arXiv subjects

Qi Wei

Publications and source records attributed to Qi Wei.

At least 19 recordsLinked to original sources

arXiv2026

The Cases LJP Never Sees: Prosecution Decision Prediction for More Complete Criminal Liability Assessment

Legal Judgment Prediction (LJP) has become a core benchmark for evaluating AI in the criminal legal domain, but it only sees criminal cases that have already passed prosecutorial review and been formally indicted. As a result, LJP leaves a substantial blind spot in assessing criminal liability, overlooking cases involving insufficient evidence, no criminal liability, or guilt exempted from punishment. To fill this gap, we propose \textbf{Prosecution Decision Prediction (PDP)}, the first Legal AI task built around prosecutorial review, which classifies each case into prosecution or one of three non-prosecution decisions and reflects legal AI's capabilities in evidence evaluation, legal subsumption, and value-based discretion. We further construct \textbf{PDP-Bench}, a benchmark of 4{,}630 real Chinese prosecutorial decisions spanning 190 charges. Extensive experiments show that state-of-the-art LLMs perform substantially worse on PDP than on LJP and that mainstream enhancement routes fail to close the gap. Moreover, controlled RLVR interventions show that simple outcome rewards fail to produce generalizable PDP discrimination.

cs.CL↗

arXiv2026

Intern-S1-Pro: Scientific Multimodal Foundation Model at Trillion Scale

We introduce Intern-S1-Pro, the first one-trillion-parameter scientific multimodal foundation model. Scaling to this unprecedented size, the model delivers a comprehensive enhancement across both general and scientific domains. Beyond stronger reasoning and image-text understanding capabilities, its intelligence is augmented with advanced agent capabilities. Simultaneously, its scientific expertise has been vastly expanded to master over 100 specialized tasks across critical science fields, including chemistry, materials, life sciences, and earth sciences. Achieving this massive scale is made possible by the robust infrastructure support of XTuner and LMDeploy, which facilitates highly efficient Reinforcement Learning (RL) training at the 1-trillion parameter level while ensuring strict precision consistency between training and inference. By seamlessly integrating these advancements, Intern-S1-Pro further fortifies the fusion of general and specialized intelligence, working as a Specializable Generalist, demonstrating its position in the top tier of open-source models for general capabilities, while outperforming proprietary models in the depth of specialized scientific tasks.

cs.LG↗

arXiv2026

Variational Rectification Inference for Learning with Noisy Labels

Label noise has been broadly observed in real-world datasets. To mitigate the negative impact of overfitting to label noise for deep models, effective strategies (\textit{e.g.}, re-weighting, or loss rectification) have been broadly applied in prevailing approaches, which have been generally learned under the meta-learning scenario. Despite the robustness of noise achieved by the probabilistic meta-learning models, they usually suffer from model collapse that degenerates generalization performance. In this paper, we propose variational rectification inference (VRI) to formulate the adaptive rectification for loss functions as an amortized variational inference problem and derive the evidence lower bound under the meta-learning framework. Specifically, VRI is constructed as a hierarchical Bayes by treating the rectifying vector as a latent variable, which can rectify the loss of the noisy sample with the extra randomness regularization and is, therefore, more robust to label noise. To achieve the inference of the rectifying vector, we approximate its conditional posterior with an amortization meta-network. By introducing the variational term in VRI, the conditional posterior is estimated accurately and avoids collapsing to a Dirac delta function, which can significantly improve the generalization performance. The elaborated meta-network and prior network adhere to the smoothness assumption, enabling the generation of reliable rectification vectors. Given a set of clean meta-data, VRI can be efficiently meta-learned within the bi-level optimization programming. Besides, theoretical analysis guarantees that the meta-network can be efficiently learned with our algorithm. Comprehensive comparison experiments and analyses validate its effectiveness for robust learning with noisy labels, particularly in the presence of open-set noise.

cs.LG↗

arXiv2026

Reliable Reasoning in SVG-LLMs via Multi-Task Multi-Reward Reinforcement Learning

