Search

Deep Reinforcement Learning (DRL) suffers from uncertainties and inaccuracies in the observation signal in realworld applications. Adversarial attack is an effective method for evaluating the robustness of DRL agents. However, existing attack methods targeting individual sampled actions have limited impacts on the overall policy distribution, particularly in continuous action spaces. To address these limitations, we propose the Distribution-Aware Projected Gradient Descent attack (DAPGD). DAPGD uses distribution similarity as the gradient perturbation input to attack the policy network, which leverages the entire policy distribution rather than relying on individual samples. We utilize the Bhattacharyya distance in DAPGD to measure policy similarity, enabling sensitive detection of subtle but critical differences between probability distributions. Our experiment results demonstrate that DAPGD achieves SOTA results compared to the baselines in three robot navigation tasks, achieving an average 22.03% higher reward drop compared to the best baseline., Comment: 10 pages, 2 figures, 2 tables

For $d\ge 1$, we construct a compact subset $K\subseteq \mathbb {R}^{d+1}$ containing a $d$-sphere of every radius between $1$ and $2$, such that for every $\delta\in (0,1)$, the $\delta$-neighbourhood of $K$ has Lebesgue measure $\lesssim |\log \delta|^{-2/d}$. This is the smallest possible order when $d=2$, and improves a result of Kolasa-Wolff (Pacific J. Math., 190(1):111-154, 1999). Our construction also generalises to Holder-continuous families of $C^{2,\alpha}$ hypersurfaces with nonzero Gaussian curvature., Comment: 17 pages, 2 figures

Recent advancements in LiDAR-Inertial Odometry (LIO) have boosted a large amount of applications. However, traditional LIO systems tend to focus more on localization rather than mapping, with maps consisting mostly of sparse geometric elements, which is not ideal for downstream tasks. Recent emerging neural field technology has great potential in dense mapping, but pure LiDAR mapping is difficult to work on high-dynamic vehicles. To mitigate this challenge, we present a new solution that tightly couples geometric kinematics with neural fields to enhance simultaneous state estimation and dense mapping capabilities. We propose both semi-coupled and tightly coupled Kinematic-Neural LIO (KN-LIO) systems that leverage online SDF decoding and iterated error-state Kalman filtering to fuse laser and inertial data. Our KN-LIO minimizes information loss and improves accuracy in state estimation, while also accommodating asynchronous multi-LiDAR inputs. Evaluations on diverse high-dynamic datasets demonstrate that our KN-LIO achieves performance on par with or superior to existing state-of-the-art solutions in pose estimation and offers improved dense mapping accuracy over pure LiDAR-based methods. The relevant code and datasets will be made available at https://**.

For $1

Compared to human vision, insect visual systems excel at rapid and precise collision detection, despite relying on only tens of thousands of neurons organized through a few neuropils. This efficiency makes them an attractive model system for developing artificial collision-detecting systems. Specifically, researchers have identified collision-selective neurons in the locust's optic lobe, called lobula giant movement detectors (LGMDs), which respond specifically to approaching objects. Research upon LGMD neurons began in the early 1970s. Initially, due to their large size, these neurons were identified as motion detectors, but their role as looming detectors was recognized over time. Since then, progress in neuroscience, computational modeling of LGMD's visual neural circuits, and LGMD-based robotics has advanced in tandem, each field supporting and driving the others. Today, with a deeper understanding of LGMD neurons, LGMD-based models have significantly improved collision-free navigation in mobile robots including ground and aerial robots. This review highlights recent developments in LGMD research from the perspectives of neuroscience, computational modeling, and robotics. It emphasizes a biologically plausible research paradigm, where insights from neuroscience inform real-world applications, which would in turn validate and advance neuroscience. With strong support from extensive research and growing application demand, this paradigm has reached a mature stage and demonstrates versatility across different areas of neuroscience research, thereby enhancing our understanding of the interconnections between neuroscience, computational modeling, and robotics. Furthermore, other motion-sensitive neurons have also shown promising potential for adopting this research paradigm.

Recently, Low Earth Orbit (LEO) satellite networks (i.e., non-terrestrial network (NTN)), such as Starlink, have been successfully deployed to provide broader coverage than terrestrial networks (TN). Due to limited spectrum resources, TN and NTN may soon share the same spectrum. Therefore, fine-grained spectrum monitoring is crucial for spectrum sharing and interference avoidance. To this end, constructing a 4D radio map (RM) including three spatial dimensions and signal spectra is important. However, this requires the large deployment of sensors, and high-speed analog-to-digital converters for extensive spatial signal collection and wide power spectrum acquisition, respectively. To address these challenges, we propose a deep unsupervised learning framework without ground truths labeling requirement, DeepRM, comprised of neural compressive sensing (CS) and tensor decomposition (TD) algorithms. Firstly, we map the CS process into the optimization of a neural networksassociated loss function, and design a sparsity-performance balance training algorithm to reconstruct a wide power spectrum under limited sub-Nquist samples. Secondly, according to the output of neural CS algorithm, we also utilize neural networks to perform TD, and construct the 3D RM for each frequency, even under very sparse sensor deployment. Extensive evaluations show that DeepRM achieves lower error than its corresponding state-of-the-art baselines, especially with limited samples., Comment: 11 pages, 14 figures

Recent JWST observations have revealed the prevalence of spiral structures at $z > 1$. Unlike in the local Universe, the origin and the consequence of spirals at this epoch remain unexplored. We use public JWST/NIRCam data from the COSMOS-Web survey to map spiral structures in eight massive ($> 10^{10.5}\,\rm M_{\odot}$) star-forming galaxies at $z_{\rm spec} \sim 1.5$. We present a method for systematically quantifying spiral arms at $z>1$, enabling direct measurements of flux distributions. Using rest-frame near-IR images, we construct morphological models accurately tracing spiral arms. We detect offsets ($\sim 0.2 - 0.8\,\rm kpc$) between the rest-frame optical and near-IR flux distributions across most arms. Drawing parallels to the local Universe, we conclude that these offsets reflect the presence of density waves. For nine out of eighteen arms, the offsets indicate spiral shocks triggered by density waves. Five arms have offsets in the opposite direction and are likely associated with tidal interactions. For the remaining cases with no detected offsets, we suggest that stochastic 'clumpy' star formation is the primary driver of their formation. In conclusion, we find a multi-faceted nature of spiral arms at $z > 1$, similar to that in the local Universe., Comment: Accepted for publication in ApJ Letters; 12 pages, 6 figures

