arXiv subjects

Hang Zhou

Publications and source records attributed to Hang Zhou.

At least 37 records · Page 2Linked to original sources

arXiv2026

An emerging baryon cycle in a galaxy 500 million years after the Big Bang

The emergence of stellar feedback as a regulator of galaxy growth marks a fundamental transition in cosmic history. At early times, rapid gas accretion and collapse may induce intense star formation before feedback becomes effective, producing feedback-free starbursts. When and how such bursts subsequently develop into self-regulated baryon cycles remain observationally unknown. Here we show that Gz9p3, a merging galaxy at $z=9.311$, is caught in this transition only 500 million years after the Big Bang. Deep JWST spectroscopy reveals a substantial neutral-gas reservoir along its merger-driven tidal structure and a multiphase outflow. Fine-structure absorption provides the first direct measurement of the electron density of the cool outflowing gas at high redshift ($\approx\,17\,{\rm cm^{-3}}$), yielding a mass-loading factor among the highest yet measured for galaxies of comparable stellar mass. The emergence of such efficient feedback after an intense burst is consistent with the delayed onset of feedback expected in feedback-free starburst models. The cool outflowing gas is unlikely to escape the host halo, implying that much of this metal-enriched material may remain available for future recycling through the circumgalactic medium. Gz9p3 therefore provides an early view of a baryon cycle being established through the interplay of merger-driven gas redistribution, bursty star formation and stellar feedback, suggesting that feedback-regulated recycling was already shaping galaxy growth during the epoch of reionization.

astro-ph.GA↗

arXiv2026

ProPINN: Demystifying Propagation Failures in Physics-Informed Neural Networks

Physics-informed neural networks (PINNs) have earned high expectations in solving partial differential equations (PDEs), but their optimization usually faces thorny challenges due to the unique derivative-dependent loss function. By analyzing the loss distribution, previous research observed the propagation failure phenomenon of PINNs, intuitively described as the correct supervision for model outputs cannot ''propagate'' from initial states or boundaries to the interior domain. Going beyond intuitive understanding, this paper provides a formal and in-depth study of propagation failure and its root cause. Based on a detailed comparison with classical finite element methods, we ascribe the failure to the conventional single-point-processing architecture of PINNs and further prove that propagation failure is essentially caused by the lower gradient correlation of PINN models on nearby collocation points. Compared to superficial loss maps, this new perspective provides a more precise quantitative criterion to identify where and why PINN fails. The theoretical finding also inspires us to present a new PINN architecture, named ProPINN, which can effectively unite the gradients of region points for better propagation. ProPINN can reliably resolve PINN failure modes and significantly surpass advanced Transformer-based models with 46% relative promotion.

cs.LG↗

arXiv2026

MVHOI: Bridge Multi-view Condition to Complex Human-Object Interaction Video Reenactment via 3D Foundation Model

Human-Object Interaction (HOI) video reenactment aims to transfer the interaction dynamics of a source video to a novel target object while preserving realistic hand-object coordination. Existing methods typically rely on sparse 2D motion controls and monocular references, which are insufficient for complex out-of-plane motion and large viewpoint changes. We present MVHOI, a two-stage framework combining implicit motion extraction, 3D-aware multi-view reasoning, and video generation. In the first stage, a motion extractor encodes object dynamics into implicit motion descriptors. Conditioned on these descriptors, our Motion-Driven Object Prior (MDOP) module queries a 3D foundation model over multi-view references of the target object and autoregressively predicts coarse object anchors, a sequence of images that track the object's evolving orientation and appearance under the source motion without any explicit pose estimation. In the second stage, a DiT-based video generation model uses these anchors as structural guidance and the multi-view references as appearance guidance. We further reuse cross-view attention from MDOP as a soft attention bias to reduce reference-view confusion. For long videos, a cross-iterative inference strategy refreshes subsequent object priors using refined video outputs. Experiments demonstrate consistent improvements over state-of-the-art methods in object fidelity, motion consistency, visual quality, and interaction realism.

cs.CV↗

arXiv2026

FAIR-Calib: Frontier-Aware Instability-Reweighted Calibration for Post-Training Quantization of Diffusion Large Language Models

