Wenbin Wu

Wenbin Wu

Large language models now power robo-advisors and trading agents, yet whether they carry built-in biases toward specific assets is largely untested. We ask three questions: do LLMs systematically prefer certain financial instruments; can an internal representation with causal leverage over those preferences be identified; and does that representation affect downstream financial decisions? We develop a three-level audit protocol and apply it to Bitcoin. First, a behavioral audit of eight frontier LLMs shows that Bitcoin's ranking among money-like instruments is frame-dependent: models place it around rank 5 of 8 as "reliable money" but near the top under crisis and autonomous-agent frames, and an attribute-swap experiment confirms rankings track functional properties, not names. Second, we open a model's internals: a search across thousands of sparse-autoencoder features in Gemma 3 identifies a dominant Bitcoin-selective feature. Amplifying it shifts the model toward the asset and suppressing it shifts the model away, even when "Bitcoin" never appears in the prompt. Third, we test financial consequences: amplification raises Bitcoin's portfolio share by 5.2 percentage points while suppression lowers it by 4.6 pp, with amplification reallocating within crypto and suppression cutting total crypto exposure. We characterize this as bounded behavioral leverage (leverage meaning causal influence over outputs, not financial leverage): an identifiable internal feature can be perturbed to move financial choices, but only within measurable limits. The framework links internal representations to external recommendations, validated with random controls and mechanism boundaries. As LLMs become autonomous financial agents, this is a first step toward a behavioral layer for emerging know-your-agent (KYA) standards: knowing what an agent prefers, and how far that preference can be moved.

Haozhen Gong, Xiaozhong Ji, Yuansen Liu et al.

MLLMs MLLMs are beginning to appear in clinical workflows, but their ability to perform complex medical reasoning remains unclear. We present Med-CMR, a fine-grained Medical Complex Multimodal Reasoning benchmark. Med-CMR distinguishes from existing counterparts by three core features: 1) Systematic capability decomposition, splitting medical multimodal reasoning into fine-grained visual understanding and multi-step reasoning to enable targeted evaluation; 2) Challenging task design, with visual understanding across three key dimensions (small-object detection, fine-detail discrimination, spatial understanding) and reasoning covering four clinically relevant scenarios (temporal prediction, causal reasoning, long-tail generalization, multi-source integration); 3) Broad, high-quality data coverage, comprising 20,653 Visual Question Answering (VQA) pairs spanning 11 organ systems and 12 imaging modalities, validated via a rigorous two-stage (human expert + model-assisted) review to ensure clinical authenticity. We evaluate 18 state-of-the-art MLLMs with Med-CMR, revealing GPT-5 as the top-performing commercial model: 57.81 accuracy on multiple-choice questions (MCQs) and a 48.70 open-ended score, outperforming Gemini 2.5 Pro (49.87 MCQ accuracy, 45.98 open-ended score) and leading open-source model Qwen3-VL-235B-A22B (49.34 MCQ accuracy, 42.62 open-ended score). However, specialized medical MLLMs do not reliably outperform strong general models, and long-tail generalization emerges as the dominant failure mode. Med-CMR thus provides a stress test for visual-reasoning integration and rare-case robustness in medical MLLMs, and a rigorous yardstick for future clinical systems.

Feng Yuan, Yifan Gao, Wenbin Wu et al.

Accurate multi-modal medical image translation requires ha-rmonizing global anatomical semantics and local structural fidelity, a challenge complicated by intermodality information loss and structural distortion. We propose ABS-Mamba, a novel architecture integrating the Segment Anything Model 2 (SAM2) for organ-aware semantic representation, specialized convolutional neural networks (CNNs) for preserving modality-specific edge and texture details, and Mamba's selective state-space modeling for efficient long- and short-range feature dependencies. Structurally, our dual-resolution framework leverages SAM2's image encoder to capture organ-scale semantics from high-resolution inputs, while a parallel CNNs branch extracts fine-grained local features. The Robust Feature Fusion Network (RFFN) integrates these epresentations, and the Bidirectional Mamba Residual Network (BMRN) models spatial dependencies using spiral scanning and bidirectional state-space dynamics. A three-stage skip fusion decoder enhances edge and texture fidelity. We employ Efficient Low-Rank Adaptation (LoRA+) fine-tuning to enable precise domain specialization while maintaining the foundational capabilities of the pre-trained components. Extensive experimental validation on the SynthRAD2023 and BraTS2019 datasets demonstrates that ABS-Mamba outperforms state-of-the-art methods, delivering high-fidelity cross-modal synthesis that preserves anatomical semantics and structural details to enhance diagnostic accuracy in clinical applications. The code is available at https://github.com/gatina-yone/ABS-Mamba

Aijie Shu, Wenbin Wu, Gbenga Ibikunle et al.

