Searcharxiv⌕ Search

arXiv subjects

Shang Gao

Publications and source records attributed to Shang Gao.

At least 19 recordsLinked to original sources
arXiv2026

CARE: Contrastive Representation Learning with Environment-Invariance Regularization for Behavioural Intention Prediction

Trajectory-based behavioural intention prediction faces environmental variation, and representations learned with a pooled contrastive objective may retain environment-specific regularities. We present CARE, a self-supervised trajectory-learning framework that couples temporally asymmetric contrastive views with an invariant-risk-minimisation (IRM)-style gradient penalty on environment-wise contrastive risks. Each input window yields an anchor, a partially masked positive view, and a temporally perturbed negative view. Masked reconstruction and observability-aware evidence consistency complement this objective by promoting temporal information retention under partial input. On an IMPTC-derived four-class intention task, CARE achieves 0.840 accuracy and 0.023 expected calibration error (ECE) under IID fine-tuning, and 0.806 accuracy with a Brier score of 0.308 on the reported held-out environment. Under frozen-encoder linear probing, reconstruction provides the largest individual held-out accuracy gain, whereas the complete objective yields the lowest held-out ECE (0.049) among tested variants. These results support the combined objective as a competitive representation-learning approach under the evaluated shift, while the IRM-style regulariser is not taken as evidence of formal invariance.

cs.LG↗
arXiv2026

The View from Nowhere: Population-Centered Agent Evolution

Self-improving AI systems can revise the designs that govern their own behavior. Yet existing approaches center improvement on selected parent agents and their evolutionary experience, leaving the broader population largely underused. We identify a substantial gap between population coverage (i.e., the tasks solved by at least one evolved variant) and the performance of the best individual agent. This gap shows that useful capabilities and diagnostic evidence emerge across the population without being consolidated into its leading agents. These observations motivate the view from nowhere, a principle for agent evolution: an agent should be improved by interpreting its behavior through population-wide patterns of success, failure, and prior self-modification. We instantiate this principle as Population-Centered Evolution (PCE). PCE distils task records and modification histories from the population into a population block, which captures recurring failures, complementary successes, and the effects of previously attempted modifications to guide improvements to a selected parent's harness. Under matched models, initial harnesses, and evolution schedules, PCE achieves 72.1% success on SWE-bench Verified and 96.7% on Polyglot, improving over a strong group-evolution baseline by 3.2 and 5.9 percentage points. In our evaluation, PCE reduces the gap between population coverage and best-agent performance by one-third on SWE-bench and closes it on Polyglot. These results suggest that treating the population as evidence, not merely as candidates for selection, provides a complementary principle for agent evolution.

cs.AI↗
arXiv2026

Grounding Predictive Reliability through Masked Observability

An uncertainty estimate is meaningful only if its semantics can be tied to observable predictive behavior. Normal-Inverse-Gamma (NIG) evidential regression provides a structured decomposition of predictive variability into data-scale and predictive-mean components, but marginal likelihood does not identify their allocation. We address this semantic ambiguity in masked representation learning. MORSE (Masked Observability for Reliable Structured Encoding) predicts the same hidden target under controlled changes in visible context and uses normalized cross-context variation to ground predictive-mean uncertainty, while a Gaussian objective learns the conditional mean and data scale. The normalized variation plays the role of the NIG factor $1/ν$, which the marginal leaves unidentified; this yields a policy-relative observability variance that measures dependence on visible evidence, distinct from variation induced by resampling the training set. On a Gaussian-process benchmark with a contextual reference built from analytic Bayes conditional means, MORSE has the lowest log-variance error among compared evidential, ensemble, and dropout estimators in all nine tested settings, while the estimator closest to training-set variation perturbs the model rather than its context in every setting, so the two references separate the estimators empirically. MORSE amortizes observability estimation into one forward pass per observation state. On a heteroscedastic pulse benchmark, its predictor's cross-context variance approaches a large-sample reference as training data increase. MORSE also improves low-label transfer on PTB-XL and in-distribution trajectory prediction on IMPTC.

cs.LG↗
arXiv2026

Observability-Aligned Evidential Masked Pretraining for Reliable VRU Motion Prediction