It is generally thought that AGN optical variability is produced, at least in part, by reprocessing of central X-rays by a surrounding accretion disc, resulting in wavelength-dependent lags between bands. Any good model of AGN optical variability should explain not only these lags, but also the overall pattern of variability as quantified by the power spectral density (PSD). Here we present $\sim$daily g'-band monitoring of the low-mass AGN NGC\,4395 over 3 years. Together with previous TESS and GTC/HiPERCAM observations we produce an optical PSD covering an unprecedented frequency range of $\sim7$ decades allowing excellent determination of PSD parameters. The PSD is well fitted by a bending power law with low-frequency slope $\alpha_{L} = 1.0 \pm 0.2$, high-frequency slope $2.1^{+0.2}_{-0.4}$ and bend timescale $3.0^{+6.6}_{-1.7}\,$\,d. This timescale is close to that derived previously from a damped random walk (DRW) model fitted to just the TESS observations, although $\alpha_{L}$ is too steep to be consistent with a DRW. We compare the observed PSD with one made from light curves synthesized assuming reprocessing of X-rays, as observed by \xmm and Swift, in a disc defined by the observed lags. The simulated PSD is also well described by a bending power law but with a bend two decades higher in frequency. We conclude that the large-amplitude optical variations seen on long-timescales are not due to disc reprocessing but require a second source of variability whose origin is unknown but could be propagating disc accretion rate variations.

The Iterative Closest Point (ICP) algorithm is a crucial component of LiDAR-based SLAM algorithms. However, its performance can be negatively affected in unstructured environments that lack features and geometric structures, leading to low accuracy and poor robustness in localization and mapping. It is known that degeneracy caused by the lack of geometric constraints can lead to errors in 6-DOF pose estimation along ill-conditioned directions. Therefore, there is a need for a broader and more fine-grained degeneracy detection and handling method. This paper proposes a new point cloud registration framework, LP-ICP, that combines point-to-line and point-to-plane distance metrics in the ICP algorithm, with localizability detection and handling. LP-ICP consists of a localizability detection module and an optimization module. The localizability detection module performs localizability analysis by utilizing the correspondences between edge points (with low local smoothness) to lines and planar points (with high local smoothness) to planes between the scan and the map. The localizability contribution of individual correspondence constraints can be applied to a broader range. The optimization module adds additional soft and hard constraints to the optimization equations based on the localizability category. This allows the pose to be constrained along ill-conditioned directions, with updates either tending towards the constraint value or leaving the initial estimate unchanged. This improves accuracy and reduces fluctuations. The proposed method is extensively evaluated through experiments on both simulation and real-world datasets, demonstrating higher or comparable accuracy than the state-of-the-art methods. The dataset and code of this paper will also be open-sourced at https://github.com/xuqingyuan2000/LP-ICP., Comment: 18 Pages, 8 Figures Submitted to IEEE Transactions on Automation Science and Engineering

Collaborative perception significantly enhances autonomous driving safety by extending each vehicle's perception range through message sharing among connected and autonomous vehicles. Unfortunately, it is also vulnerable to adversarial message attacks from malicious agents, resulting in severe performance degradation. While existing defenses employ hypothesis-and-verification frameworks to detect malicious agents based on single-shot outliers, they overlook temporal message correlations, which can be circumvented by subtle yet harmful perturbations in model input and output spaces. This paper reveals a novel blind area confusion (BAC) attack that compromises existing single-shot outlier-based detection methods. As a countermeasure, we propose GCP, a Guarded Collaborative Perception framework based on spatial-temporal aware malicious agent detection, which maintains single-shot spatial consistency through a confidence-scaled spatial concordance loss, while simultaneously examining temporal anomalies by reconstructing historical bird's eye view motion flows in low-confidence regions. We also employ a joint spatial-temporal Benjamini-Hochberg test to synthesize dual-domain anomaly results for reliable malicious agent detection. Extensive experiments demonstrate GCP's superior performance under diverse attack scenarios, achieving up to 34.69% improvements in AP@0.5 compared to the state-of-the-art CP defense strategies under BAC attacks, while maintaining consistent 5-8% improvements under other typical attacks. Code will be released at https://github.com/CP-Security/GCP.git., Comment: 15 pages

This article investigates the critical issue of dataset bias in medical imaging, with a particular emphasis on racial disparities caused by uneven population distribution in dataset collection. Our analysis reveals that medical segmentation datasets are significantly biased, primarily influenced by the demographic composition of their collection sites. For instance, Scanning Laser Ophthalmoscopy (SLO) fundus datasets collected in the United States predominantly feature images of White individuals, with minority racial groups underrepresented. This imbalance can result in biased model performance and inequitable clinical outcomes, particularly for minority populations. To address this challenge, we propose a novel training set search strategy aimed at reducing these biases by focusing on underrepresented racial groups. Our approach utilizes existing datasets and employs a simple greedy algorithm to identify source images that closely match the target domain distribution. By selecting training data that aligns more closely with the characteristics of minority populations, our strategy improves the accuracy of medical segmentation models on specific minorities, i.e., Black. Our experimental results demonstrate the effectiveness of this approach in mitigating bias. We also discuss the broader societal implications, highlighting how addressing these disparities can contribute to more equitable healthcare outcomes.

With the growing significance of network security, the classification of encrypted traffic has emerged as an urgent challenge. Traditional byte-based traffic analysis methods are constrained by the rigid granularity of information and fail to fully exploit the diverse correlations between bytes. To address these limitations, this paper introduces MH-Net, a novel approach for classifying network traffic that leverages multi-view heterogeneous traffic graphs to model the intricate relationships between traffic bytes. The essence of MH-Net lies in aggregating varying numbers of traffic bits into multiple types of traffic units, thereby constructing multi-view traffic graphs with diverse information granularities. By accounting for different types of byte correlations, such as header-payload relationships, MH-Net further endows the traffic graph with heterogeneity, significantly enhancing model performance. Notably, we employ contrastive learning in a multi-task manner to strengthen the robustness of the learned traffic unit representations. Experiments conducted on the ISCX and CIC-IoT datasets for both the packet-level and flow-level traffic classification tasks demonstrate that MH-Net achieves the best overall performance compared to dozens of SOTA methods., Comment: Accepted by AAAI 2025. The code is available at https://github.com/ViktorAxelsen/MH-Net. arXiv admin note: text overlap with arXiv:2402.07501

