相关论文: SPIRAL: Self-Evolving Action-Conditioned Video Gen…
Autonomous driving technologies face significant safety challenges while operating under rare, diverse, and visually degraded weather scenarios. These challenges become more critical in cooperative settings, where vehicles and…
In computer animation, game design, and human-computer interaction, synthesizing human motion that aligns with user intent remains a significant challenge. Existing methods have notable limitations: textual approaches offer high-level…
Perceptual studies demonstrate that conditional diffusion models excel at reconstructing video content aligned with human visual perception. Building on this insight, we propose a video compression framework that leverages conditional…
In real scenarios, videos can span several minutes or even hours. However, existing research on spatio-temporal video grounding (STVG), given a textual query, mainly focuses on localizing targets in short videos of tens of seconds,…
Text to video generation has emerged as a critical frontier in generative artificial intelligence, yet existing approaches struggle with maintaining temporal consistency, compositional understanding, and fine grained control over visual…
Long-horizon robotic manipulation poses significant challenges for autonomous systems, requiring extended reasoning, precise execution, and robust error recovery across complex sequential tasks. Current approaches, whether based on static…
The rapid advancement of video generation has rendered existing evaluation systems inadequate for assessing state-of-the-art models, primarily due to simple prompts that cannot showcase the model's capabilities, fixed evaluation operators…
Using generative models to synthesize new data has become a de-facto standard in autonomous driving to address the data scarcity issue. Though existing approaches are able to boost perception models, we discover that these approaches fail…
Learning long-horizon embodied behaviors from synthetic data remains challenging because generated scenes are often physically implausible, language-driven programs frequently "succeed" without satisfying task semantics, and high-level…
Humans perceive actions through key transitions that structure actions across multiple abstraction levels, whereas machines, relying on visual features, tend to over-segment. This highlights the difficulty of enabling hierarchical reasoning…
Most text-to-video (T2V) generators prioritize aesthetic quality, but often ignoring the spatial constraints in the generated videos. In this work, we present SPATIALALIGN, a self-improvement framework that enhances T2V models capabilities…
Streaming video generation, as one fundamental component in interactive world models and neural game engines, aims to generate high-quality, low-latency, and temporally coherent long video streams. However, most existing work suffers from…
Despite advances in text and visual generation, creating coherent long-form audio narratives remains challenging. Existing frameworks often exhibit limitations such as mismatched character settings with voice performance, insufficient…
We propose technology to enable a new medium of expression, where video elements can be looped, merged, and triggered, interactively. Like audio, video is easy to sample from the real world but hard to segment into clean reusable elements.…
Generating temporally coherent high fidelity video is an important milestone in generative modeling research. We make progress towards this milestone by proposing a diffusion model for video generation that shows very promising initial…
Temporal action segmentation is crucial for understanding long-form videos. Previous works on this task commonly adopt an iterative refinement paradigm by using multi-stage models. We propose a novel framework via denoising diffusion…
Long video understanding is challenging due to dense visual redundancy, long-range temporal dependencies, and the tendency of chain-of-thought and retrieval-based agents to accumulate semantic drift and correlation-driven errors. We argue…
Generating high-fidelity, temporally consistent videos in autonomous driving scenarios faces a significant challenge, e.g. problematic maneuvers in corner cases. Despite recent video generation works are proposed to tackcle the mentioned…
Cinemagraphs, which combine static photographs with selective, looping motion, offer unique artistic appeal. Generating them from a single photograph in a controllable manner is particularly challenging. Existing image-animation techniques…
Recent text-to-video (T2V) models have demonstrated strong capabilities in producing high-quality, dynamic videos. To improve the visual controllability, recent works have considered fine-tuning pre-trained T2V models to support…