Credit exposure in Decentralized Finance (DeFi) is often implicit and token-mediated, creating a dense web of inter-protocol dependencies. Thus, a shock to one token may result in significant and uncontrolled contagion effects. As the DeFi ecosystem becomes increasingly linked with traditional financial infrastructure through instruments, such as stablecoins, the risk posed by this dynamic demands more powerful quantification tools. We introduce DeXposure-FM, the first time-series, graph foundation model for measuring and forecasting inter-protocol credit exposure on DeFi networks, to the best of our knowledge. Employing a graph-tabular encoder, with pre-trained weight initialization, and multiple task-specific heads, DeXposure-FM is trained on the DeXposure dataset that has 43.7 million data entries, across 4,300+ protocols on 602 blockchains, covering 24,300+ unique tokens. The training is operationalized for credit-exposure forecasting, predicting the joint dynamics of (1) protocol-level flows, and (2) the topology and weights of credit-exposure links. The DeXposure-FM is empirically validated on two machine learning benchmarks; it consistently outperforms the state-of-the-art approaches, including a graph foundation model and temporal graph neural networks. DeXposure-FM further produces financial economics tools that support macroprudential monitoring and scenario-based DeFi stress testing, by enabling protocol-level systemic-importance scores, sector-level spillover and concentration measures via a forecast-then-measure pipeline. Empirical verification fully supports our financial economics tools. The model and code have been publicly available. Model: https://huggingface.co/EVIEHub/DeXposure-FM. Code: https://github.com/EVIEHub/DeXposure-FM.

Yuansen Liu, Haiming Tang, Jinlong Peng et al. · tencent-ai

Multimodal Large Language Models (MLLMs) have demonstrated significant advances in visual understanding tasks. However, their capacity to comprehend human-centric scenes has rarely been explored, primarily due to the absence of comprehensive evaluation benchmarks that take into account both the human-oriented granular level and higher-dimensional causal reasoning ability. Such high-quality evaluation benchmarks face tough obstacles, given the physical complexity of the human body and the difficulty of annotating granular structures. In this paper, we propose Human-MME, a curated benchmark designed to provide a more holistic evaluation of MLLMs in human-centric scene understanding. Compared with other existing benchmarks, our work provides three key features: 1. Diversity in human scene, spanning 4 primary visual domains with 15 secondary domains and 43 sub-fields to ensure broad scenario coverage. 2. Progressive and diverse evaluation dimensions, evaluating the human-based activities progressively from the human-oriented granular perception to the higher-dimensional reasoning, consisting of eight dimensions with 19,945 real-world image question pairs and an evaluation suite. 3. High-quality annotations with rich data paradigms, constructing the automated annotation pipeline and human-annotation platform, supporting rigorous manual labeling to facilitate precise and reliable model assessment. Our benchmark extends the single-target understanding to the multi-person and multi-image mutual understanding by constructing the choice, short-answer, grounding, ranking and judgment question components, and complex questions of their combination. The extensive experiments on 17 state-of-the-art MLLMs effectively expose the limitations and guide future MLLMs research toward better human-centric image understanding. All data and code are available at https://github.com/Yuan-Hou/Human-MME.

Wenbin Wu, Alexander Neumueller

Bitcoin's design promises resilience through decentralization, yet the physical infrastructure supporting the network creates hidden dependencies. We present the first longitudinal study of Bitcoin's resilience to submarine cable failures, using 11 years of P2P network data (2014--2025) and 68 verified cable fault events. Applying a Buldyrev-style cascade model at country level, we find that Bitcoin's clearnet (non-TOR) critical failure threshold $p_c \approx 0.72$--$0.92$ for random failures, meaning the vast majority of inter-country cables must fail before significant node disconnection. Targeted attacks are an order of magnitude more effective ($p_c = 0.05$--$0.20$). To address the majority of nodes now using TOR with unobservable locations, we develop a 4-layer multiplex model incorporating TOR relay infrastructure. Because relay bandwidth concentrates in well-connected European countries, TOR adoption increases resilience under current relay geography ($Δp_c \approx +0.02$--$+0.10$) rather than introducing hidden fragility. Empirical validation confirms weak physical-layer coupling: 87% of historical cable faults caused less than 5% node impact. We contribute: (1) a multiplex percolation framework for overlay-underlay coupling, including a 4-layer TOR relay model; (2) the first empirical measurement of Bitcoin's physical-layer resilience over a decade; and (3) evidence that TOR adoption amplifies resilience, with distributional bounds quantifying uncertainty under partial observability.

Xin Tan, Wenbin Wu, Zhiwei Zhang et al.

