Searcharxiv⌕ Search

arXiv subjects

Wei Zhao

Publications and source records attributed to Wei Zhao.

At least 19 recordsLinked to original sources
arXiv2026

Your Model Already Knows Don't Teach It, Learn to Ask It: Soft Prompting for Few-Shot Adaptation of Vision-Language Models

We address few-shot object detection with vision-language models (VLMs) in out-of-domain settings such as aerial, industrial, and medical imagery, using only ten annotated images for supervision. Existing adaptation methods are discrete prompt optimization and LoRA fine-tuning. We revisit a third option: soft prompting, where a small number of continuous prompt tokens are optimized while the pretrained backbone remains frozen. We identify two key design choices. First, placing prompt tokens at the cross-modal boundary between visual and text tokens outperforms other placements (10.0 vs. 8.4 mAP). Second, initializing prompts from the empty space token outperforms semantic and random initialization. With these choices, one to three learned tokens (7,168 parameters on average) match the best LoRA configuration on Roboflow20-VL (14.2 mAP, 10-shot) while training over 20,000x fewer parameters. Soft prompting remains harder to optimize, exhibiting higher variance across random seeds. Unlike LoRA, however, it causes no forgetting: the LoRA rank matching our accuracy reduces NaturalBench VQA accuracy by 35% relative, rising to 56% at the largest rank, whereas soft prompting leaves pretrained performance unchanged. The learned tokens behave like prompts rather than weights. They transfer to a newer model without retraining (+0.8 mAP on Qwen3.5-9B) and can be verbalized into readable prompts competitive with prompt-search methods (matching DetPO and outperforming GEPA). The approach also extends beyond detection. On RoboCasa manipulation tasks, the frozen $\pi_{0.5}$ vision-language-action policy benefits from soft prompting, matching the LoRA baseline on two of three tasks when tokens are placed at the gradient bottleneck. These results suggest modern VLMs already encode much of what is needed for specialized domains; the challenge is learning how to ask.

cs.CV↗
arXiv2026

Calibration-Aware Uncertainty Cascades for Efficient Heterogeneous Model Collaboration

Heterogeneous model collaboration seeks to exploit the complementary strengths of different models to balance predictive performance and inference cost. Existing approaches typically rely either on trained routers, which tie routing decisions to a fixed task and model pool, or on raw-confidence cascades, whose thresholds lack consistent reliability semantics across heterogeneous models. Consequently, these approaches adapt poorly to changing model pools and deployment budgets. We propose Calibration-Aware Uncertainty Cascades (CAUC), a simple post-hoc framework that independently calibrates each model's confidence and selects deployment policies using validation data. The resulting calibrated confidence scores establish a common reliability scale for accepting an early prediction, invoking a stronger model, or selectively combining model outputs. This unified decision criterion decouples deployment policies from any particular model pool or operating budget. We further show theoretically that calibration gives confidence thresholds an explicit selective-risk interpretation, whereas uncalibrated scores offer no comparable reliability guarantee. Extensive experiments demonstrate that, across six language benchmarks, CAUC achieves an average relative accuracy improvement of 1.9% over strong-model-only inference while avoiding approximately 47% of strong-model calls. On image classification benchmarks, it maintains or improves predictive performance while reducing measured GFLOPs by up to 57%.

cs.AI↗
arXiv2026

Momentum-scalar coupled turbulence with anomalous momentum and scalar diffusions. Part 1: Without external force and with long-range external force

We present a theoretical model for momentum--scalar coupled turbulence in which both fields undergo anomalous diffusion, described by fractional biharmonic operators of orders $\gamma/4$ and $\alpha/4$, respectively. Focusing on the long-range external forcing or unforced turbulence, we derive analytical expressions for the kinetic energy spectrum $E_u(k)$, the scalar spectrum $E_s(k)$, and the characteristic wavenumbers $k_K = \left( \frac{\epsilon_u^{1/3}}{c_u} \right)^{1/(\gamma - 2/3)}$ (reciprocal of Kolmogorov scale) and $k_S = \left( \frac{\epsilon_u^{1/3}}{c_s} \right)^{1/(\alpha - 2/3)}$ (reciprocal of scalar dissipation scale) as functions of $\gamma$, $\alpha$, turbulent dissipation rate $\epsilon_u$, diffusivities of momentum ($c_u$) and scalar ($c_s$), respectively. An anomalous Schmidt number $Sc_Z = k_0^{\gamma - \alpha} \frac{c_u}{c_s}$ is defined to governs the cascade topology. It describes the ratio of diffusion times of scalar and momentum on the minimum wavenumber $k_0$. Superdiffusion ($\gamma<2$ or $\alpha<2$) is shown to counter-intuitively enlarge $k_K$ and $k_S$, broadening the inertial range. The theory unifies the classical Kolmogorov--Obukhov--Corrsin--Batchelor scalings as special cases when $\gamma=\alpha=2$, and provides a foundation for understanding non-Fickian transport in complex turbulent systems.

