Searcharxiv⌕ Search

arXiv subjects

Pengfei Zhu

Publications and source records attributed to Pengfei Zhu.

At least 19 recordsLinked to original sources
arXiv2026

A2DINOv3: Rethinking Multi-Modal Object Detection via Socialized Collaboration

Multi-modal object detection is essential for robust scene understanding in challenging conditions, including low-light and adverse environments. Recent vision foundation models (e.g., DINOv3) have exhibited strong representation capabilities, yet adapting them to multi-modal scenarios remains challenging. Existing dense cross-modal fusion strategies often force heterogeneous modalities to interact indiscriminately, which may introduce redundant information and disrupt the valuable pre-trained representations. To address this issue, we revisit multi-modal fusion from the perspective of socialized learning and propose adapter to DINOv3 (A2DINOv3), a multi-expert collaboration framework with a Socialized Collaboration Protocol (SCP). Specifically, RGB and infrared branches are modeled as heterogeneous experts that independently preserve their specialized knowledge while exchanging complementary information through selective and constrained interactions. This design mitigates harmful cross-modal interference and prevents degradation of pre-trained priors during adaptation. Furthermore, a zero-initialization strategy is introduced to gradually activate cross-modal collaboration, enabling a smooth transition from modality-specific learning to cooperative representation learning. Extensive experiments on four multi-modal benchmarks, including aerial detection (GAIIC), autonomous driving (FLIR), low-light surveillance (LLVIP), and diverse real-world scenarios (M3FD), demonstrate that A2DINOv3 consistently achieves state-of-the-art performance in multi-modal object detection.

cs.CV↗
arXiv2026

Spectral Geometry and Dispersion-Constrained Projection of Diffusive Fields

Diffusive fields obey operator-imposed relations between spatial structure and temporal decay, yet conventional spectral filtering selects components primarily according to frequency or wavenumber magnitude. Here we show that the diffusion operator defines a spectral geometry in the joint space of spatial wavenumber and modal decay rate, where physically admissible modes occupy the manifold $η=α|\mathbf{k}|^2$. This geometry separates spectral scale from physical consistency: high-wavenumber modes can remain diffusion-consistent, whereas lower-wavenumber modes can violate the governing dynamics. We exploit this distinction by introducing an operator residual and a finite-width soft projection that selects spectral components according to their distance from the diffusion manifold rather than their spectral magnitude. Numerical studies demonstrate robust recovery under noise, diffusivity mismatch, and finite acquisition, and reveal a consistency--retention tradeoff governed by the manifold width. Photothermal experiments further confirm that the projection suppresses off-manifold spectral content while retaining the dominant thermal response. These results establish operator consistency as a spectral-selection principle for diffusive fields and provide a geometric framework for physics-informed processing of dissipative systems.

physics.app-ph↗
arXiv2026

Fermionic hidden zeros

We uncover and prove a general class of hidden zeros in tree-level amplitudes with massless fermions. For arbitrary even numbers and arbitrary arrangements of massless real adjoint fermions and gluons, color-ordered gauge-theory amplitudes in $D=4,6,10$ vanish on general rectangular kinematic loci supplemented by species-dependent bridge conditions. The fermion--fermion bridge is governed simply by the vector current $χ_iγ^μχ_j$, while mixed and gluonic bridges are fixed by the corresponding gauge-covariant contractions. A worldsheet analysis proves the result at arbitrary multiplicity and traces its universality to the local fusion channels $ff\to g$, $fg/gf\to f$, and $gg\to g$, with no new primitive bridge structures appearing at higher fermion multiplicity. The same mechanism extends to ten-dimensional amplitudes with gravitons and arbitrary even numbers of gravitinos in factorized gamma-traceless polarizations, and to single-trace Einstein-Yang-Mills amplitudes with adjoint gluinos and gravitons. These results expose a finite local structure underlying fermionic hidden zeros across gauge and gravitational amplitudes.

hep-th↗
arXiv2026

UniDiffFusion: A Unified Diffusion Framework for Multi-Task and Degradation-Robust Image Fusion