With the rapid advancement of vision-language models, an increasing number of studies have explored their potential for SVG generation tasks. Although existing approaches improve performance by constructing large-scale SVG datasets and introducing SVG-specific tokens, they still suffer from limited generalization, redundant paths in code outputs, and a lack of explicit reasoning. In this work, we present CTRL-S (Chain-of-Thought Reinforcement Learning for SVG), a unified framework that introduces a chain-of-thought mechanism to explicitly expose the model's reasoning process during SVG generation. To support this structured reasoning, we construct SVG-Sophia, a high-quality dataset containing 145K samples across SVG code refinement, Text-to-SVG, and Image-to-SVG tasks. By training the model to generate group-level structured SVG code, CTRL-S significantly improves structural coherence and visual fidelity. Furthermore, we adopt the GRPO algorithm and design a multi-reward optimization framework, incorporating DINO, image-text similarity, format, and code efficiency rewards. Through joint multi-reward optimization and multi-task training, our approach systematically enhances overall generation capabilities. Extensive experiments show that CTRL-S outperforms existing methods, achieving higher task success rates, superior SVG code quality, and exceptional visual fidelity.

cs.CV↗

arXiv2026

Featurized Occupation Measures for Structured Global Search in Numerical Optimal Control

Numerical optimal control has long been split between globally structured but dimensionally intractable Hamilton--Jacobi--Bellman (HJB) methods and scalable but local trajectory optimization. We introduce Featurized Occupation Measures (FOM), a finite-dimensional primal--dual interface for coupling numerical optimal control solvers with explicit HJB subsolutions: the certificate guides the primal search, while primal residuals tighten the certificate in a primal-dual language. Two realizations are developed. The explicit realization uses finite weak-form Liouville tests, and the implicit realization couples rollout-based search with sampled primal--dual residuals. Both are proved asymptotically consistent with the exact occupation-measure linear program under refinement, separating primal expressiveness from dual accuracy in the limit. The framework also gives structural conditions under which HJB-type certificates avoid full state-space representation. For factor graphs induced by compatible passivity-based interconnections, blockwise HJB inequalities assemble into globally feasible OM-dual certificates, and the decomposition is preserved under blockwise approximation. The curse of dimensionality is then shifted from state space to interconnection topology. Approximate certificates remain reusable under time shifts and bounded model perturbations, with explicit degradation bounds. On a static obstacle-avoidance benchmark, certificates of increasing tightness guide a sample-based optimizer toward global optima, confirming that even a coarse certificate carries useful global information.

math.OC↗

arXiv2026

Early-Terminable Energy-Safe Iterative Coupling for Parallel Simulation of Partitioned Port-Hamiltonian Systems

Parallel simulation of robotic systems requires partitioning the dynamics into coupled subsystems. Finite-iteration coupling across the partition boundary can inject spurious energy, even when each subsystem is passive. We propose an early-terminable, energy-safe coupling interface for port-Hamiltonian subsystems based on Douglas--Rachford splitting in wave (scattering) coordinates. The wave-domain formulation reduces passivity to norm inequalities and coupling to orthogonality. Within this setting, the deep correspondence between monotone operator theory and discrete passivity can be exploited to construct a Douglas--Rachford inner iteration whose Fej\'er monotonicity provides algorithmic dissipation. Under passivity of the subsystem integrators and an impedance-tuning condition, the proposed method guarantees discrete passivity of the augmented storage for any finite inner-iteration budget and converges to the monolithic discretization as the budget increases. Experiments on a linear--Duffing coupled-oscillator benchmark support the finite-iteration energy inequality at numerical roundoff (1e-14 in double precision), with state-error metrics decreasing over the tested inner-iteration budgets.

cs.RO↗

arXiv2026

InternVL-U: Democratizing Unified Multimodal Models for Understanding, Reasoning, Generation and Editing

