ICML 2026 论文列表

While Multimodal Diffusion Transformers (MMDiTs) have achieved remarkable success in high-fidelity generation, maintaining semantic faithfulness and structural consistency during the image editing process remains a fundamental challenge. DiT-based editing is primarily limited by cumulative drift and semantic leakage induced by new textual conditions. To address these challenges, we propose T-Edit, a training-free framework that formalizes consistent editing as a trajectory anchoring process. T-Edit explicitly decouples the inversion, reconstruction, and editing trajectories, leveraging the reconstruction branch as a structural reference to achieve real-time compensation for deviations in the latent manifold. To further reveal the internal regulation mechanism of DiTs, we analyze the spatio-temporal heterogeneity of their layer-wise structural sensitivity and accordingly propose a Dynamic Vital Layer (DVL) localization mechanism based on information energy. Furthermore, addressing the asymmetry of textual perturbations in the frequency domain distribution, we introduce a frequency-aware strategy based on tensor Singular Value Decomposition (t-SVD) to anchor (TA) high-rank structural components. Experiments show that T-Edit achieves state-of-the-art performance in both semantic alignment and structural fidelity, and can be seamlessly extended to multi-step editing and video scenarios, providing a new perspective for understanding and controlling the internal stability of DiTs.

Visual Mamba models have recently emerged as alternatives to Vision Transformers (ViTs), which suffer from quadratic complexity. While the recurrent scanning mechanism of Mamba offers computational efficiency, it inherently limits non-causal interactions between image patches. Prior works have attempted to address this limitation through various multi-scan strategies; however, these approaches suffer from inefficiencies due to suboptimal scan designs and frequent data rearrangement. Moreover, Mamba exhibits relatively slow computational speed under short token lengths, commonly used in visual tasks. In pursuit of a truly efficient vision encoder, we rethink the scan operation for vision and the computational efficiency of Mamba. To this end, we propose SF-Mamba, a novel visual Mamba with two key proposals: auxiliary patch **swapping** for encoding bidirectional information flow under an unidirectional scan and batch **folding** with periodic state reset for advanced GPU parallelism. Extensive experiments on image classification, object detection, and instance and semantic segmentation consistently demonstrate that our proposed SF-Mamba significantly outperforms state-of-the-art baselines while improving throughput across different model sizes. The source code is available at: https://github.com/sony/SF-Mamba.

Distribution matching distillation (DMD) facilitates few-step image generation by aligning a distilled student with a reference multi-step teacher. In practice, however, optimizing DMD can reduce sample diversity in few-step synthesis, and existing remedies typically rely on perceptual or adversarial regularization, leading to stability and scalability challenges during training. Here, we describe diversity-preserved DMD (DP-DMD), a role-separated distillation method inspired by the complementary roles of early and late denoising steps. Specifically, the first distillation step is trained with a teacher-derived target-prediction objective (e.g., v-prediction) to preserve sample diversity, while the remaining steps are optimized with the standard DMD loss to refine perceptual quality. DP-DMD, with no perceptual or adversarial regularization, no additional modules, and no teacher-generated reference samples, preserves sample diversity while maintaining competitive visual quality under few-step sampling, providing a simple and stable alternative to other DMD variants.

Existing lifelong person re-identification (Re-ID) methods assume that each identity maintains a relatively stable appearance distribution over time. However, in real-world scenarios, identities often reappear asynchronously with substantial clothing changes, which is not modeled in existing lifelong Re-ID formulations. We therefore study a realistic lifelong cloth-changing Re-ID (LCC) setting, in which identities reappear asynchronously under substantial clothing changes. This setting leads to two core difficulties: the model must acquire new identities while adapting representations of recurring ones, and at the same time remain robust to the substantial representation drift induced by clothing changes over time, which undermines cross-temporal identity consistency. To address these, we develop a framework that disentangles identity-intrinsic representations from clothing-induced biases, enabling identity modeling beyond appearance changes. We further introduce a Dynamic Identity-Anchor Alignment to maintain stable identity anchors under stage-wise distribution shifts. Experiments on the LTCC and PRCC benchmarks demonstrate superior performance and representational stability across multiple learning stages. Our code is available at https://github.com/joyner-7/LCC_ReID.