In doped transition metal dichalcogenides, optically created excitons (bound electron-hole pairs) can strongly interact with a Fermi sea of electrons to form Fermi polaron quasiparticles. When there are two distinct Fermi seas, as is the case in WSe$_2$, there are two flavors of lowest-energy (attractive) polarons -- singlet and triplet -- where the exciton is coupled to the Fermi sea in the same or opposite valley, respectively. Using two-dimensional coherent electronic spectroscopy, we analyze how their quantum decoherence evolves with doping density and determine the condition under which stable Fermi polarons form. Because of the large oscillator strength associated with these resonances, intrinsic quantum dynamics of polarons as well as valley coherence between coupled singlet- and triplet polarons occur on sub-picosecond time scales. Surprisingly, we find that a dark-to-bright state conversion process leads to a particularly long-lived singlet polaron valley polarization, persisting up to 200-800 ps. Valley coherence between the singlet- and triplet polaron is correlated with their energy fluctuations. Our finding provides valuable guidance for the electrical and optical control of spin and valley indexes in atomically thin semiconductors., Comment: 4 pages, 4 figures

Low-altitude mobility, exemplified by unmanned aerial vehicles (UAVs), has introduced transformative advancements across various domains, like transportation, logistics, and agriculture. Leveraging flexible perspectives and rapid maneuverability, UAVs extend traditional systems' perception and action capabilities, garnering widespread attention from academia and industry. However, current UAV operations primarily depend on human control, with only limited autonomy in simple scenarios, and lack the intelligence and adaptability needed for more complex environments and tasks. The emergence of large language models (LLMs) demonstrates remarkable problem-solving and generalization capabilities, offering a promising pathway for advancing UAV intelligence. This paper explores the integration of LLMs and UAVs, beginning with an overview of UAV systems' fundamental components and functionalities, followed by an overview of the state-of-the-art in LLM technology. Subsequently, it systematically highlights the multimodal data resources available for UAVs, which provide critical support for training and evaluation. Furthermore, it categorizes and analyzes key tasks and application scenarios where UAVs and LLMs converge. Finally, a reference roadmap towards agentic UAVs is proposed, aiming to enable UAVs to achieve agentic intelligence through autonomous perception, memory, reasoning, and tool utilization. Related resources are available at https://github.com/Hub-Tian/UAVs_Meet_LLMs.

3D object detection is crucial for Autonomous Driving (AD) and Advanced Driver Assistance Systems (ADAS). However, most 3D detectors prioritize detection accuracy, often overlooking network inference speed in practical applications. In this paper, we propose RadarNeXt, a real-time and reliable 3D object detector based on the 4D mmWave radar point clouds. It leverages the re-parameterizable neural networks to catch multi-scale features, reduce memory cost and accelerate the inference. Moreover, to highlight the irregular foreground features of radar point clouds and suppress background clutter, we propose a Multi-path Deformable Foreground Enhancement Network (MDFEN), ensuring detection accuracy while minimizing the sacrifice of speed and excessive number of parameters. Experimental results on View-of-Delft and TJ4DRadSet datasets validate the exceptional performance and efficiency of RadarNeXt, achieving 50.48 and 32.30 mAPs with the variant using our proposed MDFEN. Notably, our RadarNeXt variants achieve inference speeds of over 67.10 FPS on the RTX A4000 GPU and 28.40 FPS on the Jetson AGX Orin. This research demonstrates that RadarNeXt brings a novel and effective paradigm for 3D perception based on 4D mmWave radar., Comment: 8 pages, 5 figures, 3 tables. Code: https://github.com/Pay246-git468/RadarNeXt

Obesity is defined as the excessive accumulation or abnormal distribution of body fat. According to data from World Obesity Atlas 2024, the increase in prevalence of obesity has become a major worldwide health problem in adults as well as among children and adolescents. Although an increasing number of drugs have been approved for the treatment of obesity in recent years, many of these drugs have inevitable side effects which have increased the demand for new safe, accessible and effective drugs for obesity and prompt interest in natural products. Berberine (BBR) and its metabolites, known for their multiple pharmacological effects. Recent studies have emphatically highlighted the anti-obesity benefits of BBR and the underlying mechanisms have been gradually elucidated. However, its clinical application is limited by poor oral absorption and low bioavailability. Based on this, this review summarizes current research on the anti-obesity effects of BBR and its metabolites, including advancements in clinical trail results, understanding potential molecular mechanisms and absorption and bioavailability. As a natural compound derived from plants, BBR holds potential as an alternative approach for managing obesity., Comment: 54 pages,9 figures

Recommender systems have become increasingly vital in our daily lives, helping to alleviate the problem of information overload across various user-oriented online services. The emergence of Large Language Models (LLMs) has yielded remarkable achievements, demonstrating their potential for the development of next-generation recommender systems. Despite these advancements, LLM-based recommender systems face inherent limitations stemming from their LLM backbones, particularly issues of hallucinations and the lack of up-to-date and domain-specific knowledge. Recently, Retrieval-Augmented Generation (RAG) has garnered significant attention for addressing these limitations by leveraging external knowledge sources to enhance the understanding and generation of LLMs. However, vanilla RAG methods often introduce noise and neglect structural relationships in knowledge, limiting their effectiveness in LLM-based recommendations. To address these limitations, we propose to retrieve high-quality and up-to-date structure information from the knowledge graph (KG) to augment recommendations. Specifically, our approach develops a retrieval-augmented framework, termed K-RagRec, that facilitates the recommendation generation process by incorporating structure information from the external KG. Extensive experiments have been conducted to demonstrate the effectiveness of our proposed method., Comment: Preprint. Under review

Heterogeneous Information Networks (HINs) encapsulate diverse entity and relation types, with meta-paths providing essential meta-level semantics for knowledge reasoning, although their utility is constrained by discovery challenges. While Large Language Models (LLMs) offer new prospects for meta-path discovery due to their extensive knowledge encoding and efficiency, their adaptation faces challenges such as corpora bias, lexical discrepancies, and hallucination. This paper pioneers the mitigation of these challenges by presenting EvoPath, an innovative framework that leverages LLMs to efficiently identify high-quality meta-paths. EvoPath is carefully designed, with each component aimed at addressing issues that could lead to potential knowledge conflicts. With a minimal subset of HIN facts, EvoPath iteratively generates and evolves meta-paths by dynamically replaying meta-paths in the buffer with prioritization based on their scores. Comprehensive experiments on three large, complex HINs with hundreds of relations demonstrate that our framework, EvoPath, enables LLMs to generate high-quality meta-paths through effective prompting, confirming its superior performance in HIN reasoning tasks. Further ablation studies validate the effectiveness of each module within the framework.