Unified multimodal models (UMMs) that integrate understanding, reasoning, generation, and editing face inherent trade-offs between maintaining strong semantic comprehension and acquiring powerful generation capabilities. In this report, we present InternVL-U, a lightweight 4B-parameter UMM that democratizes these capabilities within a unified framework. Guided by the principles of unified contextual modeling and modality-specific modular design with decoupled visual representations, InternVL-U integrates a state-of-the-art Multimodal Large Language Model (MLLM) with a specialized MMDiT-based visual generation head. To further bridge the gap between aesthetic generation and high-level intelligence, we construct a comprehensive data synthesis pipeline targeting high-semantic-density tasks, such as text rendering and scientific reasoning, under a reasoning-centric paradigm that leverages Chain-of-Thought (CoT) to better align abstract user intent with fine-grained visual generation details. Extensive experiments demonstrate that InternVL-U achieves a superior performance - efficiency balance. Despite using only 4B parameters, it consistently outperforms unified baseline models with over 3x larger scales such as BAGEL (14B) on various generation and editing tasks, while retaining strong multimodal understanding and reasoning capabilities.

cs.CV↗

arXiv2026

Hierarchy-of-Groups Policy Optimization for Long-Horizon Agentic Tasks

Group-based reinforcement learning (RL), such as GRPO, has advanced the capabilities of large language models on long-horizon agentic tasks. To enable more fine-grained policy updates, recent research has increasingly shifted toward stepwise group-based policy optimization, which treats each step in a rollout trajectory independently while using a memory module to retain historical context. However, we find a key issue in estimating stepwise relative advantages, namely context inconsistency, where steps within the same group may differ in their historical contexts. Empirically, we reveal that this issue can lead to severely biased advantage estimation, thereby degrading policy optimization significantly. To address the issue, in this paper, we propose Hierarchy-of-Groups Policy Optimization (HGPO) for long-horizon agentic tasks. Specifically, within a group of rollout trajectories, HGPO assigns each step to multiple hierarchical groups according to the consistency of historical contexts. Then, for each step, HGPO computes distinct advantages within each group and aggregates them with an adaptive weighting scheme. In this way, HGPO can achieve a favorable bias-variance trade-off in stepwise advantage estimation, without extra models or rollouts. Evaluations on two challenging agentic tasks, ALFWorld and WebShop with Qwen2.5-1.5B-Instruct and Qwen2.5-7B-Instruct, show that HGPO significantly outperforms existing agentic RL methods under the same computational constraints. Code is available at https://github.com/langfengQ/verl-agent/tree/master/recipe/hgpo.

cs.LG↗

arXiv2026

Sparse Threats, Focused Defense: Criticality-Aware Robust Reinforcement Learning for Safe Autonomous Driving

Reinforcement learning (RL) has shown considerable potential in autonomous driving (AD), yet its vulnerability to perturbations remains a critical barrier to real-world deployment. As a primary countermeasure, adversarial training improves policy robustness by training the AD agent in the presence of an adversary that deliberately introduces perturbations. Existing approaches typically model the interaction as a zero-sum game with continuous attacks. However, such designs overlook the inherent asymmetry between the agent and the adversary and then fail to reflect the sparsity of safety-critical risks, rendering the achieved robustness inadequate for practical AD scenarios. To address these limitations, we introduce criticality-aware robust RL (CARRL), a novel adversarial training approach for handling sparse, safety-critical risks in autonomous driving. CARRL consists of two interacting components: a risk exposure adversary (REA) and a risk-targeted robust agent (RTRA). We model the interaction between the REA and RTRA as a general-sum game, allowing the REA to focus on exposing safety-critical failures (e.g., collisions) while the RTRA learns to balance safety with driving efficiency. The REA employs a decoupled optimization mechanism to better identify and exploit sparse safety-critical moments under a constrained budget. However, such focused attacks inevitably result in a scarcity of adversarial data. The RTRA copes with this scarcity by jointly leveraging benign and adversarial experiences via a dual replay buffer and enforces policy consistency under perturbations to stabilize behavior. Experimental results demonstrate that our approach reduces the collision rate by at least 22.66\% across all cases compared to state-of-the-art baseline methods.

