18 papers
Unlocking Token Rewards via Training-Free Reward Attribution
Sitong Wu, Haoru Tan, Bin Xia +6
In this paper, we propose an extremely efficient, training-free method to extract token-level reward signals directly from an existing deep reward model. Our core idea is to attrib…
WorldLine: Action-Driven Visual Simulation for Robotic Manipulation
Shenghe Zheng, Wenbo Li, Jiyao Zhang +4
Real-world robot learning is constrained by the cost of collecting experience and evaluating candidate behaviors. Video generation models offer a scalable foundation for visual sim…
UnityShots: Memory-Driven Multi-Shot Audio-Video Generation with Boundary-Aware Gating
Jiehui Huang, Yuechen Zhang, Bin Xia +7
Generating a coherent multi-shot video requires structured cross-shot memory. Subject appearance, scene context, and speaker identity must persist across cuts. Existing approaches…
Agentic World Modeling: Foundations, Capabilities, Laws, and Beyond
Meng Chu, Xuan Billy Zhang, Kevin Qinghong Lin +47
As AI systems move from generating text to accomplishing goals through sustained interaction, the ability to model environment dynamics becomes a central bottleneck. Agents that ma…
DreamShot: Personalized Storyboard Synthesis with Video Diffusion Prior
Junjia Huang, Binbin Yang, Pengxiang Yan +6
Storyboard synthesis plays a crucial role in visual storytelling, aiming to generate coherent shot sequences that visually narrate cinematic events with consistent characters, scen…
IndexTTS 2.5 Technical Report
Yunpei Li, Xun Zhou, Jinchao Wang +11
In prior work, we introduced IndexTTS 2, a zero-shot neural text-to-speech foundation model comprising two core components: a transformer-based Text-to-Semantic (T2S) module and a…
Index-ASR Technical Report
Zheshu Song, Lu Wang, Wei Deng +3
Automatic speech recognition (ASR) has witnessed remarkable progress in recent years, largely driven by the emergence of LLM-based ASR paradigm. Despite their strong performance on…
Wan-Move: Motion-controllable Video Generation via Latent Trajectory Guidance
Ruihang Chu, Yefei He, Zhekai Chen +10
We present Wan-Move, a simple and scalable framework that brings motion control to video generative models. Existing motion-controllable methods typically suffer from coarse contro…
UnityVideo: Unified Multi-Modal Multi-Task Learning for Enhancing World-Aware Video Generation
Jiehui Huang, Yuechen Zhang, Xu He +7
Recent video generation models demonstrate impressive synthesis capabilities but remain limited by single-modality conditioning, constraining their holistic world understanding. Th…
DreamOmni3: Scribble-based Editing and Generation
Bin Xia, Bohao Peng, Jiyang Liu +8
Recently unified generation and editing models have achieved remarkable success with their impressive performance. These models rely mainly on text prompts for instruction-based ed…
DreamOmni2: Multimodal Instruction-based Editing and Generation
Bin Xia, Bohao Peng, Yuechen Zhang +10
Recent advancements in instruction-based image editing and subject-driven generation have garnered significant attention, yet both tasks still face limitations in meeting practical…
MGM-Omni: Scaling Omni LLMs to Personalized Long-Horizon Speech
Chengyao Wang, Zhisheng Zhong, Bohao Peng +7
We present MGM-Omni, a unified Omni LLM for omni-modal understanding and expressive, long-horizon speech generation. Unlike cascaded pipelines that isolate speech synthesis, MGM-Om…
DreamVE: Unified Instruction-based Image and Video Editing
Bin Xia, Jiyang Liu, Yuechen Zhang +6
Instruction-based editing holds vast potential due to its simple and efficient interactive editing format. However, instruction-based editing, particularly for video, has been cons…
Training-Free Efficient Video Generation via Dynamic Token Carving
Yuechen Zhang, Jinbo Xing, Bin Xia +6
Despite the remarkable generation quality of video Diffusion Transformer (DiT) models, their practical deployment is severely hindered by extensive computational requirements. This…
MagicMirror: ID-Preserved Video Generation in Video Diffusion Transformers
Yuechen Zhang, Yaoyang Liu, Bin Xia +4
We present MagicMirror, a framework for generating identity-preserved videos with cinematic-level quality and dynamic motion. While recent advances in video diffusion models have s…
DreamOmni: Unified Image Generation and Editing
Bin Xia, Yuechen Zhang, Jingyao Li +5
Currently, the success of large language models (LLMs) illustrates that a unified multitasking approach can significantly enhance model usability, streamline deployment, and foster…
MoTCoder: Elevating Large Language Models with Modular of Thought for Challenging Programming Tasks
Jingyao Li, Pengguang Chen, Bin Xia +2
Large Language Models (LLMs) have showcased impressive capabilities in handling straightforward programming tasks. However, their performance tends to falter when confronted with m…
LLMGA: Multimodal Large Language Model based Generation Assistant
Bin Xia, Shiyin Wang, Yingfan Tao +2
In this paper, we introduce a Multimodal Large Language Model-based Generation Assistant (LLMGA), leveraging the vast reservoir of knowledge and proficiency in reasoning, comprehen…