Vulnerable road user (VRU) prediction must operate under partial observability and distribution shift, so reliable uncertainty matters alongside accuracy. Masked pretraining is attractive in this setting because it naturally exposes the model to missing content during self-supervision, but existing time-series masked autoencoding methods are typically deterministic and do not constrain how confidence should change with observability. We introduce eCoMAE, an evidential masked pretraining method for multivariate time series that explicitly aligns predictive evidence with what is observed. eCoMAE combines block-wise time-step masking with a Normal-Inverse-Gamma decoder and three observability-aware mechanisms: uncertainty-weighted mean consistency on positions visible in both a masked view and a reference pass, evidence suppression on masked positions, and representation consistency across stochastic masks. On IMPTC benchmark for VRU intention prediction under leave-one-environment-out weather shift, eCoMAE improves the strongest baseline from 0.7971 to 0.8068 in OOD accuracy and from 0.0718 to 0.0648 in OOD AURC. Additional evaluation on pedestrian trajectory forecasting across IMPTC, Waymo, nuScenes, and inD further yields the best fine-tuning MSE on all four datasets. These results show that observability-aligned evidential pretraining improves reliability under shift and remains effective beyond the primary benchmark.

cs.LG↗
arXiv2026

Session-Bound Behavioral Watermarking for Autonomous LLM Agents

Large Language Model (LLM) agents are increasingly acting through Web interfaces and external tools. They produce trajectories. Those trajectories may pass through several intermediaries. They can store, modify, or dispute those trajectories. In Web-based agent deployments, trajectories may pass through APIs, marketplaces, and tool servers. As such, a copied or disputed log may not by itself reveal which agent owner produced it. Behavioral watermarking can embed ownership evidence in agent action choices. However, existing methods mainly address detection, removal, rewriting, or imitation. They do not directly test whether repeated observation of watermarked trajectories enables cross-session forgery by exploiting learned action preferences. We formulate this learned-forgery threat and propose AgentAnchor, a session-keyed behavioral watermark for owner attribution from trajectory logs. We derive each step key from a secret key, a fresh public session identifier, and semantic states of recent observations, while a guarded digest of the action-policy state diversifies linear coding rows. It embeds parity evidence through a KL-bounded exponential tilt, and a trusted verifier checks a disputed log without rerunning the agent, using wrong-key calibration and abstention.

cs.CR↗
arXiv2026

Stripe antiferromagnetic order and spin dynamics in the Shastry-Sutherland Ising compound Er2Be2GeO7

In rare-earth compounds, the interplay between geometric frustration and unusual single-ion anisotropy caused by the crystal electric field often leads to exotic magnetic phases. Here, we investigate the magnetic properties of the rare-earth Shastry-Sutherland compound Er$_2$Be$_2$GeO$_7$ using bulk measurements and neutron scattering down to sub-Kelvin temperatures. A $k=(0,0,0)$ stripe-like antiferromagnetic order with locally tilted Er$^{3+}$ moments is revealed by time-of-flight neutron powder diffraction, accompanied with a $λ$-shape specific-heat anomaly at $T_N=0.84$ K. The temperature dependence of the magnetic peak intensity corresponding to the ordered moment of Er$^{3+}$ approximates to the two-dimensional Ising universality class. Thermal- and cold-neutron inelastic scattering experiments demonstrate that the strong Ising anisotropy originates from the local crystal electric field, and reveal gapped magnetic excitations with weak dispersion in the ordered state. Mean-field random-phase approximation with inequivalent nearest-neighbor couplings accounts well for the collective excitations, while classical Monte Carlo simulations yield the fractional $1/4$ and $1/2$ magnetization plateaus. Our work provides a comprehensive description of the spin correlations in Er$_2$Be$_2$GeO$_7$ with a particular focus on the classical origin of its fractional magnetization plateaus.

cond-mat.str-el↗
arXiv2026

Compass Correlations in a Square-Lattice Magnet

The square-lattice compass model is a paradigm of bond-dependent frustration, yet experimental evidence for its characteristic spin correlations has remained elusive. Here we identify compass correlations in the square-lattice intermetallic ErRu$_2$Si$_2$ using single-crystal neutron diffuse scattering. Comparative measurements on the isostructural compounds NdRu$_2$Si$_2$ and ErRu$_2$Si$_2$ reveal a pronounced contrast between nearly uniform diffuse rings in the former and strong intensity modulation between Brillouin zones in the latter. Through the magnetic neutron polarization factor, this modulation reveals compass correlations that couple moment orientation to the correlation wavevector. Crystal-field spectroscopy identifies four preferred in-plane orientations for the Er$^{3+}$ moments. A minimal compass-Heisenberg model incorporating this anisotropy quantitatively reproduces the diffuse scattering and accounts for the double-$Q$ vortex-antivortex ground state. Fits with the compass couplings fixed at values set by the dipolar energy scale retain good agreement with the data, supporting a substantial dipolar contribution to the bond-dependent interactions. Our results establish a square-lattice platform for compass physics and suggest that dipolar interactions, acting together with local crystal-field anisotropy, can shape directional magnetic correlations alongside conduction-electron-mediated exchange.