cs.LG↗

arXiv2025

InternSVG: Towards Unified SVG Tasks with Multimodal Large Language Models

General SVG modeling remains challenging due to fragmented datasets, limited transferability of methods across tasks, and the difficulty of handling structural complexity. In response, we leverage the strong transfer and generalization capabilities of multimodal large language models (MLLMs) to achieve unified modeling for SVG understanding, editing, and generation. We present the InternSVG family, an integrated data-benchmark-model suite. At its core is SAgoge, the largest and most comprehensive multimodal dataset for SVG tasks, encompassing both static graphics and dynamic animations. It covers icons, long-sequence illustrations, scientific diagrams, and dynamic animations, supporting tasks of varied difficulty levels and providing deeper hierarchies with richer attributes compared to previous datasets. Based on this resource, we introduce SArena, a companion benchmark with comprehensive task definitions and standardized evaluation that aligns with the domains and difficulty spectrum covered by SAgoge. Building on these foundations, we propose InternSVG, a unified MLLM for SVG understanding, editing, and generation with SVG-specific special tokens, subword-based embedding initialization, and a two-stage training strategy that progresses from short static SVGs to long-sequence illustrations and complex animations. This unified formulation induces positive transfer and improves overall performance. Experiments on SArena and prior benchmark confirm that InternSVG achieves substantial gains and consistently outperforms leading open and proprietary counterparts.

cs.CV↗

arXiv2025

Robust Driving Control for Autonomous Vehicles: An Intelligent General-sum Constrained Adversarial Reinforcement Learning Approach

Deep reinforcement learning (DRL) has demonstrated remarkable success in developing autonomous driving policies. However, its vulnerability to adversarial attacks remains a critical barrier to real-world deployment. Although existing robust methods have achieved success, they still suffer from three key issues: (i) these methods are trained against myopic adversarial attacks, limiting their abilities to respond to more strategic threats, (ii) they have trouble causing truly safety-critical events (e.g., collisions), but instead often result in minor consequences, and (iii) these methods can introduce learning instability and policy drift during training due to the lack of robust constraints. To address these issues, we propose Intelligent General-sum Constrained Adversarial Reinforcement Learning (IGCARL), a novel robust autonomous driving approach that consists of a strategic targeted adversary and a robust driving agent. The strategic targeted adversary is designed to leverage the temporal decision-making capabilities of DRL to execute strategically coordinated multi-step attacks. In addition, it explicitly focuses on inducing safety-critical events by adopting a general-sum objective. The robust driving agent learns by interacting with the adversary to develop a robust autonomous driving policy against adversarial attacks. To ensure stable learning in adversarial environments and to mitigate policy drift caused by attacks, the agent is optimized under a constrained formulation. Extensive experiments show that IGCARL improves the success rate by at least 27.9% over state-of-the-art methods, demonstrating superior robustness to adversarial attacks and enhancing the safety and reliability of DRL-based autonomous driving.

cs.LG↗

arXiv2025

Improving Generalizability and Undetectability for Targeted Adversarial Attacks on Multimodal Pre-trained Models

Multimodal pre-trained models (e.g., ImageBind), which align distinct data modalities into a shared embedding space, have shown remarkable success across downstream tasks. However, their increasing adoption raises serious security concerns, especially regarding targeted adversarial attacks. In this paper, we show that existing targeted adversarial attacks on multimodal pre-trained models still have limitations in two aspects: generalizability and undetectability. Specifically, the crafted targeted adversarial examples (AEs) exhibit limited generalization to partially known or semantically similar targets in cross-modal alignment tasks (i.e., limited generalizability) and can be easily detected by simple anomaly detection methods (i.e., limited undetectability). To address these limitations, we propose a novel method called Proxy Targeted Attack (PTA), which leverages multiple source-modal and target-modal proxies to optimize targeted AEs, ensuring they remain evasive to defenses while aligning with multiple potential targets. We also provide theoretical analyses to highlight the relationship between generalizability and undetectability and to ensure optimal generalizability while meeting the specified requirements for undetectability. Furthermore, experimental results demonstrate that our PTA can achieve a high success rate across various related targets and remain undetectable against multiple anomaly detection methods.

