Searcharxiv⌕ Search

arXiv subjects

Di Wang

Publications and source records attributed to Di Wang.

At least 109 records · Page 6Linked to original sources
arXiv2026

PathMoG: A Pathway-Centric Modular Graph Neural Network for Multi-Omics Survival Prediction

Cancer survival prediction from multi-omics data remains challenging because prognostic signals are high-dimensional, heterogeneous, and distributed across interacting genes and pathways. We propose PathMoG, a pathway-centric modular graph neural network for multi-omics survival prediction. PathMoG reorganizes genome-scale inputs into 354 KEGG-informed pathway modules, introduces a Hierarchical Omics Modulation module to condition gene-expression representations on mutation, copy number variation, pathway, and clinical context, and uses dual-level attention to capture both intra-pathway driver signals and inter-pathway clinical relevance. We evaluated PathMoG on 5,650 patients across 10 TCGA cancer types and observed consistent improvements over representative survival baselines. The framework further provides gene-level, pathway-level, and patient-level interpretability, supporting biologically grounded and clinically relevant risk stratification.

cs.LG↗
arXiv2026

Adaptive Multi-Subspace Representation Steering for Attribute Alignment in Large Language Models

Activation steering offers a promising approach to controlling the behavior of Large Language Models by directly manipulating their internal activations. However, most existing methods struggle to jointly steer multiple attributes, often resulting in interference and undesirable trade-offs. To address this challenge, we propose Multi-Subspace Representation Steering (MSRS), a novel framework for effective multi-attribute steering via subspace representation fine-tuning. MSRS reduces inter-attribute interference by allocating orthogonal subspaces to each attribute, isolating their influence within the model's representation space. MSRS also incorporates a hybrid subspace composition strategy: it combines attribute-specific subspaces for unique steering directions with a shared subspace for common steering directions. A dynamic weighting function learns to efficiently integrate these components for precise control. During inference, MSRS introduces a token-level steering mechanism that dynamically identifies and intervenes on the most semantically relevant tokens, enabling fine-grained behavioral modulation. Experimental results show that MSRS significantly reduces attribute conflicts, surpasses existing methods across a range of attributes, and generalizes effectively to diverse downstream tasks.

cs.AI↗
arXiv2026

HBGSA: Hydrogen Bond Graph with Self-Attention for Drug-Target Binding Affinity Prediction

Accurate prediction of drug-target binding affinity accelerates drug discovery by prioritizing compounds for experimental validation. Current methods face three limitations: sequence-based approaches discard spatial geometric constraints, structure-based methods fail to exploit hydrogen bond features, and conventional loss functions neglect prediction-target correlation, a key factor for identifying high-affinity compounds in virtual screening. We developed HBGSA (Hydrogen Bond Graph with Self-Attention), a 3.06M-parameter model that encodes hydrogen bond spatial features. HBGSA uses graph neural networks to model hydrogen bond spatial topology with self-attention enhancement and Pearson correlation loss. Experimental results on PDBbind Core Set and CSAR-HiQ dataset demonstrate that HBGSA outperforms baseline methods with strong generalization capability. Ablation studies confirm the effectiveness of hydrogen bond modeling and Pearson correlation loss.

cs.LG↗
arXiv2026

Accurate Nanoscale Mapping of Electric Fields across Random Grain Boundaries in Polycrystalline Oxides Using Precession-Assisted 4D-STEM

Space charge layers (SCLs) at grain boundaries play a crucial role in modulating local electric fields and influencing the functional properties of materials, such as oxygen vacancy migration and ionic conductivity in oxide ceramics. However, the direct experimental analysis of such localized electric fields and the corresponding charge distribution remains challenging. Conventional center-of-mass (CoM) analysis in scanning transmission electron microscopy differential phase contrast (STEM-DPC) is strongly affected by orientation-dependent contrast and dynamical scattering. Here, we demonstrate that combining electron beam precession with advanced post-processing, employing iterative edge detection via a Sobel filter and singular value decomposition (SVD), enables reliable and accurate, unbiased diffraction shift measurements with minimal crystallographic artefacts. The new method accurately refines the central disk position in nanobeam electron diffraction (NBED) patterns and thus significantly improves the extraction of the local electric field and corresponding charge distribution. Comparative analysis with conventional CoM methods shows superior accuracy and robustness for random grain boundaries in BaTiO3 and SrTiO3 as exemplary case studies. The experimental work is complemented by atomistic simulations to separate the electric field of the SCL from the mean inner potential difference of the grain boundary and the elemental segregation around the grain boundary. The in-depth analysis shows that our approach enables high-fidelity mapping of electromagnetic fields and their charge distribution in complex polycrystalline specimens, laying the groundwork for improved quantitative analysis using STEM-DPC.

