Search

This paper introduces UI-TARS, a native GUI agent model that solely perceives the screenshots as input and performs human-like interactions (e.g., keyboard and mouse operations). Unlike prevailing agent frameworks that depend on heavily wrapped commercial models (e.g., GPT-4o) with expert-crafted prompts and workflows, UI-TARS is an end-to-end model that outperforms these sophisticated frameworks. Experiments demonstrate its superior performance: UI-TARS achieves SOTA performance in 10+ GUI agent benchmarks evaluating perception, grounding, and GUI task execution. Notably, in the OSWorld benchmark, UI-TARS achieves scores of 24.6 with 50 steps and 22.7 with 15 steps, outperforming Claude (22.0 and 14.9 respectively). In AndroidWorld, UI-TARS achieves 46.6, surpassing GPT-4o (34.5). UI-TARS incorporates several key innovations: (1) Enhanced Perception: leveraging a large-scale dataset of GUI screenshots for context-aware understanding of UI elements and precise captioning; (2) Unified Action Modeling, which standardizes actions into a unified space across platforms and achieves precise grounding and interaction through large-scale action traces; (3) System-2 Reasoning, which incorporates deliberate reasoning into multi-step decision making, involving multiple reasoning patterns such as task decomposition, reflection thinking, milestone recognition, etc. (4) Iterative Training with Reflective Online Traces, which addresses the data bottleneck by automatically collecting, filtering, and reflectively refining new interaction traces on hundreds of virtual machines. Through iterative training and reflection tuning, UI-TARS continuously learns from its mistakes and adapts to unforeseen situations with minimal human intervention. We also analyze the evolution path of GUI agents to guide the further development of this domain.

Task-oriented dialog systems have witnessed substantial progress due to conversational pre-training techniques. Yet, two significant challenges persist. First, most systems primarily utilize the latest turn's state label for the generator. This practice overlooks the comprehensive value of state labels in boosting the model's understanding for future generations. Second, an overreliance on generated policy often leads to error accumulation, resulting in suboptimal responses when adhering to incorrect actions. To combat these challenges, we propose turn-level multi-task objectives for the encoder. With the guidance of essential information from labeled intermediate states, we establish a more robust representation for both understanding and generation. For the decoder, we introduce an action tree-based scheduled sampling technique. Specifically, we model the hierarchical policy as trees and utilize the similarity between trees to sample negative policy based on scheduled sampling, hoping the model to generate invariant responses under perturbations. This method simulates potential pitfalls by sampling similar negative policy, bridging the gap between task-oriented dialog training and inference. Among methods without continual pre-training, our approach achieved state-of-the-art (SOTA) performance on the MultiWOZ dataset series and was also competitive with pre-trained SOTA methods., Comment: Accepted by AAAI 2024

We present a family of graphical representations for the O($N$) spin model, where $N \ge 1$ represents the spin dimension, and $N=1,2,3$ corresponds to the Ising, XY and Heisenberg models, respectively. With an integer parameter $0 \le \ell \le N/2$, each configuration is the coupling of $\ell$ copies of subgraphs consisting of directed flows and $N -2\ell$ copies of subgraphs constructed by undirected loops, which we call the XY and Ising subgraphs, respectively. On each lattice site, the XY subgraphs satisfy the Kirchhoff flow-conservation law and the Ising subgraphs obey the Eulerian bond condition. Then, we formulate worm-type algorithms and simulate the O($N$) model on the simple-cubic lattice for $N$ from 2 to 6 at all possible $\ell$. It is observed that the worm algorithm has much higher efficiency than the Metropolis method, and, for a given $N$, the efficiency is an increasing function of $\ell$. Beside Monte Carlo simulations, we expect that these graphical representations would provide a convenient basis for the study of the O($N$) spin model by other state-of-the-art methods like the tensor network renormalization., Comment: 10 pages, 6 figures

