Lai Xing Ng

Lingdong Kong, Yaru Niu, Shaoyuan Xie et al.

Accurate depth estimation under out-of-distribution (OoD) scenarios, such as adverse weather conditions, sensor failure, and noise contamination, is desirable for safety-critical applications. Existing depth estimation systems, however, suffer inevitably from real-world corruptions and perturbations and are struggled to provide reliable depth predictions under such cases. In this paper, we summarize the winning solutions from the RoboDepth Challenge -- an academic competition designed to facilitate and advance robust OoD depth estimation. This challenge was developed based on the newly established KITTI-C and NYUDepth2-C benchmarks. We hosted two stand-alone tracks, with an emphasis on robust self-supervised and robust fully-supervised depth estimation, respectively. Out of more than two hundred participants, nine unique and top-performing solutions have appeared, with novel designs ranging from the following aspects: spatial- and frequency-domain augmentations, masked image modeling, image restoration and super-resolution, adversarial training, diffusion-based noise suppression, vision-language pre-training, learned model ensembling, and hierarchical feature enhancement. Extensive experimental analyses along with insightful observations are drawn to better understand the rationale behind each design. We hope this challenge could lay a solid foundation for future research on robust and reliable depth estimation and beyond. The datasets, competition toolkit, workshop recordings, and source code from the winning teams are publicly available on the challenge website.

Lingdong Kong, Shaoyuan Xie, Hanjiang Hu et al.

Depth estimation from monocular images is pivotal for real-world visual perception systems. While current learning-based depth estimation models train and test on meticulously curated data, they often overlook out-of-distribution (OoD) situations. Yet, in practical settings -- especially safety-critical ones like autonomous driving -- common corruptions can arise. Addressing this oversight, we introduce a comprehensive robustness test suite, RoboDepth, encompassing 18 corruptions spanning three categories: i) weather and lighting conditions; ii) sensor failures and movement; and iii) data processing anomalies. We subsequently benchmark 42 depth estimation models across indoor and outdoor scenes to assess their resilience to these corruptions. Our findings underscore that, in the absence of a dedicated robustness evaluation framework, many leading depth estimation models may be susceptible to typical corruptions. We delve into design considerations for crafting more robust depth estimation models, touching upon pre-training, augmentation, modality, model capacity, and learning paradigms. We anticipate our benchmark will establish a foundational platform for advancing robust OoD depth estimation.

Yannis Montreuil, Leina Montreuil, Axel Carlier et al.

Learning-to-Defer routes each input to the expert that minimizes expected cost, but it assumes that the information available to every expert is fixed at decision time. Many modern systems violate this assumption: after selecting an expert, one may also choose what additional information that expert should receive, such as retrieved documents, tool outputs, or escalation context. We study this problem and call it Learning-to-Defer with advice. We show that a broad family of natural separated surrogates, which learn routing and advice with distinct heads, are inconsistent even in the smallest non-trivial setting. We then introduce an augmented surrogate that operates on the composite expert--advice action space and prove an $\mathcal{H}$-consistency guarantee together with an excess-risk transfer bound, yielding recovery of the Bayes-optimal policy in the limit. Experiments on tabular, LLMs, and multi-modal tasks show that the resulting method improves over standard Learning-to-Defer while adapting its advice-acquisition behavior to the cost regime.

Ao Liang, Lingdong Kong, Tianyi Yan et al.