Diffusion Large Language Models (dLLMs) refine tokens iteratively but commit them irreversibly, leading to a "stability lag" where early decisions remain fragile even after being written. We reveal that Post-Training Quantization (PTQ) error easily flips these borderline decisions at the write frontier, which are then permanently locked in and amplified. To address this, we propose Frontier-Aware Instability-Reweighted Calibration (FAIR-Calib), a two-stage PTQ framework for dLLMs. Stage I probes a full-precision teacher to estimate a position prior that combines frontier hits and masked-stage reliability. Stage II performs off-policy, layer-wise calibration by minimizing a reweighted hidden-state MSE, effectively prioritizing the protection of fragile frontier states without requiring expensive end-to-end diffusion rollouts. We further theoretically justify our weighted objective as a surrogate for output KL divergence. Empirically, FAIR-Calib consistently outperforms state-of-the-art baselines on LLaDA and Dream (W4A4), significantly reducing frontier decision flips and suppressing post-commit mismatches across diverse benchmarks.

cs.LG↗

arXiv2026

What Should a Skill Remember? Quality--Cost Trade-offs in Cost-Aware Skill Rewriting for Language Model Agents

Large language model agents increasingly rely on skills: reusable procedural documents encoding workflows, tool use, implementation patterns, validation checks, and domain rules. Skill rewriting is often treated as prompt compression, but shorter skills can make agents more expensive by removing sparse operational anchors that prevent exploration, debugging, and recovery. We study skill rewriting through this economic lens. Our controlled framework profiles skill structure, rewrites skills using information-preservation strategies, and evaluates the rewrites under fixed task instructions, environments, and verifiers. Experiments on SkillsBench reveal distinct quality--cost trade-offs across strategies: API/code anchoring, workflow guarding, and rule/formula anchoring benefit different task families, with no universally dominant template. In the main held-out evaluation, the learned policy reduces total cost by 7.0% and downstream agent-token cost by 6.0%; in frozen cross-model transfer, the corresponding reductions average 14.7% and 13.7%, while verifier quality is preserved. These results position skill design as cost-aware operational knowledge engineering rather than prompt compression. Resources: https://github.com/1Reminding/Skill_EE.

cs.CL↗

arXiv2026

Agentic Routing: The Harness-Native Data Flywheel

Large language model agents are increasingly executed not by a single model call, but by an execution harness that manages observation, context, control, action, state, and verification. At the same time, frontier and open models are becoming structurally specialized: a model that is strong at code editing, long-context recovery, tool use, mathematical reasoning, or low-latency response may not dominate on the other axes. This makes model selection inside an agent a core systems problem rather than a per-query serving trick. Existing routing methods mostly optimize single-turn cost-quality trade-offs and therefore miss the execution state, intermediate failures, and feedback loops that make agents different from chat completion. We propose Harness-Native agentic routing, a step-level routing paradigm that selects either a single best-fit model for cost-effective execution or multiple complementary models for ensemble-style accuracy improvement, conditioned on the full harness state. The key insight is that every routing decision naturally produces a structured data record -- consisting of the query, harness state, model choice or model set, execution trace, outcome, and cost -- whose labels are supplied by the environment rather than by the router itself. These records form a harness-native data flywheel: execution traces train better routers and harness-native models, which improve cost-quality trade-offs and generate more traces under the same budget. We instantiate this idea in OpenSquilla with a four-layer routing stack, an open LightGBM cold-start ranker, and a staged router-model path that turns logged arena records into progressively stronger routing policies. The report studies singleton and multi-model routing on agentic benchmarks including DRACO and PinchBench, and argues that agentic routing is not merely cost control, but a data engine for agent-native training.

cs.CL↗

arXiv2026

HieDG: A Hierarchical Discrete Geometry-Guided Framework for Multi-Animal Tracking

Multi-animal tracking (MAT) is critical for wildlife monitoring and behavioral analysis, yet remains challenging due to uniform appearance, high density, and irregular motion. Existing methods typically follow heuristic- or query-based paradigms: the former relies on handcrafted geometric associations without end-to-end optimization, whereas the latter enables joint optimization but relies heavily on appearance embeddings. In such conditions, continuous geometric embeddings can be unstable, as small coordinate perturbations may disproportionately alter cross-frame attention weights, degrading identity association performance. To address this limitation, we propose HieDG, a Hierarchical Discrete Geometry-guided tracking framework that reformulates geometric dynamics as structured discrete representations within a query-based tracker. Instead of directly using raw geometric signals, HieDG employs a two-stage residual codebook to discretize position, scale, and velocity cues, transforming unstable continuous geometry into structured, stable discrete tokens. These tokens are aligned with visual embeddings and integrated into the tracking queries to enhance identity consistency. Extensive experiments on animal-specific benchmarks (AnimalTrack, BFT, and BuckTales) demonstrate state-of-the-art association performance with significant improvements in HOTA, AssA, and IDF1. Additional evaluations on generic multi-object tracking benchmarks, including DanceTrack and SportsMOT, show competitive performance, indicating the broader applicability of discretized geometric modeling beyond animal-specific scenarios.

