arXiv subjects

Chao Wang

Publications and source records attributed to Chao Wang.

At least 289 records · Page 16Linked to original sources

arXiv2025

SRPO: A Cross-Domain Implementation of Large-Scale Reinforcement Learning on LLM

Recent advances of reasoning models, exemplified by OpenAI's o1 and DeepSeek's R1, highlight the significant potential of Reinforcement Learning (RL) to enhance the reasoning capabilities of Large Language Models (LLMs). However, replicating these advancements across diverse domains remains challenging due to limited methodological transparency. In this work, we present two-Staged history-Resampling Policy Optimization (SRPO), which surpasses the performance of DeepSeek-R1-Zero-32B on the AIME24 and LiveCodeBench benchmarks. SRPO achieves this using the same base model as DeepSeek (i.e. Qwen2.5-32B), using only about 1/10 of the training steps required by DeepSeek-R1-Zero-32B, demonstrating superior efficiency. Building upon Group Relative Policy Optimization (GRPO), we introduce two key methodological innovations: (1) a two-stage cross-domain training paradigm designed to balance the development of mathematical reasoning and coding proficiency, and (2) History Resampling (HR), a technique to address ineffective samples. Our comprehensive experiments validate the effectiveness of our approach, offering valuable insights into scaling LLM reasoning capabilities across diverse tasks.

cs.LG↗

arXiv2025

Interpretable Locomotion Prediction in Construction Using a Memory-Driven LLM Agent With Chain-of-Thought Reasoning

Construction tasks are inherently unpredictable, with dynamic environments and safety-critical demands posing significant risks to workers. Exoskeletons offer potential assistance but falter without accurate intent recognition across diverse locomotion modes. This paper presents a locomotion prediction agent leveraging Large Language Models (LLMs) augmented with memory systems, aimed at improving exoskeleton assistance in such settings. Using multimodal inputs - spoken commands and visual data from smart glasses - the agent integrates a Perception Module, Short-Term Memory (STM), Long-Term Memory (LTM), and Refinement Module to predict locomotion modes effectively. Evaluation reveals a baseline weighted F1-score of 0.73 without memory, rising to 0.81 with STM, and reaching 0.90 with both STM and LTM, excelling with vague and safety-critical commands. Calibration metrics, including a Brier Score drop from 0.244 to 0.090 and ECE from 0.222 to 0.044, affirm improved reliability. This framework supports safer, high-level human-exoskeleton collaboration, with promise for adaptive assistive systems in dynamic industries.

cs.RO↗

arXiv2025

Gigabit-rate Quantum Key Distribution on Integrated Photonic Chips

Quantum key distribution (QKD) provides information-theoretic security guaranteed by the laws of quantum mechanics, making it resistant to future computational threats, including quantum computers. While QKD technology shows great promise, its widespread adoption depends heavily on its usability and viability, with key rate performance and cost-effectiveness serving as critical evaluation metrics. In this work, we report an integrated silicon photonics-based QKD system that achieves a secret key rate of 1.213 Gbit per second over a metropolitan distance of 10 km with polarization multiplexing. Our contributions are twofold. First, in the quantum optical layer, we developed an on-chip quantum transmitter and an efficient quantum receiver that operate at 40 Gbaud/s at room temperature. Second, we designed a discrete-modulated continuous variable (DM CV) QKD implementation with efficient information reconciliation based on polar codes, enabling potentially high-throughput real-time data processing. Our results demonstrate a practical QKD solution that combines high performance with cost efficiency. We anticipate this research will pave the way for large-scale quantum secure networks.

quant-ph↗

arXiv2025

Giant Orbital Torque-driven Picosecond Switching in Magnetic Tunnel Junctions

Orbital Hall effect was recently discovered as a novel pathway for driving magnetic moment. However, the integration of orbital Hall effect in magnetic memories suffers from low orbital-to-spin conversion efficiency and incompatibility with magnetic tunnel junctions. Here we demonstrate an orbital Hall effect-driven magnetic tunnel junction based on Ru/W bilayer, where the Ru layer possesses a strong orbital Hall conductivity and the α-W layer features an orbital-to-spin conversion efficiency exceeding 90% because of the large orbit-spin diffusivity. By harnessing the giant orbital torque, we achieve a 28.7-picosecond switching and a five to eight-fold reduction in driving voltages over conventional spin-orbit torque magnetic memories. Our work bridges the critical gap between orbital effects and magnetic memory applications, significantly advancing the field of spintronics and orbitronics.

