Searcharxiv⌕ Search

arXiv subjects

Hao Chen

Publications and source records attributed to Hao Chen.

At least 343 records · Page 19Linked to original sources
arXiv2026

Decoupled Orthogonal Dynamics: Regularization for Deep Network Optimizers

Is the standard weight decay in AdamW truly optimal? Although AdamW decouples weight decay from adaptive gradient scaling, a fundamental conflict remains: the Radial Tug-of-War. In deep learning, gradients tend to increase parameter norms to expand effective capacity while steering directions to learn features, whereas weight decay indiscriminately suppresses norm growth. This push--pull interaction induces radial oscillations, injecting noise into Adam's second-moment estimates and potentially degrading delicate tangential feature learning. We argue that magnitude and direction play distinct roles and should be decoupled in optimizer dynamics. We propose Orthogonal Dynamics Decoupling and instantiate it as AdamO: an SGD-style update handles the one-dimensional norm control, while Adam's adaptive preconditioning is confined to the tangential subspace. AdamO further incorporates curvature-adaptive radial step sizing and architecture-aware rules and projections for scale-invariant layers and low-dimensional parameters. Experiments on vision and language tasks show that AdamO improves generalization and stability over AdamW without introducing additional complex constraints.

cs.LG↗
arXiv2026

Ringmaster: How to juggle high-throughput host OS system calls from TrustZone TEEs

Many safety-critical systems require timely processing of sensor inputs to avoid potential safety hazards. Additionally, to support useful application features, such systems increasingly have a large rich operating system (OS) at the cost of potential security bugs. Thus, if a malicious party gains supervisor privileges, they could cause real-world damage by denying service to time-sensitive programs. Many past approaches to this problem completely isolate time-sensitive programs with a hypervisor; however, this prevents the programs from accessing useful OS services. We introduce Ringmaster, a novel framework that enables enclaves or TEEs (Trusted Execution Environments) to asynchronously access rich, but potentially untrusted, OS services via Linux's io_uring. When service is denied by the untrusted OS, enclaves continue to operate on Ringmaster's minimal ARM TrustZone kernel with access to small, critical device drivers. This approach balances the need for secure, time-sensitive processing with the convenience of rich OS services. Additionally, Ringmaster supports large unmodified programs as enclaves, offering lower overhead compared to existing systems. We demonstrate how Ringmaster helps us build a working highly-secure system with minimal engineering. In our experiments with an unmanned aerial vehicle, Ringmaster achieved nearly 1GiB/sec of data into enclave on a Raspberry Pi4b, 0-3% throughput overhead compared to non-enclave tasks.

cs.CR↗
arXiv2026

CAARMA: Class Augmentation with Adversarial Mixup Regularization

Speaker verification is a typical zero-shot learning task, where inference of unseen classes is performed by comparing embeddings of test instances to known examples. The models performing inference must hence naturally generate embeddings that cluster same-class instances compactly, while maintaining separation across classes. In order to learn to do so, they are typically trained on a large number of classes (speakers), often using specialized losses. However real-world speaker datasets often lack the class diversity needed to effectively learn this in a generalizable manner. We introduce CAARMA, a class augmentation framework that addresses this problem by generating synthetic classes through data mixing in the embedding space, expanding the number of training classes. To ensure the authenticity of the synthetic classes we adopt a novel adversarial refinement mechanism that minimizes categorical distinctions between synthetic and real classes. We evaluate CAARMA on multiple speaker verification tasks, as well as other representative zero-shot comparison-based speech analysis tasks and obtain consistent improvements: our framework demonstrates a significant improvement of 8\% over all baseline models. The code is available at: https://github.com/massabaali7/CAARMA/

cs.SD↗
arXiv2026

Glance and Focus Reinforcement for Pan-cancer Screening

Pan-cancer screening in large-scale CT scans remains challenging for existing AI methods, primarily due to the difficulty of localizing diverse types of tiny lesions in large CT volumes. The extreme foreground-background imbalance significantly hinders models from focusing on diseased regions, while redundant focus on healthy regions not only decreases the efficiency but also increases false positives. Inspired by radiologists' glance and focus diagnostic strategy, we introduce GF-Screen, a Glance and Focus reinforcement learning framework for pan-cancer screening. GF-Screen employs a Glance model to localize the diseased regions and a Focus model to precisely segment the lesions, where segmentation results of the Focus model are leveraged to reward the Glance model via Reinforcement Learning (RL). Specifically, the Glance model crops a group of sub-volumes from the entire CT volume and learns to select the sub-volumes with lesions for the Focus model to segment. Given that the selecting operation is non-differentiable for segmentation training, we propose to employ the segmentation results to reward the Glance model. To optimize the Glance model, we introduce a novel group relative learning paradigm, which employs group relative comparison to prioritize high-advantage predictions and discard low-advantage predictions within sub-volume groups, not only improving efficiency but also reducing false positives. In this way, for the first time, we effectively extend cutting-edge RL techniques to tackle the specific challenges in pan-cancer screening. Extensive experiments on 16 internal and 7 external datasets across 9 lesion types demonstrated the effectiveness of GF-Screen. Notably, GF-Screen leads the public validation leaderboard of MICCAI FLARE25 pan-cancer challenge, surpassing the FLARE24 champion solution by a large margin (+25.6% DSC and +28.2% NSD).

