arXiv subjects

Jie Zhou

Publications and source records attributed to Jie Zhou.

At least 199 records · Page 11Linked to original sources

arXiv2025

SVG-T2I: Scaling Up Text-to-Image Latent Diffusion Model Without Variational Autoencoder

Visual generation grounded in Visual Foundation Model (VFM) representations offers a highly promising unified pathway for integrating visual understanding, perception, and generation. Despite this potential, training large-scale text-to-image diffusion models entirely within the VFM representation space remains largely unexplored. To bridge this gap, we scale the SVG (Self-supervised representations for Visual Generation) framework, proposing SVG-T2I to support high-quality text-to-image synthesis directly in the VFM feature domain. By leveraging a standard text-to-image diffusion pipeline, SVG-T2I achieves competitive performance, reaching 0.75 on GenEval and 85.78 on DPG-Bench. This performance validates the intrinsic representational power of VFMs for generative tasks. We fully open-source the project, including the autoencoder and generation model, together with their training, inference, evaluation pipelines, and pre-trained weights, to facilitate further research in representation-driven visual generation.

cs.CV↗

arXiv2025

Nex-N1: Agentic Models Trained via a Unified Ecosystem for Large-Scale Environment Construction

The evolution of Large Language Models (LLMs) from passive responders to autonomous agents necessitates a fundamental shift in learning paradigms -- from static imitation to incentive-driven decision making. However, this transition is significantly impeded by the lack of scalable infrastructure capable of constructing high-quality interaction signals for effective policy learning. To address this, we introduce a comprehensive method designed to systematically scale the diversity and complexity of interactive environments. Our method realizes this scaling by addressing three orthogonal dimensions: (1) Complexity: NexAU, a flexible agent framework that supports building complex agent hierarchies via simple configurations; (2) Diversity: NexA4A automatically generates diverse agent hierarchies from natural language to cover infinite domains; and (3) Fidelity: NexGAP bridges the simulation-reality gap by integrating dynamic real-world environment for grounded trajectories synthesis. We train Nex-N1 upon the diverse and complex interactive environments established by our infrastructure. Empirical results on benchmarks such as SWE-bench and tau2 demonstrate that Nex-N1 consistently outperforms SOTA open-source models and achieves competitive performance against frontier proprietary models on complex agentic tasks. We open-source the Nex ecosystem and model weights to facilitate further research.

cs.CL↗

arXiv2025

RDTF: Resource-efficient Dual-mask Training Framework for Multi-frame Animated Sticker Generation

Recently, significant advancements have been achieved in video generation technology, but applying it to resource-constrained downstream tasks like multi-frame animated sticker generation (ASG) characterized by low frame rates, abstract semantics, and long tail frame length distribution-remains challenging. Parameter-efficient fine-tuning (PEFT) techniques (e.g., Adapter, LoRA) for large pre-trained models suffer from insufficient fitting ability and source-domain knowledge interference. In this paper, we propose Resource-Efficient Dual-Mask Training Framework (RDTF), a dedicated solution for multi-frame ASG task under resource constraints. We argue that training a compact model from scratch with million-level samples outperforms PEFT on large models, with RDTF realizing this via three core designs: 1) a Discrete Frame Generation Network (DFGN) optimized for low-frame-rate ASG, ensuring parameter efficiency; 2) a dual-mask based data utilization strategy to enhance the availability and diversity of limited data; 3) a difficulty-adaptive curriculum learning method that decomposes sample entropy into static and adaptive components, enabling easy-to-difficult training convergence. To provide high-quality data support for RDTFs training from scratch, we construct VSD2M-a million-level multi-modal animated sticker dataset with rich annotations (static and animated stickers, action-focused text descriptions)-filling the gap of dedicated animated data for ASG task. Experiments demonstrate that RDTF is quantitatively and qualitatively superior to state-of-the-art PEFT methods (e.g., I2V-Adapter, SimDA) on ASG tasks, verifying the feasibility of our framework under resource constraints.