We present MMD-Reg, a novel correspondence-free approach to point-cloud registration that is differentiable and has linear computational complexity in the number of points. We model registration as a nonlinear least-squares problem based on the Maximum Mean Discrepancy, approximated using random Fourier features. The resulting objective can be solved efficiently with standard methods such as Levenberg–Marquardt, and the solution is differentiable via the implicit function theorem. This allows MMD-Reg to be used as a differentiable optimization layer within end-to-end trainable models, supporting registration under challenging conditions such as poor initial alignment and partial overlap. We demonstrate this Neural MMD-Reg formulation by integrating the layer with a set transformer, training the resulting model in supervised and unsupervised settings, and comparing its performance against recent learning-based methods. We also evaluate standalone MMD-Reg, comparing its accuracy and scalability against widely used non-learning-based registration methods.

We present WhisperSplat, the first lossless steganography method for 3D Gaussian Splatting (3DGS) models that hides a full‐resolution 2D image in a single view without any degradation of the model's rendering quality elsewhere. Prior work embeds data by retraining or modifying model weights, altering novel‐view synthesis fidelity and limiting capacity. Instead, we learn a small, view‐specific noise key applied to each Gaussian's spherical‐harmonic (SH) features while keeping all other views remain indistinguishable from the original renders. We further propose a Gradual Pixel Perturbation (GPP) strategy with a cosine-decay schedule, bootstrapping fast divergence from the clean render before transitioning to a combined reconstruction and SSIM loss. Unlike prior works that are highly dependent on accurate and large pretrained decoders, our method is able to recover the hidden image through rendering with noise key, and an optional lightweight refiner to enhance recovery image quality. Across nine standard 3DGS data scenes, WhisperSplat demonstrates superior hidden image recovery quality without sacrifice in clean 3DGS model performance, when compared to prior work such as GS-Hider and KeySS.

Vision-Language Models (VLMs) are costly at inference time because they must process long sequences of visual tokens. Existing token pruning methods often degrade under high compression by blindly discarding information, breaking spatial structure or collapsing diversity. We propose SpecFlow, a training-free framework that shifts the paradigm from destructive pruning to conservative condensation, strictly enforcing spatial coverage and statistical conservation to ensure stability. Treating visual tokens as nodes in a $k$NN graph, SpecFlow (i) computes a stable importance field via spectral heat flow to preserve structural coherence, (ii) allocates budgets via adaptive spatial partitioning to guarantee coverage, and (iii) aggregates discarded information into coreset sinks to maintain statistical conservation. The method is plug-and-play, requires no fine-tuning, and is compatible with FlashAttention. Experiments confirm that our SpecFlow outperforms SOTA methods across tasks, VLM architectures, and pruning ratios. Notably, LLaVA-1.5 with SpecFlow retains 95.6\% of original performance despite pruning 88.9\% of visual tokens, offering an exceptional efficiency-accuracy balance.

Modern vision-language models achieve strong performance in static perception, but remain limited in the complex spatiotemporal reasoning required for embodied, egocentric tasks. A major source of failure is their reliance on temporal priors learned from passive video data, which often leads to spatiotemporal hallucinations and poor generalization in dynamic environments. To address this, we present EgoTSR, a curriculum-based framework for learning task-oriented spatiotemporal reasoning. EgoTSR is built on the premise that embodied reasoning should evolve from explicit spatial understanding to internalized task-state assessment and finally to long-horizon planning. To support this paradigm, we construct EgoTSR-Data, a large-scale dataset comprising 46 million samples organized into three stages: Chain-of-Thought supervision for explicit reasoning, weakly supervised tagging for internalizing reasoning, and long-horizon sequences composed of orthogonal atomic subtasks. We further introduce a Reasoning-Enhanced Task Decomposition mechanism that explicitly models causal dependencies between actions and objects, enabling controllable planning from high-level task descriptions. To rigorously validate our approach, we establish a Dual-Level Evaluation Framework that covers both atomic spatial perception and logical planning. Extensive experiments demonstrate that EgoTSR effectively eliminates chronological biases, achieving 92.4% accuracy on long-horizon logical reasoning tasks while maintaining 88.2% fine-grained perceptual precision, significantly outperforming existing open-source and closed-source state-of-the-art models.