Training machines to understand natural language and interact with humans is one of the major goals of artificial intelligence. Recent years have witnessed an evolution from matching networks to pre-trained language models (PrLMs). In contrast to the plain-text modeling as the focus of the PrLMs, dialogue texts involve multiple speakers and reflect special characteristics such as topic transitions and structure dependencies between distant utterances. However, the related PrLM models commonly represent dialogues sequentially by processing the pairwise dialogue history as a whole. Thus the hierarchical information on either utterance interrelation or speaker roles coupled in such representations is not well addressed. In this work, we propose compositional learning for holistic interaction across the utterances beyond the sequential contextualization from PrLMs, in order to capture the utterance-aware and speaker-aware representations entailed in a dialogue history. We decouple the contextualized word representations by masking mechanisms in Transformer-based PrLM, making each word only focus on the words in current utterance, other utterances, and two speaker roles (i.e., utterances of sender and utterances of the receiver), respectively. In addition, we employ domain-adaptive training strategies to help the model adapt to the dialogue domains. Experimental results show that our method substantially boosts the strong PrLM baselines in four public benchmark datasets, achieving new state-of-the-art performance over previous methods., Comment: Accepted by IEEE Transactions on Neural Networks and Learning Systems (TNNLS). Journal extension of arXiv:2009.06504

Angle-differential cross sections for neutron-induced $\alpha$ production in carbon were determined at thirty discrete neutron energy levels ranging from 6.2 to 76 MeV at the Back-n white neutron source of the China Spallation Neutron Source. Utilizing the ${\Delta}E-E$ telescopes within the Light-charged Particle Detector Array spanning angular measurements from 24.5{\deg}to 155.5{\deg} in the laboratory frame, the $^{12}C(n,\alpha)x$ reaction cross sections were obtained. These experimental findings exhibit a strong concordance with prior results and have been benchmarked against theoretical estimates from codes such as TALYS, Geant4, and assessments from the ENDF/B-VIII.0 database. Remarkably, distinct resonance-like features were observed at neutron energies of 13.7, 22.4, 29.5, and 61.8 MeV, marking their first-time identification in the literature.Furthermore, a comparative analysis involving the theoretical Distorted Wave Born Approximation was conducted., Comment: 12 pages,8 figures

A multi-turn dialogue is composed of multiple utterances from two or more different speaker roles. Thus utterance- and speaker-aware clues are supposed to be well captured in models. However, in the existing retrieval-based multi-turn dialogue modeling, the pre-trained language models (PrLMs) as encoder represent the dialogues coarsely by taking the pairwise dialogue history and candidate response as a whole, the hierarchical information on either utterance interrelation or speaker roles coupled in such representations is not well addressed. In this work, we propose a novel model to fill such a gap by modeling the effective utterance-aware and speaker-aware representations entailed in a dialogue history. In detail, we decouple the contextualized word representations by masking mechanisms in Transformer-based PrLM, making each word only focus on the words in current utterance, other utterances, two speaker roles (i.e., utterances of sender and utterances of receiver), respectively. Experimental results show that our method boosts the strong ELECTRA baseline substantially in four public benchmark datasets, and achieves various new state-of-the-art performance over previous methods. A series of ablation studies are conducted to demonstrate the effectiveness of our method., Comment: accepted by AAAI 2021

We apply a worm algorithm to simulate the quantum transverse-field Ising model in a path-integral representation of which the expansion basis is taken as the spin component along the external-field direction. In such a representation, a configuration can be regarded as a set of non-intersecting loops constructed by "kinks" for pairwise interactions and spin-down (or -up) imaginary-time segments. The wrapping probability for spin-down loops, a dimensionless quantity characterizing the loop topology on a torus, is observed to exhibit small finite-size corrections and yields a high-precision critical point in two dimensions (2D) as $h_c \! =\! 3.044\, 330(6)$, significantly improving over the existing results and nearly excluding the best one $h_c \! =\! 3.044\, 38 (2)$. At criticality, the fractal dimensions of the loops are estimated as $d_{\ell \downarrow} (1{\rm D}) \! = \! 1.37(1) \! \approx \! 11/8 $ and $d_{\ell \downarrow} (2{\rm D}) \! = \! 1.75 (3)$, consistent with those for the classical 2D and 3D O(1) loop model, respectively. An interesting feature is that in one dimension (1D), both the spin-down and -up loops display the critical behavior in the whole disordered phase ($ 0 \! \leq \! h \! < \! h_c$), having a fractal dimension $d_{\ell} \! = \! 1.750 (7)$ that is consistent with the hull dimension $d_{\rm H} \! = \! 7/4$ for critical 2D percolation clusters. The current worm algorithm can be applied to simulate other quantum systems like hard-core boson models with pairing interactions., Comment: 11 pages, 11 figures