cond-mat.mtrl-sci↗
arXiv2026

A Spatial-Resolved Proton Energy Spectrometer Based on a Scintillation-Fiber Cube

Advanced particle acceleration methods have produced high-peak-current ion beams with broad energy spread and complex spatial distribution. There is an urgent need to develop online spatial-resolved energy spectrometers for high-energy pulsed ions. This paper introduces a novel spectrometer based on a scintillation-fiber cube for online diagnosis of proton beams with broadband energy spread and complex spatial distribution. We present its working principles, experimental setup, and comprehensive calibration using monoenergetic and spatially uniform proton beams generated by a synchrotron accelerator. Calibration results confirm an energy measurement range of 6-93 MeV, a relative energy uncertainty of 0.6% at 80 MeV, and a pixel size of 0.5 mm for beam profile reconstruction. By exploiting a custom-designed energy degrader, we generated a complex proton beam and measured it with the scintillation-fiber cube spectrometer (SFICS). The results demonstrate the spectrometer's potential for online measurement of the energy spectrum and spatial distribution of complex proton beams.

physics.acc-ph↗
arXiv2026

A Functionality-Grounded Benchmark for Evaluating Web Agents in E-commerce Domains

Web agents have shown great promise in performing many tasks on ecommerce website. To assess their capabilities, several benchmarks have been introduced. However, current benchmarks in the e-commerce domain face two major problems. First, they primarily focus on product search tasks (e.g., Find an Apple Watch), failing to capture the broader range of functionalities offered by real-world e-commerce platforms such as Amazon, including account management and gift card operations. Second, existing benchmarks typically evaluate whether the agent completes the user query, but ignore the potential risks involved. In practice, web agents can make unintended changes that negatively impact the user account or status. For instance, an agent might purchase the wrong item, delete a saved address, or incorrectly configure an auto-reload setting. To address these gaps, we propose a new benchmark called Amazon-Bench. To generate user queries that cover a broad range of tasks, we propose a data generation pipeline that leverages webpage content and interactive elements (e.g., buttons, check boxes) to create diverse, functionality-grounded user queries covering tasks such as address management, wish list management, and brand store following. To improve the agent evaluation, we propose an automated evaluation framework that assesses both the performance and the safety of web agents. We systematically evaluate different agents, finding that current agents struggle with complex queries and pose safety risks. These results highlight the need for developing more robust and reliable web agents.

cs.CL↗
arXiv2026

VideoAgent: Personalized Synthesis of Scientific Videos

The technical complexity of research papers often limits their reach, necessitating more accessible formats like scientific videos to disseminate key insights through engaging narration. However, existing automated methods primarily focus on static posters or slide presentations that remain template-bound and linear. Shifting to audience-adaptive video synthesis requires addressing non-linear narrative orchestration and the joint synchronization of disparate multimodal assets. We introduce VideoAgent, a modular framework that redefines scientific video synthesis as an intent-driven planning problem. By decoupling content understanding from multimodal synthesis, VideoAgent adaptively interleaves static slides with dynamic animations to match the semantic density of the narration. We further propose SciVidEval, a benchmark evaluating multimodal quality and pedagogical utility through automated metrics and human knowledge transfer studies. Extensive experiments demonstrate that VideoAgent effectively conveys complex technical logic with high narrative fidelity and communicative impact.

cs.AI↗
arXiv2026

Benign Overfitting in Adversarial Training for Vision Transformers

Despite the remarkable success of Vision Transformers (ViTs) across a wide range of vision tasks, recent studies have revealed that they remain vulnerable to adversarial examples, much like Convolutional Neural Networks (CNNs). A common empirical defense strategy is adversarial training, yet the theoretical underpinnings of its robustness in ViTs remain largely unexplored. In this work, we present the first theoretical analysis of adversarial training under simplified ViT architectures. We show that, when trained under a signal-to-noise ratio that satisfies a certain condition and within a moderate perturbation budget, adversarial training enables ViTs to achieve nearly zero robust training loss and robust generalization error under certain regimes. Remarkably, this leads to strong generalization even in the presence of overfitting, a phenomenon known as \emph{benign overfitting}, previously only observed in CNNs (with adversarial training). Experiments on both synthetic and real-world datasets further validate our theoretical findings.