Human gameplay is a visually grounded interaction loop in which players act, reflect on failures, and watch tutorials to refine strategies. Can Vision-Language Models (VLMs) also learn from video-based reflection? We present **GameVerse**, a comprehensive video game benchmark that enables a *reflective visual interaction loop*. Moving beyond traditional ***fire-and-forget*** evaluations, it uses a novel ***reflect-and-retry*** paradigm to assess how VLMs internalize visual experience and improve policies. To facilitate systematic and scalable evaluation, we also introduce a *cognitive hierarchical taxonomy* spanning 15 globally popular games, *dual action space* for both semantic and GUI control, and *milestone evaluation* using advanced VLMs to quantify progress. Our experiments show that VLMs benefit from video-based reflection in varied settings, and perform best by combining failure trajectories and expert tutorials—a *training-free* analogue to reinforcement learning (RL) plus supervised fine-tuning (SFT).

Current 3D spatial reasoning methods face a fundamental trade-off: neuro-symbolic 3D (NS3D) concept learners achieve interpretable reasoning through compositional programs but are constrained to closed-set concept vocabularies and simple programs; end-to-end 3D multi-modal LLMs (3D MLLMs) could handle complex natural language and open-vocabulary concepts but suffer from black-box reasoning without explicit spatial verification. We introduce APEIRIA, a neuro-symbolic 3D MLLM to bridge two paradigms by distilling symbolic reasoning patterns into MLLMs with natural language chain-of-thought. Our three-stage curriculum progressively builds reasoning capabilities: a) 3D perception alignment grounds object visual-geometric features to the LLM, b) CoT-SFT teaches query decomposition and stepwise verification from symbolic program traces, and c) CoT-RL extends reasoning patterns to open-set concepts and deeply nested instructions. By transferring reasoning patterns rather than concept-specific knowledge, APEIRIA preserves key NS3D virtues: transparent reasoning and modular interchangeability of planning and perception components. Evaluations on grounding, question answering, and captioning show that APEIRIA surpasses prior NS3D methods and matches state-of-the-art 3D MLLMs on 3D spatial reasoning datasets, unifying symbolic methods' systematic reasoning with MLLMs' flexibility. Code is available at https://github.com/oceanflowlab/APEIRIA.

Single-view 3D object reconstruction presents a formidable challenge in computer vision due to the inherent limitations of information obtainable from a solitary viewpoint. Recent 3D Gaussian Splatting (3DGS) inspired approaches perform a feed-forward way of learning a neural network that predicts 3D Gaussians which compose the 3D object, given a single image. However, they often struggle with occlusions and exhibit high sensitivity to small changes in input viewpoint, leading to inconsistencies and blurry artifacts in novel view renderings. Our method leverages 3DGS and introduces a new learning scheme that continuously adapts to input viewpoints. To address inherent continuity of camera viewpoints that are represented by polar and azimuthal angles, we use Neural Ordinary Differential Equations to continuously model filter subspace of neural network, thus seamlessly embedding inductive bias of perspective distortions into its structure. By continuously adapting to view-specific features, our approach fosters view consistency in 3D reconstruction, allowing better coherency and accuracy across different angles. Experiments demonstrate that our model outperforms previous methods on multiple single-view 3D reconstruction benchmark datasets and excels in extrapolating to unseen camera angles and categories.

