arXiv subjects

Jie Zhang

Publications and source records attributed to Jie Zhang.

At least 73 records · Page 4Linked to original sources

arXiv2026

Can AI Make Money in Crypto? Measuring the Gap from Backtests to Real Markets

AI-based trading methods have rapidly evolved from machine learning and reinforcement learning to large language models (LLMs) and trading agents, yet their performance is still predominantly assessed through historical backtesting. Such evaluations provide limited evidence of whether a method can generalize to unseen future markets or whether its backtested performance can be sustained in realistic trading frictions (e.g., latency, slippage, liquidity constraints, and market impact). We present a unified benchmark that evaluates representative machine learning, reinforcement learning, LLM-based, and agent-based trading methods in cryptocurrency markets through three progressively more realistic stages: historical backtesting, prospective exchange-based paper trading, and real-money live trading. These stages jointly increase temporal realism by moving from historical to unseen future markets, and execution realism by moving from offline simulation toward live trading. This protocol enables us to quantify the backtest-to-realization gap, identify when performance begins to deteriorate, and compare how this gap differs across major classes of AI trading methods. We further provide a unified open-source system supporting all three evaluation stages, together with a public platform that continuously updates benchmark results. Code is available at https://github.com/Starlien95/Awesome-TradingAI.

cs.AI↗

arXiv2026

Backdoor as Probe: Test-Time Adversarial Defense for CLIP

Test-time adversarial defense improves the robustness of vision-language foundation models such as CLIP without retraining. However, adversarial activation shifts are typically treated as distortions to suppress, rather than signals to exploit. We turn these shifts into defense signals by repurposing the trigger-to-target mechanism of backdoors. The key is to implant a defender-controlled backdoor as a probe that is weakly activated by clean inputs but strongly activated by adversarial shifts. Based on this insight, we propose \emph{Backdoor as Probe} (BaP), a test-time adversarial defense for CLIP. BaP constructs the probe through a closed-form model edit to a selected MLP layer. It projects the average adversarial activation shift and a defender-specified semantic direction onto the layer's low-energy input and output activation subspaces to obtain the trigger and target directions, respectively. At inference time, adversarial inputs produce measurable responses along the target direction for detection. BaP then selectively rectifies detected inputs by optimizing a small perturbation that steers their representations away from adversarial shifts and toward the clean subspace. Experiments across 16 benchmarks show that BaP improves average robust accuracy from 1.0\% to 52.3\% while retaining clean accuracy, achieving performance comparable to state-of-the-art methods with up to a $5.7\times$ inference speedup. BaP further shows the generalization to adversarial attacks on large vision-language models. Project page: https://robin-wzq.github.io/Backdoor-as-Probe/

cs.CV↗

arXiv2026

V-Gym: Enhancing Agentic Visual Reasoning via Skill-Data Co-Evolution

Advances in multimodal understanding, reasoning, and tool use enable agents to tackle increasingly complex visual reasoning tasks. By distilling past execution experience into reusable skills, agents can transfer lessons from both successes and failures into future reasoning, reducing repeated errors and improving capabilities. However, limited experience may produce unreliable, poorly generalizable skills, while static datasets may lack the targeted and diverse practice needed for refinement. To address this gap, we introduce V-Gym, an autonomous framework that iteratively co-evolves procedural skills and multimodal practice data from execution trajectories. During skill evolution, V-Gym analyzes trajectories to distill and refine hierarchical skills, updating procedural guidance and applicability conditions while retaining an update only if it improves validation performance. During data evolution, V-Gym selects generation seeds by balancing data utility and exploration, then translates trajectory-identified bottlenecks into diverse, targeted practice data that expand the data bank after quality checks. The resulting practice outcomes feed back into subsequent skill updates, closing the loop for continual skill refinement. Experiments across diverse multimodal reasoning benchmarks show substantial improvements over baselines with multiple backbone models. Its evolved skills generalize across domains and models, while evolved data support more effective skill refinement, enabling autonomous diagnosis, targeted practice, and continual self-improvement.

