CVPR·ICCV·ECCV·WACV·BMVC 신규 논문을 매일 추적

Token merging has emerged as an effective training-free strategy for accelerating diffusion models by reducing redundant token computation while minimizing gene…

Diffusion and flow models generate a sample over iterative steps, each a full pass through a large network, and that pass dominates generation cost. Training-fr…

Predicting how the world responds to an action requires more than what can be seen: robots must account for environmental factors that are neither directly obse…

We introduce P$^{3}$-WAM, a unified world action model for egocentric dexterous manipulation that learns 3D perception, action-conditioned prediction, and goal-…

Recent advances in multimodal large language models (MLLMs) and 3D generation have expanded 3D understanding and synthesis. However, beyond visual fidelity, tas…

Vision-language models still struggle to understand 3D spatial relations across views and update spatial judgments as the observer moves. A common approach fuse…

Single image 3D generation aims to dress a given 3D mesh with relightable materials while faithfully preserving the visual details of a reference image. Existin…

Few-step autoregressive video generators enable streaming generation, yet they run every token through the final denoising step, regardless of how much refineme…

Recent 3D world models increasingly use features from geometry foundation models (GFMs) as predictive world states, benefiting from their rich geometric priors.…

We introduce 3DCodeVerse, a research ecosystem that enables coding agents to create editable and verifiable 3D content at scale. 3DCodeVerse comprises large-sca…

Image editing models produce impressive results for individual edits, but their quality often deteriorates over multiple editing turns. Each editing turn introd…

Reconstructing human motion in 4D requires identifying the same surface points through articulation, deformation and changes in visibility. We introduce Dense4D…

As joint audio-video generation models become more capable, they can generate audio-visual scenes exhibiting three forms of complexity: multi-event composition,…

Recent advancements in diffusion models have significantly improved text-to-image generation, enabling their application to visual storytelling, where coherent …

Video world models turn actions and camera motion into long visual rollouts, making video a natural interface for interactive simulation. Such interaction requi…

Multi-object tracking in sports broadcasts is hard for two reasons: athletes move fast and change direction abruptly, and the camera pans and zooms at the same …

Understanding characteristics and activities of individuals in complex multi-person environments is crucial for real-world applications. However, existing datas…

Reinforcement learning can align visual generators with reward signals beyond their pretraining objectives, but existing score-function methods typically introd…

Spatial intelligence lets an agent perceive and act in the physical world, and many of its judgments must be made at interaction rates: which spatial relation h…

Surveillance cameras along urban roads produce large volumes of unlabeled video that could support the monitoring of public transport, but grouping the observed…

Strong guidance in text-to-image (T2I) diffusion models concentrates sampling toward high-density modes of the conditional distribution, collapsing independentl…

Reinforcement learning (RL) enables language models to improve text-to-image (T2I) generation by rewriting prompts for a frozen image generator. Existing method…

State-of-the art approaches to retinal vessel segmentation typically require extensive annotations, a highly time-consuming process, reliant on clinical experti…

The human brain effortlessly deciphers colors and textures from visual stimuli and reconstructs the world around us, yet preserving such details remains challen…

Multimodal deep search is moving from short queries to long-horizon investigations that continually acquire evidence. However, training such agents remains cons…

Real desktop automation is neither purely visual nor purely programmatic. Agents must understand user-facing interfaces while efficiently manipulating files, sc…

Lossless image compression fundamentally relies on accurate entropy modeling, driving a recent shift toward large language model (LLM)-based methods. However, e…

Physical understanding is crucial for decision making, yet vision models struggle to infer properties such as damping that govern how materials behave. Audio en…

Reinforcement learning (RL) can elicit specialized visual capabilities in vision-language models (VLMs), yet jointly optimizing heterogeneous objectives often i…

Accurate motion prediction is critical for safe autonomous driving, yet even strong forecasters leave residual errors in their multimodal proposals. Existing re…

Thin, elongated structures are particularly sensitive to connectivity errors, as even a few local segmentation mistakes can disrupt otherwise continuous paths. …

Computer use has reached a turning point: the focus is expanding from GUI-only interaction to systems that complete tasks on users' computers through visual and…

Recent advances in Omni Language Models (OLMs) provide a unified solution for audiovisual video captioning. Nevertheless, existing approaches predominantly trea…

Few-shot adaptation often relies on an encoder's final global representation, leaving complementary information in intermediate layers underused. Combining thes…

We introduce REKI, a 2.4B vision-language-action model (VLA) pretrained exclusively on public data that sets a new Pareto frontier between performance and model…

Feed-forward transformer models have recently achieved strong performance in multi-view 3D reconstruction, but they still rely primarily on appearance-based att…

A perception system that must brake for a pedestrian does not need a low average latency. It must deliver an answer before the deadline on every frame, the wors…

Contrastive vision-language pre-training supports zero-shot chest X-ray diagnosis, but standard objectives treat every off-diagonal image-report pair in a batch…

Whole-slide images may contain coexisting lesions, yet weak supervision typically provides only the most severe diagnosis. We formulate this setting as dominant…