Generative world models are reshaping embodied AI, enabling agents to synthesize realistic 4D driving environments that look convincing but often fail physically or behaviorally. Despite rapid progress, the field still lacks a unified way to assess whether generated worlds preserve geometry, obey physics, or support reliable control. We introduce WorldLens, a full-spectrum benchmark evaluating how well a model builds, understands, and behaves within its generated world. It spans five aspects -- Generation, Reconstruction, Action-Following, Downstream Task, and Human Preference -- jointly covering visual realism, geometric consistency, physical plausibility, and functional reliability. Across these dimensions, no existing world model excels universally: those with strong textures often violate physics, while geometry-stable ones lack behavioral fidelity. To align objective metrics with human judgment, we further construct WorldLens-26K, a large-scale dataset of human-annotated videos with numerical scores and textual rationales, and develop WorldLens-Agent, an evaluation model distilled from these annotations to enable scalable, explainable scoring. Together, the benchmark, dataset, and agent form a unified ecosystem for measuring world fidelity -- standardizing how future models are judged not only by how real they look, but by how real they behave.

Yannis Montreuil, Letian Yu, Axel Carlier et al.

We study Learning to Defer for non-stationary time series with partial feedback and time-varying expert availability. At each time step, the router selects an available expert, observes the target, and sees only the queried expert's prediction. We model signed expert residuals using L2D-SLDS, a factorized switching linear-Gaussian state-space model with context-dependent regime transitions, a shared global factor enabling cross-expert information transfer, and per-expert idiosyncratic states. The model supports expert entry and pruning via a dynamic registry. Using one-step-ahead predictive beliefs, we propose an IDS-inspired routing rule that trades off predicted cost against information gained about the latent regime and shared factor. Experiments show improvements over contextual-bandit baselines and a no-shared-factor ablation.

Lingdong Kong, Xian Sun, Wei Chow et al.

AI-assisted research is crossing a threshold: fully automated systems can now generate research papers for as little as $15, while long-horizon agents can execute experiments, draft manuscripts, and simulate critique with minimal human input. Yet this productivity frontier exposes a deeper integrity problem: under scientific pressure, even frontier LLMs still fabricate results, miss hidden errors, and fail to judge novelty reliably. Studying developments through April 2026, we present an end-to-end analysis of AI across the complete research lifecycle, organized into four epistemological phases: Creation (idea generation, literature review, coding & experiments, tables & figures), Writing (paper writing), Validation (peer review, rebuttal & revision), and Dissemination (posters, slides, videos, social media, project pages, and interactive agents). We identify a sharp, stage-dependent boundary between reliable assistance and unreliable autonomy: AI excels at structured, retrieval-grounded, and tool-mediated tasks, but remains fragile for genuinely novel ideas, research-level experiments, and scientific judgment. Generated ideas often degrade after implementation, research code lags far behind pattern-matching benchmarks, and end-to-end autonomous systems have not yet consistently reached major-venue acceptance standards. We further show that greater automation can obscure rather than eliminate failure modes, making human-governed collaboration the most credible deployment paradigm. Finally, we provide a structured taxonomy, benchmark suite, and tool inventory, cross-stage design principles, and a practitioner-oriented playbook, with resources maintained at our project page.

Maxime Vaillant, Axel Carlier, Lai Xing Ng et al.

Event-based vision sensors provide significant advantages for high-speed perception, including microsecond temporal resolution, high dynamic range, and low power consumption. When combined with Spiking Neural Networks (SNNs), they can be deployed on neuromorphic hardware, enabling energy-efficient applications on embedded systems. However, this potential is severely limited by the scarcity of large-scale labeled datasets required to effectively train such models. In this work, we introduce SpikeCLR, a contrastive self-supervised learning framework that enables SNNs to learn robust visual representations from unlabeled event data. We adapt prior frame-based methods to the spiking domain using surrogate gradient training and introduce a suite of event-specific augmentations that leverage spatial, temporal, and polarity transformations. Through extensive experiments on CIFAR10-DVS, N-Caltech101, N-MNIST, and DVS-Gesture benchmarks, we demonstrate that self-supervised pretraining with subsequent fine-tuning outperforms supervised learning in low-data regimes, achieving consistent gains in few-shot and semi-supervised settings. Our ablation studies reveal that combining spatial and temporal augmentations is critical for learning effective spatio-temporal invariances in event data. We further show that learned representations transfer across datasets, contributing to efforts for powerful event-based models in label-scarce settings.

