LongLive-RAG proposes a novel Retrieval-Augmented Generation (RAG) framework to stabilize and improve the quality of long-horizon video generation by treating the entire generated history as a searcha…

The paper proposes GIM-World, a geometry-aware implicit memory framework that significantly improves long-horizon video world models by explicitly encoding 3D scene geometry into a compact memory stat…

Reasmory introduces a structured programming framework that uses explicit 3D memory and a Domain-Specific Language (DSL) to reliably enhance Vision-Language Models' spatial reasoning capabilities, ach…

MORPHOS is a novel autoregressive framework that generates dynamic 3D assets (like meshes and radiance fields) from videos by using a unified 4D representation to ensure temporal consistency and handl…

The paper proposes a unified framework that decouples long-video reasoning into semantic and visual evidence, significantly improving performance on the HD-EPIC VQA Challenge.

CamGeo is a novel framework that improves sparse camera-conditioned image-to-video generation by distilling rich 3D geometric priors into the diffusion backbone, resulting in geometrically consistent…

The paper proposes a training-free framework, Visual Representation-Guided Video-LLM Reasoning, to perform composed video retrieval by using visual examples and text instructions, achieving strong per…

VEDAL introduces a variational, error-driven asynchronous learning framework to efficiently prune 3D Gaussian Splatting, achieving high compression ratios with minimal loss in novel view synthesis qua…

The paper introduces MetricScenes, a new large-scale, in-the-wild dataset, and demonstrates that fine-tuning existing geometry models on this dataset significantly mitigates the scale-collapse problem…

VideoMLA introduces a novel Multi-Head Latent Attention (MLA) mechanism that replaces per-head KV caches with a shared low-rank content latent, significantly reducing memory and improving throughput f…

The paper introduces LL-Bench, a comprehensive benchmark for evaluating large-scale generative models on low-level vision tasks, and proposes LL-Score, an MLLM-based evaluator that better aligns quali…

The paper proposes a zero-shot reason-then-retrieve pipeline using Qwen3.5-27B to solve the challenging task of composed video retrieval (CoVR-R), achieving high performance on both validation and bli…

The paper proposes ST-DRC, a Spatial-Temporal Decoupled Reference Conditioning framework that effectively balances high-level semantic control and low-level identity fidelity for text-to-video generat…

The paper introduces an adaptive feature-optimized vision front end that intelligently selects and budgets visual features for 3D reconstruction, significantly improving reconstruction quality and com…

Real2SAM2Real introduces a framework that uses explicit 3D caches, derived from 3D lifting models, to provide robust geometric guidance to Video Diffusion Models, significantly improving spatiotempora…

GeoSAM-3D proposes a novel framework for open-vocabulary 3D scene segmentation from simple monocular video by propagating object prompts using a geodesic distance kernel on a reconstructed Gaussian sc…

The paper systematically measures the risk of current image-to-3D models generating harmful geometries, finding that these models are effective at reconstruction and existing safeguards are insufficie…

VISReg introduces a novel regularization technique that combines variance control with a Sliced-Wasserstein-based sketching objective to stabilize self-supervised learning, achieving state-of-the-art…