General image fusion aims to integrate complementary information from multiple source images, but existing methods often rely on task-specific models and struggle to maintain robust performance under diverse degradation conditions. In this paper, we propose UniDiffFusion, a unified diffusion framework for multi-task and degradation-robust image fusion. UniDiffFusion leverages the strong generative prior of a pretrained diffusion model to establish a shared fusion backbone across heterogeneous fusion tasks, while introducing task- and degradation-aware conditional adaptation to accommodate their distinct information-selection requirements. Specifically, we employ task prompt modulation to progressively adapt the shared diffusion representations to different fusion objectives, and develop a degradation prompt router to dynamically retrieve degradation-aware priors and restore corrupted source features before fusion. Furthermore, an application prompt bank is introduced to incorporate task-oriented semantic guidance for downstream applications, such as object detection and semantic segmentation, without altering the shared fusion and restoration pathways. The proposed framework is trained in a progressive manner to decouple fusion learning, degradation-aware restoration, and application-specific adaptation, thereby reducing interference among heterogeneous objectives. Extensive experiments on visible-infrared, multi-exposure, and multi-focus image fusion demonstrate that UniDiffFusion achieves superior fusion quality and robustness under both clean and degraded conditions. Moreover, UniDiffFusion consistently improves downstream detection and semantic segmentation performance, demonstrating its effectiveness as a unified diffusion framework for both perceptual fusion and task-oriented vision.

cs.CV↗
arXiv2026

A-PAIR: A Benchmark and Identity-Consistent Grounding Framework for Air-Ground Cross-View Referring Person Detection

Air-ground cross-view referring person detection is a necessary component in the language-to-perception-to-control chain of collective embodied intelligence, grounding a language command into the same physical target before ground and aerial agents can coordinate downstream actions. Existing referring expression comprehension and open-vocabulary grounding methods do not jointly account for cross-view identity consistency, making them insufficient for Air-Ground Cross-View Referring Person Detection (AGCV-RPD), which involves similar pedestrian distractors, weak aerial appearance cues, and cross-view identity consistency. To study this problem, we introduce Air-Ground Paired Identity-Aware Referring (A-PAIR), the first comprehensive AGCV-RPD benchmark, containing 22,137 cross-view referring samples. To construct A-PAIR efficiently, we propose Factorized Annotation and Referential Alignment (FARA), a semi-automatic annotation framework that generates factorized referring descriptions and identity-consistency supervision at reduced cost. We propose Identity-Consistent Referring Grounding (ICRG), a framework that combines factorized referential grounding, candidate-completeness supervision, and cross-view consistency calibration for joint air-ground pair selection. ICRG improves ground, aerial, and pair-level detection over strong baselines, increasing pair F1 from 16.65% to 22.28%. These results show that AGCV-RPD requires paired detection and identity-consistent reasoning.

cs.CV↗
arXiv2026

Socialized Detector Learning: Trajectory-Guided and Reciprocal Distillation for Heterogeneous Object Detectors

Object detection knowledge is fragmented across independently trained, heterogeneous detectors with complementary category supports. In socialized learning, this knowledge resides in a society, and learning aims to evolve the society collectively through exchange. However, aggregation-based socialization does not explicitly plan transfer order, whereas progressive multi-teacher distillation considers order but remains a one-way student enhancement in a shared category space. Building on Socialized Learning, we formulate Socialized Detector Learning (SDL) for heterogeneous, category-specialized object detectors and propose Trajectory-Guided and Reciprocal Distillation (TGRD).TGRD estimates directed operational Inter-Detector Transfer Difficulty (IDTD) from held-out feature-alignment residuals, precomputes a fixed score table, and greedily constructs a carrier trajectory. Along the trajectory, knowledge is progressively consolidated into a union-category carrier and then returned to experts through reciprocal transfer. A conditional proxy-certificate analysis shows that, under stated assumptions, the progressive certificate is no larger than an aggregated-target counterpart. On MS COCO with four heterogeneous experts and two carrier initializations, final carriers outperform epoch-matched simultaneous aggregation controls by 2.6 AP in both settings. Reciprocal detectors attain 20.8--28.4 AP on previously unsupported categories while remaining within 1.3 AP of original expert-specific performance. These results support order-aware progressive consolidation followed by reciprocal transfer as a viable mechanism for detector-society evolution.