Existing VLA models frequently fail in robotic manipulation tasks, with poorly structured fault types that often require expert diagnosis. While VLMs offer strong explanatory capabilities, their effectiveness in assisting VLAs is limited by their unclear role in diagnostics and inadequate collaboration mechanisms. To address this, we introduce VLA-FixBench, a fault evaluation dataset that spans perception, planning, and control failures, and provides annotations for task stages, fault types, and spatiotemporal repair strategies. We further propose FaultEval, a static-to-dynamic-to-real evaluation framework that benchmarks 20 VLMs across multiple fault-related dimensions. Building on these insights, we design a VLM–VLA collaboration mechanism that localizes spatiotemporal deviations and rolls back task execution to enable targeted recovery. Experiments show that FaultEval reliably characterizes VLM-based closed-loop diagnosis and repair. The upper-bound analysis using human expert intervention shows that an idealized feedback loop can improve task success rates by 13\% on LIBERO and 35\% on real-world robots. Our code, benchmark, and project page will be publicly released at: https://kakigo.github.io/VLA-FixBench/

Generating realistic 3D Human-Object Interactions (HOI) is a fundamental task for applications ranging from embodied AI to virtual content creation, which requires harmonizing high-level semantic intent with strict low-level physical constraints. Existing methods excel at semantic alignment, however, they struggle to maintain precise object contact. We reveal a key finding termed $\textit{Geometric Forgetting}$: as diffusion model depth increases, semantic feature tend to overshadow object geometry feature, causing the model to lose its perception to object geometry. To address this, we propose MaMi-HOI, a hierarchical framework reconciling Macro-level kinematic fluidity with Micro-level spatial precision. First, to counteract geometric forgetting, we introduce the Geometry-Aware Proximity Adapter (GAPA), which explicitly re-injects dense object details to perform residual snapping corrections for precise contact. Nevertheless, such aggressive local enforcement can disrupt global dynamics, leading to robotic stiffness. In response, we introduce the Kinematic Harmony Adapter (KHA), which proactively aligns whole-body posture with spatial objectives, ensuring the skeleton actively accommodates constraints without compromising naturalness. Extensive experiments validate that MaMi-HOI simultaneously achieves natural motion and precise contact. Crucially, it extends generation capabilities to long-term tasks with complex trajectories, effectively bridging the gap between global navigation and high-fidelity manipulation in 3D scenes.

3D Scene Graph Generation (3DSGG) aims to create a structured representation of 3D environment by identifying objects as nodes and their relations as edges. Existing 3DSGG methods based on RGB-D sequences typically put much focus on the adaption of neural networks to robust node and edge feature extraction in complex 3D scenes, yet ignoring the inherent intra-class diversity within each class and inter-class similarity between different categories associated with nodes and edges. In this work, we develop GMPSSG, a novel Gaussian Mixture-distributed Prototype mining framework for 3DSGG. Specifically, we model different categories with independent Gaussian Mixture-distributed Prototype to effectively mitigate inter-class similarity, while employing multiple Gaussian components within each prototype to capture intra-class diversity. Moreover, Prototype-anchored Representation Learning is introduced to construct a well-structured and mutually independent category space; Topology-aware Prototype Interaction is devised to capture implicit co-occurrence priors within the scene, and leverage them to calibrate prototype distributions, thereby ensuring the plausibility of node-edge matching. Experiments on 3DSSG dataset demonstrate GMPSSG outperforms various top-leading methods. Our code is available at GMPSSG.

Audio-driven visual dubbing aims to synchronize a video's lip movements with new speech but is fundamentally challenged by the lack of ideal training data: paired videos differing only in lip motion. Existing methods circumvent this via mask-based inpainting. However, masking inevitably destroys spatiotemporal context, leading to identity drift and poor robustness (e.g., to occlusions), while also inducing lip-shape leakage that degrades lip sync. To bridge this gap, we propose X-Dub, a novel two-stage generative bootstrapping framework leveraging powerful Diffusion Transformers to unlock mask-free dubbing. Our core insight is to repurpose a mask-based inpainting model exclusively as a dedicated data generator to synthesize scalable, high-fidelity pseudo-paired data, which is subsequently utilized to train and bootstrap a robust, mask-free editing model as the final video dubber. The final dubber is liberated from masking artifacts and leverages the complete video input for high-fidelity inference. We further introduce timestep-adaptive multi-phase learning to disentangle conflicting objectives (structure, lip motion, and texture) across diffusion phases, facilitating stable convergence and advanced editing quality. Additionally, we present X-DubBench, a benchmark for diverse scenarios. Extensive experiments demonstrate that our method achieves state-of-the-art performance with superior lip sync, visual quality, and robustness. Code, demos, and additional resources are available at https://github.com/KlingAIResearch/X-Dub.

