MOJITO: Modal Joint Learning for Unified End-to-End Autonomous Driving

End-to-end autonomous driving systems commonly follow a cascaded two-stage pipeline where a perception stage compresses multi-modal sensor inputs into a compact context and a downstream planner predicts trajectories conditioned on this context. We argue that this one-way perception-to-planning interface forces sensor inputs into a compact representation, losing the fine-grained details critical for planning. Moreover, by constraining the planner to this compressed context, it is difficult to leverage the rich representations offered by modern vision foundation models. To address these issues, we propose MOJITO, a unified sensor-to-action framework for end-to-end autonomous driving built on modal joint learning. MOJITO removes the cascaded interface and instead performs block-wise Modal Joint Attention that simultaneously updates action, image, and LiDAR features, allowing the planner to directly access multi-modal features during action generation. MOJITO achieves 88.9 PDMS on the NAVSIM v1 dataset and 88.4 EPDMS on the more challenging NAVSIM v2 dataset, setting a new state-of-the-art. Extensive experiments further demonstrate strong scalability, instruction following, and diverse trajectory generation. Code and models are available at https://github.com/mumucc01/MOJITO.

Straight-Path Flow Matching for Incomplete Multi-View Clustering

Incomplete Multi-View Clustering addresses the problem of clustering multi-modal data when certain views are missing. Recent end-to-end generative approaches leverage diffusion models to recover missing views via stochastic noise-to-data trajectories. While expressive, such mechanisms are not explicitly designed for clustering, as they initialize from cluster-agnostic noise and rely on stochastic denoising dynamics. In this work, we revisit probability path design in end-to-end generative IMVC. We introduce a flow-matching framework with a linear interpolation path between paired view representations, that replaces diffusion with probability flows between observed and missing views. We provide a formal analysis showing that deterministic ODE flows are inherently better aligned with clustering objectives than diffusion-based stochastic trajectories, especially in terms of transport mechanisms that respect class-conditional data distributions and maintain cluster consistency in finite-step regimes. Building upon this insight, we develop an end-to-end IMVC architecture that integrates straight-path flow-matching view completion with cluster-level and entropy-based alignment to enforce cross-view clustering consistency. Extensive experiments on standard IMVC benchmarks demonstrate that the proposed framework establishes new state-of-the-art performance.

ArcAD: Anomaly-Rectified Calibration for Cold-Start Supervised Anomaly Detection

The deployment of Industrial Anomaly Detection (IAD) in real-world manufacturing frequently encounters a challenging cold-start bottleneck, in which limited normal samples fail to represent the full normal distribution and only a few anomalies are available. Under such a regime, existing methods struggle to form compact normal boundaries and fail to effectively exploit supervised signals from rare defects. To address this challenge, we propose Anomaly-Rectified Cold-start AD (ArcAD), a plug-and-play calibration framework for reconstruction-based IAD baselines. ArcAD follows a push-pull learning paradigm to construct a compact and discriminative normal boundary under data scarcity. On the one hand, ArcAD projects limited normal samples onto a hypersphere and pulls them into multiple compact clusters to maximize coverage of the normal manifold. On the other hand, it synthesizes pseudo-anomalies on the hypersphere and leverages real anomalies to push the boundary inward and sharpen anomaly discrimination. Extensive experiments on MVTec-AD, VisA, Real-IAD, and MANTA demonstrate that ArcAD significantly outperforms state-of-the-art supervised and unsupervised methods in both single-class and multi-class settings under cold-start conditions. Code is available at: https://github.com/LGC-AD/ArcAD.

Panoramic Scene Analysis: A Survey from Distortion-Aware Engineering to Sphere-Native Foundation Modeling

Panoramic images capture the complete visual sphere in a single frame, providing spatial context unattainable by conventional cameras. Yet this completeness comes at a geometric cost: the 2-sphere cannot be faithfully mapped to the plane, and every planar representation introduces distortions that violate the assumptions underlying standard vision architectures. This survey traces the evolution of panoramic scene analysis along a methodological trajectory, from projection-based adaptation, through distortion-aware engineering, to sphere-native modeling and geometry-aware tokenization for foundation models, and argues that this evolution reflects a progressive deepening of geometric commitment rather than a simple accumulation of techniques. We organize the literature along two orthogonal dimensions: architectural design (how operators interact with spherical geometry) and training paradigm (how knowledge is transferred across domains). Covering dense prediction (semantic segmentation, depth estimation, and room layout estimation), unified multi-task understanding, open-world perception, vision-language reasoning, and dynamic video analysis, we identify a central unresolved tension: among the methods surveyed, none simultaneously delivers strict spherical equivariance and full reuse of perspective-pretrained foundation-model weights, and we argue that this is a structural rather than incidental gap. We further expose five systematic gaps in current evaluation protocols, namely the absence of spherical-area-weighted metrics, seam-consistency testing, polar-robustness stratification, cross-projection generalization, and open-world protocol standardization, and propose a six-point research roadmap toward general-purpose panoramic intelligence. The corresponding repository is publicly available at: https://github.com/zhuqinfeng1999/Awesome-Panoramic-Scene-Analysis.