cs.CV↗
arXiv2026

RACO: Reliability-Aware Coarse-Goal Optimization for Inspection-Oriented UAV Vision-Language Navigation

UAV vision-language navigation (UAV-VLN) is commonly evaluated as goal reaching, but inspection-oriented deployment requires the agent to stop within a valid inspection region and avoid falsely confirming visually or semantically similar distractors. This requirement exposes a key weakness in existing coarse-to-fine UAV-VLN policies: the coarse goal predicted before local refinement is often treated as reliable, although it may drift toward plausible but incorrect object regions and limit the ability of the local stage to recover. To systematically evaluate this problem, we introduce LG-UVI, an object-centric inspection evaluation setting derived from CityNav/CityRefer. LG-UVI extends standard UAV-VLN episodes with target objects, hard distractors, type-aware inspection regions, and diagnostics for inspection-region arrival and object-level confirmation. To address this inspection-oriented setting, we further propose RACO, a reliability-aware adaptive coarse-to-fine navigation framework. Instead of treating the predicted coarse goal as a fixed waypoint, RACO views it as a runtime hypothesis and uses object-level candidate anchors to check and correct coarse localization before Stage 1 and at the Stage 1-to-Stage 2 boundary. RACO also applies scale-adaptive terminal refinement to handle terminal near-miss cases using runtime-observable geometric and anchor-based evidence. Under a unified online evaluation protocol, RACO improves SR over the reproduced HETT baseline by 9.53 and 7.98 percentage points on validation-unseen and test-unseen, respectively. It also improves inspection-region arrival and reduces false verification risk, showing that coarse-goal reliability optimization is an effective complement to existing coarse-to-fine UAV-VLN policies.

cs.RO↗
arXiv2026

Socialized Division and Collaboration: Rethinking Class-Incremental Learning under Optimization Conflicts

Class-incremental learning is commonly instantiated as a single-model paradigm, where a unified model sequentially adapts to an unbounded stream of sessions. While effective under mild distributional shifts, this formulation becomes strained when successive sessions induce incompatible optimization directions, leading to destructive interference and catastrophic forgetting. We argue that such forgetting reflects a structural limitation of enforcing heterogeneous learning dynamics within a single parameter space. Motivated by social solidarity theory, we propose Socialized Division and Collaboration (SDC) as a reformulation of continual learning that decomposes session learning across specialized models in response to optimization conflicts, while enabling coordinated collaboration. To support this formulation with a principled allocation mechanism, we introduce an energy-based session-model compatibility criterion grounded in Helmholtz free energy, which guides adaptive session allocation and model evolution under conflicting objectives. This framework integrates session assignment, model evolution, and collaborative inference into a unified pipeline, offering an alternative to monolithic continual learning formulations and highlighting a broader design principle for learning under persistent optimization conflicts.

cs.AI↗
arXiv2026

DynCur-Geo: Dynamic Curiosity Reward Shaping for Multimodal Active Geo-Localization

Active geo-localization enables low-altitude UAVs to search for specified targets from limited local aerial observations, supporting time-sensitive applications such as search and rescue and emergency inspection. However, multimodal target cues, restricted views, and sparse feedback make it difficult to balance exploration with target convergence. Existing curiosity-driven methods assign a fixed intrinsic-reward weight throughout search, which can continue rewarding novelty after the agent nears the target and induce detours. We propose DynCur-Geo, a dynamic curiosity framework that adjusts prediction-error intrinsic reward according to remaining target distance. A distance-aware gate encourages early exploration and shifts the policy toward goal-directed behavior near the target, while potential-based reward shaping supplies dense progress guidance. Experiments across multimodal, cross-scene, disaster-affected, and long-range settings show consistent gains over active geo-localization baselines.

cs.CV↗
arXiv2026

SelfDRSC++: Self-Supervised Dual Reversed Rolling Shutter Correction via Video Interpolation