cs.CV↗

arXiv2025

InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency

We introduce InternVL 3.5, a new family of open-source multimodal models that significantly advances versatility, reasoning capability, and inference efficiency along the InternVL series. A key innovation is the Cascade Reinforcement Learning (Cascade RL) framework, which enhances reasoning through a two-stage process: offline RL for stable convergence and online RL for refined alignment. This coarse-to-fine training strategy leads to substantial improvements on downstream reasoning tasks, e.g., MMMU and MathVista. To optimize efficiency, we propose a Visual Resolution Router (ViR) that dynamically adjusts the resolution of visual tokens without compromising performance. Coupled with ViR, our Decoupled Vision-Language Deployment (DvD) strategy separates the vision encoder and language model across different GPUs, effectively balancing computational load. These contributions collectively enable InternVL3.5 to achieve up to a +16.0\% gain in overall reasoning performance and a 4.05$\times$ inference speedup compared to its predecessor, i.e., InternVL3. In addition, InternVL3.5 supports novel capabilities such as GUI interaction and embodied agency. Notably, our largest model, i.e., InternVL3.5-241B-A28B, attains state-of-the-art results among open-source MLLMs across general multimodal, reasoning, text, and agentic tasks -- narrowing the performance gap with leading commercial models like GPT-5. All models and code are publicly released.

cs.CV↗

arXiv2025

Chiral superfluorescence from perovskite superlattices at room temperature

Superfluorescence (SF) is the collective emission of intense, coherent light from an interacting ensemble of quantum emitters1-4. While SF has been observed in several solid-state materials5-8, the spontaneous generation of circularly polarized SF from chiral materials (chiral SF) has not been realized9,10. Here, we report the first observation of chiral SF originating from edge states in large-area (>100 um * 100 um) vertically aligned chiral perovskite superlattices at room-temperature. Theoretical quantum optics calculations describe the transition from initially unpolarized, incoherent spontaneous emission to a coherent chiral SF state, quantitatively reproducing both the experimentally observed generation of circular polarization (up to ~14%) and its reversal in sign with opposite material handedness. Moreover, we show that both the intensity and the degree of circular polarization of chiral SF can be modulated by a weak magnetic field, enabling precise control over solid-state quantum light emission at room temperature. Our findings demonstrate an interplay between chirality and many-body quantum coherence, thereby revealing promising new directions for chirality-controlled quantum-optical applications.

physics.optics↗

arXiv2025

Mapping at First Sense: A Lightweight Neural Network-Based Indoor Structures Prediction Method for Robot Autonomous Exploration

Autonomous exploration in unknown environments is a critical challenge in robotics, particularly for applications such as indoor navigation, search and rescue, and service robotics. Traditional exploration strategies, such as frontier-based methods, often struggle to efficiently utilize prior knowledge of structural regularities in indoor spaces. To address this limitation, we propose Mapping at First Sense, a lightweight neural network-based approach that predicts unobserved areas in local maps, thereby enhancing exploration efficiency. The core of our method, SenseMapNet, integrates convolutional and transformerbased architectures to infer occluded regions while maintaining computational efficiency for real-time deployment on resourceconstrained robots. Additionally, we introduce SenseMapDataset, a curated dataset constructed from KTH and HouseExpo environments, which facilitates training and evaluation of neural models for indoor exploration. Experimental results demonstrate that SenseMapNet achieves an SSIM (structural similarity) of 0.78, LPIPS (perceptual quality) of 0.68, and an FID (feature distribution alignment) of 239.79, outperforming conventional methods in map reconstruction quality. Compared to traditional frontier-based exploration, our method reduces exploration time by 46.5% (from 2335.56s to 1248.68s) while maintaining a high coverage rate (88%) and achieving a reconstruction accuracy of 88%. The proposed method represents a promising step toward efficient, learning-driven robotic exploration in structured environments.