cond-mat.str-el↗
arXiv2026

E2S-Pruner: Progressive Two-Stage Evidence Fusion for Visual Token Pruning in Vision-Language Models

Vision-language models typically encode an image into hundreds of visual tokens, incurring substantial inference latency and GPU memory overhead. Existing pruning methods largely rely on attention scores and directly aggregate outputs across attention heads and network layers, making it difficult to characterize evidential uncertainty and conflict. We propose E2S-Pruner, a progressive two-stage evidence-fusion framework for visual token pruning that requires no auxiliary model, trainable parameters, or fine-tuning. In the first stage, E2S-Pruner treats each attention head as an independent evidence source, estimates its reliability from evidence clarity and inter-head consistency, and represents each visual token using three states: important, unimportant, and uncertain. In the second stage, Dempster--Shafer evidence theory is used to quantify inter-layer conflict and fuse complementary evidence from multiple network layers. We further introduce a spatial novelty constraint that promotes coverage of distinct image regions and prevents the retained tokens from concentrating in a few locally salient areas. On LLaVA-1.5-7B, E2S-Pruner retains 98.0%, 96.8%, and 90.6% of the aggregate performance when the average numbers of retained visual tokens are 192, 128, and 64, respectively, while improving throughput by 1.96x and 2.09x under the 128-token and 64-token settings. Experiments on Qwen2-VL-7B further demonstrate cross-model generalization. Code is available at https://github.com/taoyu-qian/E2S-Pruner.git.

cs.CV↗
arXiv2026

Elementary magnons and interacting multi-magnon quasiparticles in the effective spin-$\frac{1}{2}$ kagome-staircase magnet Co$_{3}$V$_{2}$O$_{8}$

The excitation spectrum of an anisotropic magnet provides a direct link between its microscopic Hamiltonian and interaction-driven quasiparticles. Here we use high-resolution time-domain terahertz spectroscopy to map the magnetic excitations of the three-dimensional kagome-staircase compound Co$_{3}$V$_{2}$O$_{8}$ as functions of temperature and magnetic field. At low energies, polarization-resolved spectra identify magnetic-dipole-active one-magnon modes and track their evolution across the ferromagnetic and spin-density-wave phases. Combining their field dependence with previously reported inelastic-neutron-scattering dispersions, we determine an effective spin-$\frac{1}{2}$ Hamiltonian with strongly anisotropic exchange that quantitatively reproduces the one-magnon spectrum. This model provides a noninteracting benchmark for the high-energy response, where we observe sharp branches with field slopes that are two to four times those of the one-magnon modes, together with anticrossings between branches of different magnon numbers. Their sharpness, polarization dependence, and departure from the calculated multi-magnon continua identify them as interacting multi-magnon quasiparticles that can be stabilized by strong exchange anisotropy.

cond-mat.str-el↗
arXiv2026

Tremerity-Fi: Non-Contact Daily-Life Tremor Severity Assessment by Commercial mmWave Radar

Tremor is a common symptom of neurological diseases. The regular assessment of daily tremors facilitates the evaluation of disease progression and assists clinicians in optimizing treatment strategies. However, current home monitoring solutions have difficulty in dealing with user cooperation, privacy concerns, environmental interference, and system generalization, leading to feasibility concerns in activities of daily living (ADL). To this end, we propose Tremerity-Fi, a non-contact and privacy-friendly tremor severity assessment system based on mmWave radar. To realize Tremerity-Fi, we first design an adaptive beamforming algorithm to accurately identify useful but weak signals from numerous reflections captured in the environment. Second, unlike primary reflections commonly used in mmWave sensing, we leverage multipath reflections that carry useful information about the target's motion, even though they are generally considered harmful, to help reconstruct hand signals and improve sensing performance. Furthermore, we propose an unsupervised domain adaptation algorithm to improve the ability to adapt to unseen environments and users. We collect a diverse dataset of 5 patients and 25 healthy subjects in 3 scenarios, such as offices, homes, and hospitals. Extensive experiments show that our system achieves 94.51% accuracy in tremor detection, about 5 higher than the SOTA mmWave radar method, and 89.13% in tremor severity assessment, demonstrating its sufficient potential as a tremor monitoring assistant for patients with neurological diseases.

