arXiv subjects

Haotian Wu

Publications and source records attributed to Haotian Wu.

At least 37 records · Page 2Linked to original sources

arXiv2025

Adaptive SGD with Line-Search and Polyak Stepsizes: Nonconvex Convergence and Accelerated Rates

We extend the convergence analysis of AdaSLS and AdaSPS in [Jiang and Stich, 2024] to the nonconvex setting, presenting a unified convergence analysis of stochastic gradient descent with adaptive Armijo line-search (AdaSLS) and Polyak stepsize (AdaSPS) for nonconvex optimization. Our contributions include: (1) an $\mathcal{O}(1/\sqrt{T})$ convergence rate for general nonconvex smooth functions, (2) an $\mathcal{O}(1/T)$ rate under quasar-convexity and interpolation, and (3) an $\mathcal{O}(1/T)$ rate under the strong growth condition for general nonconvex functions.

math.OC↗

arXiv2025

EffiReason-Bench: A Unified Benchmark for Evaluating and Advancing Efficient Reasoning in Large Language Models

Large language models (LLMs) with Chain-of-Thought (CoT) prompting achieve strong reasoning but often produce unnecessarily long explanations, increasing cost and sometimes reducing accuracy. Fair comparison of efficiency-oriented approaches is hindered by fragmented evaluation practices. We introduce EffiReason-Bench, a unified benchmark for rigorous cross-paradigm evaluation of efficient reasoning methods across three categories: Reasoning Blueprints, Dynamic Execution, and Post-hoc Refinement. To enable step-by-step evaluation, we construct verified CoT annotations for CommonsenseQA and LogiQA via a pipeline that enforces standardized reasoning structures, comprehensive option-wise analysis, and human verification. We evaluate 7 methods across 6 open-source LLMs (1B-70B) on 4 datasets spanning mathematics, commonsense, and logic, and propose the E3-Score, a principled metric inspired by economic trade-off modeling that provides smooth, stable evaluation without discontinuities or heavy reliance on heuristics. Experiments show that no single method universally dominates; optimal strategies depend on backbone scale, task complexity, and architecture.

cs.CL↗

arXiv2025

Thinking with Nothinking Calibration: A New In-Context Learning Paradigm in Reasoning Large Language Models

Reasoning large language models (RLLMs) have recently demonstrated remarkable capabilities through structured and multi-step reasoning. While prior research has primarily focused on improving their training and inference strategies, their potential for in-context learning (ICL) remains largely underexplored. To fill this gap, we propose Thinking with Nothinking Calibration (JointThinking), a new ICL paradigm that prompts the model to generate two answers in parallel: one in Thinking mode and the other in Nothinking mode. A second round of Thinking is triggered only when the two initial responses are inconsistent, using a single prompt with two different answers. Extensive experiments across multiple reasoning benchmarks demonstrate that JointThinking significantly outperforms few-shot chain-of-thought (CoT), thinking twice and majority voting. Moreover, it achieves comparable in-distribution performance to training-based SOTA reasoning method, while substantially outperforming on out-of-distribution tasks. We further conduct a systematic analysis of the calibration mechanism, showing the importance of structural thinking diversity and the benefits of consistency check. Additionally, we observe that the performance gap between actual and ideal reasoning narrows as model size increases in the second thinking, indicating the strong scalability of our approach. Finally, we discuss current limitations and outline promising directions for future ICL research in RLLMs.

cs.CL↗

arXiv2025

Compression Beyond Pixels: Semantic Compression with Multimodal Foundation Models

Recent deep learning-based methods for lossy image compression achieve competitive rate-distortion performance through extensive end-to-end training and advanced architectures. However, emerging applications increasingly prioritize semantic preservation over pixel-level reconstruction and demand robust performance across diverse data distributions and downstream tasks. These challenges call for advanced semantic compression paradigms. Motivated by the zero-shot and representational capabilities of multimodal foundation models, we propose a novel semantic compression method based on the contrastive language-image pretraining (CLIP) model. Rather than compressing images for reconstruction, we propose compressing the CLIP feature embeddings into minimal bits while preserving semantic information across different tasks. Experiments show that our method maintains semantic integrity across benchmark datasets, achieving an average bit rate of approximately 2-3* 10(-3) bits per pixel. This is less than 5% of the bitrate required by mainstream image compression approaches for comparable performance. Remarkably, even under extreme compression, the proposed approach exhibits zero-shot robustness across diverse data distributions and downstream tasks.