cs.CV↗

arXiv2026

Confirmation and Refutation of Lyman Continuum Leakers at $z\sim3$ with JWST NIRSpec/IFU

Our understanding of the physical mechanisms and environments conducive to the escape of Lyman-continuum (LyC) radiation within the first 2 Gyr of cosmic history remains limited. Here we present a detailed analysis of JWST/NIRSpec medium-resolution IFU observations of two LyC-leaker candidates, LACES-94460 and LACES-104037 at z = 3.1, selected from deep HST/WFC3 F336W imaging and supported by ground-based spectroscopy. We first rule out LACES-94460 as a genuine LyC leaker, demonstrating that its apparent F336W signal originates from a nearby low-redshift interloper at z = 1.6, unambiguously identified through IFU spectroscopy. In contrast, for LACES-104037 we spectroscopically confirm bona fide LyC emission arising from a tidal-tail structure during the early stage of a galaxy merger, dubbed LACES104037-LyC. LACES104037-LyC exhibits extremely low rest-frame optical emission-line equivalent widths together with an exceptionally strong LyC flux. Within a picket-fence model framework, we reproduce its observed spectral and photometric properties with a young stellar population of age $\sim5$ Myr and a LyC escape fraction of $f_{\mathrm{esc}} \sim 99\%$. Our identification and detailed modeling of LACES104037-LyC provide one of the first compelling observational demonstrations for merger-driven LyC escape, indicating that galaxy mergers may represent an important and previously underappreciated contributor to the ionizing photon budget relevant for cosmic reionization. Furthermore, our analysis highlights the critical role of sub-kiloparsec resolution spectroscopy in securely identifying LyC leakers, removing contamination from closely projected low-redshift interlopers, and pinpointing the physical regions responsible for LyC leakage.

astro-ph.GA↗

arXiv2026

Transolver-3: Scaling Up Transformer Solvers to Industrial-Scale Geometries

Deep learning has emerged as a transformative tool for the neural surrogate modeling of partial differential equations (PDEs), known as neural PDE solvers. However, scaling these solvers to industrial-scale geometries with over $10^8$ cells remains a fundamental challenge due to the prohibitive memory complexity of processing high-resolution meshes. We present Transolver-3, a new member of the Transolver family as a highly scalable framework designed for high-fidelity physics simulations. To bridge the gap between limited GPU capacity and the resolution requirements of complex engineering tasks, we introduce two key architectural optimizations: faster slice and deslice by exploiting matrix multiplication associative property and geometry slice tiling to partition the computation of physical states. Combined with an amortized training strategy by learning on random subsets of original high-resolution meshes and a physical state caching technique during inference, Transolver-3 enables high-fidelity field prediction on industrial-scale meshes. Extensive experiments demonstrate that Transolver-3 can handle meshes with over 160 million cells, achieving impressive performance across three challenging simulation benchmarks, including aircraft and automotive design tasks. Code is available at https://github.com/thuml/Transolver-3.

cs.LG↗

arXiv2026

RefAlign: Representation Alignment for Reference-to-Video Generation

Reference-to-video (R2V) generation is a controllable video synthesis paradigm that constrains the generation process using both text prompts and reference images, enabling applications such as personalized advertising and virtual try-on. In practice, existing R2V methods typically introduce additional high-level semantic or cross-modal features alongside the VAE latent representation of the reference image and jointly feed them into the diffusion Transformer (DiT). These auxiliary representations provide semantic guidance and act as implicit alignment signals, which can partially alleviate pixel-level information leakage in the VAE latent space. However, they may still struggle to address copy--paste artifacts and multi-subject confusion caused by modality mismatch across heterogeneous encoder features. In this paper, we propose RefAlign, a representation alignment framework that explicitly aligns DiT reference-branch features to the semantic space of a visual foundation model (VFM). The core of RefAlign is a reference alignment loss that pulls the reference features and VFM features of the same subject closer to improve identity consistency, while pushing apart the corresponding features of different subjects to enhance semantic discriminability. This simple yet effective strategy is applied only during training, incurring no inference-time overhead, and achieves a better balance between text controllability and reference fidelity. Extensive experiments on the OpenS2V-Eval benchmark demonstrate that RefAlign outperforms current state-of-the-art methods in TotalScore, validating the effectiveness of explicit reference alignment for R2V tasks.

cs.CV↗

arXiv2026

Visual Generation in the New Era: An Evolution from Atomic Mapping to Agentic World Modeling