cs.MM↗

arXiv2025

Point3R: Streaming 3D Reconstruction with Explicit Spatial Pointer Memory

Dense 3D scene reconstruction from an ordered sequence or unordered image collections is a critical step when bringing research in computer vision into practical scenarios. Following the paradigm introduced by DUSt3R, which unifies an image pair densely into a shared coordinate system, subsequent methods maintain an implicit memory to achieve dense 3D reconstruction from more images. However, such implicit memory is limited in capacity and may suffer from information loss of earlier frames. We propose Point3R, an online framework targeting dense streaming 3D reconstruction. To be specific, we maintain an explicit spatial pointer memory directly associated with the 3D structure of the current scene. Each pointer in this memory is assigned a specific 3D position and aggregates scene information nearby in the global coordinate system into a changing spatial feature. Information extracted from the latest frame interacts explicitly with this pointer memory, enabling dense integration of the current observation into the global coordinate system. We design a 3D hierarchical position embedding to promote this interaction and design a simple yet effective fusion mechanism to ensure that our pointer memory is uniform and efficient. Our method achieves competitive or state-of-the-art performance on various tasks with low training costs. Code: https://github.com/YkiWu/Point3R.

cs.CV↗

arXiv2025

Quantitative Stability of the Clifford Torus as a Willmore Minimizer

For an integral $2$-varifold $V\subset \mathbb{S}^3$ with square-integrable mean curvature, unit density, and support of genus at least $1$, assume that its Willmore energy satisfies \[ \mathcal{W}(V)\le 2π^2+δ^2,\qquad δ<δ_0\ll1. \] We show that the support $Σ=\operatorname{spt}V$ is, after applying a suitable conformal transformation of $\mathbb{S}^3$, quantitatively close to the Clifford torus. More precisely, under an appropriate conformal normalization, the surface $Σ$ admits a $W^{2,2}$ conformal parametrization by the flat torus whose conformal factor and metric coefficients differ from those of the Clifford torus by at most $Cδ$.

math.DG↗

arXiv2025

Efficient Covariance Estimation for Sparsified Functional Data

Motivated by recent work involving the analysis of leveraging spatial correlations in sparsified mean estimation, we present a novel procedure for constructing covariance estimator. The proposed Random-knots (Random-knots-Spatial) and B-spline (Bspline-Spatial) estimators of the covariance function are computationally efficient. Asymptotic pointwise of the covariance are obtained for sparsified individual trajectories under some regularity conditions. Our proposed nonparametric method well perform the functional principal components analysis for the case of sparsified data, where the number of repeated measurements available per subject is small. In contrast, classical functional data analysis requires a large number of regularly spaced measurements per subject. Model selection techniques, such as the Akaike information criterion, are used to choose the model dimension corresponding to the number of eigenfunctions in the model. Theoretical results are illustrated with Monte Carlo simulation experiments. Finally, we cluster multi-domain data by replacing the covariance function with our proposed covariance estimator during PCA.

stat.ME↗

arXiv2025

BiFingerPose: Bimodal Finger Pose Estimation for Touch Devices

Finger pose offers promising opportunities to expand human computer interaction capability of touchscreen devices. Existing finger pose estimation algorithms that can be implemented in portable devices predominantly rely on capacitive images, which are currently limited to estimating pitch and yaw angles and exhibit reduced accuracy when processing large-angle inputs (especially when it is greater than 45 degrees). In this paper, we propose BiFingerPose, a novel bimodal based finger pose estimation algorithm capable of simultaneously and accurately predicting comprehensive finger pose information. A bimodal input is explored, including a capacitive image and a fingerprint patch obtained from the touchscreen with an under-screen fingerprint sensor. Our approach leads to reliable estimation of roll angle, which is not achievable using only a single modality. In addition, the prediction performance of other pose parameters has also been greatly improved. The evaluation of a 12-person user study on continuous and discrete interaction tasks further validated the advantages of our approach. Specifically, BiFingerPose outperforms previous SOTA methods with over 21% improvement in prediction performance, 2.5 times higher task completion efficiency, and 23% better user operation accuracy, demonstrating its practical superiority. Finally, we delineate the application space of finger pose with respect to enhancing authentication security and improving interactive experiences, and develop corresponding prototypes to showcase the interaction potential. Our code will be available at https://github.com/XiongjunGuan/DualFingerPose.

cs.CV↗

arXiv2025

Conan: Progressive Learning to Reason Like a Detective over Multi-Scale Visual Evidence