cs.LG↗
arXiv2026

Curriculum-RLAIF: Curriculum Alignment with Reinforcement Learning from AI Feedback

Reward models trained through Reinforcement Learning from AI Feedback (RLAIF) methods frequently suffer from limited generalizability, which hinders the alignment performance of policy models. This challenge stems from various issues, including distribution shift, preference label noise, and mismatch of overly challenging samples with model capacity. In this paper, we aim to enhance the generalizability of reward models through a data-centric approach, driven by the insight that these issues are inherently intertwined from a uniform perspective of data difficulty. Accordingly, we propose a novel framework, Curriculum-RLAIF, which constructs preference pairs with varying difficulty levels and then produces a specific curriculum for reward model training. Comprehensive experimental results suggest that reward models trained with Curriculum-RLAIF achieve improved generalizability, boosting the alignment performance of policy models by a significant margin without incurring additional inference costs compared to various existing non-curriculum baselines. Further analysis and comparison with alternative strategies highlight the superiority of Curriculum-RLAIF in simplicity, efficiency, and effectiveness.

cs.AI↗
arXiv2026

Visual Self-Fulfilling Alignment: Shaping Safety-Oriented Personas via Threat-Related Images

Multimodal large language models (MLLMs) face safety misalignment, where visual inputs enable harmful outputs. To address this, existing methods require explicit safety labels or contrastive data; yet, threat-related concepts are concrete and visually depictable, while safety concepts, like helpfulness, are abstract and lack visual referents. Inspired by the Self-Fulfilling mechanism underlying emergent misalignment, we propose Visual Self-Fulfilling Alignment (VSFA). VSFA fine-tunes vision-language models (VLMs) on neutral VQA tasks constructed around threat-related images, without any safety labels. Through repeated exposure to threat-related visual content, models internalize the implicit semantics of vigilance and caution, shaping safety-oriented personas. Experiments across multiple VLMs and safety benchmarks demonstrate that VSFA reduces the attack success rate, improves response quality, and mitigates over-refusal while preserving general capabilities. Our work extends the self-fulfilling mechanism from text to visual modalities, offering a label-free approach to VLMs alignment.

cs.CV↗
arXiv2026

CoLA: A Choice Leakage Attack Framework to Expose Privacy Risks in Subset Training

Training models on a carefully chosen portion of data rather than the full dataset is now a standard preprocess for modern ML. From vision coreset selection to large-scale filtering in language models, it enables scalability with minimal utility loss. A common intuition is that training on fewer samples should also reduce privacy risks. In this paper, we challenge this assumption. We show that subset training is not privacy free: the very choices of which data are included or excluded can introduce new privacy surface and leak more sensitive information. Such information can be captured by adversaries either through side-channel metadata from the subset selection process or via the outputs of the target model. To systematically study this phenomenon, we propose CoLA (Choice Leakage Attack), a unified framework for analyzing privacy leakage in subset selection. In CoLA, depending on the adversary's knowledge of the side-channel information, we define two practical attack scenarios: Subset-aware Side-channel Attacks and Black-box Attacks. Under both scenarios, we investigate two privacy surfaces unique to subset training: (1) Training-membership MIA (TM-MIA), which concerns only the privacy of training data membership, and (2) Selection-participation MIA (SP-MIA), which concerns the privacy of all samples that participated in the subset selection process. Notably, SP-MIA enlarges the notion of membership from model training to the entire data-model supply chain. Experiments on vision and language models show that existing threat models underestimate subset-training privacy risks: the expanded privacy surface leaks both training and selection membership, extending risks from individual models to the broader ML ecosystem.

cs.CR↗
arXiv2026

Understanding and Improving Continuous Adversarial Training for LLMs via In-context Learning Theory