Haldane fractional exclusion statistics (FES) has a long history of intense studies, but its realization in physical systems is rare. Here we study repulsively interacting Bose gases at and near a quantum critical point, and find evidences that such strongly correlated gases obey simple non-mutual FES over a wide range of interaction strengths in both one and two dimensions. Based on exact solutions in one dimension, quantum Monte Carlo simulations and experiments in both dimensions, we show that the thermodynamic properties of these interacting gases, including entropy per particle, density and pressure, are essentially equivalent to those of non-interacting particles with FES. Accordingly, we establish a simple interaction-to-FES mapping that reveals the statistical nature of particle-hole symmetry breaking induced by interaction in such quantum many-body systems. Whereas strongly interacting Bose gases reach full fermionization in one dimension, they exhibit incomplete fermionization in two dimensions. Our results open a route to understanding correlated interacting systems via non-interacting particles with FES in arbitrary dimensions., Comment: There are 4 figures in the main text as well as a supplemental material

The main candidate for the superfluid pathways in solid Helium-4 are dislocations with Burgers vector along the hcp symmetry axis. Here we focus on quantum behavior of a generic edge dislocation which can perform superclimb -- climb supported by the superflow along its core. The role of the long range elastic interactions between jogs is addressed by Monte Carlo simulations. It is found that such interactions do not change qualitatively the phase diagram found without accounting for such forces. Their main effect consists of renormalizing the effective scale determining compressibility of the dislocation in the Tomonaga-Luttinger Liquid phase. It is also found that the quantum rough phase of the dislocation can be well described within the gaussian approximation which features off-diagonal long range order in 1D for the superfluid order parameter along the core., Comment: 9 pages and 7 figures

A compact photoneutron source (PNS), based on an electron linac was designed and constructed to provide required nuclear data for the design of Thorium Molten Salt Reactor (TMSR). Many local shielding are built to reduce the background of neutron and {\gamma} rays, making the location of the time of flight (TOF) detector be fixed at 6.2 m place. Under the existing layout, some physical parameters are very difficult to get by the experiments, while can be obtained by the Monte Carlo simulation method. However, for the deep penetration problem of the neutron and {\gamma} rays transport in the channel of PNS with complex geometry, the normal Monte Carlo method is inefficient since electron transport calculation need a large amount of computing time and neutrons have little contribution to the detector in far-source region. In this work, the subsection method is applied in the simulation for PNS, which divide the simulation process in two steps, recording the neutron and {\gamma} rays information passing through the source window in the first step and adopting the covariance reduction techniques in the second step. The simulated neutron flux and energy spectrum at the TOF detector place with the relative error 1.6% are well agreement with the experimental results, achieving an efficiency 23 times better than the normal method. This method is fast and efficient in predicting the physical parameters, providing a required verification and initiating the foreseen physics experiment., Comment: 10 pages, 7 figures, 2 tables

We report a new scenario of time-of-flight (TOF) technique in which fast neutrons and delayed gamma-ray signals were both recorded in a millisecond time window in harsh environments induced by high-intensity lasers. The delayed gamma signals, arriving far later than the original fast neutron and often being ignored previously, were identified to be the results of radiative captures of thermalized neutrons. The linear correlation between gamma photon number and the fast neutron yield shows that these delayed gamma events can be employed for neutron diagnosis. This method can reduce the detecting efficiency dropping problem caused by prompt high-flux gamma radiation, and provides a new way for neutron diagnosing in high-intensity laser-target interaction experiments.