Video reasoning, which requires multi-step deduction across frames, remains a major challenge for multimodal large language models (MLLMs). While reinforcement learning (RL)-based methods enhance reasoning capabilities, they often rely on text-only chains that yield ungrounded or hallucinated conclusions. Conversely, frame-retrieval approaches introduce visual grounding, yet still struggle with inaccurate evidence localization. To address these limitations, we present Conan, a framework for evidence-grounded multi-step video reasoning. Conan identifies context and evidence frames, reasons over cross-frame clues, and adaptively decides when to conclude or explore further. To achieve this, we 1) construct Conan-91K, a large-scale dataset of automatically generated reasoning traces that include frame identification, evidence reasoning, and action decision, and 2) design a multi-stage progressive cold-start strategy combined with an Identification-Reasoning-Action (AIR) RLVR training framework to progressively incentivize multi-step visual reasoning. Extensive experiments on six multi-step reasoning benchmarks demonstrate that Conan surpasses the baseline Qwen2.5-VL-7B-Instruct by an average of over 10% in accuracy, achieving state-of-the-art performance. Furthermore, Conan generalizes effectively to long video understanding tasks, validating its strong scalability and robustness.

cs.CV↗

arXiv2025

Identifying the $3$-qubit $W$ state with quantum uncertainty relation

The $W$ state, a canonical representative of multipartite quantum entanglement, plays a crucial role in quantum information science due to its robust entanglement properties. Quantum uncertainty relations, on the other hand, are a fundamental cornerstone of quantum mechanics. This paper introduces a novel approach to Identifying tripartite $W$ states by leveraging tripartite quantum uncertainty relations. By employing a specific set of non-commuting observables, we formulate an uncertainty-based criterion for identifying $W$ states and rigorously demonstrate its generality in distinguishing them from other tripartite entangled states, such as the Greenberger-Horne-Zeilinger state. Our approach bypasses the need for complete quantum state tomography, as it requires only the verification of a set of uncertainty inequalities for efficient $W$-state identification. This work provides a new theoretical tool for identifying multipartite entangled states and underscores the significant role of quantum uncertainty relations in entanglement characterization.

quant-ph↗

arXiv2025

ComoRAG: A Cognitive-Inspired Memory-Organized RAG for Stateful Long Narrative Reasoning

Narrative comprehension on long stories and novels has been a challenging domain attributed to their intricate plotlines and entangled, often evolving relations among characters and entities. Given the LLM's diminished reasoning over extended context and its high computational cost, retrieval-based approaches remain a pivotal role in practice. However, traditional RAG methods could fall short due to their stateless, single-step retrieval process, which often overlooks the dynamic nature of capturing interconnected relations within long-range context. In this work, we propose ComoRAG, holding the principle that narrative reasoning is not a one-shot process, but a dynamic, evolving interplay between new evidence acquisition and past knowledge consolidation, analogous to human cognition on reasoning with memory-related signals in the brain. Specifically, when encountering a reasoning impasse, ComoRAG undergoes iterative reasoning cycles while interacting with a dynamic memory workspace. In each cycle, it generates probing queries to devise new exploratory paths, then integrates the retrieved evidence of new aspects into a global memory pool, thereby supporting the emergence of a coherent context for the query resolution. Across four challenging long-context narrative benchmarks (200K+ tokens), ComoRAG outperforms strong RAG baselines with consistent relative gains up to 11% compared to the strongest baseline. Further analysis reveals that ComoRAG is particularly advantageous for complex queries requiring global context comprehension, offering a principled, cognitively motivated paradigm towards retrieval-based stateful reasoning. Our framework is made publicly available at https://github.com/EternityJune25/ComoRAG.

cs.CL↗

arXiv2025

Dissecting Long-Chain-of-Thought Reasoning Models: An Empirical Study

Despite recent progress in training long-chain-of-thought reasoning models via scaling reinforcement learning (RL), its underlying training dynamics remain poorly understood, and several counterintuitive behaviors persist. This work focuses on three key aspects: (1) We systematically analyze the roles of positive and negative samples in scaling RL, revealing that positive samples mainly facilitate precise fitting to the training data, whereas negative samples significantly enhance generalization and robustness. Interestingly, while positive samples are essential for convergence in the zero-RL setting, training on negative samples alone suffices to attain strong reasoning performance and even better generalization in cold-start scenarios. (2) We identify substantial data inefficiency in group relative policy optimization, where over half of the samples yield zero advantage. To address this, we explore two strategies, including relative length rewards and offline sample injection, to leverage these data better and enhance reasoning efficiency and capability. (3) We investigate unstable performance across various reasoning models and benchmarks, attributing instability to uncertain problems with ambiguous outcomes, and demonstrate that greedy decoding can distort evaluation by flipping the correctness of responses. Our code is available at: https://github.com/takagi97/Dissect-Long-Reason-Models.