Vision-and-Language Navigation in Continuous Environments (VLN-CE) requires agents to make fine-grained navigation decisions under partial observability. However, most existing methods rely on open-loop execution, lacking mechanisms to detect and correct internal state drift during inference. We propose SC$^{2}$-WM, a self-correcting world model framework that introduces internal feedback for closed-loop decision making in VLN-CE. Our method derives feedback from world-model foresight to perform state-level plan refinement before action execution. To handle challenging scenarios, we further introduce conditional world-aware adaptation, which enables model-level correction by selectively updating the world model at test time when feedback indicates model capacity insufficiency. Experiments on standard VLN-CE benchmarks demonstrate improved navigation robustness and generalization. Our code is available at https://github.com/sunrise-ikun/SC2_WM.

Reasoning over table images remains challenging for Large Vision-Language Models (LVLMs) due to complex layouts and tightly coupled structure-content information. Existing solutions often depend on expensive supervised training, reinforcement learning, or external tools, limiting efficiency and scalability. This work addresses a key question: how to adapt LVLMs to table reasoning with minimal annotation and no external tools? Specifically, we first introduce DiSCo, a Disentangled Structure-Content alignment framework that explicitly separates structural abstraction from semantic grounding during multimodal alignment, efficiently adapting LVLMs to tables structures. Building on DiSCo, we further present Table-GLS, a Global-to-Local Structure-guided reasoning framework that performs table reasoning via structured exploration and evidence-grounded inference. Extensive experiments across diverse benchmarks demonstrate that our framework efficiently enhances LVLM's table understanding and reasoning capabilities, particularly generalizing to unseen table structures. Our data and code are available at https://github.com/AAAndy-Zhu/TableVLM.

Face fill-light enhancement (FFE) brightens underexposed faces by adding virtual fill light while keeping the original scene illumination and background unchanged. Most face relighting methods aim to reshape overall lighting, which can suppress the input illumination or modify the entire scene, leading to foreground–background inconsistency and mismatching practical FFE needs. To support scalable learning, we introduce LightYourFace-160K (LYF-160K), a large-scale paired dataset built with a physically consistent renderer that injects a disk-shaped area fill light controlled by six disentangled factors, producing 160K before-and-after pairs. We first pretrain a physics-aware lighting prompt (PALP) that embeds the 6D parameters into conditioning tokens, using an auxiliary planar-light reconstruction objective. Building on a pretrained diffusion backbone, we then train a fill-light diffusion (FiLitDiff), an efficient one-step model conditioned on physically grounded lighting codes, enabling controllable and high-fidelity fill lighting at low computational cost. Experiments on held-out paired sets demonstrate strong perceptual quality and competitive full-reference metrics, while better preserving background illumination. The dataset and model will be at https://github.com/gobunu/Light-Up-Your-Face.

Recent works have explored integrating Vision-Language Models (VLMs) with classical planners that rely on symbolic representations of planning problem to generate long-horizon plans for complex embodied tasks. However, in open-ended environments, these symbolic representations obtained from perception are often incomplete, leading to suboptimal performance. To address this, we introduce SCOPE, a self-adaptive symbolic planning framework that supports refining action plans and evolving the symbolic world—the symbolic representations of open-ended environments. SCOPE comprises two synergistic modules: a Symbolic Execution Simulator (SESim) that conducts symbolic validation and real execution of action plans, leveraging the feedback to refine the plans and evolve the symbolic world; and a Self-Adaptive Symbolic Memory (SASMem) that further distills feedback into evolving symbolic knowledge to enhance long-horizon planning and modeling of the symbolic world. Experiments in open-ended environments show that SCOPE significantly improves the completeness of the symbolic world, the success rate of plans under environment perturbations, and cross-task grounding and adaptability across diverse embodied scenarios.