CogPortrait: Fine-Grained Eye-Region Control in Portrait Animation via Hierarchical Agent Planning

Portrait animation methods have achieved substantial visual quality and lip synchronization, but fine-grained manipulation of the eye region still faces a trade-off between input granularity and motion accuracy. Existing methods using emotion labels or coarse text prompts are insufficient for describing subtle ocular dynamics, whereas approaches based on Action Units or driving videos provide higher fidelity at the cost of a heavier input burden. These limitations are still restrictive for beyond-emotion states (e.g., thinking) and drowsiness. In light of the above, we propose CogPortrait, a two-stage framework that generates portrait animations from high-level labels. In the first stage, three chain-of-thought Multimodal Large Language Models (MLLMs) agents compile high-level labels into facial keypoints through temporal event planning, prototype retrieval, and composition from a real-behavior library, and semantic-physiological constraint enforcement. In the second stage, a DiT-based video generation backbone synthesizes the final animation conditioned on the keypoints, reference portrait, audio, and text prompt, enhanced by a dynamic classifier-free guidance strategy with eye-region-aware reweighting and KTO-based refinement for boundary cases. We further introduce the EMH benchmark covering diverse emotions and beyond-emotion categories with two AU-level metrics for evaluating fine-grained eye-region and head-motion control. Extensive experiments on HDTF and the EMH benchmark demonstrate that CogPortrait achieves more precise eye-region control than existing methods while maintaining supe- rior visual quality and identity consistency

Dictionary-Aligned Concept Control for Safeguarding Multimodal LLMs

Multimodal Large Language Models (MLLMs) have been shown to be vulnerable to malicious queries that can elicit unsafe responses. Recent work uses prompt engineering, response classification, or finetuning to improve MLLM safety. Nevertheless, such approaches are often ineffective against evolving malicious patterns, may require rerunning the query, or demand heavy computational resources. Steering the activations of a frozen model at inference time has recently emerged as a flexible and effective solution. However, existing steering methods for MLLMs typically handle only a narrow set of safety-related concepts or struggle to adjust specific concepts without affecting others. To address these challenges, we introduce Dictionary-Aligned Concept Control (DACO), a framework that utilizes a curated concept dictionary and a Sparse Autoencoder (SAE) to provide granular control over MLLM activations. First, we curate a dictionary of 15,000 multimodal concepts by retrieving over 400,000 caption-image stimuli and summarizing their activations into concept directions. We name the dataset DACO-400K. Second, we show that the curated dictionary can be used to intervene activations via sparse coding. Third, we propose a new steering approach that uses our dictionary to initialize the training of an SAE and automatically annotate the semantics of the SAE atoms for safeguarding MLLMs. Experiments on multiple MLLMs (e.g., QwenVL, LLaVA, InternVL) across safety benchmarks (e.g., MM-SafetyBench, JailBreakV) show that DACO significantly improves MLLM safety while maintaining general-purpose capabilities.

Chain of World: World Model Thinking in Latent Motion

Vision-Language-Action (VLA) models are a promising path toward embodied intelligence, yet they often overlook the predictive and temporal-causal structure underlying visual dynamics. World-model VLAs address this by predicting future frames, but waste capacity reconstructing redundant backgrounds. Latent-action VLAs encode frame-to-frame transitions compactly, but lack temporally continuous dynamic modeling and world knowledge. To overcome these limitations, we introduce CoWVLA (Chain-of-World VLA), a new "Chain of World" paradigm that unifies world-model temporal reasoning with a disentangled latent motion representation. First, a pretrained video VAE serves as a latent motion extractor, explicitly factorizing video segments into structure and motion latents. Then, during pre-training, the VLA learns from an instruction and an initial frame to infer a continuous latent motion chain and predict the segment's terminal frame. Finally, during co-fine-tuning, this latent dynamic is aligned with discrete action prediction by jointly modeling sparse keyframes and action sequences in a unified autoregressive decoder. This design preserves the world-model benefits of temporal reasoning and world knowledge while retaining the compactness and interpretability of latent actions, enabling efficient visuomotor learning. Extensive experiments on robotic simulation benchmarks show that CoWVLA outperforms existing world-model and latent-action approaches and achieves moderate computational efficiency, highlighting its potential as a more effective VLA pretraining paradigm. The project website can be found at https://fx-hit.github.io/cowvla-io.