cond-mat.mtrl-sci↗

arXiv2025

LAYOUTDREAMER: Physics-guided Layout for Text-to-3D Compositional Scene Generation

Recently, the field of text-guided 3D scene generation has garnered significant attention. High-quality generation that aligns with physical realism and high controllability is crucial for practical 3D scene applications. However, existing methods face fundamental limitations: (i) difficulty capturing complex relationships between multiple objects described in the text, (ii) inability to generate physically plausible scene layouts, and (iii) lack of controllability and extensibility in compositional scenes. In this paper, we introduce LayoutDreamer, a framework that leverages 3D Gaussian Splatting (3DGS) to facilitate high-quality, physically consistent compositional scene generation guided by text. Specifically, given a text prompt, we convert it into a directed scene graph and adaptively adjust the density and layout of the initial compositional 3D Gaussians. Subsequently, dynamic camera adjustments are made based on the training focal point to ensure entity-level generation quality. Finally, by extracting directed dependencies from the scene graph, we tailor physical and layout energy to ensure both realism and flexibility. Comprehensive experiments demonstrate that LayoutDreamer outperforms other compositional scene generation quality and semantic alignment methods. Specifically, it achieves state-of-the-art (SOTA) performance in the multiple objects generation metric of T3Bench.

cs.CV↗

arXiv2025

Multispectral radiation temperature inversion based on Transformer-LSTM-SVM

The key challenge in multispectral radiation thermometry is accurately measuring emissivity. Traditional constrained optimization methods often fail to meet practical requirements in terms of precision, efficiency, and noise resistance. However, the continuous advancement of neural networks in data processing offers a potential solution to this issue. This paper presents a multispectral radiation thermometry algorithm that combines Transformer, LSTM (Long Short-Term Memory), and SVM (Support Vector Machine) to mitigate the impact of emissivity, thereby enhancing accuracy and noise resistance. In simulations, compared to the BP neural network algorithm, GIM-LSTM, and Transformer-LSTM algorithms, the Transformer-LSTM-SVM algorithm demonstrates an improvement in accuracy of 1.23%, 0.46% and 0.13%, respectively, without noise. When 5% random noise is added, the accuracy increases by 1.39%, 0.51%, and 0.38%, respectively. Finally, experiments confirmed that the maximum temperature error using this method is less than 1%, indicating that the algorithm offers high accuracy, fast processing speed, and robust noise resistance. These characteristics make it well-suited for real-time high-temperature measurements with multi-wavelength thermometry equipment.

physics.optics↗

arXiv2025

RFMI: Estimating Mutual Information on Rectified Flow for Text-to-Image Alignment

Rectified Flow (RF) models trained with a Flow matching framework have achieved state-of-the-art performance on Text-to-Image (T2I) conditional generation. Yet, multiple benchmarks show that synthetic images can still suffer from poor alignment with the prompt, i.e., images show wrong attribute binding, subject positioning, numeracy, etc. While the literature offers many methods to improve T2I alignment, they all consider only Diffusion Models, and require auxiliary datasets, scoring models, and linguistic analysis of the prompt. In this paper we aim to address these gaps. First, we introduce RFMI, a novel Mutual Information (MI) estimator for RF models that uses the pre-trained model itself for the MI estimation. Then, we investigate a self-supervised fine-tuning approach for T2I alignment based on RFMI that does not require auxiliary information other than the pre-trained model itself. Specifically, a fine-tuning set is constructed by selecting synthetic images generated from the pre-trained RF model and having high point-wise MI between images and prompts. Our experiments on MI estimation benchmarks demonstrate the validity of RFMI, and empirical fine-tuning on SD3.5-Medium confirms the effectiveness of RFMI for improving T2I alignment while maintaining image quality.