Realizing odd-parity, time-reversal-preserving, non-relativistic spin splitting is a central goal for spintronics applications. We propose a group-theory-based microscopic framework to induce odd-parity spin splitting from coplanar antiferromagnetic (AFM) states without spin-orbit coupling (SOC). We develop phenomenological models for 421 conventional period-doubling AFM systems in non-symmorphic space groups and construct minimal microscopic models for 119 of these. We find that these AFM states can attain three possible competing ground states. These ground states all break symmetries in addition to those broken by the usual AFM order. Specifically, they give rise to either odd-parity spin-splitting, nematic order, or scalar odd-parity order related to multiferroicity. Our microscopic theories reveal that the odd-parity spin-splitting energy scale is generically large and further reveal that the scalar odd-parity order gives a non-zero Berry curvature dipole without SOC. We identify 67 materials in the Magndata database for which our theory applies. We provide DFT calculations on FeSe that reveal an $h$-wave spin splitting consistent with our symmetry arguments and apply our microscopic model to determine the non-relativistic Edelstein response for CeNiAsO.

Recent explorations of the cosmic microwave background and the large-scale structure of the universe have indicated a preference for sizable neutrino self-interactions, much stronger than what the Standard Model offers. When interpreted in the context of simple particle-physics models with a light, neutrinophilic scalar mediator, some of the hints are already in tension with the combination of terrestrial, astrophysical and cosmological constraints. We take a novel approach by considering neutrino self-interactions through a mediator with a smooth, continuous, spectral density function. We consider Georgi's unparticle with a mass gap as a concrete example and point out two useful effects for mitigating two leading constraints. 1) The Unparticle is ``broadband'' -- it occupies a wide range of masses which allows it to pass the early universe constraint on effective number of extra neutrinos ($\Delta N_{\rm eff.}$) even if the mass gap lies below the MeV scale. 2) Scattering involving unparticles is less resonant -- which lifts the constraint set by IceCube based on a recent measurement of ultra-high-energy cosmogenic neutrinos. Our analysis shows that an unparticle mediator can open up ample parameter space for strong neutrino self-interactions of interest to cosmology and serves a well-motivated target for upcoming experiments., Comment: 13 pages, 7 figures

We study the finite basis problem for $4$-element additively idempotent semirings whose additive reducts are quasi-antichains. Up to isomorphism, there are $93$ such algebras. We show that with the exception of the semiring $S_{(4, 435)}$, all of them are finitely based.

Topological materials for classical waves offer remarkable potential in applications such as sensing, waveguiding and signal processing, leveraging topological protection effects like strong robustness, immunity to backscattering and unidirectional transmission. This work presents the simultaneous inverse design of pseudospin-dependent topological edge states for acoustic and electromagnetic waves in two-dimensional $C_{\textrm{6v}}$ phoxonic crystals. The phoxonic crystals are created by arranging the silicon columns periodically in the air background. We propose a multi-objective optimization framework based on the NSGA-II collaborated with the finite element approach, where the bandgaps of acoustic and electromagnetic waves are treated separately as the objective values. The topological nature of bandgaps is determined by analyzing the positional relationships of paired degenerate modes through the modal field calculations, enabling the customization of one of the two bandgaps within the same unit cell. Unlike traditional approaches relying on the band inversion to induce topological phase transitions, the proposed approach directly generates a pair of unit cells with distinct topological properties for both wave types, achieving the maximum bandgap matching in each case. We further demonstrate the existence of the pseudospin-dependent topological edge states for both acoustic and electromagnetic waves, verifying their unidirectionality and robustness against backscattering and defects. This work establishes a systematic strategy for customizing phoxonic topological states, offering a new avenue for the inverse design of multi-functional devices based on both sound and light.

Face Anti-Spoofing (FAS) is essential for ensuring the security and reliability of facial recognition systems. Most existing FAS methods are formulated as binary classification tasks, providing confidence scores without interpretation. They exhibit limited generalization in out-of-domain scenarios, such as new environments or unseen spoofing types. In this work, we introduce a multimodal large language model (MLLM) framework for FAS, termed Interpretable Face Anti-Spoofing (I-FAS), which transforms the FAS task into an interpretable visual question answering (VQA) paradigm. Specifically, we propose a Spoof-aware Captioning and Filtering (SCF) strategy to generate high-quality captions for FAS images, enriching the model's supervision with natural language interpretations. To mitigate the impact of noisy captions during training, we develop a Lopsided Language Model (L-LM) loss function that separates loss calculations for judgment and interpretation, prioritizing the optimization of the former. Furthermore, to enhance the model's perception of global visual features, we design a Globally Aware Connector (GAC) to align multi-level visual representations with the language model. Extensive experiments on standard and newly devised One to Eleven cross-domain benchmarks, comprising 12 public datasets, demonstrate that our method significantly outperforms state-of-the-art methods., Comment: Accepted to AAAI2025(Oral)

Theory-of-Mind (ToM) is a fundamental psychological capability that allows humans to understand and interpret the mental states of others. Humans infer others' thoughts by integrating causal cues and indirect clues from broad contextual information, often derived from past interactions. In other words, human ToM heavily relies on the understanding about the backgrounds and life stories of others. Unfortunately, this aspect is largely overlooked in existing benchmarks for evaluating machines' ToM capabilities, due to their usage of short narratives without global backgrounds. In this paper, we verify the importance of understanding long personal backgrounds in ToM and assess the performance of LLMs in such realistic evaluation scenarios. To achieve this, we introduce a novel benchmark, CharToM-QA, comprising 1,035 ToM questions based on characters from classic novels. Our human study reveals a significant disparity in performance: the same group of educated participants performs dramatically better when they have read the novels compared to when they have not. In parallel, our experiments on state-of-the-art LLMs, including the very recent o1 model, show that LLMs still perform notably worse than humans, despite that they have seen these stories during pre-training. This highlights the limitations of current LLMs in capturing the nuanced contextual information required for ToM reasoning., Comment: 17 pages, under review

We introduce EnerVerse, a comprehensive framework for embodied future space generation specifically designed for robotic manipulation tasks. EnerVerse seamlessly integrates convolutional and bidirectional attention mechanisms for inner-chunk space modeling, ensuring low-level consistency and continuity. Recognizing the inherent redundancy in video data, we propose a sparse memory context combined with a chunkwise unidirectional generative paradigm to enable the generation of infinitely long sequences. To further augment robotic capabilities, we introduce the Free Anchor View (FAV) space, which provides flexible perspectives to enhance observation and analysis. The FAV space mitigates motion modeling ambiguity, removes physical constraints in confined environments, and significantly improves the robot's generalization and adaptability across various tasks and settings. To address the prohibitive costs and labor intensity of acquiring multi-camera observations, we present a data engine pipeline that integrates a generative model with 4D Gaussian Splatting (4DGS). This pipeline leverages the generative model's robust generalization capabilities and the spatial constraints provided by 4DGS, enabling an iterative enhancement of data quality and diversity, thus creating a data flywheel effect that effectively narrows the sim-to-real gap. Finally, our experiments demonstrate that the embodied future space generation prior substantially enhances policy predictive capabilities, resulting in improved overall performance, particularly in long-range robotic manipulation tasks., Comment: Website: https://sites.google.com/view/enerverse