cs.LG↗

arXiv2025

A Lightweight Complex-Valued Deformable CNN for High-Quality Computer-Generated Holography

Holographic displays have significant potential in virtual reality and augmented reality owing to their ability to provide all the depth cues. Deep learning-based methods play an important role in computer-generated holography (CGH). During the diffraction process, each pixel exerts an influence on the reconstructed image. However, previous works face challenges in capturing sufficient information to accurately model this process, primarily due to the inadequacy of their effective receptive field (ERF). Here, we designed complex-valued deformable convolution for integration into network, enabling dynamic adjustment of the convolution kernel's shape to increase flexibility of ERF for better feature extraction. This approach allows us to utilize a single model while achieving state-of-the-art performance in both simulated and optical experiment reconstructions, surpassing existing open-source models. Specifically, our method has a peak signal-to-noise ratio that is 2.04 dB, 5.31 dB, and 9.71 dB higher than that of CCNN-CGH, HoloNet, and Holo-encoder, respectively, when the resolution is 1920$\times$1072. The number of parameters of our model is only about one-eighth of that of CCNN-CGH.

physics.optics↗

arXiv2025

Continuous Autoregressive Language Models

The efficiency of large language models (LLMs) is fundamentally limited by their sequential, token-by-token generation process. We argue that overcoming this bottleneck requires a new design axis for LLM scaling: increasing the semantic bandwidth of each generative step. To this end, we introduce Continuous Autoregressive Language Models (CALM), a paradigm shift from discrete next-token prediction to continuous next-vector prediction. CALM uses a high-fidelity autoencoder to compress a chunk of K tokens into a single continuous vector, from which the original tokens can be reconstructed with over 99.9\% accuracy. This allows us to model language as a sequence of continuous vectors instead of discrete tokens, which reduces the number of generative steps by a factor of K. The paradigm shift necessitates a new modeling toolkit; therefore, we develop a comprehensive likelihood-free framework that enables robust training, evaluation, and controllable sampling in the continuous domain. Experiments show that CALM significantly improves the performance-compute trade-off, achieving the performance of strong discrete baselines at a significantly lower computational cost. More importantly, these findings establish next-vector prediction as a powerful and scalable pathway towards ultra-efficient language models. Code: https://github.com/shaochenze/calm. Project: https://shaochenze.github.io/blog/2025/CALM.

cs.CL↗

arXiv2025

Preliminary Demonstration of Diamond-GaN pn Diodes via Grafting

Ultrawide bandgap (UWBG) semiconductors exhibit exceptional electrical and thermal properties, offering strong potential for high power and high frequency electronics. However, efficient doping in UWBG materials is typically limited to either n type or p type, constraining their application to unipolar devices. The realization of pn junctions through heterogeneous integration of complementary UWBG or WBG semiconductors is hindered by lattice mismatch and thermal expansion differences. Here, we report the preliminary demonstration of diamond GaN heterojunction pn diodes fabricated via grafting. A single crystalline p plus diamond nanomembrane was integrated onto an epitaxially grown c plane n plus GaN substrate with an ultrathin ALD Al2O3 interlayer. The resulting diodes exhibit an ideality factor of 1.55 and a rectification ratio of over 1e4. Structural and interfacial properties were examined by AFM, XRD, Raman, and STEM, providing critical insights to guide further optimization of diamond GaN pn heterojunction devices.

cond-mat.mtrl-sci↗

arXiv2025

Efficient Speech Language Modeling via Energy Distance in Continuous Latent Space