Adversarial training (AT) is an effective defense for large language models (LLMs) against jailbreak attacks, but performing AT on LLMs is costly. To improve the efficiency of AT for LLMs, recent studies propose continuous AT (CAT) that searches for adversarial inputs within the continuous embedding space of LLMs during AT. While CAT has achieved empirical success, its underlying mechanism, i.e., why adversarial perturbations in the embedding space can help LLMs defend against jailbreak prompts synthesized in the input token space, remains unknown. This paper presents the first theoretical analysis of CAT on LLMs based on in-context learning (ICL) theory. For linear transformers trained with adversarial examples from the embedding space on in-context linear regression tasks, we prove a robust generalization bound that has a negative correlation with the perturbation radius in the embedding space. This clearly explains why CAT can defend against jailbreak prompts from the LLM's token space. Further, the robust bound shows that the robustness of an adversarially trained LLM is closely related to the singular values of its embedding matrix. Based on this, we propose to improve LLM CAT by introducing an additional regularization term, which depends on singular values of the LLM's embedding matrix, into the objective function of CAT. Experiments on real-world LLMs demonstrate that our method can help LLMs achieve a better jailbreak robustness-utility tradeoff. The code is available at https://github.com/fshp971/continuous-adv-icl.

cs.LG↗
arXiv2026

Proximal Supervised Fine-Tuning

Supervised fine-tuning (SFT) of foundation models often leads to poor generalization, where prior capabilities deteriorate after tuning on new tasks or domains. Inspired by trust-region policy optimization (TRPO) and proximal policy optimization (PPO) in reinforcement learning (RL), we propose Proximal SFT (PSFT). This fine-tuning objective incorporates the benefits of trust-region, effectively constraining policy drift during SFT while maintaining competitive tuning. By viewing SFT as a special case of policy gradient methods with constant positive advantages, we derive PSFT that stabilizes optimization and leads to generalization, while leaving room for further optimization in subsequent post-training stages. Experiments across mathematical and human-value domains show that PSFT matches SFT in-domain, outperforms it in out-of-domain generalization, remains stable under prolonged training without causing entropy collapse, and provides a stronger foundation for the subsequent optimization.

cs.LG↗
arXiv2026

STARS: Skill-Triggered Audit for Request-Conditioned Invocation Safety in Agent Systems

Autonomous language-model agents increasingly rely on installable skills and tools to complete user tasks. Static skill auditing can expose capability surface before deployment, but it cannot determine whether a particular invocation is unsafe under the current user request and runtime context. We therefore study skill invocation auditing as a continuous-risk estimation problem: given a user request, candidate skill, and runtime context, predict a score that supports ranking and triage before a hard intervention is applied. We introduce STARS, which combines a static capability prior, a request-conditioned invocation risk model, and a calibrated risk-fusion policy. To evaluate this setting, we construct SIA-Bench, a benchmark of 3,000 invocation records with group-safe splits, lineage metadata, runtime context, canonical action labels, and derived continuous-risk targets. On a held-out split of indirect prompt injection attacks, calibrated fusion reaches 0.439 high-risk AUPRC, improving over 0.405 for the contextual scorer and 0.380 for the strongest static baseline, while the contextual scorer remains better calibrated with 0.289 expected calibration error. On the locked in-distribution test split, gains are smaller and static priors remain useful. The resulting claim is therefore narrower: request-conditioned auditing is most valuable as an invocation-time risk-scoring and triage layer rather than as a replacement for static screening. Code is available at https://github.com/123zgj123/STARS.

cs.AI↗
arXiv2026

Hierarchical Alignment: Enforcing Hierarchical Instruction-Following in LLMs through Logical Consistency

Large language models increasingly operate under multiple instructions from heterogeneous sources with different authority levels, including system policies, user requests, tool outputs, and retrieved context. While prior work on instruction hierarchy highlights the importance of respecting instruction priorities, it mainly focuses on adversarial attacks and overlooks the benign but common instruction conflicts that arise in real-world applications. In such settings, models must not only avoid security violations but also preserve task utility and behavioral consistency when instructions partially or implicitly conflict. We propose Neuro-Symbolic Hierarchical Alignment (NSHA) for hierarchical instruction-following by explicitly modeling and enforcing instruction priorities. At inference time, we introduce solver-guided reasoning that formulates instruction resolution as a constraint satisfaction problem, enabling the model to derive a maximally consistent set of applicable instructions under hierarchical constraints. At training time, NSHA distills solver-based decisions into model parameters using automatically constructed supervision. We evaluate our approach on rule following, task execution, tool use, and safety, covering both single-turn and multi-turn interactions, and show that NSHA significantly improves performance under such conflicts while maintaining competitive utility in reference settings.