Continuous gravitational waves (CWs) emission from neutron stars carries information about their internal structure and equation of state, and it can provide tests of General Relativity. We present a search for CWs from a set of 45 known pulsars in the first part of the fourth LIGO--Virgo--KAGRA observing run, known as O4a. We conducted a targeted search for each pulsar using three independent analysis methods considering the single-harmonic and the dual-harmonic emission models. We find no evidence of a CW signal in O4a data for both models and set upper limits on the signal amplitude and on the ellipticity, which quantifies the asymmetry in the neutron star mass distribution. For the single-harmonic emission model, 29 targets have the upper limit on the amplitude below the theoretical spin-down limit. The lowest upper limit on the amplitude is $6.4\!\times\!10^{-27}$ for the young energetic pulsar J0537-6910, while the lowest constraint on the ellipticity is $8.8\!\times\!10^{-9}$ for the bright nearby millisecond pulsar J0437-4715. Additionally, for a subset of 16 targets we performed a narrowband search that is more robust regarding the emission model, with no evidence of a signal. We also found no evidence of non-standard polarizations as predicted by the Brans-Dicke theory., Comment: main paper: 12 pages, 6 figures, 4 tables

Recently, the increasing deployment of LEO satellite systems has enabled various space analytics (e.g., crop and climate monitoring), which heavily relies on the advancements in deep learning (DL). However, the intermittent connectivity between LEO satellites and ground station (GS) significantly hinders the timely transmission of raw data to GS for centralized learning, while the scaled-up DL models hamper distributed learning on resource-constrained LEO satellites. Though split learning (SL) can be a potential solution to these problems by partitioning a model and offloading primary training workload to GS, the labor-intensive labeling process remains an obstacle, with intermittent connectivity and data heterogeneity being other challenges. In this paper, we propose LEO-Split, a semi-supervised (SS) SL design tailored for satellite networks to combat these challenges. Leveraging SS learning to handle (labeled) data scarcity, we construct an auxiliary model to tackle the training failure of the satellite-GS non-contact time. Moreover, we propose a pseudo-labeling algorithm to rectify data imbalances across satellites. Lastly, an adaptive activation interpolation scheme is devised to prevent the overfitting of server-side sub-model training at GS. Extensive experiments with real-world LEO satellite traces (e.g., Starlink) demonstrate that our LEO-Split framework achieves superior performance compared to state-ofthe-art benchmarks., Comment: 13 pages, 15 figures

Open-vocabulary panoptic reconstruction offers comprehensive scene understanding, enabling advances in embodied robotics and photorealistic simulation. In this paper, we propose PanopticRecon++, an end-to-end method that formulates panoptic reconstruction through a novel cross-attention perspective. This perspective models the relationship between 3D instances (as queries) and the scene's 3D embedding field (as keys) through their attention map. Unlike existing methods that separate the optimization of queries and keys or overlook spatial proximity, PanopticRecon++ introduces learnable 3D Gaussians as instance queries. This formulation injects 3D spatial priors to preserve proximity while maintaining end-to-end optimizability. Moreover, this query formulation facilitates the alignment of 2D open-vocabulary instance IDs across frames by leveraging optimal linear assignment with instance masks rendered from the queries. Additionally, we ensure semantic-instance segmentation consistency by fusing query-based instance segmentation probabilities with semantic probabilities in a novel panoptic head supervised by a panoptic loss. During training, the number of instance query tokens dynamically adapts to match the number of objects. PanopticRecon++ shows competitive performance in terms of 3D and 2D segmentation and reconstruction performance on both simulation and real-world datasets, and demonstrates a user case as a robot simulator. Our project website is at: https://yuxuan1206.github.io/panopticrecon_pp/, Comment: 18 pages, 10 figures

In the face of escalating surveillance and censorship within the cyberspace, the sanctity of personal privacy has come under siege, necessitating the development of steganography, which offers a way to securely hide messages within innocent-looking texts. Previous methods alternate the texts to hide private massages, which is not secure. Large Language Models (LLMs) provide high-quality and explicit distribution, which is an available mathematical tool for secure steganography methods. However, existing attempts fail to achieve high capacity, time efficiency and correctness simultaneously, and their strongly coupling designs leave little room for refining them to achieve better performance. To provide a secure, high-capacity and efficient steganography method, we introduce ShiMer. Specifically, ShiMer pseudorandomly shifts the probability interval of the LLM's distribution to obtain a private distribution, and samples a token according to the private bits. ShiMer produced steganographic texts are indistinguishable in quality from the normal texts directly generated by the language model. To further enhance the capacity of ShiMer, we design a reordering algorithm to minimize the occurrence of interval splitting during decoding phase. Experimental results indicate that our method achieves the highest capacity and efficiency among existing secure steganography techniques.

Both particle physics experiments and cosmological observations have been used to explore neutrino properties. Cosmological researches of neutrinos often rely on the early-universe cosmic microwave background observations or other late-universe probes, which mostly focus on large-scale structures. We introduce a distinct probe, the 21-cm forest, that differs from other probes in both time and scale. Actually, the 21-cm forest is a unique tool for studying small-scale structures in the early universe. Below the free-streaming scale, massive neutrinos suppress the matter power spectrum, influencing small-scale fluctuations in the distribution of matter. The one-dimensional (1D) power spectrum of the 21-cm forest can track these fluctuations across different scales, similar to the matter power spectrum, providing an effective method to probe neutrino mass. Although heating effects in the early universe can also impact the 1D power spectrum of the 21-cm forest, we assess the potential of the 21-cm forest as a tool for measuring neutrino mass, given that the temperature of the intergalactic medium can be constrained using other methods within a certain range. We also discuss the impact of cosmological parameters on our results. In the ideal scenario, the 21-cm forest observation will have the ability to constrain the total neutrino mass to around 0.1 eV. With the accumulation of observational data and advancements in observational technology, the 21-cm forest holds great promise as an emerging and potent tool for measuring neutrino mass., Comment: 8 pages, 4 figures

This Letter reports the precise measurement of reactor antineutrino spectrum and flux based on the full data set of 4.7 million inverse-beta-decay (IBD) candidates collected at Daya Bay near detectors. Expressed in terms of the IBD yield per fission, the antineutrino spectra from all reactor fissile isotopes and the specific $\mathrm{^{235}U}$ and $\mathrm{^{239}Pu}$ isotopes are measured with 1.3$\%$, 3$\%$ and 8$\%$ uncertainties respectively near the 3 MeV spectrum peak in reconstructed energy, reaching the best precision in the world. The total antineutrino flux and isotopic $\mathrm{^{235}U}$ and $\mathrm{^{239}Pu}$ fluxes are precisely measured to be $5.84\pm0.07$, $6.16\pm0.12$ and $4.16\pm0.21$ in units of $10^{-43} \mathrm{cm^2/fission}$. These measurements are compared with the Huber-Mueller (HM) model, the reevaluated conversion model based on the Kurchatov Institute (KI) measurement and the latest Summation Model (SM2023). The Daya Bay flux shows good consistency with KI and SM2023 models, but disagrees with HM model. The Daya Bay spectrum, however, disagrees with all model predictions.