cs.CV↗
arXiv2026

Zero-Shot Knowledge Base Resizing for Rate-Adaptive Digital Semantic Communication

Digital semantic communication systems, which often leverage the Vector Quantized Variational Autoencoder (VQ-VAE) framework, are pivotal for future wireless networks. In a VQ-VAE-based semantic communication system, the transmission rate is directly governed by the size of a discrete codebook known as knowledge base (KB). However, the KB size is a fixed hyperparameter, meaning that adapting the rate requires training and storing a separate model for each desired size -- a practice that is too computationally and storage-prohibitive to achieve truly granular rate control. To address this, we introduce a principled, zero-shot KB resizing method that enables on-the-fly rate adaptation without any retraining. Our approach establishes a global importance ranking for all vectors within a single, large parent KB by uncovering its inherent semantic hierarchy. This is achieved via a three-step framework: 1) embedding KB vectors into hyperbolic space to reveal their hierarchical relationships; 2) constructing a master semantic tree using a minimum spanning tree algorithm; 3) enabling instant resizing by iteratively pruning the least important leaf nodes. Extensive simulations demonstrate that our method achieves reconstruction quality nearly identical to that of dedicated KBs trained from scratch, while demanding only a fraction of the computational budget. Moreover, our approach exhibits superior robustness at very low rates, where conventional KBs suffer from catastrophic failure. Our work resolves a fundamental limitation of VQ-VAE-based semantic communication systems, offering a practical and efficient path toward flexible and rate-adaptive semantic communication.

cs.IT↗
arXiv2026

Reinforced Rate Control for Neural Video Compression via Inter-Frame Rate-Distortion Awareness

Neural video compression (NVC) has demonstrated superior compression efficiency, yet effective rate control remains a significant challenge due to complex temporal dependencies. Existing rate control schemes typically leverage frame content to capture distortion interactions, overlooking inter-frame rate dependencies arising from shifts in per-frame coding parameters. This often leads to suboptimal bitrate allocation and cascading parameter decisions. To address this, we propose a reinforcement-learning (RL)-based rate control framework that formulates the task as a frame-by-frame sequential decision process. At each frame, an RL agent observes a spatiotemporal state and selects coding parameters to optimize a long-term reward that reflects rate-distortion (R-D) performance and bitrate adherence. Unlike prior methods, our approach jointly determines bitrate allocation and coding parameters in a single step, independent of group of pictures (GOP) structure. Extensive experiments across diverse NVC architectures show that our method reduces the average relative bitrate error to 1.20% and achieves up to 13.45% bitrate savings at typical GOP sizes, outperforming existing approaches. In addition, our framework demonstrates improved robustness to content variation and bandwidth fluctuations with lower coding overhead, making it highly suitable for practical deployment.

eess.IV↗
arXiv2026

Reliable Use of Lemmas via Eligibility Reasoning and Section$-$Aware Reinforcement Learning

Recent large language models (LLMs) perform strongly on mathematical benchmarks yet often misapply lemmas, importing conclusions without validating assumptions. We formalize lemma$-$judging as a structured prediction task: given a statement and a candidate lemma, the model must output a precondition check and a conclusion$-$utility check, from which a usefulness decision is derived. We present RULES, which encodes this specification via a two$-$section output and trains with reinforcement learning plus section$-$aware loss masking to assign penalty to the section responsible for errors. Training and evaluation draw on diverse natural language and formal proof corpora; robustness is assessed with a held$-$out perturbation suite; and end$-$to$-$end evaluation spans competition$-$style, perturbation$-$aligned, and theorem$-$based problems across various LLMs. Results show consistent in$-$domain gains over both a vanilla model and a single$-$label RL baseline, larger improvements on applicability$-$breaking perturbations, and parity or modest gains on end$-$to$-$end tasks; ablations indicate that the two$-$section outputs and section$-$aware reinforcement are both necessary for robustness.