physics.flu-dyn↗
arXiv2026

Momentum-scalar coupled turbulence with anomalous momentum and scalar diffusions. Part 2: With short-range external force and implementation in electrokinetic turbulence

We extend the generalized anomalous diffusion framework established in Part I to the short-range forcing regime ($\beta > 2/3$), where the multiscale-force dominated (MFD) subrange is intercalated after the inertial subrange, competing directly with the dissipation ranges. Focusing on electrokinetic (EK) turbulence as the prototypical example with $\beta=1$, we derive the relations for the velocity and scalar dissipation wavenumbers, $k_{MD}$ and $k_{SD}$, across all four subranges of the Quad-cascade process (inertial, constant-$\Pi_u$, constant-$\Pi_s$, and variable flux). By incorporating Golestanian's predicted anomalous diffusion regimes for electrolytes, we construct comprehensive phase diagrams showing how the relative magnitudes of $k_{MD}$ and $k_{SD}$ are governed by the scale-dependent anomalous Schmidt number $Sc_Z$. We identify two new spectral subranges that emerge exclusively in this short-range forcing regime: (i) the convective-viscous subrange ($k_{MD} \ll k \ll k_{SD}$) of velocity spectrum for $Sc_Z \gg 1$, where the scalar field drives a viscous flow yielding $E_u \sim k^{-\left(\frac{3}{2} + \frac{\xi_s}{2}\right)}$ with a stretched-exponential cutoff; and (ii) the diffusive-forcing subrange ($k_{SD} \ll k \ll k_{MD}$) of scalar spectrum for $Sc_Z \ll 1$ and $\gamma \leq \alpha$, where the scalar dissipation range determines the electric forcing, leading to $E_s \sim k^{\xi_u - 2\alpha}$. These results provide a complete analytical map of EK turbulence under anomalous diffusion, revealing how external parameters such as electric field strength and ionic diffusivity determine the cascade topology.

physics.flu-dyn↗
arXiv2026

Tripwire: Triggering Aligned Refusal via Statistically Certified Safety Neurons

Neuron- and path-level interventions offer the finest-grained route to defending large language models (LLMs) against jailbreak attacks, yet existing methods fall short of this promise, i.e., they often compromise model utility significantly. Specifically, one line of work suppresses toxic neurons to erase harmful semantics, but since such semantics are distributed across the network, blocking every pathway forces a large intervention footprint. An alternative line of research focus on identify safety neurons using external classifiers. While promising, the existing approaches suffer from compromising neurons that are important for the model utility as well. Moreover, both approaches remain always on and thus perturb every benign request even when no attack is present. To address these limitations, we present \ours{}, a training-free defense that first identifies safety-specific neurons through per-neuron hypothesis tests under false-discovery-rate control together with a utility-specificity filter. Based on this identification, a trigger-style clamp holds the selected neurons at their harmful-conditional mean activations, injecting an internal harmful-input signal that triggers the refusal behavior learned during alignment. The clamp is then realized by two provably equivalent deployment modes, namely a detector-gated inference-time intervention and an offline bias-patch weight edit. Extensive experiments across four safety-aligned LLMs and four representative attacks demonstrate that \ours{} reduces the average attack success rate to at most 2.0\% while incurring a utility drop of only 0.5\% to 5.3\% on MT-Bench, the smallest among all defenses. Code is available at https://anonymous.4open.science/r/Tripwire-65C4.