Dang Hoang Duy, Yannis Montreuil, Maxime Meyer et al.

Learning-to-Defer (L2D) methods route each query either to a predictive model or to external experts. While existing work studies this problem in batch settings, real-world deployments require handling streaming data, changing expert availability, and shifting expert distribution. We introduce the first online L2D algorithm for multiclass classification with bandit feedback and a dynamically varying pool of experts. Our method achieves regret guarantees of $O((n+n_e)T^{2/3})$ in general and $O((n+n_e)\sqrt{T})$ under a low-noise condition, where $T$ is the time horizon, $n$ is the number of labels, and $n_e$ is the number of distinct experts observed across rounds. The analysis builds on novel $\mathcal{H}$-consistency bounds for the online framework, combined with first-order methods for online convex optimization. Experiments on synthetic and real-world datasets demonstrate that our approach effectively extends standard Learning-to-Defer to settings with varying expert availability and reliability.

Haiqian Han, Lingdong Kong, Jianing Li et al.

Event cameras have the potential to revolutionize vision systems with their high temporal resolution and dynamic range, yet they remain susceptible to lens flare, a fundamental optical artifact that causes severe degradation. In event streams, this optical artifact forms a complex, spatio-temporal distortion that has been largely overlooked. We present E-Deflare, the first systematic framework for removing lens flare from event camera data. We first establish the theoretical foundation by deriving a physics-grounded forward model of the non-linear suppression mechanism. This insight enables the creation of the E-Deflare Benchmark, a comprehensive resource featuring a large-scale simulated training set, E-Flare-2.7K, and the first-ever paired real-world test set, E-Flare-R, captured by our novel optical system. Empowered by this benchmark, we design E-DeflareNet, which achieves state-of-the-art restoration performance. Extensive experiments validate our approach and demonstrate clear benefits for downstream tasks. Code and datasets are publicly available.

Lingdong Kong, Ao Liang, Tianyi Yan et al.

Today's driving world models can generate remarkably realistic dash-cam videos, yet no single model excels universally. Some generate photorealistic textures but violate basic physics; others maintain geometric consistency but fail when subjected to closed-loop planning. This disconnect exposes a critical gap: the field evaluates how real generated worlds appear, but rarely whether they behave realistically. We introduce WorldLens, a unified benchmark that measures world-model fidelity across the full spectrum, from pixel quality and 4D geometry to closed-loop driving and human perceptual alignment, through five complementary aspects and 24 standardized dimensions. Our evaluation of six representative models reveals that no existing approach dominates across all axes: texture-rich models violate geometry, geometry-aware models lack behavioral fidelity, and even the strongest performers achieve only 2-3 out of 10 on human realism ratings. To bridge algorithmic metrics with human perception, we further contribute WorldLens-26K, a 26,808-entry human-annotated preference dataset pairing numerical scores with textual rationales, and WorldLens-Agent, a vision-language evaluator distilled from these judgments that enables scalable, explainable auto-assessment. Together, the benchmark, dataset, and agent form a unified ecosystem for assessing generated worlds not merely by visual appeal, but by physical and behavioral fidelity.

Lingdong Kong, Youquan Liu, Lai Xing Ng et al.

Event-based semantic segmentation (ESS) is a fundamental yet challenging task for event camera sensing. The difficulties in interpreting and annotating event data limit its scalability. While domain adaptation from images to event data can help to mitigate this issue, there exist data representational differences that require additional effort to resolve. In this work, for the first time, we synergize information from image, text, and event-data domains and introduce OpenESS to enable scalable ESS in an open-world, annotation-efficient manner. We achieve this goal by transferring the semantically rich CLIP knowledge from image-text pairs to event streams. To pursue better cross-modality adaptation, we propose a frame-to-event contrastive distillation and a text-to-event semantic consistency regularization. Experimental results on popular ESS benchmarks showed our approach outperforms existing methods. Notably, we achieve 53.93% and 43.31% mIoU on DDD17 and DSEC-Semantic without using either event or frame labels.