cs.CL↗
arXiv2026

Superposition unifies power-law training dynamics

We investigate the role of feature superposition in the emergence of power-law training dynamics using a teacher-student framework. We first derive an analytic theory for training without superposition, establishing that the power-law training exponent depends on both the input data statistics and channel importance. Remarkably, we discover that a superposition bottleneck induces a transition to a universal power-law exponent of $\sim 1$, independent of data and channel statistics. This one over time training with superposition represents an up to tenfold acceleration compared to the purely sequential learning that takes place in the absence of superposition. Our finding that superposition leads to rapid training with a data-independent power law exponent may have important implications for a wide range of neural networks that employ superposition, including production-scale large language models.

cs.LG↗
arXiv2026

Non-Equilibrium Phase Transition in a Boundary-Driven Dissipative Fermionic Chain

We demonstrate that a boundary-localized periodic (Floquet) drive can induce nontrivial long-range correlations in a non-interacting fermionic chain which is additionally subject to boundary dissipation. Surprisingly, we find that this phenomenon occurs even when the corresponding isolated bulk is in a trivial gapped phase with exponentially decaying correlations. We argue that this boundary-drive induced non-equilibrium transition (as witnessed through the correlation matrix) is driven by a resonance mechanism whereby the drive frequency bridges bulk energy gaps, allowing boundary-injected particles and holes to propagate and mediate long-range correlations into the bulk. We also numerically establish that when the drive bridges a particle-hole gap, the induced long-range order scales as a power law with the bulk pairing potential ($χ\sim γ^2$). Our results highlight the potential of localized coherent driving for generating macroscopic order in open quantum systems.

quant-ph↗
arXiv2026

Electronic Origin of Density Wave Orders in a Trilayer Nickelate

The discovery of superconductivity in Ruddlesden-Popper nickelates has established a new frontier in the study of high-temperature superconductors. However, the underlying pairing mechanism and its relationship to the material's electronic and magnetic ground states remain elusive. Since unconventional superconductivity often emerges from a complex interplay of magnetic correlations, elucidating the magnetic ground state of the nickelates at ambient pressure is crucial for understanding the emergence of superconductivity under high pressure. Here, we combine high-resolution angle-resolved photoemission spectroscopy with tight-binding model simulation to investigate the electronic structure of the representative trilayer Ruddlesden-Popper nickelate La$_4$Ni$_3$O$_{10}$. We provide the first experimental evidence of band splitting induced by interlayer coupling and further resolve the momentum-dependent density wave gap structures along all the Fermi surfaces. Our findings identify the mirror-selective Fermi surface nesting as the origin of the interlayer antiferromagnetic spin density wave and demonstrate the dominant role of Ni-3d$_{z^2}$ orbitals in the low-energy physics of La$_4$Ni$_3$O$_{10}$. These results provide a fundamental framework for understanding the magnetic interactions and high-temperature superconductivity mechanism in the Ruddlesden-Popper nickelate family.

cond-mat.supr-con↗
arXiv2026

Thinking Broad, Acting Fast: Latent Reasoning Distillation from Multi-Perspective Chain-of-Thought for E-Commerce Relevance

Effective relevance modeling is crucial for e-commerce search, as it aligns search results with user intent and enhances customer experience. Recent work has leveraged large language models (LLMs) to address the limitations of traditional relevance models, especially for long-tail and ambiguous queries. By incorporating Chain-of-Thought (CoT) reasoning, these approaches improve both accuracy and interpretability through multi-step reasoning. However, two key limitations remain: (1) most existing approaches rely on single-perspective CoT reasoning, which fails to capture the multifaceted nature of e-commerce relevance (e.g., user intent vs. attribute-level matching vs. business-specific rules); and (2) although CoT-enhanced LLM's offer rich reasoning capabilities, their high inference latency necessitates knowledge distillation for real-time deployment, yet current distillation methods discard the CoT rationale structure at inference, using it as a transient auxiliary signal and forfeiting its reasoning utility. To address these challenges, we propose a novel framework that better exploits CoT semantics throughout the optimization pipeline. Specifically, the teacher model leverages Multi-Perspective CoT (MPCoT) to generate diverse rationales and combines Supervised Fine-Tuning (SFT) with Direct Preference Optimization (DPO) to construct a more robust reasoner. For distillation, we introduce Latent Reasoning Knowledge Distillation (LRKD), which endows a student model with a lightweight inference-time latent reasoning extractor, allowing efficient and low-latency internalization of the LLM's sophisticated reasoning capabilities. Evaluated in offline experiments and online A/B tests on an e-commerce search advertising platform serving tens of millions of users daily, our method delivers significant offline gains, showing clear benefits in both commercial performance and user experience.

