Visual Representation Alignment for Multimodal Large Language Models

Multimodal large language models (MLLMs) trained with visual instruction tuning have achieved strong performance across diverse tasks, yet they remain limited in vision-centric tasks such as object counting or spatial reasoning. We attribute this gap to the prevailing text-only supervision paradigm, which provides only indirect guidance for the visual pathway and often leads MLLMs to discard fine-grained visual details during training. In this paper, we present VIsual Representation ALignment (VIRAL), a simple yet effective regularization strategy that aligns the internal visual representations of MLLMs with those of pre-trained vision foundation models (VFMs). By explicitly enforcing this alignment, VIRAL enables the model not only to retain critical visual details from the input vision encoder but also to complement additional visual knowledge from VFMs, thereby enhancing its ability to reason over complex visual inputs. Our experiments demonstrate consistent improvements across all tasks on widely adopted multimodal benchmarks. Furthermore, we conduct comprehensive ablation studies to validate the key design choices underlying our framework. We believe this simple finding opens up an important direction for the effective integration of visual information in training MLLMs.

Learning to Track Any Points from Human Motion

Human motion, with its inherent complexities, such as non-rigid deformations, articulated movements, clothing distortions, and frequent occlusions caused by limbs or other individuals, provides a rich and challenging source of supervision that is crucial for training robust and generalizable point trackers. Despite the suitability of human motion, acquiring extensive training data for point tracking remains difficult due to laborious manual annotation. Our proposed pipeline, AnthroTAP, addresses this by proposing an automated pipeline to generate pseudo-labeled training data, leveraging the Skinned Multi-Person Linear (SMPL) model. We first fit the SMPL model to detected humans in video frames, project the resulting 3D mesh vertices onto 2D image planes to generate pseudo-trajectories, handle occlusions using ray-casting, and filter out unreliable tracks based on optical flow consistency. A point tracking model trained on AnthroTAP annotated dataset achieves state-of-the-art performance on the TAP-Vid benchmark, surpassing other models trained on real videos while using 10,000 times less data and only 1 day in 4 GPUs, compared to 256 GPUs used in recent state-of-the-art.

PLOT: Pseudo-Labeling via Video Object Tracking for Scalable Monocular 3D Object Detection

Monocular 3D object detection (M3OD) has long faced challenges due to data scarcity caused by high annotation costs and inherent 2D-to-3D ambiguity. Although various weakly supervised methods and pseudo-labeling methods have been proposed to address these issues, they are mostly limited by domain-specific learning or rely solely on shape information from a single observation. In this paper, we propose a novel pseudo-labeling framework that uses only video data and is more robust to occlusion, without requiring a multi-view setup, additional sensors, camera poses, or domain-specific training. Specifically, we explore a technique for aggregating the pseudo-LiDARs of both static and dynamic objects across temporally adjacent frames using object point tracking, enabling 3D attribute extraction in scenarios where 3D data acquisition is infeasible. Extensive experiments demonstrate that our method ensures reliable accuracy and strong scalability, making it a practical and effective solution for M3OD.

Vid-CamEdit: Video Camera Trajectory Editing with Generative Rendering from Estimated Geometry

We introduce Vid-CamEdit, a novel framework for video camera trajectory editing, enabling the re-synthesis of monocular videos along user-defined camera paths. This task is challenging due to its ill-posed nature and the limited multi-view video data for training. Traditional reconstruction methods struggle with extreme trajectory changes, and existing generative models for dynamic novel view synthesis cannot handle in-the-wild videos. Our approach consists of two steps: estimating temporally consistent geometry, and generative rendering guided by this geometry. By integrating geometric priors, the generative model focuses on synthesizing realistic details where the estimated geometry is uncertain. We eliminate the need for extensive 4D training data through a factorized fine-tuning framework that separately trains spatial and temporal components using multi-view image and video data. Our method outperforms baselines in producing plausible videos from novel camera trajectories, especially in extreme extrapolation scenarios on real-world footage.

Aligned Novel View Image and Geometry Synthesis via Cross-modal Attention Instillation

We introduce a diffusion-based framework that performs aligned novel view image and geometry generation via a warping-and-inpainting methodology. Unlike prior methods that require dense posed images or pose-embedded generative models limited to in-domain views, our method leverages off-the-shelf geometry predictors to predict partial geometries viewed from reference images, and formulates novel-view synthesis as an inpainting task for both image and geometry. To ensure accurate alignment between generated images and geometry, we propose cross-modal attention distillation, where attention maps from the image diffusion branch are injected into a parallel geometry diffusion branch during both training and inference. This multi-task approach achieves synergistic effects, facilitating geometrically robust image synthesis as well as well-defined geometry prediction. We further introduce proximity-based mesh conditioning to integrate depth and normal cues, interpolating between point cloud and filtering erroneously predicted geometry from influencing the generation process. Empirically, our method achieves high-fidelity extrapolative view synthesis on both image and geometry across a range of unseen scenes, delivers competitive reconstruction quality under interpolation settings, and produces geometrically aligned colored point clouds for comprehensive 3D completion. Project page is available at https://cvlab-kaist.github.io/MoAI.