cs.CV↗

arXiv2025

DPC: Dual-Prompt Collaboration for Tuning Vision-Language Models

The Base-New Trade-off (BNT) problem universally exists during the optimization of CLIP-based prompt tuning, where continuous fine-tuning on base (target) classes leads to a simultaneous decrease of generalization ability on new (unseen) classes. Existing approaches attempt to regulate the prompt tuning process to balance BNT by appending constraints. However, imposed on the same target prompt, these constraints fail to fully avert the mutual exclusivity between the optimization directions for base and new. As a novel solution to this challenge, we propose the plug-and-play Dual-Prompt Collaboration (DPC) framework, the first that decoupling the optimization processes of base and new tasks at the prompt level. Specifically, we clone a learnable parallel prompt based on the backbone prompt, and introduce a variable Weighting-Decoupling framework to independently control the optimization directions of dual prompts specific to base or new tasks, thus avoiding the conflict in generalization. Meanwhile, we propose a Dynamic Hard Negative Optimizer, utilizing dual prompts to construct a more challenging optimization task on base classes for enhancement. For interpretability, we prove the feature channel invariance of the prompt vector during the optimization process, providing theoretical support for the Weighting-Decoupling of DPC. Extensive experiments on multiple backbones demonstrate that DPC can significantly improve base performance without introducing any external knowledge beyond the base classes, while maintaining generalization to new classes. Code is available at: https://github.com/JREion/DPC.

cs.CV↗

arXiv2025

Efficient Diffusion Posterior Sampling for Noisy Inverse Problems

The pretrained diffusion model as a strong prior has been leveraged to address inverse problems in a zero-shot manner without task-specific retraining. Different from the unconditional generation, the measurement-guided generation requires estimating the expectation of clean image given the current image and the measurement. With the theoretical expectation expression, the crucial task of solving inverse problems is to estimate the noisy likelihood function at the intermediate image sample. Using the Tweedie's formula and the known noise model, the existing diffusion posterior sampling methods perform gradient descent step with backpropagation through the pretrained diffusion model. To alleviate the costly computation and intensive memory consumption of the backpropagation, we propose an alternative maximum-a-posteriori (MAP)-based surrogate estimator to the expectation. With this approach and further density approximation, the MAP estimator for linear inverse problem is the solution to a traditional regularized optimization, of which the loss comprises of data fidelity term and the diffusion model related prior term. Integrating the MAP estimator into a general denoising diffusion implicit model (DDIM)-like sampler, we achieve the general solving framework for inverse problems. Our approach highly resembles the existing $Π$GDM without the manifold projection operation of the gradient descent direction. The developed method is also extended to nonlinear JPEG decompression. The performance of the proposed posterior sampling is validated across a series of inverse problems, where both VP and VE SDE-based pretrained diffusion models are taken into consideration.

math.OC↗

arXiv2025

Can Large Language Models Unveil the Mysteries? An Exploration of Their Ability to Unlock Information in Complex Scenarios

Combining multiple perceptual inputs and performing combinatorial reasoning in complex scenarios is a sophisticated cognitive function in humans. With advancements in multi-modal large language models, recent benchmarks tend to evaluate visual understanding across multiple images. However, they often overlook the necessity of combinatorial reasoning across multiple perceptual information. To explore the ability of advanced models to integrate multiple perceptual inputs for combinatorial reasoning in complex scenarios, we introduce two benchmarks: Clue-Visual Question Answering (CVQA), with three task types to assess visual comprehension and synthesis, and Clue of Password-Visual Question Answering (CPVQA), with two task types focused on accurate interpretation and application of visual data. For our benchmarks, we present three plug-and-play approaches: utilizing model input for reasoning, enhancing reasoning through minimum margin decoding with randomness generation, and retrieving semantically relevant visual information for effective data integration. The combined results reveal current models' poor performance on combinatorial reasoning benchmarks, even the state-of-the-art (SOTA) closed-source model achieves only 33.04% accuracy on CVQA, and drops to 7.38% on CPVQA. Notably, our approach improves the performance of models on combinatorial reasoning, with a 22.17% boost on CVQA and 9.40% on CPVQA over the SOTA closed-source model, demonstrating its effectiveness in enhancing combinatorial reasoning with multiple perceptual inputs in complex scenarios. The code will be publicly available.

cs.CV↗

arXiv2025

When Large Language Models Meet Evolutionary Algorithms: Potential Enhancements and Challenges