cs.AI↗
arXiv2026

How Do VLMs Behave When Blind or Misled? Behavioral Evaluation of VLMs on Scientific Figures

Existing vision-language model (VLM) benchmarks emphasize perception and reasoning accuracy (how well VLMs describe and reason about what they see in an image), with limited attention to behavioral reliability under uncertainty (how they behave when visual evidence is missing or misleading). We introduce SciFigBench, a diagnostic VLM benchmark for scientific figure understanding that jointly evaluates perception, reasoning, and behavioral reliability under uncertainty. It contains 250 figures with high-quality human annotations across three evaluation aspects, totaling 600+ hours of annotation effort. We further extend these figures via image transformations, reasoning questions, resistance probes, caption-bias probes, and confirmed selective-blur targets, producing over 34,000 evaluation setups for stress testing. We further propose the Admittance-Resistance-Inductance (A-R-I) framework to evaluate whether models acknowledge insufficient evidence, resist misleading context, and infer cautiously from partial information. Our results reveal substantial behavioral differences among models. GPT-5.2 achieves the highest description quality (MQM 91.6) with strong reasoning accuracy (78.4%), yet hallucinates unreadable content in 96% of cases, whereas Gemini 3.1 Pro, a comparably capable model (MQM 90.2, reasoning 81.0%), admits uncertainty in 71% of such cases and achieves the strongest resistance score (0.91). These findings show that high perception and reasoning accuracy alone do not guarantee behavioral reliability, a dimension critical for deployment in scientific workflows.

cs.CL↗
arXiv2026

Is the ACL Responsible NLP Checklist a Box-Ticking Exercise? A Large-Scale Analysis of EMNLP 2025

Responsible NLP practice includes a) transparency, b) ethics, and c) societal impacts. The Responsible NLP Checklist aims to push these goals, and promote responsible practice. Recently, ACL released the EMNLP 2025 Checklists to aid transparency on the current research practice, which we focus on. We curate and release the first two datasets of: a) all the checklist responses and justifications from the EMNLP 2025 Main and Finding tracks; b) checklist reference linking to paper sections. We also provide the first analysis of recent EMNLP Checklists, by examining $73,922$ responses and justifications to them. For the Main track, we find that authors isolate ethics questions of the Checklist from the paper's bulk, mimicking the trend of ethics being an afterthought. We then examine \texttt{NO} responses. We find $44.9\%$ of justifications are poor or bad-faith, being brief or empty. Then, we find significant issues with the checklist design and effort of authors, namely that $6\%$ of all checklists contained logical contradictions between parent and child responses. We also find evidence of surface compliance for responsible ethics, with $53\%$ authors dismissing potential risks or social impacts of their work, for which there should be none. We compare this to the Findings track, noticing a similar trend in both tracks. Lastly, we discuss the implications of the checklist design and provide recommendations for future checklist iterations. Including: a) enforcing a minimum word count, b) enforcing more scrutiny on the risks of appliances.

cs.CL↗
arXiv2026

Macaron-V1: Towards Open Continual Learning with Self-Improvement and Mixture-of-LoRA

Macaron-V1 is an open agent-model family for experiential intelligence: learning from experience in real environments and continuing to learn after deployment. It is organized around two system goals. Adaptation is pursued through recursive improvement of versioned model-harness pairs, where experience from one configuration is evaluated under an external contract and used to construct its successor. Collaboration is pursued via the Mixture-of-LoRA (MoL) architecture that freezes a base model, composes specialist LoRA adapters, and selects one LoRA per user turn. The flagship Macaron-V1-Venti (748B) combines a 744B GLM-5.2 base with four LoRAs for chat, agent, coding, and GenUI; the Qwen3.6-35B-based Macaron-V1-Tall (50B) uses the same design for local deployment. This report presents Macaron-V1 as a co-designed system spanning architecture, algorithms, and infrastructure. The MoL architecture supports continual learning through extensible LoRA specialists. The algorithm combines Model-Harness Co-design and recursive self-improvement loop, including the UI4A component-native GenUI harness, a stateful action substrate, versioned Harness Context Protocol contract, and the agentic RL framework MindForge. The supporting infrastructure includes the post-training platform MinT, the long-context RL method LongStraw, and stability techniques for sparse MoE and DSA base models. We evaluate Macaron-V1 on Personal Intelligence, GenUI, and general capability benchmarks against frontier baselines. Our results validate the current system, while compounding gains from continual learning and collective intelligence remain open questions.