cs.CV↗

arXiv2025

Actions Speak Louder Than Words: Rate-Reward Trade-off in Markov Decision Processes

The impact of communication on decision-making systems has been extensively studied under the assumption of dedicated communication channels. We instead consider communicating through actions, where the message is embedded into the actions of an agent which interacts with the environment in a Markov decision process (MDP) framework. We conceptualize the MDP environment as a finite-state channel (FSC), where the actions of the agent serve as the channel input, while the states of the MDP observed by another agent (i.e., receiver) serve as the channel output. Here, we treat the environment as a communication channel over which the agent communicates through its actions, while at the same time, trying to maximize its reward. We first characterize the optimal information theoretic trade-off between the average reward and the rate of reliable communication in the infinite-horizon regime. Then, we propose a novel framework to design a joint control/coding policy, termed \textit{Act2Comm}, which seamlessly embeds messages into actions. From a communication perspective, \textit{Act2Comm} functions as a learning-based channel coding scheme for non-differentiable FSCs under input-output constraints. From a control standpoint, \textit{Act2Comm} learns an MDP policy that incorporates communication capabilities, though at the cost of some control performance. Overall, \textit{Act2Comm} effectively balances the dual objectives of control and communication in this environment. Experimental results validate \textit{Act2Comm}'s capability to enable reliable communication while maintaining a certain level of control performance.

cs.IT↗

arXiv2025

LotteryCodec: Searching the Implicit Representation in a Random Network for Low-Complexity Image Compression

We introduce and validate the lottery codec hypothesis, which states that untrained subnetworks within randomly initialized networks can serve as synthesis networks for overfitted image compression, achieving rate-distortion (RD) performance comparable to trained networks. This hypothesis leads to a new paradigm for image compression by encoding image statistics into the network substructure. Building on this hypothesis, we propose LotteryCodec, which overfits a binary mask to an individual image, leveraging an over-parameterized and randomly initialized network shared by the encoder and the decoder. To address over-parameterization challenges and streamline subnetwork search, we develop a rewind modulation mechanism that improves the RD performance. LotteryCodec outperforms VTM and sets a new state-of-the-art in single-image compression. LotteryCodec also enables adaptive decoding complexity through adjustable mask ratios, offering flexible compression solutions for diverse device constraints and application requirements.

eess.IV↗

arXiv2025

Realizing Fully-Connected Layers Over the Air via Reconfigurable Intelligent Surfaces

By leveraging the waveform superposition property of the multiple access channel, over-the-air computation (AirComp) enables the execution of digital computations through analog means in the wireless domain, leading to faster processing and reduced latency. In this paper, we propose a novel approach to implement a neural network (NN) consisting of digital fully connected (FC) layers using physically reconfigurable hardware. Specifically, we investigate reconfigurable intelligent surfaces (RISs)-assisted multiple-input multiple-output (MIMO) systems to emulate the functionality of a NN for over-the-air inference. In this setup, both the RIS and the transceiver are jointly configured to manipulate the ambient wireless propagation environment, effectively reproducing the adjustable weights of a digital FC layer. We refer to this new computational paradigm as \textit{AirFC}. We formulate an imitation error minimization problem between the effective channel created by RIS and a target FC layer by jointly optimizing over-the-air parameters. To solve this non-convex optimization problem, an extremely low-complexity alternating optimization algorithm is proposed, where semi-closed-form/closed-form solutions for all optimization variables are derived. Simulation results show that the RIS-assisted MIMO-based AirFC can achieve competitive classification accuracy. Furthermore, it is also shown that a multi-RIS configuration significantly outperforms a single-RIS setup, particularly in line-of-sight (LoS)-dominated channels.

cs.IT↗

arXiv2025

Implementing Neural Networks Over-the-Air via Reconfigurable Intelligent Surfaces