Modern consumer cameras often use rolling shutter, capturing scenes row-by-row and causing distortion in dynamic scenes. Existing correction methods rely on supervised learning with high-frame-rate global shutter images as ground truth. We propose SelfDRSC++, a self-supervised framework for RS distortion correction {from simultaneously captured top-to-bottom and bottom-to-top RS images}. A lightweight network with a bidirectional correlation matching block jointly optimizes optical flows and corrected RS features, improving performance with fewer parameters. A self-supervised strategy enforces {a physically constrained RS--GS--RS cycle} between input and reconstructed dual reversed RS images. RS reconstruction is formulated as a specialized video frame interpolation task, enabling feasible one-stage training. Extensive experiments on synthetic and real-world data show that SelfDRSC++ achieves competitive quantitative performance, improves perceptual quality, and produces high-frame-rate GS sequences with better temporal consistency.

cs.CV↗
arXiv2026

Electronic excitation of ultrafast collective amorphous-amorphous transitions in glassy phase-change material

The intrinsic nature of glass states and glass transitions remain a fundamental open question in condensed-matter physics and materials science. The key to solving the glass transition problem lies in achieving a complete understanding of the physics governing the structural relaxation. Nonetheless, directly probing dynamic atomic-scale structural changes in order to identify the precise local structural motifs and establish quantitative structure-property relationships remains an outstanding challenge. By combining femtosecond electron diffraction with time-dependent density-functional theory molecular dynamics simulations, we directly capture ultrafast amorphous-amorphous transitions indicated by collective bond stretching (0.2 ps) and angle bending (0.5-2 ps) in glassy phase-change material GeTe. The ultrafast bond stretching is accompanied by localized oscillation modes with the frequency of 3.10 THz, unambiguously signaling the local Peierls-like bonding structure and the flexibility of these polarized bonds. These ultrafast collective atomic motions, captured across timescales ranging from femtoseconds to picoseconds, directly reveals the structural origin of the boson peak and provide compelling evidence for many-body interactions in amorphous materials. Furthermore, the ultrafast amorphous-amorphous transitions induce a drastic insulator-metal transition, directly revealing both the underlying switching mechanism and the fundamental speed limit of the ovonic threshold switch. These insights establish a fundamental framework for rationally engineering relaxation pathways and phase-change/threshold switch in amorphous materials. Femtosecond electron diffraction provides a powerful novel approach to deciphering the structural complexity and functional mechanisms of amorphous materials by resolving collective atomic motions from random diffusion dynamics in the time domain.

cond-mat.mtrl-sci↗
arXiv2026

Sub-angstrom many-body localization driven by phononic flat bands in real quantum materials

Defects, fluctuations, degenerate states and correlated interactions facilitate the emergence of exotic properties in condensed matter systems while also inducing atomic-scale local correlated structures that deviate from the average long-range order. Establishing the structure-property relationship from the perspective of these atomic-scale local correlated structures remains ambiguous and controversial due to the lack of direct methods for identifying such local correlated structures. In this work, based on the photoexcited ultrafast structural response, we propose a Bragg scattering phase breaking regime to identify sub-angstrom local correlated structures in quantum materials. With this regime, we unambiguously identify the many-body-interaction driven local correlated structures in the low temperature ground state of AgCrSe2, characterized by static off-center displacements of Ag atoms ranging from 0 to 0.5 angstrom. The competition between Ag-Ag Coulomb correlations and potential wells induced by CrSe2 layers, leading to phononic flat bands and driving the system into a many body localization (MBL) regime. As temperature rising, these static local correlated structures transform to a dynamic state where the thermal fluctuations overwhelm the multiple localized states. These distinctive local correlated structures constitute the first experimental observation of MBL with vortex-like topological characteristic in a real material system. Emergent vibrational modes arising from MBL have been confirmed and show excellent agreement with inelastic neutron scattering experiments. Our work not only offers a universal approach to characterize sub-angstrom local correlated structures across a wide range of quantum materials but also deepens our understanding of the fundamental mechanism behind exotic properties from the perspective of atomic-scale local correlated structures.

cond-mat.mtrl-sci↗
arXiv2026

CAP: A Scalable Benchmark for Evaluating Cross-Site Browser Agents with Complex Actions and Perception