cs.LG↗
arXiv2026

Smart membrane: high content in situ monitoring barrier on chip with artificial neural network

Conventional transepithelial electrical resistance (TEER) technique provides only a low-content analysis of cell-layer conditions, necessitating repeated microscopic assessments of morphology and cell-cell contacts outside the incubator for barrier-on-chip systems. This work presents a novel high-content TEER device in the form of a novel nanoporous membrane that facilitates continuous electrical measurement of cell-substrate impedance sensing (ECIS). The ultrathin (700 nm) membrane, composed of ultra-low-stress SixNy, is monolithically integrated into wafer-level fabricated chips sealed with glass lids. Coplanar ECIS electrodes were connected to custom electronics to record impedance under sinusoidal excitation. Human umbilical vein endothelial cells (HUVECs) were seeded and continuously recorded impedance spectra were compared with bright-field and fluorescence microscopy, revealing distinct phases of monolayer formation. With one-dimensional convolutional neural network (Conv1d) and Kolmogorov-Arnold Network (KAN) trained with a small amount of Nyquist-diagrams, phases of (I) adherence, (II) outspreading, (III) confluence and (IV) barrier maturity with tight junction formation could be recognized with 95% confidence. As further proof of concept, reversible and irreversible barrier weakening using modulators PN159 and BAC was identified in this way. Our studies have demonstrated that an immediate and automatable non-invasive detection of in-vitro barrier dynamics within barrier-on-chip systems, eliminating the need for microscopy and endpoint staining. We expect this ECIS technique will find broad applications in organ-on-chip systems for in situ monitoring physiological or pathological states of tissue barrier.

eess.SP↗
arXiv2026

TopoGR: Revealing and Preserving Latent Structure of Semantic ID in Generative Recommendation

Semantic ID-based generative recommendation tokenizes each item into a sequence of discrete semantic IDs and predicts the next item by generating semantic IDs. However, existing methods typically regard SIDs as independent discrete symbols, while often overlooking the topology of the learned semantic ID space. We identify a structural mismatch between tokenization and generation: the tokenizer learns a structured code space with semantic neighborhood relations, whereas the generator consumes semantic ID tokens as independent categorical symbols. Consequently, item relatedness is reduced to exact semantic ID overlap, making it difficult to identify semantically similar items whose semantic IDs do not overlap. To address this issue, we propose TopoGR, a topology-preserving generative recommendation framework based on Bit-decomposable Semantic ID(Binary SID). Each Binary SID is learned in a bit-decomposable form and can be deterministically converted to a standard integer SID, while exposing an explicit Hamming geometry. TopoGR exploits this topology at three stages: binary SID features preserve Hamming proximity at the input layer; Hamming soft targets inject topology-aware supervision; and Hamming-consistent reranking aligns candidate items with the predicted binary prototype during inference. We further verify that the Hamming topology can capture item relatedness beyond exact SID matching. Experiments on four benchmark datasets show that TopoGR consistently outperforms existing state-of-the-art baselines in recommendation performance.

cs.IR↗
arXiv2026

PRIME: Plasticity Recovery in Multi-Agent Environments for UAV-Assisted Emergency Communication Networks

Most reinforcement learning controllers for these networks assume stationary conditions, and the few that handle change react to the external environment while leaving the network's internal state unexamined. We show that sustained non-stationarity damages this internal state directly: as objectives shift, neurons progressively fall dormant and the shared policy loses the capacity to learn. The obvious remedy, resetting dormant neurons, is unsafe under shared-parameter multi-agent training: many neurons that appear inactive are still receiving strong training gradients, and whether a neuron appears dormant depends on which agent's observations it processes. PRIME (Plasticity Recovery In Multi-agent Environments) therefore verifies both directions before intervening. Extending the bidirectional Silent Neuron framework to cooperative multi-agent reinforcement learning, it aggregates activation and gradient statistics over the full team batch, reads the backward signal from the gradient the training loss has already deposited , not from a hand-crafted proxy, and reinitializes only neurons that are simultaneously activation-dormant and gradient-silent. Useful representations are preserved while learning capacity is restored. On a phase-switching UAV emergency communication simulator, PRIME improves interquartile mean return by 24.9\% over MAPPO and holds dormant neuron fractions at 10--20\% versus 40--45\%; ablations attribute the gains to the gradient signal and team-level aggregation rather than to the specific reset operator. A dynamic regret bound shows that the perturbation cost scales with the small silent-subspace dimension rather than the full parameter count.