cs.IR↗
arXiv2026

SeedVR2: One-Step Video Restoration via Diffusion Adversarial Post-Training

Recent advances in diffusion-based video restoration (VR) demonstrate significant improvement in visual quality, yet yield a prohibitive computational cost during inference. While several distillation-based approaches have exhibited the potential of one-step image restoration, extending existing approaches to VR remains challenging and underexplored, particularly when dealing with high-resolution video in real-world settings. In this work, we propose a one-step diffusion-based VR model, termed as SeedVR2, which performs adversarial VR training against real data. To handle the challenging high-resolution VR within a single step, we introduce several enhancements to both model architecture and training procedures. Specifically, an adaptive window attention mechanism is proposed, where the window size is dynamically adjusted to fit the output resolutions, avoiding window inconsistency observed under high-resolution VR using window attention with a predefined window size. To stabilize and improve the adversarial post-training towards VR, we further verify the effectiveness of a series of losses, including a proposed feature matching loss without significantly sacrificing training efficiency. Extensive experiments show that SeedVR2 can achieve comparable or even better performance compared with existing VR approaches in a single step.

cs.CV↗
arXiv2026

Unusual Dual Flat Bands and two-dimensional Dirac-node Arc State in Kagome Metal Ni3In2S2

Kagome materials are at the frontier of condensed matter physics. An ideal kagome lattice features only one geometrically frustrated flat band spanning the entire momentum space and a single Dirac cone at the Brillouin-zone corners. However, for the first time, here we observe unusual flat-band and Dirac physics in the newly discovered "322" kagome material Ni3In2S2 by combining high-resolution synchrotron- and laser-based angle-resolved photoemission spectroscopy with a micro-focused beam, scanning tunneling microscopy, and first-principles calculations. We resolve two distinct electronic flat-band states located in close proximity to the Fermi level: a robust Topological Surface Flat Band at ~40 meV below the Fermi level on the Sulfur-terminated surface, originating from weak topological insulator states, and a kagome lattice-derived flat band at ~100 meV binding energy with an ultranarrow bandwidth (~5 meV). Instead of the single Dirac cone, the Indium-terminated surface hosts a rare two-dimensional Dirac-node arc state, where the gapless Dirac nodes extend along an open one-dimensional line crossing the Brillouin-zone boundary, exhibiting sharp linear dispersion, exceptionally high Fermi velocity, and pronounced circular dichroism. These findings establish Ni3In2S2 as a unique topological kagome metal in which multiple flat-band states of different physical origin coexist with an unusual Dirac-node arc, opening an avenue for discovering flat-band--driven and topology-enabled quantum phenomena.

cond-mat.mtrl-sci↗
arXiv2026

Computational TIRF enables optical sectioning beyond the evanescent field for widefield fluorescence microscopy

The resolving ability of widefield fluorescence microscopy is fundamentally limited by out-of-focus background owing to its low axial resolution, particularly for densely labeled biological samples. Although total internal reflection fluorescence (TIRF) microscopy provides strong near-surface sectioning, they are intrinsically restricted to shallow imaging depths. Here we present computational TIRF (cTIRF), a deep learning-based imaging modality that generates TIRF-like sectioned images directly from conventional widefield epifluorescence measurements without any optical modification. By integrating a physics-informed forward model into network training, cTIRF achieves effective background suppression and axial resolution enhancement while maintaining consistency with the measured widefield data. We demonstrate that cTIRF recovers near-surface structures with performance comparable to experimental TIRF, and further enables both single-frame and volumetric sectioned reconstruction in densely labeled samples where conventional TIRF fails. This work establishes cTIRF as a practical and deployable alternative to hardware-based optical sectioning in fluorescence microscopy, enabled by rapid adaptation to new imaging systems with minimal calibration data.