In this paper, we investigate reconfigurable intelligent surface (RIS)-aided multiple-input-multiple-output (MIMO) OAC systems designed to emulate the fully-connected (FC) layer of a neural network (NN) via analog OAC, where the RIS and the transceivers are jointly adjusted to engineer the ambient wireless propagation environment to emulate the weights of the target FC layer. We refer to this novel computational paradigm as AirFC. We first study the case in which the precoder, combiner, and RIS phase shift matrices are jointly optimized to minimize the mismatch between the OAC system and the target FC layer. To solve this non-convex optimization problem, we propose a low-complexity alternating optimization algorithm, where semi-closed-form/closed-form solutions for all optimization variables are derived. Next, we consider training of the system parameters using two distinct learning strategies, namely centralized training and distributed training. In the centralized training approach, training is performed at either the transmitter or the receiver, whichever possesses the channel state information (CSI), and the trained parameters are provided to the other terminal. In the distributed training approach, the transmitter and receiver iteratively update their parameters through back and forth transmissions by leveraging channel reciprocity, thereby avoiding CSI acquisition and significantly reducing computational complexity. Subsequently, we extend our analysis to a multi-RIS scenario by exploiting its spatial diversity gain to enhance the system performance. Simulation results show that the AirFC system realized by the RIS-aided MIMO configuration achieves satisfactory classification accuracy.

cs.IT↗

arXiv2025

Learning Semantic Directions for Feature Augmentation in Domain-Generalized Medical Segmentation

Medical image segmentation plays a crucial role in clinical workflows, but domain shift often leads to performance degradation when models are applied to unseen clinical domains. This challenge arises due to variations in imaging conditions, scanner types, and acquisition protocols, limiting the practical deployment of segmentation models. Unlike natural images, medical images typically exhibit consistent anatomical structures across patients, with domain-specific variations mainly caused by imaging conditions. This unique characteristic makes medical image segmentation particularly challenging. To address this challenge, we propose a domain generalization framework tailored for medical image segmentation. Our approach improves robustness to domain-specific variations by introducing implicit feature perturbations guided by domain statistics. Specifically, we employ a learnable semantic direction selector and a covariance-based semantic intensity sampler to modulate domain-variant features while preserving task-relevant anatomical consistency. Furthermore, we design an adaptive consistency constraint that is selectively applied only when feature adjustment leads to degraded segmentation performance. This constraint encourages the adjusted features to align with the original predictions, thereby stabilizing feature selection and improving the reliability of the segmentation. Extensive experiments on two public multi-center benchmarks show that our framework consistently outperforms existing domain generalization approaches, achieving robust and generalizable segmentation performance across diverse clinical domains.

cs.CV↗

arXiv2025

Semantics-Guided Diffusion for Deep Joint Source-Channel Coding in Wireless Image Transmission

Joint source-channel coding (JSCC) offers a promising avenue for enhancing transmission efficiency by jointly incorporating source and channel statistics into the system design. A key advancement in this area is the deep joint source and channel coding (DeepJSCC) technique that designs a direct mapping of input signals to channel symbols parameterized by a neural network, which can be trained for arbitrary channel models and semantic quality metrics. This paper advances the DeepJSCC framework toward a semantics-aligned, high-fidelity transmission approach, called semantics-guided diffusion DeepJSCC (SGD-JSCC). Existing schemes that integrate diffusion models (DMs) with JSCC face challenges in transforming random generation into accurate reconstruction and adapting to varying channel conditions. SGD-JSCC incorporates two key innovations: (1) utilizing some inherent information that contributes to the semantics of an image, such as text description or edge map, to guide the diffusion denoising process; and (2) enabling seamless adaptability to varying channel conditions with the help of a semantics-guided DM for channel denoising. The DM is guided by diverse semantic information and integrates seamlessly with DeepJSCC. In a slow fading channel, SGD-JSCC dynamically adapts to the instantaneous signal-to-noise ratio (SNR) directly estimated from the channel output, thereby eliminating the need for additional pilot transmissions for channel estimation. In a fast fading channel, we introduce a training-free denoising strategy, allowing SGD-JSCC to effectively adjust to fluctuations in channel gains. Numerical results demonstrate that, guided by semantic information and leveraging the powerful DM, our method outperforms existing DeepJSCC schemes, delivering satisfactory reconstruction performance even at extremely poor channel conditions.

cs.IT↗

arXiv2025

Identifying Materials-Level Sources of Performance Variation in Superconducting Transmon Qubits