Pre-trained large language models (LLMs) exhibit powerful capabilities for generating natural text. Evolutionary algorithms (EAs) can discover diverse solutions to complex real-world problems. Motivated by the common collective and directionality of text generation and evolution, this paper first illustrates the conceptual parallels between LLMs and EAs at a micro level, which includes multiple one-to-one key characteristics: token representation and individual representation, position encoding and fitness shaping, position embedding and selection, Transformers block and reproduction, and model training and parameter adaptation. These parallels highlight potential opportunities for technical advancements in both LLMs and EAs. Subsequently, we analyze existing interdisciplinary research from a macro perspective to uncover critical challenges, with a particular focus on evolutionary fine-tuning and LLM-enhanced EAs. These analyses not only provide insights into the evolutionary mechanisms behind LLMs but also offer potential directions for enhancing the capabilities of artificial agents.

cs.NE↗

arXiv2025

TPC: Cross-Temporal Prediction Connection for Vision-Language Model Hallucination Reduction

Vision-language models (VLMs) have achieved remarkable advancements, capitalizing on the impressive capabilities of large language models (LLMs) across diverse tasks. Despite this, a critical challenge known as hallucination occurs when models overconfidently describe objects or attributes absent from the image, a problem exacerbated by the tendency of VLMs to rely on linguistic priors. This limitation reduces model reliability in high-stakes applications. In this work, we have observed the characteristic of logits' continuity consistency enhancement and introduced a straightforward and efficient method, Cross-Temporal Prediction Connection (TPC), designed to enhance the semantic consistency of logits by connecting them temporally across timesteps. TPC amplifies information flow and improves coherence, effectively reducing hallucination. Extensive experiments show that TPC surpasses existing representatives, delivering superior performance in both accuracy and efficiency while maintaining robustness in open-ended text generation tasks.

cs.CV↗

arXiv2025

Advancing vision-language models in front-end development via data synthesis

Modern front-end (FE) development, especially when leveraging the unique features of frameworks like React and Vue, presents distinctive challenges. These include managing modular architectures, ensuring synchronization between data and visual outputs for declarative rendering, and adapting reusable components to various scenarios. Such complexities make it particularly difficult for state-of-the-art large vision-language models (VLMs) to generate accurate and functional code directly from design images. To address these challenges, we propose a reflective agentic workflow that synthesizes high-quality image-text data to capture the diverse characteristics of FE development. This workflow automates the extraction of self-contained\footnote{A \textbf{self-contained} code snippet is one that encapsulates all necessary logic, styling, and dependencies, ensuring it functions independently without requiring external imports or context.} code snippets from real-world projects, renders the corresponding visual outputs, and generates detailed descriptions that link design elements to functional code. To further expand the scope and utility of the synthesis, we introduce three data synthesis strategies: Evolution-based synthesis, which enables scalable and diverse dataset expansion; Waterfall-Model-based synthesis, which generates logically coherent code derived from system requirements; and Additive Development synthesis, which iteratively increases the complexity of human-authored components. We build a large vision-language model, Flame, trained on the synthesized datasets and demonstrate its effectiveness in generating React code via the $\text{pass}@k$ metric. Our results suggest that a code VLM trained to interpret images before code generation may achieve better performance.

cs.CV↗

arXiv2025

Large Language Models for Interpretable Mental Health Diagnosis

We propose a clinical decision support system (CDSS) for mental health diagnosis that combines the strengths of large language models (LLMs) and constraint logic programming (CLP). Having a CDSS is important because of the high complexity of diagnostic manuals used by mental health professionals and the danger of diagnostic errors. Our CDSS is a software tool that uses an LLM to translate diagnostic manuals to a logic program and solves the program using an off-the-shelf CLP engine to query a patient's diagnosis based on the encoded rules and provided data. By giving domain experts the opportunity to inspect the LLM-generated logic program, and making modifications when needed, our CDSS ensures that the diagnosis is not only accurate but also interpretable. We experimentally compare it with two baseline approaches of using LLMs: diagnosing patients using the LLM-only approach, and using the LLM-generated logic program but without expert inspection. The results show that, while LLMs are extremely useful in generating candidate logic programs, these programs still require expert inspection and modification to guarantee faithfulness to the official diagnostic manuals. Additionally, ethical concerns arise from the direct use of patient data in LLMs, underscoring the need for a safer hybrid approach like our proposed method.

cs.AI↗

arXiv2025

Global Neural Networks and The Data Scaling Effect in Financial Time Series Forecasting