Large language models are increasingly deployed as autonomous agents that interact with the web through browsers. While recent progress has been driven by benchmarks that evaluate end-to-end task success, these evaluations largely overlook two fundamental sources of difficulty in real web browsing: complex actions over rich user interfaces and visual perception of dynamically rendered content, especially in workflows that span multiple websites. We introduce CAP, a scalable benchmark for evaluating browser agents on cross-site, human-like web tasks that require non-trivial UI interactions and visual understanding. Specifically, we adopt a decomposition-and-recomposition pipeline that first abstracts each website into a structured site card capturing user-facing functions, complex execution operations, and perceptual requirements, and then recomposes these components into realistic cross-site workflows. Each task is therefore grounded in multiple specific operations on each website, enabling fine-grained diagnosis. Built on this framework, we construct 420 tasks across 108 real-world websites and 24 domains under careful quality control. Experiments on state-of-the-art browser agents using our verifiable agent-as-a-judge evaluation framework show low success rates and reveal that perception-heavy interactions remain a major bottleneck, exposing substantial gaps between current agents and real-world web browsing demands.

cs.AI↗
arXiv2026

Towards a new paradigm of scientific discovery with socialized artificial intelligence

Scientific discovery has advanced through successive transformations in the organization of knowledge. Observation and experimentation established the empirical foundations of science. Theory made it possible to derive general principles from particular phenomena. Computation extended inquiry into systems beyond direct observation, while data-intensive methods opened new spaces of pattern and prediction. Science now confronts a different frontier. The central challenge is no longer simply to produce more information, but to organize expanding knowledge, reasoning, and evidence into a coherent process of discovery. Here, we introduce Bridging Literature, Agents, and Zero-gap Experimentation (BLAZE), a paradigm of socialized scientific intelligence. BLAZE conceives AI not as an assistant for isolated research tasks, but as an organizational infrastructure for scientific discovery. It connects persistent knowledge, collective reasoning, empirical validation, and human judgment within a continuous research lifecycle, transforming fragmented activities into a cumulative process of inquiry, criticism, and revision. The central premise of BLAZE is that scientific intelligence does not arise from computation alone. It emerges from the sustained interaction among knowledge, hypotheses, experiments, and collective verification. By organizing humans and machines within a shared scientific process, BLAZE makes discovery more traceable, reproducible, and cumulative while preserving human creativity, judgment, and responsibility. Socialized scientific intelligence may provide a foundation for the next era of science. Its purpose is not to replace human discovery, but to extend the scale, depth, and continuity of collective scientific inquiry.

cs.AI↗
arXiv2026

Quantitative Infrared Thermographic Assessment of Hand Cooling Dynamics During Controlled Contact with Metal Plates

This study investigates the spatiotemporal thermal response of human hands during controlled contact cooling using short wave infrared (SWIR), mid wave infrared (MWIR), and long wave infrared (LWIR) thermography. Three participants simultaneously placed one hand on a cooling metal plate and the contralateral hand on a reference plate maintained near room temperature. Temperature evolution was analyzed in five anatomical regions, including the distal finger, proximal finger, vessel associated region, non vessel region, and forearm. Quantitative metrics, including temperature variation, bilateral temperature difference, initial cooling rate, and frequency-domain amplitude, were extracted from the thermal image sequences. The results showed that the finger regions exhibited the largest temperature reductions and highest cooling rates, indicating greater sensitivity to thermal stimulation than the dorsal hand and forearm. MWIR and LWIR measurements revealed highly consistent cooling dynamics, while LWIR imaging provided enhanced thermal contrast and sensitivity. Frequency-domain analysis demonstrated that the dominant thermal response was concentrated in the low frequency range below 0.05 Hz. Furthermore, pixel-wise cooling rate maps highlighted substantial spatial heterogeneity across the hand surface. Numerical bioheat simulations confirmed that blood perfusion and skin plate contact conductance are key factors governing the cooling response. These findings demonstrate the potential of dynamic infrared thermography as a non-contact tool for assessing peripheral thermoregulation and vascular function during controlled cooling experiments.

physics.app-ph↗
arXiv2026

Structured Illumination Scanning Thermography (SISTER)

