Related papers: Mora: Enabling Generalist Video Generation via A M…
Retrieval-based multimodal document QA aims to identify and integrate relevant information from visually rich documents with complex multimodal structures. While retrieval-augmented generation (RAG) has shown strong performance in…
Modern human labor is characterized by specialization; we train for years and develop particular tools that allow us to perform well across a variety of tasks. In addition, AI agents have been specialized for domains such as software…
Multimodal large language models (MLLMs) have demonstrated strong capabilities in visual understanding, yet they remain limited in complex, multi-step reasoning that requires deep searching and integrating visual evidence with external…
The spatio-temporal complexity of video data presents significant challenges in tasks such as compression, generation, and inpainting. We present four key contributions to address the challenges of spatiotemporal video processing. First, we…
Web agents, which couple language models with browsing and tool-use capabilities, show promise as open web assistants. Yet progress is increasingly limited by the lack of scalable, process-level supervision. Existing benchmarks are largely…
With the growing demand for short videos and personalized content, automated Video Log (Vlog) generation has become a key direction in multimodal content creation. Existing methods mostly rely on predefined scripts, lacking dynamism and…
Current approaches rely on zero-shot evaluation due to the absence of training data; while proprietary models such as GPT-4 exhibit strong reasoning capabilities, smaller open-source models remain ineffective at complex tool use. To address…
The December 2024 release of OpenAI's Sora, a powerful video generation model driven by natural language prompts, highlights a growing convergence between large language models (LLMs) and video synthesis. As these multimodal systems evolve…
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…
We introduce Audio-Agent, a multimodal framework for audio generation, editing and composition based on text or video inputs. Conventional approaches for text-to-audio (TTA) tasks often make single-pass inferences from text descriptions.…
With the rapid advancements in Large Language Models (LLMs), an increasing number of studies have leveraged LLMs as the cognitive core of agents to address complex task decision-making challenges. Specially, recent research has demonstrated…
Multimodality-to-Multiaudio (MM2MA) generation faces significant challenges in synthesizing diverse and contextually aligned audio types (e.g., sound effects, speech, music, and songs) from multimodal inputs (e.g., video, text, images),…
Code generation aims to produce code that fulfills requirements written in natural languages automatically. Large language Models (LLMs) like ChatGPT have demonstrated promising effectiveness in this area. Nonetheless, these LLMs often fail…
This report presents the approach adopted in the Modelscope-Sora challenge, which focuses on fine-tuning data for video generation models. The challenge evaluates participants' ability to analyze, clean, and generate high-quality datasets…
Despite tremendous progress in dexterous manipulation, current visuomotor policies remain fundamentally limited by two challenges: they struggle to generalize under perceptual or behavioral distribution shifts, and their performance is…
Video generation has been used to generate visual plans for controlling robotic systems. Given an image observation and a language instruction, previous work has generated video plans which are then converted to robot controls to be…
The Mixture-of-Agents (MoA) framework has shown promise in improving large language model (LLM) performance by aggregating outputs from multiple agents. However, existing MoA systems often rely on static routers that do not fully capture…
Existing multi-object image generation methods face difficulties in achieving precise alignment between localized image generation regions and their corresponding semantics based on language descriptions, frequently resulting in…
Video generation models have achieved remarkable progress in the past year. The quality of AI video continues to improve, but at the cost of larger model size, increased data quantity, and greater demand for training compute. In this…
Existing video generation models predominantly emphasize appearance fidelity while exhibiting limited ability to synthesize complex human motions, such as whole-body movements, long-range dynamics, and fine-grained human-environment…