Lingdong Kong, Shaoyuan Xie, Hanjiang Hu et al. · tsinghua

In the realm of autonomous driving, robust perception under out-of-distribution conditions is paramount for the safe deployment of vehicles. Challenges such as adverse weather, sensor malfunctions, and environmental unpredictability can severely impact the performance of autonomous systems. The 2024 RoboDrive Challenge was crafted to propel the development of driving perception technologies that can withstand and adapt to these real-world variabilities. Focusing on four pivotal tasks -- BEV detection, map segmentation, semantic occupancy prediction, and multi-view depth estimation -- the competition laid down a gauntlet to innovate and enhance system resilience against typical and atypical disturbances. This year's challenge consisted of five distinct tracks and attracted 140 registered teams from 93 institutes across 11 countries, resulting in nearly one thousand submissions evaluated through our servers. The competition culminated in 15 top-performing solutions, which introduced a range of innovative approaches including advanced data augmentation, multi-sensor fusion, self-supervised learning for error correction, and new algorithmic strategies to enhance sensor robustness. These contributions significantly advanced the state of the art, particularly in handling sensor inconsistencies and environmental variability. Participants, through collaborative efforts, pushed the boundaries of current technologies, showcasing their potential in real-world scenarios. Extensive evaluations and analyses provided insights into the effectiveness of these solutions, highlighting key trends and successful strategies for improving the resilience of driving perception systems. This challenge has set a new benchmark in the field, providing a rich repository of techniques expected to guide future research in this field.

Yannis Montreuil, Axel Carlier, Lai Xing Ng et al.

Two-stage Learning-to-Defer (L2D) enables optimal task delegation by assigning each input to either a fixed main model or one of several offline experts, supporting reliable decision-making in complex, multi-agent environments. However, existing L2D frameworks assume clean inputs and are vulnerable to adversarial perturbations that can manipulate query allocation--causing costly misrouting or expert overload. We present the first comprehensive study of adversarial robustness in two-stage L2D systems. We introduce two novel attack strategie--untargeted and targeted--which respectively disrupt optimal allocations or force queries to specific agents. To defend against such threats, we propose SARD, a convex learning algorithm built on a family of surrogate losses that are provably Bayes-consistent and $(\mathcal{R}, \mathcal{G})$-consistent. These guarantees hold across classification, regression, and multi-task settings. Empirical results demonstrate that SARD significantly improves robustness under adversarial attacks while maintaining strong clean performance, marking a critical step toward secure and trustworthy L2D deployment.

Yannis Montreuil, Shu Heng Yeo, Axel Carlier et al.

Large Language Models excel in generative tasks but exhibit inefficiencies in structured text selection, particularly in extractive question answering. This challenge is magnified in resource-constrained environments, where deploying multiple specialized models for different tasks is impractical. We propose a Learning-to-Defer framework that allocates queries to specialized experts, ensuring high-confidence predictions while optimizing computational efficiency. Our approach integrates a principled allocation strategy with theoretical guarantees on optimal deferral that balances performance and cost. Empirical evaluations on SQuADv1, SQuADv2, and TriviaQA demonstrate that our method enhances answer reliability while significantly reducing computational overhead, making it well-suited for scalable and efficient EQA deployment.

Yannis Montreuil, Axel Carlier, Lai Xing Ng et al.