This paper is devoted to order-one explicit approximations of random periodic solutions to multiplicative noise driven stochastic differential equations (SDEs) with non-globally Lipschitz coefficients. The existence of the random periodic solution is demonstrated as the limit of the pull-back of the discretized SDE. A novel approach is introduced to analyze mean-square error bounds of the proposed scheme that does not depend on a prior high-order moment bounds of the numerical approximations. Under mild assumptions, the proposed scheme is proved to achieve an expected order-one mean square convergence in the infinite time horizon. Numerical examples are finally provided to verify the theoretical results.

Biometrics authentication has become increasingly popular due to its security and convenience; however, traditional biometrics are becoming less desirable in scenarios such as new mobile devices, Virtual Reality, and Smart Vehicles. For example, while face authentication is widely used, it suffers from significant privacy concerns. The collection of complete facial data makes it less desirable for privacy-sensitive applications. Lip authentication, on the other hand, has emerged as a promising biometrics method. However, existing lip-based authentication methods heavily depend on static lip shape when the mouth is closed, which can be less robust due to lip shape dynamic motion and can barely work when the user is speaking. In this paper, we revisit the nature of lip biometrics and extract shape-independent features from the lips. We study the dynamic characteristics of lip biometrics based on articulator motion. Building on the knowledge, we propose a system for shape-independent continuous authentication via lip articulator dynamics. This system enables robust, shape-independent and continuous authentication, making it particularly suitable for scenarios with high security and privacy requirements. We conducted comprehensive experiments in different environments and attack scenarios and collected a dataset of 50 subjects. The results indicate that our system achieves an overall accuracy of 99.06% and demonstrates robustness under advanced mimic attacks and AI deepfake attacks, making it a viable solution for continuous biometric authentication in various applications.

The generalized estimating equation (GEE) method is a popular tool for longitudinal data analysis. However, GEE produces biased estimates when the outcome of interest is associated with cluster size, a phenomenon known as informative cluster size (ICS). In this study, we address this issue by formulating the impact of ICS and proposing an integrated approach to mitigate its effects. Our method combines the concept of within-cluster resampling with a penalized quasi-likelihood framework applied to each resampled dataset, ensuring consistency in model selection and estimation. To aggregate the estimators from the resampled datasets, we introduce a penalized mean regression technique, resulting in a final estimator that improves true positive discovery rates while reducing false positives. Simulation studies and an application to yeast cell-cycle gene expression data demonstrate the excellent performance of the proposed penalized quasi-likelihood method via within-cluster resampling.

Polaritons in two-dimensional (2D) materials provide unique opportunities for controlling light at nanoscales. Tailoring these polaritons via gradient polaritonic surfaces with space-variant response can enable versatile light-matter interaction platforms with advanced functionalities. However, experimental progress has been hampered by the optical losses and poor light confinement of conventionally used artificial nanostructures. Here, we demonstrate natural gradient polaritonic surfaces based on superlattices of solitons-localized structural deformations-in a prototypical moire system, twisted bilayer graphene on boron nitride. We demonstrate on-off switching and continuous modulation of local polariton-soliton interactions, which results from marked modifications of topological and conventional soliton states through variation of local strain direction. Furthermore, we reveal the capability of these structures to spatially modify the near-field profile, phase, and propagation direction of polaritons in record-small footprints, enabling generation and electrical switching of directional polaritons. Our findings open up new avenues toward nanoscale manipulation of light-matter interactions and spatial polariton engineering through gradient moire superlattices., Comment: 18 pages, 4 figures

Existing neural methods for the Travelling Salesman Problem (TSP) mostly aim at finding a single optimal solution. To discover diverse yet high-quality solutions for Multi-Solution TSP (MSTSP), we propose a novel deep reinforcement learning based neural solver, which is primarily featured by an encoder-decoder structured policy. Concretely, on the one hand, a Relativization Filter (RF) is designed to enhance the robustness of the encoder to affine transformations of the instances, so as to potentially improve the quality of the found solutions. On the other hand, a Multi-Attentive Adaptive Active Search (MA3S) is tailored to allow the decoders to strike a balance between the optimality and diversity. Experimental evaluations on benchmark instances demonstrate the superiority of our method over recent neural baselines across different metrics, and its competitive performance against state-of-the-art traditional heuristics with significantly reduced computational time, ranging from $1.3\times$ to $15\times$ faster. Furthermore, we demonstrate that our method can also be applied to the Capacitated Vehicle Routing Problem (CVRP).

Retrieval-Augmented Generation (RAG) systems enhance large language models (LLMs) by integrating external knowledge sources, enabling more accurate and contextually relevant responses tailored to user queries. However, these systems remain vulnerable to corpus poisoning attacks that can significantly degrade LLM performance through the injection of malicious content. To address these challenges, we propose TrustRAG, a robust framework that systematically filters compromised and irrelevant contents before they are retrieved for generation. Our approach implements a two-stage defense mechanism: At the first stage, it employs K-means clustering to identify potential attack patterns in retrieved documents using cosine similarity and ROUGE metrics as guidance, effectively isolating suspicious content. Secondly, it performs a self-assessment which detects malicious documents and resolves discrepancies between the model's internal knowledge and external information. TrustRAG functions as a plug-and-play, training-free module that integrates seamlessly with any language model, whether open or closed-source. In addition, TrustRAG maintains high contextual relevance while strengthening defenses against corpus poisoning attacks. Through extensive experimental validation, we demonstrate that TrustRAG delivers substantial improvements in retrieval accuracy, efficiency, and attack resistance compared to existing approaches across multiple model architectures and datasets. We have made TrustRAG available as open-source software at \url{https://github.com/HuichiZhou/TrustRAG}.