3D occupancy perception holds a pivotal role in recent vision-centric autonomous driving systems by converting surround-view images into integrated geometric and semantic representations within dense 3D grids. Nevertheless, current models still encounter two main challenges: modeling depth accurately in the 2D-3D view transformation stage, and overcoming the lack of generalizability issues due to sparse LiDAR supervision. To address these issues, this paper presents GEOcc, a Geometric-Enhanced Occupancy network tailored for vision-only surround-view perception. Our approach is three-fold: 1) Integration of explicit lift-based depth prediction and implicit projection-based transformers for depth modeling, enhancing the density and robustness of view transformation. 2) Utilization of mask-based encoder-decoder architecture for fine-grained semantic predictions; 3) Adoption of context-aware self-training loss functions in the pertaining stage to complement LiDAR supervision, involving the re-rendering of 2D depth maps from 3D occupancy features and leveraging image reconstruction loss to obtain denser depth supervision besides sparse LiDAR ground-truths. Our approach achieves State-Of-The-Art performance on the Occ3D-nuScenes dataset with the least image resolution needed and the most weightless image backbone compared with current models, marking an improvement of 3.3% due to our proposed contributions. Comprehensive experimentation also demonstrates the consistent superiority of our method over baselines and alternative approaches.

Wenbin Wu

In traditional banking, repeated deposit-and-lend cycles let a single dollar of reserves support multiple dollars of claims. Decentralized finance produces an analogous structure with tokens. Constructing a Token Graph of 10,200 tokens across 200 blockchains, this paper maps the resulting hierarchy and shows that, by late 2025, each dollar of base assets supports $4.7 of total claims. An embedded yield correction disentangles two channels that raw data conflates: a compositional channel, where lending protocols concentrate in deeper tiers and mechanically raise average yields; and a liquidity channel, where each derivation step reduces secondary-market depth and depresses yields in liquidity-sensitive pools. The liquidity channel concentrates in DEX pools and vanishes in lending pools. A yield decomposition shows that the tier gradient operates entirely through fundamental protocol yields, not incentive-token emissions; quantile regressions reveal that the structural associations concentrate in the upper tail of the yield distribution, with near-zero effects at the median. These findings reframe DeFi's "double counting" as a structural risk question and identify liquidity fragmentation as the primary mechanism associated with yield variation across the token hierarchy.

Wenbin Wu, Kejiang Qian, Alexis Lui et al.

We curate the DeXposure dataset, the first large-scale dataset for inter-protocol credit exposure in decentralized financial networks, covering global markets of 43.7 million entries across 4.3 thousand protocols, 602 blockchains, and 24.3 thousand tokens, from 2020 to 2025. A new measure, value-linked credit exposure between protocols, is defined as the inferred financial dependency relationships derived from changes in Total Value Locked (TVL). We develop a token-to-protocol model using DefiLlama metadata to infer inter-protocol credit exposure from the token's stock dynamics, as reported by the protocols. Based on the curated dataset, we develop three benchmarks for machine learning research with financial applications: (1) graph clustering for global network measurement, tracking the structural evolution of credit exposure networks, (2) vector autoregression for sector-level credit exposure dynamics during major shocks (Terra and FTX), and (3) temporal graph neural networks for dynamic link prediction on temporal graphs. From the analysis, we observe (1) a rapid growth of network volume, (2) a trend of concentration to key protocols, (3) a decline of network density (the ratio of actual connections to possible connections), and (4) distinct shock propagation across sectors, such as lending platforms, trading exchanges, and asset management protocols. The DeXposure dataset and code have been released publicly. We envision they will help with research and practice in machine learning as well as financial risk monitoring, policy analysis, DeFi market modeling, amongst others. The dataset also contributes to machine learning research by offering benchmarks for graph clustering, vector autoregression, and temporal graph analysis.

Shuying Liu, Wenbin Wu, Jiaxian Wu et al.

We propose an approach to estimate arm and hand dynamics from monocular video by utilizing the relationship between arm and hand. Although monocular full human motion capture technologies have made great progress in recent years, recovering accurate and plausible arm twists and hand gestures from in-the-wild videos still remains a challenge. To solve this problem, our solution is proposed based on the fact that arm poses and hand gestures are highly correlated in most real situations. To fully exploit arm-hand correlation as well as inter-frame information, we carefully design a Spatial-Temporal Parallel Arm-Hand Motion Transformer (PAHMT) to predict the arm and hand dynamics simultaneously. We also introduce new losses to encourage the estimations to be smooth and accurate. Besides, we collect a motion capture dataset including 200K frames of hand gestures and use this data to train our model. By integrating a 2D hand pose estimation model and a 3D human pose estimation model, the proposed method can produce plausible arm and hand dynamics from monocular video. Extensive evaluations demonstrate that the proposed method has advantages over previous state-of-the-art approaches and shows robustness under various challenging scenarios.