We introduce the first one-stage Top-$k$ Learning-to-Defer framework, which unifies prediction and deferral by learning a shared score-based model that selects the $k$ most cost-effective entities-labels or experts-per input. While existing one-stage L2D methods are limited to deferring to a single expert, our approach jointly optimizes prediction and deferral across multiple entities through a single end-to-end objective. We define a cost-sensitive loss and derive a novel convex surrogate that is independent of the cardinality parameter $k$, enabling generalization across Top-$k$ regimes without retraining. Our formulation recovers the Top-1 deferral policy of prior score-based methods as a special case, and we prove that our surrogate is both Bayes-consistent and $\mathcal{H}$-consistent under mild assumptions. We further introduce an adaptive variant, Top-$k(x)$, which dynamically selects the number of consulted entities per input to balance predictive accuracy and consultation cost. Experiments on CIFAR-10 and SVHN confirm that our one-stage Top-$k$ method strictly outperforms Top-1 deferral, while Top-$k(x)$ achieves superior accuracy-cost trade-offs by tailoring allocations to input complexity.

Yannis Montreuil, Shu Heng Yeo, Axel Carlier et al.

The Two-Stage Learning-to-Defer (L2D) framework has been extensively studied for classification and, more recently, regression tasks. However, many real-world applications require solving both tasks jointly in a multi-task setting. We introduce a novel Two-Stage L2D framework for multi-task learning that integrates classification and regression through a unified deferral mechanism. Our method leverages a two-stage surrogate loss family, which we prove to be both Bayes-consistent and $(\mathcal{G}, \mathcal{R})$-consistent, ensuring convergence to the Bayes-optimal rejector. We derive explicit consistency bounds tied to the cross-entropy surrogate and the $L_1$-norm of agent-specific costs, and extend minimizability gap analysis to the multi-expert two-stage regime. We also make explicit how shared representation learning -- commonly used in multi-task models -- affects these consistency guarantees. Experiments on object detection and electronic health record analysis demonstrate the effectiveness of our approach and highlight the limitations of existing L2D methods in multi-task scenarios.

Lingdong Kong, Dongyue Lu, Xiang Xu et al.

Cross-platform adaptation in event-based dense perception is crucial for deploying event cameras across diverse settings, such as vehicles, drones, and quadrupeds, each with unique motion dynamics, viewpoints, and class distributions. In this work, we introduce EventFly, a framework for robust cross-platform adaptation in event camera perception. Our approach comprises three key components: i) Event Activation Prior (EAP), which identifies high-activation regions in the target domain to minimize prediction entropy, fostering confident, domain-adaptive predictions; ii) EventBlend, a data-mixing strategy that integrates source and target event voxel grids based on EAP-driven similarity and density maps, enhancing feature alignment; and iii) EventMatch, a dual-discriminator technique that aligns features from source, target, and blended domains for better domain-invariant learning. To holistically assess cross-platform adaptation abilities, we introduce EXPo, a large-scale benchmark with diverse samples across vehicle, drone, and quadruped platforms. Extensive experiments validate our effectiveness, demonstrating substantial gains over popular adaptation methods. We hope this work can pave the way for more adaptive, high-performing event perception across diverse and complex environments.

Yannis Montreuil, Axel Carlier, Lai Xing Ng et al.

Existing Learning-to-Defer (L2D) frameworks are limited to single-expert deferral, forcing each query to rely on only one expert and preventing the use of collective expertise. We introduce the first framework for Top-$k$ Learning-to-Defer, which allocates queries to the $k$ most cost-effective entities. Our formulation unifies and strictly generalizes prior approaches, including the one-stage and two-stage regimes, selective prediction, and classical cascades. In particular, it recovers the usual Top-1 deferral rule as a special case while enabling principled collaboration with multiple experts when $k>1$. We further propose Top-$k(x)$ Learning-to-Defer, an adaptive variant that learns the optimal number of experts per query based on input difficulty, expert quality, and consultation cost. To enable practical learning, we develop a novel surrogate loss that is Bayes-consistent, $\mathcal{H}_h$-consistent in the one-stage setting, and $(\mathcal{H}_r,\mathcal{H}_g)$-consistent in the two-stage setting. Crucially, this surrogate is independent of $k$, allowing a single policy to be learned once and deployed flexibly across $k$. Experiments across both regimes show that Top-$k$ and Top-$k(x)$ deliver superior accuracy-cost trade-offs, opening a new direction for multi-expert deferral in L2D.

