to continuous outputs like salience scores and inter-frame embeddings that capture inter-frame relations. To overcome these limitations, we propose utilizing LLM encoders instead of decoders. Through a feasibility study, we demonstrate that LLM encoders effectively refine inter-concept relations in multimodal embeddings, even without being trained on textual embeddings. We also show that the refinement capability of LLM encoders can be transferred to other embeddings, such as BLIP and T5, as long as these embeddings exhibit similar inter-concept similarity patterns to CLIP embeddings. We present a general framework for integrating LLM encoders into existing VMR architectures, specifically within the fusion module. Through experimental validation, we demonstrate the effectiveness of our proposed methods by achieving state-of-the-art performance in VMR. The source code can be accessed at https://github.com/fletcherjiang/LLMEPET., Comment: Accepted to ACM Multimedia 2024

Vision language models (VLMs) have achieved impressive progress in diverse applications, becoming a prevalent research direction. In this paper, we build FIRE, a feedback-refinement dataset, consisting of 1.1M multi-turn conversations that are derived from 27 source datasets, empowering VLMs to spontaneously refine their responses based on user feedback across diverse tasks. To scale up the data collection, FIRE is collected in two components: FIRE-100K and FIRE-1M, where FIRE-100K is generated by GPT-4V, and FIRE-1M is freely generated via models trained on FIRE-100K. Then, we build FIRE-Bench, a benchmark to comprehensively evaluate the feedback-refining capability of VLMs, which contains 11K feedback-refinement conversations as the test data, two evaluation settings, and a model to provide feedback for VLMs. We develop the FIRE-LLaVA model by fine-tuning LLaVA on FIRE-100K and FIRE-1M, which shows remarkable feedback-refining capability on FIRE-Bench and outperforms untrained VLMs by 50%, making more efficient user-agent interactions and underscoring the significance of the FIRE dataset.

The discovery of superconductivity in 3$d$-transition metal compounds with strong magnetism is interesting but rare. Especially for Mn-based compounds, there exist only very limited materials that show superconductivity. Here, we report the discovery of superconductivity up to 14.2 K in a Mn-based material MnB$_4$. By applying high pressures, we found the continuous suppression of a weak insulating behavior and the occurrence of superconductivity after about 30 GPa. With further increasing pressure, $T_\text{c}$ is gradually enhanced and reaches the maximum value of about 14.2 K at 150 GPa with a Fermi-Liquid behavior in the normal states. The synchrotron X-ray diffraction data reveal the unchanged monoclinic (S.G: $P2_1/c$) symmetry but an unusual crossover of the lattice parameters $b$ and $c$. Theoretical calculations based on the electron-phonon coupling picture reveal a very low $T_\text{c}$ (less than 1 K), manifesting an exotic pairing mechanism beyond the Bardeen-Cooper-Schrieffer (BCS) theory. Our findings show a promising way to explore high $T_\text{c}$ superconductivity by combining the 3d-transition metal magnetic elements and light elements., Comment: 36 pages total; 24 pages of main text with 5 figures, 12 pages of supplement with 1 table and 8 figures

This paper presents UltraEdit, a large-scale (approximately 4 million editing samples), automatically generated dataset for instruction-based image editing. Our key idea is to address the drawbacks in existing image editing datasets like InstructPix2Pix and MagicBrush, and provide a systematic approach to producing massive and high-quality image editing samples. UltraEdit offers several distinct advantages: 1) It features a broader range of editing instructions by leveraging the creativity of large language models (LLMs) alongside in-context editing examples from human raters; 2) Its data sources are based on real images, including photographs and artworks, which provide greater diversity and reduced bias compared to datasets solely generated by text-to-image models; 3) It also supports region-based editing, enhanced by high-quality, automatically produced region annotations. Our experiments show that canonical diffusion-based editing baselines trained on UltraEdit set new records on MagicBrush and Emu-Edit benchmarks. Our analysis further confirms the crucial role of real image anchors and region-based editing data. The dataset, code, and models can be found in https://ultra-editing.github.io., Comment: 32 pages, 14 figures

Recently, graph condensation has emerged as a prevalent technique to improve the training efficiency for graph neural networks (GNNs). It condenses a large graph into a small one such that a GNN trained on this small synthetic graph can achieve comparable performance to a GNN trained on the large graph. However, while existing graph condensation studies mainly focus on the best trade-off between graph size and the GNNs' performance (model utility), the security issues of graph condensation have not been studied. To bridge this research gap, we propose the task of backdoor graph condensation. Effective backdoor attacks on graph condensation aim to (1) maintain the quality and utility of condensed graphs despite trigger injections and (2) ensure trigger effectiveness through the condensation process, yielding a high attack success rate. To pursue the objectives, we devise the first backdoor attack against graph condensation, denoted as BGC, where effective attack is launched by consistently updating triggers throughout condensation and focusing on poisoning representative nodes. The extensive experiments demonstrate the effectiveness of our attack. BGC achieves a high attack success rate (close to 1.0) and good model utility in all cases. Furthermore, the results against multiple defense methods demonstrate BGC's resilience under their defenses. Finally, we conduct studies to analyze the factors that influence the attack performance., Comment: Revise the figures and add some discussions