cs.CV↗

arXiv2026

Beyond Saying Less: Fine-Grained Alignment for Informative and Faithful Vision-Language Models

Object hallucination remains a major challenge for large vision-language models. While off-policy preference optimization proves to be an effective solution, on-policy reinforcement learning provides a more promising direction as it directly targets a model's current failure modes. However, we find that without fine-grained reward formulation and allocation, on-policy optimization often falls into an easy shortcut: reducing hallucinations merely by saying less---making fewer valid claims. To comprehensively resolve this, we propose a fine-grained alignment framework that couples dense reward signals at the data level with precise credit assignment at the algorithmic level. Specifically, we first construct the Dense Object Presence and Absence (DOPA) dataset to address sparse annotations that prevent valid object claims from being verified and rewarded. DOPA exhaustively annotates the deterministic presence and absence of every concept across an expanded vocabulary, significantly increasing the density of reliable reward signals during on-policy rollouts. Second, we propose Subsentence-level Credit Assignment for on-Policy Optimization (SCAPO) to prevent response-level shared advantages from allowing local hallucinations to compromise all other valid outputs within the same response. By assigning credit to each subsentence independently based on its object claims, SCAPO can precisely reinforce faithful generations and penalize hallucinations. Furthermore, we leverage the resulting faithful image descriptions as auxiliary context to transfer generative gains to discriminative tasks. Experiments demonstrate that our method produces highly informative, faithful descriptions in generative tasks while yielding clear performance gains on discriminative evaluation.

cs.CV↗

arXiv2026

Render Before Reading: Visual Rendering as a Prompt Injection Defense

Large language models are vulnerable to prompt injection attacks, where third-party adversarial content can hijack the model's behavior. In this paper, we study the role played by the adversarial data's input modality, and identify a systematic asymmetry: multimodal LLMs are more likely to follow adversarial instruction when they appear as text than when the same instruction is delivered through a non-textual channel (e.g., as an image). We hypothesize that this modality gap arises from text-centric instruction tuning, which teaches models to obey textual instructions while treating other modalities mainly as content to parse or describe. We then demonstrate how this gap can be turned into a training-free defense, by rendering all untrusted payloads as typographic images (or audio) before they reach the model. Across ten models and two prompt injection benchmarks (DirectInject and AgentDojo) we show that our defense Pictionary consistently reduces attack success rates even against the strongest adaptive attacks and human red teamers, while largely preserving benign utility. We further show that benign fine-tuning on image-rendered instructions erodes the modality gap, tracing it to the text-centric instruction-tuning distribution.

cs.CR↗

arXiv2026

Calibrating One-Round Membership Inference with Neighbors

The state-of-the-art Membership Inference (MI) methods calibrate their signal separately for each example using reference models, auxiliary models trained to exclude the target. This paradigm scales poorly to modern large models, however, whose training is too expensive to replicate. This has motivated one-round settings, where only a single trained model is available; but without reference models the per-example calibration that drives the strongest attacks can no longer be estimated, leaving the membership signal weak. We ask whether neighbors of the target point can recover this calibration without training any additional model. Our key observation is that reference models serve only to reveal how an example behaves under models not trained on it, and that querying the target model on nearby samples yields the same information. We propose two complementary ways to obtain such neighbors, and show that querying them against an early training checkpoint further sharpens the signal. We evaluate across three image classification datasets and three training setups, showing that neighbors yield strong membership signals and competitive attack performance at no additional training cost.

cs.CR↗

arXiv2026

One Attack to Fool Them All: Highly Transferable Black-Box Adversarial Attacks on Frontier MLLMs