High-dimensional longitudinal data have become increasingly prevalent in recent studies, and penalized generalized estimating equations (GEEs) are often used to model such data. However, the desirable properties of the GEE method can break down when the outcome of interest is associated with cluster size, a phenomenon known as informative cluster size. In this article, we address this issue by formulating the effect of informative cluster size and proposing a novel weighted GEE approach to mitigate its impact, while extending the penalized version for high-dimensional settings. We show that the penalized weighted GEE approach achieves consistency in both model selection and estimation. Theoretically, we establish that the proposed penalized weighted GEE estimator is asymptotically equivalent to the oracle estimator, assuming the true model is known. This result indicates that the penalized weighted GEE approach retains the excellent properties of the GEE method and is robust to informative cluster sizes, thereby extending its applicability to highly complex situations. Simulations and a real data application further demonstrate that the penalized weighted GEE outperforms the existing alternative methods.

Large language models (LLMs) have revolutionised numerous fields, with LLM-as-a-service (LLMSaaS) having a strong generalisation ability that offers accessible solutions directly without the need for costly training. In contrast to the widely studied prompt engineering for task solving directly (in vivo), this paper explores its potential in in-vitro applications. These involve using LLM to generate labels to help the supervised training of mainstream models by (1) noisy label correction and (2) training data augmentation with LLM-generated labels. In this paper, we evaluate this approach in the emerging field of empathy computing -- automating the prediction of psychological questionnaire outcomes from inputs like text sequences. Specifically, crowdsourced datasets in this domain often suffer from noisy labels that misrepresent underlying empathy. By leveraging LLM-generated labels to train pre-trained language models (PLMs) like RoBERTa, we achieve statistically significant accuracy improvements over baselines, achieving a state-of-the-art Pearson correlation coefficient of 0.648 on NewsEmp benchmarks. In addition, we bring insightful discussions, including current challenges in empathy computing, data biases in training data and evaluation metric selection. Code and LLM-generated data are available at https://github.com/hasan-rakibul/LLMPathy (available once the paper is accepted)., Comment: This work has been submitted to the IEEE for possible publication

We present STORM, a spatio-temporal reconstruction model designed for reconstructing dynamic outdoor scenes from sparse observations. Existing dynamic reconstruction methods often rely on per-scene optimization, dense observations across space and time, and strong motion supervision, resulting in lengthy optimization times, limited generalization to novel views or scenes, and degenerated quality caused by noisy pseudo-labels for dynamics. To address these challenges, STORM leverages a data-driven Transformer architecture that directly infers dynamic 3D scene representations--parameterized by 3D Gaussians and their velocities--in a single forward pass. Our key design is to aggregate 3D Gaussians from all frames using self-supervised scene flows, transforming them to the target timestep to enable complete (i.e., "amodal") reconstructions from arbitrary viewpoints at any moment in time. As an emergent property, STORM automatically captures dynamic instances and generates high-quality masks using only reconstruction losses. Extensive experiments on public datasets show that STORM achieves precise dynamic scene reconstruction, surpassing state-of-the-art per-scene optimization methods (+4.3 to 6.6 PSNR) and existing feed-forward approaches (+2.1 to 4.7 PSNR) in dynamic regions. STORM reconstructs large-scale outdoor scenes in 200ms, supports real-time rendering, and outperforms competitors in scene flow estimation, improving 3D EPE by 0.422m and Acc5 by 28.02%. Beyond reconstruction, we showcase four additional applications of our model, illustrating the potential of self-supervised learning for broader dynamic scene understanding., Comment: Project page at: https://jiawei-yang.github.io/STORM/

Synthesizing photo-realistic visual observations from an ego vehicle's driving trajectory is a critical step towards scalable training of self-driving models. Reconstruction-based methods create 3D scenes from driving logs and synthesize geometry-consistent driving videos through neural rendering, but their dependence on costly object annotations limits their ability to generalize to in-the-wild driving scenarios. On the other hand, generative models can synthesize action-conditioned driving videos in a more generalizable way but often struggle with maintaining 3D visual consistency. In this paper, we present DreamDrive, a 4D spatial-temporal scene generation approach that combines the merits of generation and reconstruction, to synthesize generalizable 4D driving scenes and dynamic driving videos with 3D consistency. Specifically, we leverage the generative power of video diffusion models to synthesize a sequence of visual references and further elevate them to 4D with a novel hybrid Gaussian representation. Given a driving trajectory, we then render 3D-consistent driving videos via Gaussian splatting. The use of generative priors allows our method to produce high-quality 4D scenes from in-the-wild driving data, while neural rendering ensures 3D-consistent video generation from the 4D scenes. Extensive experiments on nuScenes and street view images demonstrate that DreamDrive can generate controllable and generalizable 4D driving scenes, synthesize novel views of driving videos with high fidelity and 3D consistency, decompose static and dynamic elements in a self-supervised manner, and enhance perception and planning tasks for autonomous driving., Comment: Project page: https://pointscoder.github.io/DreamDrive/

Loop I/North Polar Spur (NPS) is the giant arc structure above the Galactic plane observed in radio sky. There is a long-standing debate about its origin. While many people believe it is created by nearby supernova remnants (SNRs), some others consider it is a giant bubble close to the Galactic Center (GC), associated with the Fermi Bubble and eROSITA X-ray bubble. In ultralong wavelength band (wavelength $\gtrsim 10$ m or frequency $\lesssim 30$ MHz), particularly below $\sim 10$ MHz, the free-free absorption of radio signal by the diffuse electrons in interstellar medium (ISM) becomes significant, resulting in sky morphology largely differs from higher frequencies. In this paper, we predict the Loop I/NPS morphology at ultralong wavelength band. We develop emissivity models for the two Loop I/NPS origin scenarios. We find that: For SNR model, the full Loop I/NPS is still a bright arc even at frequency as low as $\sim 1$ MHz. In GC model, while above $\sim 3$ MHz it is still visible; below this frequency it is visible only at Galactic latitude $b\gtrsim 30\degree$. At $b\lesssim 30 \degree$ the Loop I/NPS is invisible due to the absorption by ISM electrons between the GC and the Sun. Upcoming space ultralong wavelentgh projects such as DSL and FARSIDE can potentially distinguish these two scenarios and provide decisive information about the origin of Loop I/NPS., Comment: 11 pages,5 figures

