Related papers: GenMAC: Compositional Text-to-Video Generation wit…
Text-to-image (T2I) models have achieved remarkable progress, yet they continue to struggle with complex prompts that require simultaneously handling multiple objects, relations, and attributes. Existing inference-time strategies, such as…
Recently, text-to-motion models have opened new possibilities for creating realistic human motion with greater efficiency and flexibility. However, aligning motion generation with event-level textual descriptions presents unique challenges…
In text-to-motion generation, controllability as well as generation quality and speed has become increasingly critical. The controllability challenges include generating a motion of a length that matches the given textual description and…
The content of visual and audio scenes is multi-faceted such that a video can be paired with various audio and vice-versa. Thereby, in video-to-audio generation task, it is imperative to introduce steering approaches for controlling the…
Agentic code generation requires large language models (LLMs) capable of complex context management and multi-step reasoning. Prior multi-agent frameworks attempt to address these challenges through collaboration, yet they often suffer from…
Graphical User Interface (GUI) agents can automate complex tasks across digital environments, but their development is hindered by the scarcity of high-quality trajectory data for training. Existing approaches rely on expensive human…
Technological developments have produced methods that can generate educational videos from input text or sound. Recently, the use of deep learning techniques for image and video generation has been widely explored, particularly in…
The vision and language generative models have been overgrown in recent years. For video generation, various open-sourced models and public-available services have been developed to generate high-quality videos. However, these methods often…
Text-to-motion synthesis is a crucial task in computer vision. Existing methods are limited in their universality, as they are tailored for single-person or two-person scenarios and can not be applied to generate motions for more…
Recent large language models (LLMs) achieve impressive performance in source-conditioned text generation but often fail to correctly provide fine-grained attributions for their outputs, undermining verifiability and trust. Moreover,…
Amodal completion, the task of inferring invisible object parts, faces significant challenges in maintaining semantic consistency and structural integrity. Prior progressive approaches are inherently limited by inference instability and…
Text-to-Audio-Video (T2AV) generation is rapidly becoming a core interface for media creation, yet its evaluation remains fragmented. Existing benchmarks largely assess audio and video in isolation or rely on coarse embedding similarity,…
Data incompleteness severely impedes the reliability of multimodal systems. Existing reconstruction methods face distinct bottlenecks: conventional parametric/generative models are prone to hallucinations due to over-reliance on internal…
Open-ended image generation is no longer a simple prompt-to-image problem. High-quality generation often requires an agent to combine a model's internal generative ability with external resources. As requests become more diverse and…
In this paper, we propose XGC-AVis, a multi-agent framework that enhances the audio-video temporal alignment capabilities of multimodal large models (MLLMs) and improves the efficiency of retrieving key video segments through 4 stages:…
Software development is a collaborative endeavor that requires individuals from different departments to work together in order to collectively develop a high-quality software system. In this context, people have begun to explore a method…
Although existing text-to-motion (T2M) methods can produce realistic human motion from text description, it is still difficult to align the generated motion with the desired postures since using text alone is insufficient for precisely…
Referring-based Video Object Segmentation is a multimodal problem that requires producing fine-grained segmentation results guided by external cues. Traditional approaches to this task typically involve training specialized models, which…
Recent advances in video diffusion models shows promise for generating robotic decision-making data, with trajectory conditions further enabling fine-grained control. However, existing methods primarily focus on individual object motion and…
Generating consistent long videos is a complex challenge: while diffusion-based generative models generate visually impressive short clips, extending them to longer durations often leads to memory bottlenecks and long-term inconsistency. In…