SO3UFormer: Learning Intrinsic Spherical Features for Rotation-Robust Panoramic Segmentation

Panoramic semantic segmentation models are typically trained under a strict gravity-aligned assumption. However, real-world captures often deviate from this canonical orientation due to unconstrained camera motions, such as the rotational jitter of handheld devices or the dynamic attitude shifts of aerial platforms. This discrepancy causes standard spherical Transformers to overfit global latitude cues, leading to performance collapse under 3D reorientations. To address this, we introduce SO3UFormer, a rotation-robust architecture designed to learn intrinsic spherical features that are less sensitive to the underlying coordinate frame. Our approach rests on three geometric pillars: (1) an intrinsic feature formulation that decouples the representation from the gravity vector by removing absolute latitude encoding; (2) quadrature-consistent spherical attention that accounts for non-uniform sampling densities; and (3) a gauge-aware relative positional mechanism that encodes local angular geometry using tangent-plane projected angles and discrete gauge pooling, avoiding reliance on global axes. We further use index-based spherical resampling together with a logit-level SO(3)-consistency regularizer during training. To rigorously benchmark robustness, we introduce Pose35, a dataset variant of Stanford2D3D perturbed by random rotations within $\pm 35^\circ$. Under the extreme test of arbitrary full SO(3) rotations, existing SOTAs fail catastrophically: the baseline SphereUFormer drops from 67.53 mIoU to 25.26 mIoU. In contrast, SO3UFormer demonstrates remarkable stability, achieving 72.03 mIoU on Pose35 and retaining 70.67 mIoU under full SO(3) rotations.

3D-Learning: Diffusion-Augmented Distributionally Robust Decision-Focused Learning

Predict-then-Optimize (PTO) pipelines are widely employed in computing and networked systems, where Machine Learning (ML) models are used to predict critical contextual information for downstream decision-making tasks such as cloud LLM serving, data center demand response, and edge workload scheduling. However, these ML predictors are often vulnerable to out-of-distribution (OOD) samples at test time, leading to significant decision performance degradation due to large prediction errors. To address the generalization challenges under OOD conditions, we present the framework of Distributionally Robust Decision-Focused Learning (DR-DFL), which trains ML models to optimize decision performance under the worst-case distribution. Instead of relying on classical Distributionally Robust Optimization (DRO) techniques, we propose Diffusion-Augmented Distributionally Robust Decision-Focused Learning (3D-Learning), which searches for the worst-case distribution within the parameterized space of a diffusion model. By leveraging the powerful distribution modeling capabilities of diffusion models, 3D-Learning identifies worst-case distributions that remain consistent with real data, achieving a favorable balance between average and worst-case scenarios. Empirical results on an LLM resource provisioning task demonstrate that 3D-Learning outperforms existing DRO and Data Augmentation methods in OOD generalization performance.

Visual Prompt-Agnostic Evolution

Visual Prompt Tuning (VPT) adapts a frozen Vision Transformer (ViT) to downstream tasks by inserting a small number of learnable prompt tokens into the token sequence at each layer. However, we observe that existing VPT variants often suffer from unstable training dynamics, characterized by gradient oscillations. A layer-wise analysis reveals that shallow-layer prompts tend to stagnate early, while deeper-layer prompts exhibit high-variance oscillations, leading to cross-layer mismatch. These issues slow convergence and degrade final performance. To address these challenges, we propose Prompt-Agnostic Evolution ($\mathtt{PAE}$), which strengthens vision prompt tuning by explicitly modeling prompt dynamics. From a frequency-domain perspective, we initialize prompts in a task-aware direction by uncovering and propagating frequency shortcut patterns that the backbone inherently exploits for recognition. To ensure coherent evolution across layers, we employ a shared Koopman operator that imposes a global linear transformation instead of uncoordinated, layer-specific updates. Finally, inspired by Lyapunov stability theory, we introduce a regularizer that constrains error amplification during evolution. Extensive experiments show that $\mathtt{PAE}$ accelerates convergence with an average $1.41\times$ speedup and improves accuracy by 1--3% on 25 datasets across multiple downstream tasks. Beyond performance, $\mathtt{PAE}$ is prompt-agnostic and lightweight, and it integrates seamlessly with diverse VPT variants without backbone modification or inference-time changes.