eess.SP↗
arXiv2026

Strongly frustrated 2D magnetism in a 3D hexagonal perovskite

Exotic quantum phenomena are often found to occur in spin systems that exhibit low-dimensional magnetism. By combining nuclear magnetic resonance, neutron scattering, and muon-spin spectroscopy ($μ$SR) techniques, we report a rare instance of strongly frustrated two-dimensional (2D) magnetism in a three-dimensional (3D) hexagonal perovskite. Here, Ba$_2$La$_2$MnTe$_2$O$_{12}$, a triangular-lattice magnet, is shown to undergo a magnetic transition at $T_\mathrm{N} \approx$ 4.4 K, below which the manganese moments form a 120$^{\circ}$ AFM order within the $ab$-plane, while staying disordered along the $c$-axis. This exotic ground state, which exhibits ideal 2D magnetism, is highly consistent with the persistently strong spin fluctuations and the large internal field distributions revealed by zero-field $μ$SR. Further, the 2D magnetism also leads to a significant frustration, much larger than that of most known magnetically-ordered frustrated systems. Our work on Ba$_2$La$_2$MnTe$_2$O$_{12}$ not only challenges the interpretations of magnetic order in other 3D hexagonal perovskites, but it also provides insight into how the dimensionality affects the exotic magnetic states.

cond-mat.str-el↗
arXiv2026

TRACER: Training-Free Closed-Loop Structured Inference for Traffic Accident Reconstruction

Traffic accident reconstruction is a forensic inverse problem that requires recovering physically consistent motion from sparse and heterogeneous evidence. Existing learning-based approaches predominantly optimize for semantic plausibility or visual realism, rather than quantitative agreement with measurable geometry and dynamics. Here, we present TRACER, a training-free framework that formulates reconstruction as a closed-loop structured inference process. Instead of directly generating dense trajectories, our framework constructs and iteratively refines event-anchored motion hypotheses under geometric, kinematic, and interaction constraints, guided by structured case memory and consistency-driven diagnosis. This design enables incremental, interpretable corrections when evidence is insufficient, making the accident reconstruction process more aligned with the workflow of human experts. Experiments on real-world accident data show that TRACER achieves improved geometric fidelity, velocity consistency, and collision accuracy over both data-driven and physics-based baselines.

cs.LG↗
arXiv2026

Noise-Aware Visual Representation Learning for Medical Visual Question Answering

Medical visual question answering (Med-VQA) has strong potential for clinical decision support by enabling AI models to interpret medical images and answer clinically relevant queries. Recent approaches typically connect off-the-shelf vision encoders with large language models (LLMs) through lightweight mapping networks to reduce computational cost. However, these methods often overlook the importance of handling noise and small irrelevant changes in visual representations. To address these challenges, we propose a noise-aware Med-VQA framework that incorporates a denoising autoencoder before visual embeddings are mapped into the input space of an LLM. The denoising autoencoder is pretrained to reconstruct clean visual embeddings from corrupted inputs, encouraging the model to learn robust visual representations that are less sensitive to noise. The resulting embeddings are then projected into the language model embedding space using a multi-layer perceptron (MLP), forming visual prefix tokens that provide image information to the LLM. To enable efficient adaptation without full retraining, we employ parameter-efficient fine-tuning using low-rank adaptation (LoRA). The proposed method is evaluated on the SLAKE and PathVQA benchmarks. Experimental results show improved robustness to noisy input embeddings while maintaining competitive clean performance across multiple evaluation criteria. These findings suggest that learning more robust visual representations can enhance Med-VQA performance and robustness.

cs.CV↗
arXiv2026

XTransfer: Modality-Agnostic Few-Shot Model Transfer for Human Sensing at the Edge

Deep learning for human sensing on edge systems presents significant potential for smart applications. However, its training and development are hindered by the limited availability of sensor data and resource constraints of edge systems. While transferring pre-trained models to different sensing applications is promising, existing methods often require extensive sensor data and computational resources, resulting in high costs and limited transferability. In this paper, we propose XTransfer, a first-of-its-kind method enabling modality-agnostic, few-shot model transfer with resource-efficient design. XTransfer flexibly uses pre-trained models and transfers knowledge across different modalities by (i) model repairing that safely mitigates modality shift by adapting pre-trained layers with only few sensor data, and (ii) layer recombining that efficiently searches and recombines layers of interest from source models in a layer-wise manner to restructure models. We benchmark various baselines across diverse human sensing datasets spanning different modalities. The results show that XTransfer achieves state-of-the-art performance while significantly reducing the costs of sensor data collection, model training, and edge deployment.

cs.CV↗
arXiv2026

Emergent Vortex Ordering in a Multiflavor Pyrochlore-Lattice Compound GeCo$_2$O$_4$