Adversarial attacks have long posed a fundamental threat to machine learning systems. As multimodal large language models (MLLMs) rapidly evolve and become widely deployed, assessing their vulnerability to such attacks is essential for their safe use. In this work, we investigate whether a single adversarial image can consistently mislead diverse frontier MLLMs in black-box settings. We propose O-Attack, a highly transferable black-box attack framework. This framework builds on our insight that surrogate models contain a broad, high-level, cross-modally aligned semantic space. This space extends beyond final-layer outputs and provides multiple semantically consistent representations that remain underexploited by existing attacks. Within this space, O-Attack anchors aligned representations, progressively broadens semantic conditions, and optimizes perturbations through semantic consensus to promote consistent target alignment. By fully exploiting this space with the same surrogate models as M-Attack, O-Attack raises attack success rates on GPT-5.4 (29.1% to 77.2%), Claude-4.6 (42.8% to 81.6%), and Gemini-3.1 (38.2% to 80.9%). Extensive experiments across 24 MLLMs show that O-Attack outperforms six state-of-the-art methods in black-box transferability, with consistent effectiveness across prompts and improved efficiency and imperceptibility. This work exposes the practical safety risks posed by black-box adversarial attacks against frontier MLLMs, underscoring the need for more rigorous robustness evaluation and more effective defenses.

cs.CV↗

arXiv2026

Few-Shot Specific Emitter Identification via Integrated Complex Variational Mode Decomposition and Spatial Attention Transfer

Specific emitter identification (SEI) utilizes passive hardware characteristics to authenticate transmitters, providing a robust physical-layer security solution. However, most deep-learning-based methods rely on extensive data or require prior information, which poses challenges in real-world scenarios with limited labeled data. We propose an integrated complex variational mode decomposition algorithm that decomposes and reconstructs complex-valued signals to approximate the original transmitted signals, thereby enabling more accurate feature extraction. We further utilize a temporal convolutional network to effectively model the sequential signal characteristics, and introduce a spatial attention mechanism to adaptively weight informative signal segments, significantly enhancing identification performance. Additionally, the branch network allows leveraging pre-trained weights from other data while reducing the need for auxiliary datasets. Ablation experiments on the simulated data demonstrate the effectiveness of each component of the model. An accuracy comparison on a public dataset reveals that our method achieves 96% accuracy using only 10 symbols without requiring any prior knowledge.

eess.SP↗

arXiv2026

When and Where to Trust the Teacher: Unifying On-Policy Distillation and GRPO through Entropy-Calibrated Credit Assignment

Reinforcement learning with verifiable rewards (RLVR) supervises mathematical reasoning through final-answer correctness, but provides little guidance on individual tokens. On-policy distillation (OPD) supplies dense feedback on student-generated responses, yet teacher preference need not reflect correctness. Recent hybrids combine OPD and verifier-derived advantages or reweight task credit using teacher ratios. However, teacher guidance enters after verifier-based group normalization, and token reweighting need not preserve the total task credit assigned to each response. We introduce Unified Entropy-Calibrated Credit Redistribution for GRPO (UECR-GRPO), which integrates verifier and teacher signals within a single GRPO-style update at both the response and token levels. \emph{Path-Utility Unification} (PUU) combines verifier reward and a teacher-to-anchor path log-ratio in a single KL-regularized objective. Its on-policy implementation uses a length-normalized teacher score and combines both rewards before group normalization and PPO clipping, allowing teacher evidence to influence the response ranking. \emph{Entropy-Calibrated Redistribution} (ECR) then uses the signed teacher--old-policy token gap to redistribute the verifier-derived component. Full-vocabulary teacher entropy attenuates uncertain guidance, while a response-wise zero-sum projection preserves the total task credit and its token-wise sign before clipping. Across five mathematical reasoning benchmarks, UECR-GRPO achieves average $\mathrm{Avg@12}$ accuracies of 17.21\% and 65.09\% with Qwen3-1.7B and Qwen3-4B students, respectively, exceeding the strongest baseline at each scale by 0.89 and 0.56 percentage points.

cs.LG↗

arXiv2026

Longitudinal Retinal Vascular Remodeling in Myopic Children Treated with Orthokeratology or Defocus Lenses: A Two-Year Comparative Study