This paper investigates the problem of understanding dynamic 3D scenes from egocentric observations, a key challenge in robotics and embodied AI. Unlike prior studies that explored this as long-form video understanding and utilized egocentric video only, we instead propose an LLM-based agent, Embodied VideoAgent, which constructs scene memory from both egocentric video and embodied sensory inputs (e.g. depth and pose sensing). We further introduce a VLM-based approach to automatically update the memory when actions or activities over objects are perceived. Embodied VideoAgent attains significant advantages over counterparts in challenging reasoning and planning tasks in 3D scenes, achieving gains of 4.9% on Ego4D-VQ3D, 5.8% on OpenEQA, and 11.7% on EnvQA. We have also demonstrated its potential in various embodied AI tasks including generating embodied interactions and perception for robot manipulation. The code and demo will be made public., Comment: project page: https://embodied-videoagent.github.io/

In recent years, Convolutional Neural Networks (CNNs) have been widely adopted in computer vision. Complex CNN architecture running on CPU or GPU has either insufficient throughput or prohibitive power consumption. Hence, there is a need to have dedicated hardware to accelerate the computation workload to solve these limitations. In this paper, we accelerate a CNN for image classification with the CIFAR-10 dataset using Vitis-AI on Xilinx Zynq UltraScale+ MPSoC ZCU104 FPGA evaluation board. The work achieves 3.33-5.82x higher throughput and 3.39-6.30x higher energy efficiency than CPU and GPU baselines. It shows the potential to extract 2D features for downstream tasks, such as depth estimation and 3D reconstruction.

Event cameras are biologically inspired sensors that emit events asynchronously with remarkable temporal resolution, garnering significant attention from both industry and academia. Mainstream methods favor frame and voxel representations, which reach a satisfactory performance while introducing time-consuming transformation, bulky models, and sacrificing fine-grained temporal information. Alternatively, Point Cloud representation demonstrates promise in addressing the mentioned weaknesses, but it ignores the polarity information, and its models have limited proficiency in abstracting long-term events' features. In this paper, we propose a frequency-aware network named FECNet that leverages Event Cloud representations. FECNet fully utilizes 2S-1T-1P Event Cloud by innovating the event-based Group and Sampling module. To accommodate the long sequence events from Event Cloud, FECNet embraces feature extraction in the frequency domain via the Fourier transform. This approach substantially extinguishes the explosion of Multiply Accumulate Operations (MACs) while effectively abstracting spatial-temporal features. We conducted extensive experiments on event-based object classification, action recognition, and human pose estimation tasks, and the results substantiate the effectiveness and efficiency of FECNet., Comment: Under Review

Vertically parametrised polynomial systems are a particular nice class of parametrised polynomial systems for which a lot of interesting algebraic information is encoded in its combinatorics. Given a fixed polynomial system, we empirically study what constitutes a good vertically parametrised polynomial system that gives rise to it and how to construct said vertically parametrised polynomial system. For data, we use all polynomial systems in ODEbase, which we have transcribed to an OSCAR readable format, and made available as a Julia package OscarODEbase., Comment: 14 pages, 3 figures

In this letter, we have used a non-unitary mixing scheme to resolve the tension between NO$\nu$A and T2K data. It is demonstrated that the results of NO$\nu$A and T2K can be explained by the effects by non-unitary mixing arising from $\alpha_{00}$ and $\alpha_{10}$. For $\alpha_{00}$ there is a large overlap between the allowed NO$\nu$A and T2K regions for NH on the $\sin^2\theta_{23}-\delta_{\rm CP}$ plane at $1\,\sigma$. However, the tension still exists. NO$\nu$A rules out unitary mixing at a $3\,\sigma$ level, whereas T2K strongly prefers unitary mixing. For $\alpha_{10}$, the tension can be \textbf{well resolved} with the best-fit point for NH at $|\alpha_{10}|=0.06$ for both experiments., Comment: 9 pages, 8 figures, 2 tables

This paper provides a comprehensive review of the design and implementation of automatically generated assessment reports (AutoRs) for formative use in K-12 Science, Technology, Engineering, and Mathematics (STEM) classrooms. With the increasing adoption of technology-enhanced assessments, there is a critical need for human-computer interactive tools that efficiently support the interpretation and application of assessment data by teachers. AutoRs are designed to provide synthesized, interpretable, and actionable insights into students' performance, learning progress, and areas for improvement. Guided by cognitive load theory, this study emphasizes the importance of reducing teachers' cognitive demands through user-centered and intuitive designs. It highlights the potential of diverse information presentation formats such as text, visual aids, and plots and advanced functionalities such as live and interactive features to enhance usability. However, the findings also reveal that many existing AutoRs fail to fully utilize these approaches, leading to high initial cognitive demands and limited engagement. This paper proposes a conceptual framework to inform the design, implementation, and evaluation of AutoRs, balancing the trade-offs between usability and functionality. The framework aims to address challenges in engaging teachers with technology-enhanced assessment results, facilitating data-driven decision-making, and providing personalized feedback to improve the teaching and learning process., Comment: Submitted to ETRD

Multimodal large language models (MLLMs) have achieved significant advancements in integrating visual and linguistic understanding. While existing benchmarks evaluate these models in context-rich, real-life scenarios, they often overlook fundamental perceptual skills essential for environments deviating from everyday realism. In particular, geometric perception, the ability to interpret spatial relationships and abstract visual patterns, remains underexplored. To address this limitation, we introduce GePBench, a novel benchmark designed to assess the geometric perception capabilities of MLLMs. Results from extensive evaluations reveal that current state-of-the-art MLLMs exhibit significant deficiencies in such tasks. Additionally, we demonstrate that models trained with data sourced from GePBench show notable improvements on a wide range of downstream tasks, underscoring the importance of geometric perception as a foundation for advanced multimodal applications. Our code and datasets will be publicly available.

The placement problem in very large-scale integration (VLSI) is a critical step in chip design, the goal of which is to optimize the wirelength of circuit components within a confined area while adhering to non-overlapping constraints. Most analytical placement models often rely on smooth approximations, thereby sacrificing the accuracy of wirelength estimation. To mitigate these inaccuracies, this paper introduces a novel approach that directly optimizes the original nonsmooth wirelength and proposes an innovative penalty model tailored for the global placement problem. Specifically, we transform the non-overlapping constraints into rectified linear penalty functions, allowing for a more precise formulation of the problem. Notably, we reformulate the resultant optimization problem into an equivalent framework resembling deep neural network training. Leveraging automatic differentiation techniques from deep learning, we efficiently compute the subgradient of the objective function, thus facilitating the application of stochastic subgradient methods to solve the model. To enhance the algorithm's performance, several advanced techniques are further introduced, leading to significant improvements in both efficiency and solution quality. Numerical experiments conducted on GSRC benchmark circuits demonstrate that our proposed model and algorithm achieve significant reductions in wirelength while effectively eliminating overlaps, highlighting its potential as a transformative advancement for large-scale VLSI placement., Comment: 22pages, 9 figures