The Superconducting Materials and Systems (SQMS) Center, a DOE National Quantum Information Science Research Center, has conducted a comprehensive and coordinated study using superconducting transmon qubit chips with known performance metrics to identify the underlying materials-level sources of device-to-device performance variation. Following qubit coherence measurements, these qubits of varying base superconducting metals and substrates have been examined with various nondestructive and invasive material characterization techniques at Northwestern University, Ames National Laboratory, and Fermilab as part of a blind study. We find trends in variations of the depth of the etched substrate trench, the thickness of the surface oxide, and the geometry of the sidewall, which when combined, lead to correlations with the T$_1$ lifetime across different devices. In addition, we provide a list of features that varied from device to device, for which the impact on performance requires further studies. Finally, we identify two low-temperature characterization techniques that may potentially serve as proxy tools for qubit measurements. These insights provide materials-oriented solutions to not only reduce performance variations across neighboring devices, but also to engineer and fabricate devices with optimal geometries to achieve performance metrics beyond the state-of-the-art values.

quant-ph↗

arXiv2025

Zero-Shot Semantic Communication with Multimodal Foundation Models

Most existing semantic communication (SemCom) systems use deep joint source-channel coding (DeepJSCC) to encode task-specific semantics in a goal-oriented manner. However, their reliance on predefined tasks and datasets significantly limits their flexibility and generalizability in practical deployments. Multi-modal foundation models provide a promising solution by generating universal semantic tokens. Inspired by this, we introduce SemCLIP, a zero-shot SemCom framework leveraging the contrastive language-image pre-training (CLIP) model. By transmitting CLIP-generated image tokens instead of raw images, SemCLIP enables efficient SemCom under low bandwidth and challenging channel conditions, facilitating diverse downstream tasks and zero-shot applications. Specifically, we propose a DeepJSCC scheme for efficient CLIP token encoding. To mitigate potential degradation caused by compression and channel noise, a multi-modal transmission-aware prompt learning mechanism is designed at the receiver, which adapts prompts based on transmission quality, enhancing system robustness and channel adaptability. Simulation results demonstrate that SemCLIP outperforms the baselines, achieving a $41\%$ improvement in zero-shot performance at low signal-to-noise ratios. Meanwhile, SemCLIP reduces bandwidth usage by more than $50$-fold compared to alternative image transmission methods, demonstrating the potential of foundation models towards a generalized, task-agnostic SemCom solution.

eess.SP↗

arXiv2025

A Hybrid Cloud Management Plane for Data Processing Pipelines

As organizations increasingly rely on data-driven insights, the ability to run data intensive applications seamlessly across multiple cloud environments becomes critical for tapping into cloud innovations while complying with various security and regulatory requirements. However, big data application development and deployment remain challenging to accomplish in such environments. With the increasing containerization and modernization of big data applications, we argue that a unified control/management plane now makes sense for running these applications in hybrid cloud environments. To this end, we study the problem of building a generic hybrid-cloud management plane to radically simplify managing big data applications. A generic architecture for hybrid-cloud management, called Titchener, is proposed in this paper. Titchener comprises of independent and loosely coupled local control planes interacting with a highly available public cloud hosted global management plane. We describe a possible instantiation of Titchener based on Kubernetes and address issues related to global service discovery, network connectivity and access control enforcement. We also validate our proposed designs with a real management plane implementation based on a popular big data workflow orchestration in hybrid-cloud environments.

cs.DC↗

arXiv2025

Accelerating Graph Indexing for ANNS on Modern CPUs

In high-dimensional vector spaces, Approximate Nearest Neighbor Search (ANNS) is a key component in database and artificial intelligence infrastructures. Graph-based methods, particularly HNSW, have emerged as leading solutions among various ANNS approaches, offering an impressive trade-off between search efficiency and accuracy. Many modern vector databases utilize graph indexes as their core algorithms, benefiting from various optimizations to enhance search performance. However, the high indexing time associated with graph algorithms poses a significant challenge, especially given the increasing volume of data, query processing complexity, and dynamic index maintenance demand. This has rendered indexing time a critical performance metric for users. In this paper, we comprehensively analyze the underlying causes of the low graph indexing efficiency on modern CPUs, identifying that distance computation dominates indexing time, primarily due to high memory access latency and suboptimal arithmetic operation efficiency. We demonstrate that distance comparisons during index construction can be effectively performed using compact vector codes at an appropriate compression error. Drawing from insights gained through integrating existing compact coding methods in the graph indexing process, we propose a novel compact coding strategy, named Flash, designed explicitly for graph indexing and optimized for modern CPU architectures. By minimizing random memory accesses and maximizing the utilization of SIMD (Single Instruction, Multiple Data) instructions, Flash significantly enhances cache hit rates and arithmetic operations. Extensive experiments conducted on eight real-world datasets, ranging from ten million to one billion vectors, exhibit that Flash achieves a speedup of 10.4$\times$ to 22.9$\times$ in index construction efficiency, while maintaining or improving search performance.