Neural networks have revolutionized many empirical fields, yet their application to financial time series forecasting remains controversial. In this study, we demonstrate that the conventional practice of estimating models locally in data-scarce environments may underlie the mixed empirical performance observed in prior work. By focusing on volatility forecasting, we employ a dataset comprising over 10,000 global stocks and implement a global estimation strategy that pools information across cross-sections. Our econometric analysis reveals that forecasting accuracy improves markedly as the training dataset becomes larger and more heterogeneous. Notably, even with as little as 12 months of data, globally trained networks deliver robust predictions for individual stocks and portfolios that are not even in the training dataset. Furthermore, our interpretation of the model dynamics shows that these networks not only capture key stylized facts of volatility but also exhibit resilience to outliers and rapid adaptation to market regime changes. These findings underscore the importance of leveraging extensive and diverse datasets in financial forecasting and advocate for a shift from traditional local training approaches to integrated global estimation methods.

econ.EM↗

arXiv2025

UbiMoE: A Ubiquitous Mixture-of-Experts Vision Transformer Accelerator With Hybrid Computation Pattern on FPGA

Compared to traditional Vision Transformers (ViT), Mixture-of-Experts Vision Transformers (MoE-ViT) are introduced to scale model size without a proportional increase in computational complexity, making them a new research focus. Given the high performance and reconfigurability, FPGA-based accelerators for MoE-ViT emerge, delivering substantial gains over general-purpose processors. However, existing accelerators often fall short of fully exploring the design space, leading to suboptimal trade-offs between resource utilization and performance. To overcome this problem, we introduce UbiMoE, a novel end-to-end FPGA accelerator tailored for MoE-ViT. Leveraging the unique computational and memory access patterns of MoE-ViTs, we develop a latency-optimized streaming attention kernel and a resource-efficient reusable linear kernel, effectively balancing performance and resource consumption. To further enhance design efficiency, we propose a two-stage heuristic search algorithm that optimally tunes hardware parameters for various FPGA resource constraints. Compared to state-of-the-art (SOTA) FPGA designs, UbiMoE achieves 1.34x and 3.35x throughput improvements for MoE-ViT on Xilinx ZCU102 and Alveo U280 platforms, respectively, while enhancing energy efficiency by 1.75x and 1.54x. Our implementation is available at https://github.com/DJ000011/UbiMoE.

cs.AR↗

arXiv2025

Information Theoretic Text-to-Image Alignment

Diffusion models for Text-to-Image (T2I) conditional generation have recently achieved tremendous success. Yet, aligning these models with user's intentions still involves a laborious trial-and-error process, and this challenging alignment problem has attracted considerable attention from the research community. In this work, instead of relying on fine-grained linguistic analyses of prompts, human annotation, or auxiliary vision-language models, we use Mutual Information (MI) to guide model alignment. In brief, our method uses self-supervised fine-tuning and relies on a point-wise (MI) estimation between prompts and images to create a synthetic fine-tuning set for improving model alignment. Our analysis indicates that our method is superior to the state-of-the-art, yet it only requires the pre-trained denoising network of the T2I model itself to estimate MI, and a simple fine-tuning strategy that improves alignment while maintaining image quality. Code available at https://github.com/Chao0511/mitune.

cs.LG↗

arXiv2025

PiLocNet: Physics-informed neural network on 3D localization with rotating point spread function

For the 3D localization problem using point spread function (PSF) engineering, we propose a novel enhancement of our previously introduced localization neural network, LocNet. The improved network is a physics-informed neural network (PINN) that we call PiLocNet. Previous works on the localization problem may be categorized separately into model-based optimization and neural network approaches. Our PiLocNet combines the unique strengths of both approaches by incorporating forward-model-based information into the network via a data-fitting loss term that constrains the neural network to yield results that are physically sensible. We additionally incorporate certain regularization terms from the variational method, which further improves the robustness of the network in the presence of image noise, as we show for the Poisson and Gaussian noise models. This framework accords interpretability to the neural network, and the results we obtain show its superiority. Although the paper focuses on the use of single-lobe rotating PSF to encode the full 3D source location, we expect the method to be widely applicable to other PSFs and imaging problems that are constrained by known forward processes.

cs.LG↗