cs.MA↗
arXiv2026

Convergence Analysis of the Restarted Moving-Anchored Extra-Gradient Method in the Absence of Local Lipschitz Continuity

In this paper, we introduce the moving-anchored extra-gradient (MAEG) method for solving monotone inclusion problems involving the sum of a continuous monotone operator and a maximal monotone operator. Notably, the distance from the anchor point to the solution set is designed to be monotonically non-increasing. Under Lipschitz continuity of the forward operator, MAEG attains an $\mathcal{O}(1/k)$ non-asymptotic iteration complexity, and when a positive anchor-update parameter is used, it further achieves an $o(1/k)$ asymptotic rate. Furthermore, leveraging the specific behavior of the anchor point, we propose a tailored restart strategy. We demonstrate that this strategy ensures convergence even in the absence of local Lipschitz continuity, while preserving the original iteration complexity guarantees whenever the Lipschitz condition holds.

math.OC↗
arXiv2026

Physics-informed neural networks by Gradient-Guided Gaussian Adaptive Sampling (3GAS-PINNs)

Physics-informed neural networks (PINNs) provide a mesh-free framework for solving partial differential equations, yet their performance in nonlinear problems is often limited by slow convergence, gradient imbalance, and insufficient resolution to capture localized intermittent structures such as shock waves[1]. These issues arise primarily from the use of fixed weights of loss and uniform collocation point distributions, which cannot adapt to the evolving complexity of the solution field during training. To address these challenges, Gradient-Guided Gaussian Adaptive Sampling Physics-Informed Neural Networks (3GAS-PINNs) is proposed in this paper, which combines uniform probability distribution and Gaussian-smoothed probability distribution derived from the spatial gradients of solution, to maintain global constraint satisfaction as well as concentrating collocation points in regions of high gradient. Thus, intermittency structures like shock wave and solitons can be accurately captured. The method is evaluated on three benchmark nonlinear problems, including one-dimensional forced Burgers equation, Korteweg-de Vries (KdV) equation and nonlinear Schrodinger equation, all of which exhibit steep gradients or strong nonlinearity. In comparison with baseline PINNs, 3GAS-PINNs can effectively promote the physical consistency in intermittent regions. The accuracy of the numerical simulation can be improved by a factor of up to 14.

cs.LG↗
arXiv2026

Your Data Manifold is Secretly a Reward Model: Shell-LCC for Text-to-Video Generation

Recent text-to-video (T2V) diffusion models rely heavily on auxiliary reward signals (e.g., via reward models or DPO) to align generated content with human aesthetics and improve realism. These signals, however, incur substantial computational overhead, require costly human annotations, and often yield limited improvement in fine-grained local details. In this paper, we argue that your data manifold is secretly a reward model. By explicitly modeling the manifold structure of high-quality Supervised Fine-Tuning (SFT) data and encouraging video latents to lie on this manifold, we derive dense, differentiable, and nearly cost-free reward signals that significantly improve video quality, particularly in mitigating low-level distortions. Our modeling builds upon Local Coordinate Coding (LCC), which captures the `skeleton' of the manifold. However, directly applying LCC suffers from mean regression, pulling latents toward the geometric mean and losing high-frequency details. We therefore extend it to Shell Local Coordinate Coding (Shell-LCC), which models the manifold `surface' as an isotropic shell to align with the true high-density region. Experiments demonstrate that our approach improves realism, enhances high-frequency details, reduces over-smoothing artifacts, and alleviates motion blur.

cs.CV↗
arXiv2026

Yuvion LLM: An Adversarially-Aware Large Language Model for Content And AI Safety