cs.DB↗

arXiv2025

Multi-level Conflict-Aware Network for Multi-modal Sentiment Analysis

Multimodal Sentiment Analysis (MSA) aims to recognize human emotions by exploiting textual, acoustic, and visual modalities, and thus how to make full use of the interactions between different modalities is a central challenge of MSA. Interaction contains alignment and conflict aspects. Current works mainly emphasize alignment and the inherent differences between unimodal modalities, neglecting the fact that there are also potential conflicts between bimodal combinations. Additionally, multi-task learning-based conflict modeling methods often rely on the unstable generated labels. To address these challenges, we propose a novel multi-level conflict-aware network (MCAN) for multimodal sentiment analysis, which progressively segregates alignment and conflict constituents from unimodal and bimodal representations, and further exploits the conflict constituents with the conflict modeling branch. In the conflict modeling branch, we conduct discrepancy constraints at both the representation and predicted output levels, avoiding dependence on the generated labels. Experimental results on the CMU-MOSI and CMU-MOSEI datasets demonstrate the effectiveness of the proposed MCAN.

cs.CL↗

arXiv2025

Multiview Point Cloud Registration Based on Minimum Potential Energy for Free-Form Blade Measurement

Point cloud registration is an essential step for free-form blade reconstruction in industrial measurement. Nonetheless, measuring defects of the 3D acquisition system unavoidably result in noisy and incomplete point cloud data, which renders efficient and accurate registration challenging. In this paper, we propose a novel global registration method that is based on the minimum potential energy (MPE) method to address these problems. The basic strategy is that the objective function is defined as the minimum potential energy optimization function of the physical registration system. The function distributes more weight to the majority of inlier points and less weight to the noise and outliers, which essentially reduces the influence of perturbations in the mathematical formulation. We decompose the solution into a globally optimal approximation procedure and a fine registration process with the trimmed iterative closest point algorithm to boost convergence. The approximation procedure consists of two main steps. First, according to the construction of the force traction operator, we can simply compute the position of the potential energy minimum. Second, to find the MPE point, we propose a new theory that employs two flags to observe the status of the registration procedure. We demonstrate the performance of the proposed algorithm on four types of blades. The proposed method outperforms the other global methods in terms of both accuracy and noise resistance.

cs.CV↗

arXiv2024

Cross-View-Prediction: Exploring Contrastive Feature for Hyperspectral Image Classification

This paper presents a self-supervised feature learning method for hyperspectral image classification. Our method tries to construct two different views of the raw hyperspectral image through a cross-representation learning method. And then to learn semantically consistent representation over the created views by contrastive learning method. Specifically, four cross-channel-prediction based augmentation methods are naturally designed to utilize the high dimension characteristic of hyperspectral data for the view construction. And the better representative features are learned by maximizing mutual information and minimizing conditional entropy across different views from our contrastive network. This 'Cross-View-Predicton' style is straightforward and gets the state-of-the-art performance of unsupervised classification with a simple SVM classifier.

cs.CV↗

arXiv2024

Spatiotemporal Superfocusing

Superfocusing confines light within subwavelength structures, breaking the diffraction limit. Structures with spatial singularities, such as metallic cones, are crucial to enable nanoscale focusing, leading to significant advancements in nanophotonics, sensing, and imaging. Here, we exploit the spatiotemporal analogue of the wedge structure, i.e. a dielectric medium sandwiched between two subluminal interfaces with distinct velocities, to focus propagating waves beyond the diffraction limit, achieving spatiotemporal superfocusing. Within this structure, an incident pulse undergoes continuous spatial and temporal compression due to Doppler effects, which accumulates and results in an extreme focusing as it approaches the spatiotemporal vertex. Remarkably, unlike the field localization in conventional superfocusing, the compressed light in spatiotemporal wedges experiences significant amplification and then couple to the far field in free space. Our findings represent an indispensable paradigm for extreme concentration and amplification of propagating waves in space-time dimensions.

physics.optics↗