Fine-Grained Perturbation Guidance via Attention Head Selection

Recent guidance methods in diffusion models steer reverse sampling by perturbing the model to construct an implicit weak model and guide generation away from it. Among these approaches, attention perturbation has demonstrated strong empirical performance in unconditional scenarios where classifier-free guidance is not applicable. However, existing attention perturbation methods lack principled approaches for determining where perturbations should be applied, particularly in Diffusion Transformer (DiT) architectures where quality-relevant computations are distributed across layers. In this paper, we investigate the granularity of attention perturbations, ranging from the layer level down to individual attention heads, and discover that specific heads govern distinct visual concepts such as structure, style, and texture quality. Building on this insight, we propose "HeadHunter", a systematic framework for iteratively selecting attention heads that align with user-centric objectives, enabling fine-grained control over generation quality and visual attributes. In addition, we introduce SoftPAG, which linearly interpolates each selected head's attention map toward an identity matrix, providing a continuous knob to tune perturbation strength and suppress artifacts. Our approach not only mitigates the oversmoothing issues of existing layer-level perturbation but also enables targeted manipulation of specific visual styles through compositional head selection. We validate our method on modern large-scale DiT-based text-to-image models including Stable Diffusion 3 and FLUX.1, demonstrating superior performance in both general quality enhancement and style-specific guidance. Our work provides the first head-level analysis of attention perturbation in diffusion models, uncovering interpretable specialization within attention layers and enabling practical design of effective perturbation strategies.

Text-Aware Image Restoration with Diffusion Models

Image restoration aims to recover degraded images. However, existing diffusion-based restoration methods, despite great success in natural image restoration, often struggle to faithfully reconstruct textual regions in degraded images. Those methods frequently generate plausible but incorrect text-like patterns, a phenomenon we refer to as text-image hallucination. In this paper, we introduce Text-Aware Image Restoration (TAIR), a novel restoration task that requires the simultaneous recovery of visual contents and textual fidelity. To tackle this task, we present SA-Text, a large-scale benchmark of 100K high-quality scene images densely annotated with diverse and complex text instances. Furthermore, we propose a multi-task diffusion framework, called TeReDiff, that integrates internal features from diffusion models into a text-spotting module, enabling both components to benefit from joint training. This allows for the extraction of rich text representations, which are utilized as prompts in subsequent denoising steps. Extensive experiments demonstrate that our approach consistently outperforms state-of-the-art restoration methods, achieving significant gains in text recognition accuracy. See our project page: https://cvlab-kaist.github.io/TAIR/

Active Test-time Vision-Language Navigation

Vision-Language Navigation (VLN) policies trained on offline datasets often exhibit degraded task performance when deployed in unfamiliar navigation environments at test time, where agents are typically evaluated without access to external interaction or feedback. Entropy minimization has emerged as a practical solution for reducing prediction uncertainty at test time; however, it can suffer from accumulated errors, as agents may become overconfident in incorrect actions without sufficient contextual grounding. To tackle these challenges, we introduce ATENA (Active TEst-time Navigation Agent), a test-time active learning framework that enables a practical human-robot interaction via episodic feedback on uncertain navigation outcomes. In particular, ATENA learns to increase certainty in successful episodes and decrease it in failed ones, improving uncertainty calibration. Here, we propose mixture entropy optimization, where entropy is obtained from a combination of the action and pseudo-expert distributions-a hypothetical action distribution assuming the agent's selected action to be optimal-controlling both prediction confidence and action preference. In addition, we propose a self-active learning strategy that enables an agent to evaluate its navigation outcomes based on confident predictions. As a result, the agent stays actively engaged throughout all iterations, leading to well-grounded and adaptive decision-making. Extensive evaluations on challenging VLN benchmarks-REVERIE, R2R, and R2R-CE-demonstrate that ATENA successfully overcomes distributional shifts at test time, outperforming the compared baseline methods across various settings.

Seurat: From Moving Points to Depth

Accurate depth estimation from monocular videos remains challenging due to ambiguities inherent in single-view geometry, as crucial depth cues like stereopsis are absent. However, humans often perceive relative depth intuitively by observing variations in the size and spacing of objects as they move. Inspired by this, we propose a novel method that infers relative depth by examining the spatial relationships and temporal evolution of a set of tracked 2D trajectories. Specifically, we use off-the-shelf point tracking models to capture 2D trajectories. Then, our approach employs spatial and temporal transformers to process these trajectories and directly infer depth changes over time. Evaluated on the TAPVid-3D benchmark, our method demonstrates robust zero-shot performance, generalizing effectively from synthetic to real-world datasets. Results indicate that our approach achieves temporally smooth, high-accuracy depth predictions across diverse domains.

D^2USt3R: Enhancing 3D Reconstruction with 4D Pointmaps for Dynamic Scenes

We address the task of 3D reconstruction in dynamic scenes, where object motions degrade the quality of previous 3D pointmap regression methods, such as DUSt3R, originally designed for static 3D scene reconstruction. Although these methods provide an elegant and powerful solution in static settings, they struggle in the presence of dynamic motions that disrupt alignment based solely on camera poses. To overcome this, we propose D^2USt3R that regresses 4D pointmaps that simultaneiously capture both static and dynamic 3D scene geometry in a feed-forward manner. By explicitly incorporating both spatial and temporal aspects, our approach successfully encapsulates spatio-temporal dense correspondence to the proposed 4D pointmaps, enhancing downstream tasks. Extensive experimental evaluations demonstrate that our proposed approach consistently achieves superior reconstruction performance across various datasets featuring complex motions.