Recent visual generation models have made major progress in photorealism, typography, instruction following, and interactive editing, yet they still struggle with spatial reasoning, persistent state, long-horizon consistency, and causal understanding. We argue that the field should move beyond appearance synthesis toward intelligent visual generation: plausible visuals grounded in structure, dynamics, domain knowledge, and causal relations. To frame this shift, we introduce a five-level taxonomy: Atomic Generation, Conditional Generation, In-Context Generation, Agentic Generation, and World-Modeling Generation, progressing from passive renderers to interactive, agentic, world-aware generators. We analyze key technical drivers, including flow matching, unified understanding-and-generation models, improved visual representations, post-training, reward modeling, data curation, synthetic data distillation, and sampling acceleration. We further show that current evaluations often overestimate progress by emphasizing perceptual quality while missing structural, temporal, and causal failures. By combining benchmark review, in-the-wild stress tests, and expert-constrained case studies, this roadmap offers a capability-centered lens for understanding, evaluating, and advancing the next generation of intelligent visual generation systems.

cs.CV↗

arXiv2026

Accurate Small-Signal Modeling of Digitally Controlled Buck Converters with ADC-PWM Synchronization

Digital control has become increasingly widespread in modern power electronic converters. When acquiring feedback signals such as the inductor current, synchronizing the analog-to-digital converter (ADC) with the digital pulse-width modulator (DPWM) is commonly employed to accurately track their steady-state average. However, the small-signal implications of such synchronization have not been investigated. This paper presents an exact small-signal model for digitally controlled buck converters operating in forced continuous-conduction mode (FCCM) under constant-frequency current-mode control, explicitly accounting for DPWM-ADC synchronization. Using a sampled-data framework, the proposed model captures all sideband effects introduced by the sampling process, yielding precise predictions of both analog and digital loop gains, even at frequencies beyond the switching and sampling frequencies. Both asymmetrical and symmetrical carrier modulations are considered. Furthermore, the digital loop gain is derived in closed form using the modified z-transform, enabling low-complexity compensator design and stability assessment. Within this framework, the analog loop gain can be directly obtained from the digital loop gain, thereby eliminating the need for computationally intensive infinite series evaluations. The validity of the proposed model is confirmed through both simulation and experimental results.

eess.SY↗

arXiv2026

Testing lepton-flavor-violating decay of doubly charged Higgs bosons in type-II seesaw via photon fusion at the high-energy LHC

Tiny neutrino masses can be explained by the type-II seesaw mechanism, where a triplet scalar under $SU(2)_{L}$ is predicted. Collider searches for this exotic scalar have been extensively conducted, especially for its doubly charged component $Δ^{\pm\pm}$. Utilizing the forward detectors at the Large Hadron Collider (LHC), we study the probing sensitivity for the elastic photon fusion production of the scalars $pp\to p(γγ\toΔ^{++}Δ^{--})p$ followed by the lepton-flavor-violating (LFV) decay channels $Δ^{\pm\pm}\to e^{\pm}μ^{\pm}$. With a high center-of-mass energy of 100 TeV and several luminosity scenarios, we can extensively broaden the exclusion bounds in the parametric space of Br$(Δ^{\pm\pm}\to e^{\pm}μ^{\pm})$ versus the triplet scalar mass $m_Δ$. Specifically, at the 100 TeV LHC with an integrated luminosity of 3 ab$^{-1}$, the mass exclusion limit at 95\% C.L. can reach around 1150 GeV with the assumption of inverted neutrino mass hierarchy.

hep-ph↗

arXiv2026

PhySense: Sensor Placement Optimization for Accurate Physics Sensing

Physics sensing plays a central role in many scientific and engineering domains, which inherently involves two coupled tasks: reconstructing dense physical fields from sparse observations and optimizing scattered sensor placements to observe maximum information. While deep learning has made rapid advances in sparse-data reconstruction, existing methods generally omit optimization of sensor placements, leaving the mutual enhancement between reconstruction and placement on the shelf. To change this suboptimal practice, we propose PhySense, a synergistic two-stage framework that learns to jointly reconstruct physical fields and to optimize sensor placements, both aiming for accurate physics sensing. The first stage involves a flow-based generative model enhanced by cross-attention to adaptively fuse sparse observations. Leveraging the reconstruction feedback, the second stage performs sensor placement via projected gradient descent to satisfy spatial constraints. We further prove that the learning objectives of the two stages are consistent with classical variance-minimization principles, providing theoretical guarantees. Extensive experiments across three challenging benchmarks, especially a 3D geometry dataset, indicate PhySense achieves state-of-the-art physics sensing accuracy and discovers informative sensor placements previously unconsidered. Code is available at this repository: https://github.com/thuml/PhySense.