Yannis Montreuil, Axel Carlier, Lai Xing Ng et al.

Learning-to-Defer routes each input to the expert that minimizes expected cost, but it assumes that the information available to every expert is fixed at decision time. Many modern systems violate this assumption: after selecting an expert, one may also choose what additional information that expert should receive, such as retrieved documents, tool outputs, or escalation context. We study this problem and call it Learning-to-Defer with advice. We show that a broad family of natural separated surrogates, which learn routing and advice with distinct heads, is inconsistent even in the smallest non-trivial setting. We then introduce an augmented surrogate that operates on the composite expert--advice action space and prove an $\mathcal{H}$-consistency guarantee together with an excess-risk transfer bound, yielding recovery of the Bayes-optimal policy in the limit. Experiments on tabular, language, and multi-modal tasks show that the resulting method improves over standard Learning-to-Defer while adapting its advice-acquisition behavior to the cost regime; a synthetic benchmark confirms the failure mode predicted for separated surrogates.

Yannis Montreuil, Letian Yu, Axel Carlier et al.

Learning-to-Defer (L2D) enables hybrid decision-making by routing inputs either to a predictor or to external experts. While promising, L2D is highly vulnerable to adversarial perturbations, which can not only flip predictions but also manipulate deferral decisions. Prior robustness analyses focus solely on two-stage settings, leaving open the end-to-end (one-stage) case where predictor and allocation are trained jointly. We introduce the first framework for adversarial robustness in one-stage L2D, covering both classification and regression. Our approach formalizes attacks, proposes cost-sensitive adversarial surrogate losses, and establishes theoretical guarantees including $\mathcal{H}$, $(\mathcal{R }, \mathcal{F})$, and Bayes consistency. Experiments on benchmark datasets confirm that our methods improve robustness against untargeted and targeted attacks while preserving clean performance.

Lingdong Kong, Dongyue Lu, Ao Liang et al.

Event cameras offer microsecond-level latency and robustness to motion blur, making them ideal for understanding dynamic environments. Yet, connecting these asynchronous streams to human language remains an open challenge. We introduce Talk2Event, the first large-scale benchmark for language-driven object grounding in event-based perception. Built from real-world driving data, we provide over 30,000 validated referring expressions, each enriched with four grounding attributes -- appearance, status, relation to viewer, and relation to other objects -- bridging spatial, temporal, and relational reasoning. To fully exploit these cues, we propose EventRefer, an attribute-aware grounding framework that dynamically fuses multi-attribute representations through a Mixture of Event-Attribute Experts (MoEE). Our method adapts to different modalities and scene dynamics, achieving consistent gains over state-of-the-art baselines in event-only, frame-only, and event-frame fusion settings. We hope our dataset and approach will establish a foundation for advancing multimodal, temporally-aware, and language-driven perception in real-world robotics and autonomy.

Lingdong Kong, Dongyue Lu, Ao Liang et al.

Event cameras capture changes in brightness with microsecond precision and remain reliable under motion blur and challenging illumination, offering clear advantages for modeling highly dynamic scenes. Yet, their integration with natural language understanding has received little attention, leaving a gap in multimodal perception. To address this, we introduce Talk2Event, the first large-scale benchmark for language-driven object grounding using event data. Built on real-world driving scenarios, Talk2Event comprises 5,567 scenes, 13,458 annotated objects, and more than 30,000 carefully validated referring expressions. Each expression is enriched with four structured attributes -- appearance, status, relation to the viewer, and relation to surrounding objects -- that explicitly capture spatial, temporal, and relational cues. This attribute-centric design supports interpretable and compositional grounding, enabling analysis that moves beyond simple object recognition to contextual reasoning in dynamic environments. We envision Talk2Event as a foundation for advancing multimodal and temporally-aware perception, with applications spanning robotics, human-AI interaction, and so on.