Purposes: To characterize longitudinal retinal vascular changes in myopic children treated with orthokeratology (OK) or multifocal defocus lenses (Defocus) and to examine their association with axial elongation. Methods: In this retrospective cohort study, 43 myopic children underwent comprehensive clinical examination and fundus photography at baseline, 12 months, and 24 months. Axial length (AL) and spherical equivalent refraction (SER) were recorded at baseline, 6, 12, and 24 months. An automated segmentation model extracted vascular parameters, main vessel angle (MA), branching angle (BA), bifurcation edge angle (BEA), crossover point (COP), and terminal vessel count (TVC). Repeated-measures ANOVA assessed temporal changes. Pearson or Spearman correlations evaluated associations between AL and vascular metrics. Results: Over 24 months, the OK group exhibited significantly slower axial elongation than the Defocus group (0.214 mm and 0.522 mm, p < 0.01). In the OK group, MA and BA decreased modestly, BEA in arteries declined gradually, but COP and TVC remained relatively stable. The Defocus group demonstrated more pronounced decreases in MA and BA, an increase in BEA, and significant reductions in COP and TVC (p < 0.05). Correlation analysis revealed stronger associations between AL and vascular parameters, especially COP and TVC, in the Defocus group at all time points, whereas only BA and BEA correlated with AL in the OK group. Conclusions: OK lenses mitigate axial elongation and induce milder retinal vascular remodeling compared to Defocus lenses. Distinct temporal patterns of vascular metrics changes were observed between the two interventions, and correlate differentially with axial growth.

cs.CV↗

arXiv2026

ZMIS-SAM: Segment Anything Model Enhanced with Wavelet Transform for Zooplankton Microscopy Image Instance Segmentation

As primary consumers in the marine food chain, zooplankton play a crucial role in maintaining marine ecological balance. However, the Segment Anything Model (SAM) exhibits limited performance in microscopic image instance segmentation due to its lack of zooplankton-specific domain knowledge. To address these challenges, we propose a novel instance segmentation model based on SAM and wavelet transform (ZMIS-SAM), effectively tackling issues such as inaccurate classification, discontinuous segmentation of slender appendages, and incomplete boundary segmentation. Our framework incorporates three core innovations: ZM-ViT enhances SAM's capability to model zooplankton morphology and image intensity distributions through two lightweight adapters, the Neighboring Feature Aggregation Module (NFAM) improves continuous segmentation of semi-transparent slender appendages by integrating general-purpose and domain-specific features, and the Wavelet-based Multi-scale Multi-directional Feature Enhancement (WM2FE) module effectively recovers high-frequency details to refine boundary segmentation completeness. Extensive experiments demonstrate that ZMIS-SAM achieves state-of-the-art instance segmentation performance on the zooplankton dataset and exhibits strong generalization capability across multiple public cross-domain datasets.

cs.CV↗

arXiv2026

Controlling risks of AI in chemical science with agents

Artificial intelligence is rapidly advancing scientific discovery, but this progress carries risks of misuse, such as the creation of harmful substances, or circumvention of established regulations. In this paper, we first demonstrate the risks by highlighting real-world examples of AI misuse in chemical science, which underscore the need for effective safety alignment for these AI models. In response, we propose SciGuard, an agent-based guardrail that employs large language models, tools and external knowledge to assess and control risks in scientific AI interactions. For a fair comparison, we introduce a benchmark SciMT (Scientific Multi-Task) to assess both the safety and utility of different AI systems. SciGuard achieves a state-of-the-art harmlessness score on red-teaming queries, while maintaining high performance on benign tasks, without sacrificing scientific knowledge. Finally, we call for continued research and dialogue to ensure the safe deployment of AI in science.

cs.AI↗

arXiv2026

Unifying Plasticity in Ordered and Disordered Matter using Topological and Geometrical Descriptors