eess.SP↗

arXiv2026

Harnessing hidden quantum metric response in a 2D magnet via nonlocal photovoltaic effect

The quantum geometry of Bloch wavefunctions underpins a wealth of emergent phenomena in quantum materials. Its imaginary part, the Berry curvature, has long been recognized as a key source for hallmark effects such as quantum Hall and topological phenomena, etc. The real part of quantum geometry, the quantum metric, has recently garnered considerable attention due to predictions of a range of unconventional nonlinear and nonequilibrium responses. Such responses usually vanish in centrosymmetric systems, largely restricting relevant studies to non-centrosymmetric materials. Here we challenge this convention by revealing that the vanished quantum metric response can survive in a hidden form. Using a non-local photovoltaic scheme in a layered magnetic semiconductor, we spatially separate mutually compensating photocurrents and thereby detect such hidden quantum metric response. We demonstrate this effect across distinct magnetic states and down to the ultrathin limit. Moreover, we realize reconfigurable, nonvolatile and probabilistic photodetection enabled by the quantum metric response. These results not only fundamentally expand the material landscape for quantum geometric physics, but also open new gateway to harvest the quantum geometric contributions for state-of-the-art nonvolatile reprogrammable sensing and computing applications.

cond-mat.mes-hall↗

arXiv2026

A Novel Segment-Based Tracking Algorithm for HLT under High-Occupancy and Complex Conditions

In the High-Level Trigger (HLT) of both electron-positron and hadron collision experiments, the tracking process for large-volume gaseous detectors typically consumes a latency of hundreds of milliseconds. Upgrades of existing experiments and the development of next-generation facilities demand enhanced HLT tracking performance: handling higher detector occupancy and suppressing latency. To address high occupancy conditions, a novel HLT tracking algorithm based on track segments is proposed. This method involves constructing a pattern bank comprising 11 pre-defined patterns, optimizing edge-matrix formation using position, momentum, and timing criteria, and merging stereo superlayer segments to improve track consistency. These measures significantly reduce the number of stored segments and the size of the edge matrix, thereby lowering the complexity of global tracking. Even at 25\% occupancy, the number of elements for global tracking is reduced to approximately 400-500, while the density of the edge matrix remains below 1\%. With the depth-first search within connected components, the simulation results show that the algorithm maintains stable performance with occupancy ranging from 5\% to 25\%, achieving a data compression ratio of approximately 50\% to 70\%. Validation against the STCF offline reconstruction algorithm confirms that the HLT algorithm preserves high signal-hit retention without introducing significant adverse effects on offline tracking efficiency or on the reconstruction. These results demonstrate that the proposed algorithm can retain high-quality signal hits across a broad range of occupancy levels, indicating a strong potential for further development and adaptation to even more challenging, high-luminosity experimental conditions.

physics.ins-det↗

arXiv2026

The Structure and Evolution of LRDs: Insights from JWST NIRSpec Medium and High Resolution Spectroscopy at $z\sim4$

We present an analysis of medium/high-resolution JWST/NIRSpec spectra for 11 LRDs at $z \sim 4$. By decomposing the broad and narrow components of the Balmer emission lines, we investigate the connection between line emission and UV/optical continua for the LRD population. We find that the broad H$α$ luminosity strongly correlates with the optical continuum (but not with the UV), indicating a common AGN origin for both. In contrast, the [O III] line strength is correlated with the UV continuum rather than the optical. Using the width and luminosity of the broad H$α$ line, we estimate central black hole masses of $10^6-10^8 M_{\odot}$ accreting at high Eddington ratios, consistent with an early ($λ_{\rm Edd} \sim 0.6$), rapid-growth phase of AGN evolution. Assuming a constant mass accretion rate in the framework of slim-disk models, we infer growth timescales of $\sim 10^5-10^7\rm yr$, and suggest LRDs may evolve into narrow-line Seyfert 1 galaxies. Upper limits from our spectra indicate that LRDs exhibit intrinsically weak optical Fe II emission compared to typical AGN. To simultaneously account for the inferred broad-line region size and observed luminosity, we propose a "Clumpy Envelope" model in which the optical emission arises from an extended, clumpy gas with a characteristic radius of tens of light-days. The diversity in observed optical continuum shapes can be explained by radial temperature gradients and self-absorption effects within this structure. Our results demonstrate the power of JWST high-resolution spectroscopy in probing the central engines and physical nature of the LRD population.

astro-ph.GA↗