As large language models are increasingly deployed in real-world systems, safety failures can still lead to harmful outputs and dangerous misuse. We argue that the essence of safety is adversarial: many failures arise not from natural inputs alone, but from strategic attempts to evade model policies and safeguards. However, existing general-purpose model development largely overlook this adversarial nature, and often remain insufficient for realistic safety scenarios involving planning, tool use, and multi-step reasoning, causing measured safety performance to overestimate real deployment robustness. To address this gap, we present Yuvion LLM, a large language model built for adversarially robust content safety and broader AI safety. Yuvion LLM treats adversarial robustness and agentic capability as first-class objectives. Its pipeline combines adversarially aware data construction, knowledge-enhanced continued pretraining, and policy-grounded multi-task safety post-training, including risk-aware supervised fine-tuning and reinforcement learning-based policy optimization, together with safety-aware agentic reinforcement learning for tool use and multi-step reasoning in complex safety scenarios. We further introduce the Yuvion LLM RiskEval (YLRE), a collection of 93 benchmarks across four evaluation categories, covering diverse open and internal evaluations with a focus on safety, adversarial robustness, and real-world capability requirements. Across these evaluations, Yuvion LLM demonstrates clear advantages on safety-focused benchmarks and particularly strong robustness under adversarial conditions, while maintaining solid overall capability. Notably, Yuvion-8B outperforms most state-of-the-art baselines, including substantially larger models such as GPT-5.4 and Qwen3-MAX, on several safety tasks.

cs.CL↗
arXiv2026

Yuvion VL: A Multimodal Foundation Model for Adversarial Content and AI Safety

General-purpose models often struggle to reliably identify and understand real-world multimodal risks, largely due to the inherent multimodal adversarial nature of content and AI safety. We present Yuvion VL, a family of multimodal large language models purpose-built for content and AI safety, with both instruction-tuned and reasoning-oriented variants. Yuvion VL addresses this gap by treating safety as an inherently adversarial and multimodal problem and designing the entire pipeline around adversarial robustness. For data construction, we develop an automated pipeline integrating adversarial-aware data synthesis with multi-stage quality control, producing large-scale, high-quality multimodal samples augmented with domain knowledge and reasoning annotations. For training, we adopt a three-stage pipeline that includes continued pretraining for risk-concept cross-modal alignment, instruct post-training for production-grade safety tasks, and reasoning post-training for enhanced interpretability and performance in complex tasks. We further introduce Confuse-then-Contrast Fine-Tuning, a contrastive framework that mines model-specific confusions and constructs multi-image contrastive groups to enforce explicit discrimination of fine-grained visual-semantic elements, enabling the model to distinguish between visually similar cases with different safety implications in adversarial safety tasks. To support rigorous evaluation, we further introduce Yuvion VL RiskEval (YVRE), a collection of benchmarks covering diverse open and internal evaluations, with a focus on content and AI safety, adversarial robustness, and real-world capability requirements. Experiments show that Yuvion VL-32B achieves industry-leading safety performance, surpassing comparably sized open-source models and best closed-source commercial models, while maintaining comparable general capabilities.

cs.CV↗
arXiv2026

RISE: Relay Inference and Online Scheduling for Efficient Edge-Device Collaborative Diffusion Model Services

Text-to-image diffusion models are increasingly deployed at the network edge to serve heterogeneous workloads with diverse quality and latency requirements. However, existing deployment strategies choose either large edge-side models with high fidelity but high latency or lightweight device-side models that offer speed at the cost of semantic coherence. Moreover, these approaches rarely split the denoising workload between models of different sizes across edge servers and user devices. To bridge this gap, we propose RISE, a method for edge-device diffusion model services that combines relay inference with online scheduling. Driven by the finding that the latent intensity exhibits minimal deviation after a model handoff, RISE uses a training-free relay mechanism that exploits the shared latent space within a model family: the large model on the edge handles the early denoising steps that shape semantic structure, then passes the intermediate latent to a small device-side model for detail refinement. To deploy this mechanism as a practical service, a contextual bandit scheduler selects the best relay configuration based on prompt complexity, user preferences, network quality and real-time node loads. Experiments on two benchmarks show that RISE's relay mechanism achieves up to 2.1$\times$ speedup while preserving full-model quality, and its context-aware scheduler effectively balances quality and latency under mixed workloads.

cs.DC↗