Identifying the regions responsible for plastic flow in amorphous solids remains an open problem, since structural disorder seems to prevent the direct application of concepts such as dislocations, topological defects that successfully describe irreversible deformations in crystalline systems. Here, we introduce fields of dislocation, disclination, and incompatibility densities, that in crystals reduce to the standard sources of plasticity and assess their predictive power in amorphous materials. We find that, in a simulated two-dimensional glass as well in two- and three-dimensional experimental granular systems, these fields exhibit strong spatial correlations with $D^2_{\text{min}}$, a standard descriptor used to locate plastic events in disordered solids under shear, indicating that these fields are indeed reliable quantities for predicting plastic events. In contrast to $D^2_{\rm min}$, these fields provide deeper insight into how local rotational and translational motions become coupled well before the onset of plastic events. Moreover, by allowing the two contributions to be disentangled, they reveal that rotational defects become increasingly dominant in three dimensions. Our approach paves the way for describing plasticity in crystalline and amorphous solids in a unified manner.

cond-mat.soft↗

arXiv2026

HyperParallel-FSDP: Topology-Aware Fully Sharded Training with Layout-Driven Muon on Ascend SuperPods

Declarative SPMD programming uses tensor sharding descriptions to drive distributed execution, separating parallelization from model code. However, the evaluated PyTorch DTensor stack dispatches every operator below autograd, incurring repeated dispatch and metadata costs, while lacking an inexpensive end-to-end validation path. Existing FSDP and distributed Muon implementations also mismatch two-tier supernode topologies: FSDP relies on explicit parameter packing and unpacking, and Muon's whole-matrix orthogonalization conflicts with parameter sharding. We observe that distributed tensors need only express sharding semantics at the tensor API boundary above autograd, allowing differentiation and kernels to operate on plain tensors. Based on this insight, we present HyperParallel-FSDP, featuring: (1) dual-mode DTensor execution, using one sharding plan for both a production mode with one-time layout resolution and no steady-state dispatch overhead, and a validation mode with end-to-end metadata propagation, fail-fast checks, and gradient-equivalence testing; (2) topology-aware FSDP, with zero-copy intra-supernode collectives, fused inter-supernode reduction, and a cross-layer backward pipeline that avoids waits on slow links; and (3) layout-driven distributed Muon, with sharding-derived communication groups, deduplicated orthogonalization, and shape-fused Newton-Schulz iterations. On Atlas 900 A3 SuperPoD, HyperParallel-FSDP scales from 16 dies to 384 cards (768 ranks), sustaining 421k tokens/s for a 505B-parameter MoE while FSDP communication uses 2.9% of step time. It reduces mean step time by 29.7% versus PyTorch FSDP2 and 25.5% versus Megatron DDP, with Pearson correlation above 0.999997 over 1,000 steps. Distributed Muon improves profiler step time by 5.4-16.0% over competing systems. Source code is available at https://atomgit.com/mindspore/hyper-parallel.

cs.DC↗

arXiv2026

Qwen-Image-Flash: Rethinking the Training Recipe for Few-Step Distillation

Few-step distillation has emerged as a critical component in the development of advanced visual generative foundation models, substantially reducing inference overhead while enabling real-time generation and cost-efficient deployment across a broad range of practical scenarios. However, prior work has predominantly focused on advancing training objectives, while comparatively overlooking the training recipe, which has become increasingly critical in the era of large-scale foundation models. In this work, we systematically revisit the training recipe under the well-established distribution matching distillation (DMD) framework for both text-to-image generation and image editing, focusing on three key dimensions: training data composition, teacher guidance within DMD, and task mixture. Our empirical analysis reveals several non-obvious and counterintuitive phenomena, ultimately motivating the development of Qwen-Image-Flash. These findings highlight that effective few-step distillation depends not only on carefully designed objectives, but also on a principled training recipe.

cs.CV↗

arXiv2026

High-order Energy-stable and Charge-conservative Lagrangian FEM for 3D Incompressible Inductionless MHD equations with Variable Density