Entangled spin and orbital degrees of freedom provide a multiflavor route to novel magnetic states inaccessible in conventional spin systems. Here, we report the experimental identification of an emergent vortex lattice in the multiflavor pyrochlore-lattice compound GeCo$_2$O$_4$. By combining comprehensive neutron scattering experiments with a regularized regression framework, we identify substantial Kitaev interactions among the nearest-neighboring Co$^{2+}$ pseudospins, which cooperate with geometric frustration to stabilize the vortex order. These results reveal an unexpected route to vortex-lattice order in a three-dimensional Kitaev-frustrated magnet and demonstrate a regularized protocol for Hamiltonian determination in frustrated quantum materials.

cond-mat.str-el↗
arXiv2026

Liquid-Gas Criticality of Hyperuniform Fluids

In statistical physics, it is well established that the liquid-gas (LG) phase transition with divergent critical fluctuations belongs to the Ising universality class. Whether non-equilibrium effects can alter this universal behavior remains a fundamental open question. In this work, we theoretically prove that non-equilibrium hyperuniform (HU) fluids with additional center-of-mass conservation exhibit LG criticality different from the Ising universality class. As a specific case, we investigate a 2D HU fluid composed of active spinners, where phase separation is driven by dissipative collisions. Strikingly, at the critical point, the 2D HU fluid displays finite density fluctuations $S(q)\sim q^η$ with $η=0$, while the compressibility still diverges. The critical point is thus calm yet highly susceptible, in fundamental violation of the conventional fluctuation-dissipation relation. Consistently, we observe short-range pair correlation functions coexisting with quasi-long-range response functions at the critical point. Based on a generalized Model B and renormalization-group analysis, we prove that hyperuniformity reduces the upper critical dimension $d_c$ from $4$ to $2$. Moreover, the critical point exhibits Gaussian density fluctuations and non-divergent energy fluctuations. Furthermore, the HU fluid undergoes non-conventional spinodal decomposition. The origin of the above anomalies lies in the non-equilibrium nature of the system which obeys a generalized fluctuation-dissipation relation $2\mathrm{Im}~ χ(q,ω) ={ω}C(q,ω)/{k_B T_{\text{eff}}(q)}$ with a scale-dependent effective temperature $T_{\rm eff}(q) \propto q^2$. These findings establish a striking exception to conventional paradigms of critical phenomena and illustrate how non-equilibrium forces can fundamentally reshape universality classes.

cond-mat.stat-mech↗
arXiv2026

LOPT: Learning Optimal Pigovian Tax in Sequential Social Dilemmas

In multi-agent reinforcement learning, each agent acts to maximize its individual accumulated rewards. Nevertheless, individual accumulated rewards could not fully reflect how others perceive them, resulting in selfish behaviors that undermine global performance. The externality theory, defined as ``the activities of one economic actor affect the activities of another in ways that are not reflected in market transactions,'' is applicable to analyze the social dilemmas in MARL. One of its most profound non-market solutions, ``Pigovian Tax'', which internalizes externalities by taxing those who create negative externalities and subsidizing those who create positive externalities, could aid in developing a mechanism to resolve MARL's social dilemmas. The purpose of this paper is to apply externality theory to analyze social dilemmas in MARL. To internalize the externalities in MARL, the \textbf{L}earning \textbf{O}ptimal \textbf{P}igovian \textbf{T}ax method (LOPT), is proposed, where an additional agent is introduced to learn the tax/allowance allocation policy so as to approximate the optimal ``Pigovian Tax'' which accurately reflects the externalities for all agents. Furthermore, a reward shaping mechanism based on the approximated optimal ``Pigovian Tax'' is applied to reduce the social cost of each agent and tries to alleviate the social dilemmas. Compared with existing state-of-the-art methods, the proposed LOPT leads to higher collective social welfare in both the Escape Room and the Cleanup environments, which shows the superiority of our method in solving social dilemmas.

cs.MA↗
arXiv2026

Codimension-Two Spiral Spin-Liquid in the Effective Honeycomb-Lattice Compound Cs$_3$Fe$_2$Cl$_9$

A codimension-two spiral spin-liquid is a correlated paramagnetic state with one-dimensional ground state degeneracy hosted within a three-dimensional lattice. Here, via neutron scattering experiments and numerical simulations, we establish the existence of a codimension-two spiral spin-liquid in the effective honeycomb-lattice compound Cs$_3$Fe$_2$Cl$_9$, which demonstrates a novel path to spiral spin-liquids by overcoming the long-standing impediment of weak further-neighbor interactions. In the long-range ordered regime, competing spiral and spin density wave orders emerge as a function of applied magnetic field, among which a possible order-by-disorder transition is identified.

cond-mat.str-el↗