We introduce SLED, an alternative approach to speech language modeling by encoding speech waveforms into sequences of continuous latent representations and modeling them autoregressively using an energy distance objective. The energy distance offers an analytical measure of the distributional gap by contrasting simulated and target samples, enabling efficient training to capture the underlying continuous autoregressive distribution. By bypassing reliance on residual vector quantization, SLED avoids discretization errors and eliminates the need for the complicated hierarchical architectures common in existing speech language models. It simplifies the overall modeling pipeline while preserving the richness of speech information and maintaining inference efficiency. Empirical results demonstrate that SLED achieves strong performance in both zero-shot and streaming speech synthesis, showing its potential for broader applications in general-purpose speech language models.

cs.CL↗

arXiv2025

Cross-layer Attention Sharing for Pre-trained Large Language Models

To enhance the efficiency of the attention mechanism within large language models (LLMs), previous works primarily compress the KV cache or group attention heads, while largely overlooking redundancy between layers. Our comprehensive analyses across various LLMs show that highly similar attention patterns persist within most layers. It's intuitive to reduce the redundancy by sharing attention weights across layers. However, further analysis reveals two challenges: (1) Directly sharing the weight matrix without carefully rearranging the attention heads proves to be ineffective; (2) Shallow layers are vulnerable to small deviations in attention weights. Driven by these insights, we introduce LISA, a lightweight substitute for self-attention in well-trained LLMs. LISA employs tiny feed-forward networks to align attention heads between adjacent layers and low-rank matrices to approximate differences in layer-wise attention weights. Evaluations encompassing 13 typical benchmarks demonstrate that LISA maintains high response quality in terms of accuracy and perplexity while reducing redundant attention calculations within 53%-84% of the total layers. Our implementations of LISA achieve a 6x compression of Q and K matrices within the attention mechanism, with maximum throughput improvements 19.5%, 32.3%, and 40.1% for LLaMA3-8B, LLaMA2-7B, and LLaMA2-13B, respectively.

cs.CL↗

arXiv2025

Code-driven Number Sequence Calculation: Enhancing the inductive Reasoning Abilities of Large Language Models

Large language models (LLMs) make remarkable progress in reasoning tasks. Among different reasoning modes, inductive reasoning, due to its better alignment with human learning, attracts increasing interest. However, research on inductive reasoning faces certain challenges. First, existing inductive data mostly focuses on superficial regularities while lacking more complex internal patterns. Second, current works merely prompt LLMs or finetune on simple prompt-response pairs, but do not provide precise thinking processes nor implement difficulty control. Unlike previous work, we address these challenges by introducing \textit{CodeSeq}, a synthetic post-training dataset built from number sequences. We package number sequences into algorithmic problems to discover their general terms, defining a general term generation (GTG) task correspondingly. Our pipeline generates supervised finetuning data by reflecting on failed test cases and incorporating iterative corrections, thereby teaching LLMs to learn autonomous case generation and self-checking. Additionally, it leverages reinforcement learning with a novel Case-Synergy Solvability Scaling Reward based on both solvability, estimated from the problem pass rate, and the success rate of self-directed case generation, enabling models to learn more effectively from both successes and failures. Experimental results show that the models trained with \textit{CodeSeq} improve on various reasoning tasks and can preserve the models' OOD performance.

cs.CL↗

arXiv2025

LightQANet: Quantized and Adaptive Feature Learning for Low-Light Image Enhancement

Low-light image enhancement (LLIE) aims to improve illumination while preserving high-quality color and texture. However, existing methods often fail to extract reliable feature representations due to severely degraded pixel-level information under low-light conditions, resulting in poor texture restoration, color inconsistency, and artifact. To address these challenges, we propose LightQANet, a novel framework that introduces quantized and adaptive feature learning for low-light enhancement, aiming to achieve consistent and robust image quality across diverse lighting conditions. From the static modeling perspective, we design a Light Quantization Module (LQM) to explicitly extract and quantify illumination-related factors from image features. By enforcing structured light factor learning, LQM enhances the extraction of light-invariant representations and mitigates feature inconsistency across varying illumination levels. From the dynamic adaptation perspective, we introduce a Light-Aware Prompt Module (LAPM), which encodes illumination priors into learnable prompts to dynamically guide the feature learning process. LAPM enables the model to flexibly adapt to complex and continuously changing lighting conditions, further improving image enhancement. Extensive experiments on multiple low-light datasets demonstrate that our method achieves state-of-the-art performance, delivering superior qualitative and quantitative results across various challenging lighting scenarios.

cs.CV↗