cs.RO↗

arXiv2025

Nonequilibrium mean-field approach for quantum transport with off-diagonal disorder

For the nanoscale structures, disorder scattering plays a vital role in the carriers' transport, including electrons and high-frequency phonons. The capability for effectively treating the disorders, including both diagonal and off-diagonal disorders, is indispensable for quantum transport simulation of realistic device materials. In this work, we report a self-consistent nonequilibrium mean-field quantum transport approach, by combining the auxiliary coherent potential approximation (ACPA) and non-equilibrium Green's function method, for calculating the phonon transport through disordered material structures with the force-constant disorders (including the Anderson-type disorder). The nonequilibrium vertex correction (NVC) is derived in an extended local degree of freedom to account for both the multiple disorder scattering by force-constant disorder and the nonequilibrium quantum statistics. We have tested ACPA-NVC method with the fluctuation-dissipation theorem at the equilibrium and obtained very good agreement with supercell calculations for the phonon transmission. To demonstrate the applicability, we apply ACPA-NVC to calculate the thermal conductance for the disordered Ni/Pt interface, and important effects of force-constant disorder are revealed. ACPA-NVC method provides an effective quantum transport approach for simulating disordered nanoscale devices, and the generalization to simulate disordered nanoelectronic device is straightforward.

cond-mat.mes-hall↗

arXiv2024

Candidate Pseudolabel Learning: Enhancing Vision-Language Models by Prompt Tuning with Unlabeled Data

Fine-tuning vision-language models (VLMs) with abundant unlabeled data recently has attracted increasing attention. Existing methods that resort to the pseudolabeling strategy would suffer from heavily incorrect hard pseudolabels when VLMs exhibit low zero-shot performance in downstream tasks. To alleviate this issue, we propose a Candidate Pseudolabel Learning method, termed CPL, to fine-tune VLMs with suitable candidate pseudolabels of unlabeled data in downstream tasks. The core of our method lies in the generation strategy of candidate pseudolabels, which progressively generates refined candidate pseudolabels by both intra- and inter-instance label selection, based on a confidence score matrix for all unlabeled data. This strategy can result in better performance in true label inclusion and class-balanced instance selection. In this way, we can directly apply existing loss functions to learn with generated candidate psueudolabels. Extensive experiments on nine benchmark datasets with three learning paradigms demonstrate the effectiveness of our method. Our code can be found at https://github.com/vanillaer/CPL-ICML2024.

cs.LG↗

arXiv2024

Test-Time Multimodal Backdoor Detection by Contrastive Prompting

While multimodal contrastive learning methods (e.g., CLIP) can achieve impressive zero-shot classification performance, recent research has revealed that these methods are vulnerable to backdoor attacks. To defend against backdoor attacks on CLIP, existing defense methods focus on either the pre-training stage or the fine-tuning stage, which would unfortunately cause high computational costs due to numerous parameter updates and are not applicable in black-box settings. In this paper, we provide the first attempt at a computationally efficient backdoor detection method to defend against backdoored CLIP in the \emph{inference} stage. We empirically find that the visual representations of backdoored images are \emph{insensitive} to \emph{benign} and \emph{malignant} changes in class description texts. Motivated by this observation, we propose BDetCLIP, a novel test-time backdoor detection method based on contrastive prompting. Specifically, we first prompt a language model (e.g., GPT-4) to produce class-related description texts (benign) and class-perturbed random texts (malignant) by specially designed instructions. Then, the distribution difference in cosine similarity between images and the two types of class description texts can be used as the criterion to detect backdoor samples. Extensive experiments validate that our proposed BDetCLIP is superior to state-of-the-art backdoor detection methods, in terms of both effectiveness and efficiency. Our codes are publicly available at: https://github.com/Purshow/BDetCLIP.

cs.CV↗