cs.CL↗
arXiv2026

ChangeBridge: Spatiotemporal Image Generation with Multimodal Controls for Remote Sensing

Spatiotemporal image generation is a highly meaningful task, which can generate future scenes conditioned on given observations. However, existing change generation methods can only handle event-driven changes (e.g., new buildings) and fail to model cross-temporal variations (e.g., seasonal shifts). In this work, we propose ChangeBridge, a conditional spatiotemporal image generation model for remote sensing. Given pre-event images and multimodal event controls, ChangeBridge generates post-event scenes that are both spatially and temporally coherent. The core idea is a drift-asynchronous diffusion bridge. Specifically, it consists of three main modules: a) Composed Bridge Initialization, which replaces noise initialization. It starts the diffusion from a composed pre-event state, modeling a diffusion bridge process. b) Asynchronous Drift Diffusion, which uses a pixel-wise drift map, assigning different drift magnitudes to event and temporal evolution. This enables differentiated generation during the pre-to-post transition. c) Drift-Aware Denoising, which embeds the drift map into the denoising network, guiding drift-aware reconstruction. Experiments show that ChangeBridge can generate better cross-spatiotemporal aligned scenarios compared to state-of-the-art methods. Additionally, ChangeBridge shows great potential for land-use planning and as a data generation engine for a series of change detection tasks. Code is available at https://github.com/zhenghuizhao/ChangeBridge

cs.CV↗
arXiv2026

$U$-spin sum rules for two-body decays of bottom baryons

$U$-spin symmetry, which reflects the symmetry between the down-type $d$ and $s$ quarks, is a powerful tool for analyzing heavy hadron weak decays. Motivated by recent experimental achievements in the bottom baryon sector, we study the $U$-spin sum rules for bottom baryon decays. The effective Hamiltonian for $b$ quark decay is zero under the $U$-spin lowering operators $U_-^n$, permitting us to derive $U$-spin sum rules involving only the $b\to d$ transition or $b\to s$ transition. Moreover, a new operator, $S_b=U_++rU_3-r^2U_-$, is proposed to generate $U$-spin sum rules involving both the $b\to d$ and $b\to s$ transitions. The proof that the effective Hamiltonian for $b$ quark decay is zero under $U_-^n$ and $S_b$ is presented. The master formulas for generating $U$-spin sum rules for the two-body decays of bottom baryons involving $b\to c\overline cd/s$, $b\to c\overline ud/s$, $b\to u\overline ud/s$, and $b\to u\overline cd/s$ transitions are derived. Numerous $U$-spin sum rules for the two-body decays of bottom baryons are obtained through these master formulas, which provide hints for new decay modes and enable the extraction of dynamical information. As a phenomenological analysis, some branching fractions are predicted according to $U$-spin symmetry. Several rate and decay parameter sum rules beyond the $U$-spin limit are found, providing a more precise test of flavor symmetry in the bottom baryon sector. Moreover, some $CP$ asymmetry relations for $U$-spin conjugate pairs in heavy baryon decays are derived for the first time by taking partial-wave amplitudes into account.

hep-ph↗
arXiv2026

Predicting LLM Output Length via Entropy-Guided Representations

The long-tailed distribution of sequence lengths in LLM serving and reinforcement learning (RL) sampling causes significant computational waste due to excessive padding in batched inference. Existing methods rely on auxiliary models for static length prediction, but they incur high overhead, generalize poorly, and fail in stochastic "one-to-many" sampling scenarios. We introduce a lightweight framework that reuses the main model's internal hidden states for efficient length prediction. Our framework features two core components: 1) Entropy-Guided Token Pooling (EGTP), which uses on-the-fly activations and token entropy for highly accurate static prediction with negligible cost, and 2) Progressive Length Prediction (PLP), which dynamically estimates the remaining length at each decoding step to handle stochastic generation. To validate our approach, we build and release ForeLen, a comprehensive benchmark with long-sequence, Chain-of-Thought, and RL data. On ForeLen, EGTP achieves state-of-the-art accuracy, reducing MAE by 29.16\% over the best baseline. Integrating our methods with a length-aware scheduler yields significant end-to-end throughput gains. Our work provides a new technical and evaluation baseline for efficient LLM inference.

cs.AI↗