Conventional non-invasive photothermal imaging techniques are fundamentally constrained by the diffusive nature of heat transport, which causes severe energy dissipation during subsurface reconstruction. Although modulation-based approaches partially mitigate this limitation by encoding depth information into phase delay and amplitude attenuation, they remain inherently restricted by repeated temporal excitation, long acquisition times, and stitching artifacts in large-area inspection. In this work, we propose a structured illumination scanning thermography (SISTER) framework that replaces conventional temporal modulation with continuous spatial scanning under static structured illumination. The key theoretical insight is that heat diffusion is governed by a Markov semigroup, while sample motion transforms static spatial illumination into an equivalent temporal excitation through a Galilean coordinate transformation. This formulation enables dynamic-to-static reconstruction without repeated temporal modulation and provides a unified interpretation of spatial scanning and conventional signal modulation. A scanning system is integrated to implement the proposed framework together with a dynamic-to-static reconstruction algorithm for continuous subsurface defect inspection. Both numerical simulations and experimental results demonstrate that the proposed method significantly improves spatial continuity, signal-to-noise ratio, and detection capability while effectively eliminating stitching artifacts and reducing acquisition complexity. The proposed SISTER framework establishes a unified theoretical foundation for scanning photothermal imaging and provides a practical paradigm for high-efficiency, large-scale industrial non-destructive testing.

physics.app-ph↗
arXiv2026

Rethinking Air-Ground Collaboration: A Progressive Cross-Task Benchmark and Socialized Learning Framework

Air-ground collaborative perception is crucial for robust visual understanding in real-world dynamic environments. However, existing studies typically formulate collaboration as single-task cross-view fusion, overlooking the functional dependencies among localization, target association, and fine-grained parsing. In addition, the heterogeneous nature of aerial and ground views introduces substantial geometric, scale, and occlusion discrepancies, making uniform feature sharing vulnerable to negative transfer. To tackle these issues, we model air-ground perception as a progressive cross-task collaboration task and construct the Air-Ground Progressive Collaboration (AGPC) benchmark, a spatio-temporally aligned benchmark comprising more than 745K raw video frames. Built upon this benchmark, we propose Socialized Co-Perception (SCP), a coarse-to-fine framework that organizes collaboration progressively from aerial global localization to ground target association and identity-aware parsing. Its core module, the Dual-Layer Router (DLR), decouples input-side multi-scale expert selection from output-side task-conditioned modulation, enabling selective cross-view and cross-task interaction while suppressing harmful interference. Extensive experiments demonstrate the effectiveness of SCP. It achieves a 3.73\% coevolutionary gain and a 7.86\% improvement in average downstream performance. These results show that task-conditioned collaboration is more effective than uniform fusion for heterogeneous air-ground perception. The code is available at https://github.com/g1136639260-spec/AGSCP.

cs.CV↗
arXiv2026

Generalized Virtual-Wave Theory for Photothermal Coherence Tomography under Arbitrary Excitation Toward Non-Contact Industrial Inspection of Composite Materials

Photothermal imaging is a powerful noncontact and nondestructive technique for subsurface inspection of composite materials, yet its performance is fundamentally limited by the diffusive and irreversible nature of heat transport, leading to severe image blurring and ambiguous depth interpretation. The concept of virtual waves provides a route to overcome this limitation by linking diffusion fields to propagating wave fields, but existing approaches are largely restricted to idealized impulsive excitation. Here, we propose a generalized virtual-wave photothermal tomography framework that extends the diffusion-to-wave transformation to arbitrary boundary excitations, including pulsed, harmonic, and chirped waveforms. Starting from the heat equation with a general source term, we derive a Fredholm integral mapping between the measured diffusion field and a virtual wave field governed by a wave equation, explicitly enforcing causality and thermodynamic irreversibility. The resulting ill-posed inverse problem is solved using ADMM or truncated SVD, depending on the excitation characteristics. Numerical and experimental results demonstrate that the proposed method converts blurred thermal responses into wave-like fields with clear wavefronts and reflections, enabling improved depth localization and tomographic reconstruction. Experiments on carbon fiber reinforced polymer samples with embedded defects show enhanced contrast, sharper boundaries, and more reliable depth interpretation compared with conventional thermographic techniques. This work establishes a unified and physically grounded framework for wave-based photothermal tomography under realistic excitation conditions.

physics.app-ph↗