physics.optics↗
arXiv2026

ConSurv: Multimodal Continual Learning for Survival Analysis

Survival prediction of cancers is crucial for clinical practice, as it informs mortality risks and influences treatment plans. However, a static model trained on a single dataset fails to adapt to the dynamically evolving clinical environment and continuous data streams, limiting its practical utility. While continual learning (CL) offers a solution to learn dynamically from new datasets, existing CL methods primarily focus on unimodal inputs and suffer from severe catastrophic forgetting in survival prediction. In real-world scenarios, multimodal inputs often provide comprehensive and complementary information, such as whole slide images and genomics; and neglecting inter-modal correlations negatively impacts the performance. To address the two challenges of catastrophic forgetting and complex inter-modal interactions between gigapixel whole slide images and genomics, we propose ConSurv, the first multimodal continual learning (MMCL) method for survival analysis. ConSurv incorporates two key components: Multi-staged Mixture of Experts (MS-MoE) and Feature Constrained Replay (FCR). MS-MoE captures both task-shared and task-specific knowledge at different learning stages of the network, including two modality encoders and the modality fusion component, learning inter-modal relationships. FCR further enhances learned knowledge and mitigates forgetting by restricting feature deviation of previous data at different levels, including encoder-level features of two modalities and the fusion-level representations. Additionally, we introduce a new benchmark integrating four datasets, Multimodal Survival Analysis Incremental Learning (MSAIL), for comprehensive evaluation in the CL setting. Extensive experiments demonstrate that ConSurv outperforms competing methods across multiple metrics.

cs.LG↗
arXiv2026

Integrated Sensing and Semantic Communication with Adaptive Source-Channel Coding

Semantic communication has emerged as a new paradigm to facilitate the performance of integrated sensing and communication systems in 6G. However, most of the existing works mainly focus on sensing data compression to reduce the subsequent communication overheads, without considering the integrated transmission framework for both the SemCom and sensing tasks. This paper proposes an adaptive source-channel coding and beamforming design framework for integrated sensing and SemCom systems by jointly optimizing the coding rate for SemCom task and the transmit beamforming for both the SemCom and sensing tasks. Specifically, an end-to-end semantic distortion function is approximated by deriving an upper bound composing of source and channel coding induced components, and then a hybrid Cramér-Rao bound (HCRB) is also derived for target position under imperfect time synchronization. To facilitate the joint optimization, a distortion minimization problem is formulated by considering the HCRB threshold, channel uses, and power budget. Subsequently, an alternative optimization algorithm composed of successive convex approximation and fractional programming is proposed to address this problem by decoupling it into two subproblems for coding rate and beamforming designs, respectively. Simulation results demonstrate that our proposed scheme outperforms the conventional deep joint source-channel coding -water filling-zero forcing benchmark.

eess.SP↗
arXiv2026

CausalSpatial: A Benchmark for Object-Centric Causal Spatial Reasoning

Humans can look at a static scene and instantly predict what happens next -- will moving this object cause a collision? We call this ability Causal Spatial Reasoning. However, current multimodal large language models (MLLMs) cannot do this, as they remain largely restricted to static spatial perception, struggling to answer "what-if" questions in a 3D scene. We introduce CausalSpatial, a diagnostic benchmark evaluating whether models can anticipate consequences of object motions across four tasks: Collision, Compatibility, Occlusion, and Trajectory. Results expose a severe gap: humans score 84% while GPT-5 achieves only 54%. Why do MLLMs fail? Our analysis uncovers a fundamental deficiency: models over-rely on textual chain-of-thought reasoning that drifts from visual evidence, producing fluent but spatially ungrounded hallucinations. To address this, we propose the Causal Object World model (COW), a framework that externalizes the simulation process by generating videos of hypothetical dynamics. With explicit visual cues of causality, COW enables models to ground their reasoning in physical reality rather than linguistic priors. We make the dataset and code publicly available here: https://github.com/CausalSpatial/CausalSpatial

cs.CV↗
arXiv2026

Comparative validation of surgical phase recognition, instrument keypoint estimation, and instrument instance segmentation in endoscopy: Results of the PhaKIR 2024 challenge

Reliable recognition and localization of surgical instruments in endoscopic video recordings are foundational for a wide range of applications in computer- and robot-assisted minimally invasive surgery (RAMIS), including surgical training, skill assessment, and autonomous assistance. However, robust performance under real-world conditions remains a significant challenge. Incorporating surgical context - such as the current procedural phase - has emerged as a promising strategy to improve robustness and interpretability. To address these challenges, we organized the Surgical Procedure Phase, Keypoint, and Instrument Recognition (PhaKIR) sub-challenge as part of the Endoscopic Vision (EndoVis) challenge at MICCAI 2024. We introduced a novel, multi-center dataset comprising thirteen full-length laparoscopic cholecystectomy videos collected from three distinct medical institutions, with unified annotations for three interrelated tasks: surgical phase recognition, instrument keypoint estimation, and instrument instance segmentation. Unlike existing datasets, ours enables joint investigation of instrument localization and procedural context within the same data while supporting the integration of temporal information across entire procedures. We report results and findings in accordance with the BIAS guidelines for biomedical image analysis challenges. The PhaKIR sub-challenge advances the field by providing a unique benchmark for developing temporally aware, context-driven methods in RAMIS and offers a high-quality resource to support future research in surgical scene understanding.

cs.CV↗