In order to measure the total cross section for thermal neutrons, a photoneutron source (PNS, phase 1) has been developed for the acquisition of nuclear data for the Thorium Molten Salt Reactor (TMSR) at the Shanghai Institute of Applied Physics (SINAP). PNS is an electron LINAC pulsed neutron facility that uses the time-of-flight (TOF) technique. It records the neutron TOF and identifies neutrons and $\gamma$-rays by using a digital signal processing technique. The background is obtained by using a combination of employing 12.8 cm boron-loaded polyethylene(PEB) (5$\%$ w.t.) to block the flight path and Monte Carlo methods. The neutron total cross sections of natural beryllium are measured in the neutron energy region from 0.007 to 0.1 eV. The present measurement result is compared with the fold Harvey data with the response function of PNS., Comment: 9 pages,10 figures

We discuss how to reveal the massive Goldstone mode, often referred to as the Higgs amplitude mode, near the Superfluid-to-Insulator quantum critical point (QCP) in a system of two-dimensional ultracold bosonic atoms in optical lattices. The spectral function of the amplitude response is obtained by analytic continuation of the kinetic energy correlation function calculated by Monte Carlo methods. Our results enable a direct comparison with the recent experiment [M. Endres, T. Fukuhara, D. Pekker, M. Cheneau, P. Schau{\ss}, C. Gross, E. Demler, S. Kuhr, and I. Bloch, Nature 487, 454-458 (2012)], and demonstrate a good agreement for temperature shifts induced by lattice modulation. Based on our numerical analysis, we formulate the necessary conditions in terms of homogeneity, detuning from the QCP and temperature in order to reveal the massive Goldstone resonance peak in spectral functions experimentally. We also propose to apply a local modulation at the trap center to overcome the inhomogeneous broadening caused by the parabolic trap confinement., Comment: 7 pages, 5 figures

The photoneutron source (PNS, phase 1), an electron linear accelerator (linac)-based pulsed neutron facility that uses the time-of-flight (TOF) technique, was constructed for the acquisition of nuclear data from the thorium molten salt reactor(TMSR) at the Shanghai Institute of Applied Physics (SINAP). The neutron detector signal, with the information on the pulse arrival time, pulse shape, and pulse height, was recorded by using a waveform digitizer (WFD). By using the pulse height and pulse-shape discrimination (PSD) analysis to identify neutrons and $\gamma$-rays, the neutron TOF spectrum was obtained by employing a simple electronic design, and a new WFD-based DAQ system was developed and tested in this commissioning experiment. The developed DAQ system is characterized by a very high efficiency with respect to millisecond neutron TOF spectroscopy, Comment: 5 pages, 7 figures

We compute the universal conductivity of the (2+1)-dimensional XY universality class, which is realized for a superfluid-to-Mott insulator quantum phase transition at constant density. Based on large-scale Monte Carlo simulations of the classical (2+1)-dimensional $J$-current model and the two-dimensional Bose-Hubbard model, we can precisely determine the conductivity on the quantum critical plateau, $\sigma(\infty)=0.359(4)\sigma_Q$ with $\sigma_Q$ the conductivity quantum. The universal conductivity curve is the standard example with the lowest number of components where the bottoms-up AdS/CFT correspondence from string theory can be tested and made to use [R. C. Myers, S. Sachdev, and A. Singh, Phys. Rev. D83, 066017 (2011)]. For the first time, the shape of the $\sigma(i\omega_n)- \sigma(\infty)$ function in the Matsubara representation is accurate enough for a conclusive comparison and establishes the particle-like nature of charge transport. We find that the holographic gauge/gravity duality theory for transport properties can be made compatible with the data if temperature of the horizon of the black brane is different from the temperature of the conformal field theory. The requirements for measuring the universal conductivity in a cold gas experiment are also determined by our calculation., Comment: 8 pages, 12 figures

We present spectral functions for the magnitude squared of the order parameter in the scaling limit of the two-dimensional superfluid to Mott insulator quantum phase transition at constant density, which has emergent particle-hole symmetry and Lorentz invariance. The universal functions for the superfluid, Mott insulator, and normal liquid phases reveal a low-frequency resonance which is relatively sharp and is followed by a damped oscillation (in the first two phases only) before saturating to the quantum critical plateau. The counterintuitive resonance feature in the insulating and normal phases calls for deeper understanding of collective modes in the strongly coupled (2+1)-dimensional relativistic field theory. Our results are derived from analytically continued correlation functions obtained from path-integral Monte Carlo simulations of the Bose-Hubbard model., Comment: 5 pages, 6 figures