Computer vision (CV) is one of the most crucial fields in artificial intelligence. In recent years, a variety of deep learning models based on convolutional neural networks (CNNs) and Transformers have been designed to tackle diverse problems in CV. These algorithms have found practical applications in areas such as robotics and facial recognition. Despite the increasing power of current CV models, several fundamental questions remain unresolved: Why do CNNs require deep layers? What ensures the generalization ability of CNNs? Why do residual-based networks outperform fully convolutional networks like VGG? What is the fundamental difference between residual-based CNNs and Transformer-based networks? Why can CNNs utilize LoRA and pruning techniques? The root cause of these questions lies in the lack of a robust theoretical foundation for deep learning models in CV. To address these critical issues and techniques, we employ the Universal Approximation Theorem (UAT) to provide a theoretical basis for convolution- and Transformer-based models in CV. By doing so, we aim to elucidate these questions from a theoretical perspective.

With an increasing social demand for fine-grained sentiment analysis (SA), implicit sentiment analysis (ISA) poses a significant challenge with the absence of salient cue words in expressions. It necessitates reliable reasoning to understand how the sentiment is aroused and thus determine implicit sentiments. In the era of Large Language Models (LLMs), Encoder-Decoder (ED) LLMs have gained popularity to serve as backbone models for SA applications, considering impressive text comprehension and reasoning ability among diverse tasks. On the other hand, Decoder-only (DO) LLMs exhibit superior natural language generation and in-context learning capabilities. However, their responses may contain misleading or inaccurate information. To identify implicit sentiment with reliable reasoning, this study proposes RVISA, a two-stage reasoning framework that harnesses the generation ability of DO LLMs and the reasoning ability of ED LLMs to train an enhanced reasoner. Specifically, we adopt three-hop reasoning prompting to explicitly furnish sentiment elements as cues. The generated rationales are utilized to fine-tune an ED LLM into a skilled reasoner. Additionally, we develop a straightforward yet effective verification mechanism to ensure the reliability of the reasoning learning. We evaluated the proposed method on two benchmark datasets and achieved state-of-the-art results in ISA performance., Comment: 11 pages, 6 figures, and 4 tables

Language models have emerged as a critical area of focus in artificial intelligence, particularly with the introduction of groundbreaking innovations like ChatGPT. Large-scale Transformer networks have quickly become the leading approach for advancing natural language processing algorithms. Built on the Transformer architecture, these models enable interactions that closely mimic human communication and, equipped with extensive knowledge, can even assist in guiding human tasks. Despite their impressive capabilities and growing complexity, a key question remains-the theoretical foundations of large language models (LLMs). What makes Transformer so effective for powering intelligent language applications, such as translation and coding? What underlies LLMs' ability for In-Context Learning (ICL)? How does the LoRA scheme enhance the fine-tuning of LLMs? And what supports the practicality of pruning LLMs? To address these critical questions and explore the technological strategies within LLMs, we leverage the Universal Approximation Theory (UAT) to offer a theoretical backdrop, shedding light on the mechanisms that underpin these advancements.

This paper presents OmniJARVIS, a novel Vision-Language-Action (VLA) model for open-world instruction-following agents in Minecraft. Compared to prior works that either emit textual goals to separate controllers or produce the control command directly, OmniJARVIS seeks a different path to ensure both strong reasoning and efficient decision-making capabilities via unified tokenization of multimodal interaction data. First, we introduce a self-supervised approach to learn a behavior encoder that produces discretized tokens for behavior trajectories $\tau = \{o_0, a_0, \dots\}$ and an imitation learning policy decoder conditioned on these tokens. These additional behavior tokens will be augmented to the vocabulary of pretrained Multimodal Language Models. With this encoder, we then pack long-term multimodal interactions involving task instructions, memories, thoughts, observations, textual responses, behavior trajectories, etc into unified token sequences and model them with autoregressive transformers. Thanks to the semantically meaningful behavior tokens, the resulting VLA model, OmniJARVIS, can reason (by producing chain-of-thoughts), plan, answer questions, and act (by producing behavior tokens for the imitation learning policy decoder). OmniJARVIS demonstrates excellent performances on a comprehensive collection of atomic, programmatic, and open-ended tasks in open-world Minecraft. Our analysis further unveils the crucial design principles in interaction data formation, unified tokenization, and its scaling potentials. The dataset, models, and code will be released at https://craftjarvis.org/OmniJARVIS., Comment: accepted on NeurIPS 2024