In this paper, we develop a high-order, energy-stable and charge-conservative Lagrangian finite element method for variable-density incompressible inductionless magnetohydrodynamic (MHD) equations. The method utilizes the moving high-order curved tetrahedral mesh to track the material interface. Second-order Backward Differentiation Formula (BDF2) is used for the temporal discretization of material derivative, together with the second-order Adams--Bashforth method (AB2) for the update of control points of the meshes. High-order isoparametric Taylor-Hood elements with grad-div stabilization are used for the velocity-pressure pair. While, to ensure the discrete charge conservation, high-order parametric $\BH(\Div)$-conforming element is adopted for the current density. In the absence of external force, the unconditional energy-stability of the fully discrete scheme is proven. Finally, 3D numerical experiments are conducted to confirm the expected high-order accuracy for smooth solutions, the energy stability property and the capability of the proposed method.

math.NA↗

arXiv2026

Segment Any Motion with Radar: Robust Multimodal Moving-Object Segmentation and Tracking

Moving-object perception must decide which image regions correspond to real motion and keep every instance identified over time. Methods that read motion from appearance, optical flow, or estimated trajectories lose that evidence under poor illumination, adverse weather, reflections, and occlusion. Radar is a natural remedy because it measures radial velocity directly instead of inferring it from photometric correspondence. However, existing benchmarks do not jointly provide radar measurements, dense moving-instance masks, and temporally consistent identities for surveillance. We therefore introduce RGBTR-Motion, a synchronized and calibrated fixed-camera benchmark that pairs RGB, thermal, and radar streams with dense instance masks and temporally consistent identities across diverse surveillance scenes. We also develop SAM-Radar, an RGB, thermal, and radar-based segmentation and tracking framework built on SAM 3. SAM-Radar's radar-aware detector fuses calibrated RGBT features with radar returns that are grounded at their projected image locations, and motion supervision, implemented as foreground classification of those projected returns, teaches the detector to reject clutter without any text prompt. The tracker associates accepted radar returns with individual trajectories and uses them as physical evidence that a visually degraded target remains present. This allows it to bridge short periods of low visibility or occlusion and reconnect a reappearing target to its existing identity instead of starting a new track. SAM-Radar attains 0.7027 IoU and 0.8090 F1-50, and raises MOTA, HOTA, and IDF1 by 0.2977, 0.1603, and 0.2857 over the strongest competing values.

cs.CV↗

arXiv2026

Generalized supremum convolutions on the tensor product of unit intervals: t-conorms and triangle functions

The complete-lattice tensor product $\mathbb{E}=[0,1]\otimes[0,1]$ arises naturally in the algebra of truth values for type-2 fuzzy sets. For a monotone surjective map $S$ that is continuous on $[0,1[^2$ and a monotone map $T$ having $1$ as identity, we consider the generalized supremum convolution \[ (f\otimes_{_{S,T}}g)(x)=\sup_{S(u,v)=x}T(f(u),g(v)) \] on $\mathbb{E}$. Rather than assuming classical algebraic structures for $S$ and $T$ from the outset, we ask when they are forced by requiring the induced convolution itself to be a t-conorm. We prove that $\otimes_{_{S,T}}$ is a t-conorm on $\mathbb{E}$ if and only if $S$ is a continuous t-conorm and either $S=\max$ or $T$ is a right-continuous t-norm; in the exceptional case $S=\max$, the convolution is simply the pointwise maximum for every admissible $T$. The same convolution mechanism also yields an order-dual description of triangle functions on the space of distance distribution functions $Δ^+$. Using an order-reversing isomorphism between $Δ^+$ and a boundary variant of $\mathbb{E}$, we show that $τ_{_{T^*,L}}$ is a triangle function precisely when $L$ is a continuous t-conorm with no zero divisor and, unless $L=\max$, $T^*$ is a left-continuous t-conorm; moreover, when $L\neq\max$, continuity of $τ_{_{T^*,L}}$ is equivalent to continuity of $T^*$. This resolves the remaining $τ_{_{T^*,L}}$ part of the Schweizer--Sklar problem.

math.GM↗