16 papers
Towards a Systematic Study of Embodied System 2 over Full Task Execution Cycles
Yuxi Wei, Ye Fang, Shuai Yang +3
An embodied brain, or System 2, must turn an abstract goal into actions while discovering relevant scene conditions and checking whether executed skills achieved their intended eff…
Widespread steep X-ray spectra of luminous quasars and their implications for future X-ray surveys
A. Tortosa, L. Zappacosta, E. Piconcelli +54
Luminous quasars (QSOs) at the Epoch of Reionization (EoR, ) host billion-solar-mass black holes assembled within the first Gyr of cosmic time. Their X-ray emission prob…
D-VLA: Dual-Memory Dual-Frequency Vision-Language-Action Model For Long Dynamic Manipulation
Zijian Ye, Chengqi Wei, Wei Huang +9
Long-horizon manipulation requires robots to remember cues that are no longer in view while responding to moving objects. Yet vision-language-action (VLA) policies often rely on th…
Aero Realtime: Fully Aligned Input-Output Streams for Low-Latency Streaming Multimodal Generation
Kaichen Zhang, Wei Huang, Keming Wu +2
Existing streaming multimodal models process observations incrementally but still follow a turn-based prefill-then-decode pattern, making them non-duplex: new observations cannot n…
JoyAI-Video-Edit: Real-Time Open-Ended Video Editing with Autoregressive Diffusion
Yicheng Xiao, Wenxun Dai, Xinran Qin +22
Real-time video editing requires low-latency causal generation with bounded computational resources while preserving source fidelity and long-term temporal consistency. We present…
Is This Edit Correct? A Multi-Dimensional Benchmark for Reasoning-Aware Image Editing
Yixuan Ding, Wei Huang, Ruijie Quan +2
Diffusion-based image editing has achieved strong visual fidelity under natural language instructions, yet most existing systems still operate at the level of surface instruction f…
Veda: Scalable Video Diffusion via Distilled Sparse Attention
Shihao Han, Hao Yang, Xinting Hu +3
Scaling Diffusion Transformers to generate high-resolution, long videos is constrained by the quadratic cost of self-attention, and existing sparse attention methods degrade under…
ParaVT: Taming the Tool Prior Paradox for Parallel Tool Use in Agentic Video Reinforcement Learning
Zuhao Yang, Kaichen Zhang, Sudong Wang +7
Training large multimodal models (LMMs) via reinforcement learning (RL) to natively invoke video-processing tools (e.g., cropping) has become a promising route to long-video unders…
LongLive-2.0: An NVFP4 Parallel Infrastructure for Long Video Generation
Yukang Chen, Luozhou Wang, Wei Huang +13
We present LongLive-2.0, an NVFP4-based parallel infrastructure throughout the full training and inference workflow of long video generation, addressing speed and memory bottleneck…
Vision Foundation Models as Generalist Tokenizers for Image Generation
Anlin Zheng, Qi Han, Xin Wen +5
In this work, we explore the largely unexplored direction of building a generalist image tokenizer directly on top of a frozen vision foundation model (VFM). To build this tokenize…
Visual Generation in the New Era: An Evolution from Atomic Mapping to Agentic World Modeling
Keming Wu, Zuhao Yang, Kaichen Zhang +24
Recent visual generation models have made major progress in photorealism, typography, instruction following, and interactive editing, yet they still struggle with spatial reasoning…
Hita: Holistic Tokenizer for Autoregressive Image Generation
Anlin Zheng, Haochen Wang, Yucheng Zhao +4
Vanilla autoregressive image generation models generate visual tokens step-by-step, limiting their ability to capture holistic relationships among token sequences. Moreover, becaus…
Vision Foundation Models as Effective Visual Tokenizers for Autoregressive Image Generation
Anlin Zheng, Xin Wen, Xuanyang Zhang +5
In this work, we present a novel direction to build an image tokenizer directly on top of a frozen vision foundation model, which is a largely underexplored area. Specifically, we…
DiST-4D: Disentangled Spatiotemporal Diffusion with Metric Depth for 4D Driving Scene Generation
Jiazhe Guo, Yikang Ding, Xiwu Chen +8
Current generative models struggle to synthesize dynamic 4D driving scenes that simultaneously support temporal extrapolation and spatial novel view synthesis (NVS) without per-sce…
MuDG: Taming Multi-modal Diffusion with Gaussian Splatting for Urban Scene Reconstruction
Yingshuang Zou, Yikang Ding, Chuanrui Zhang +6
Recent breakthroughs in radiance fields have significantly advanced 3D scene reconstruction and novel view synthesis (NVS) in autonomous driving. Nevertheless, critical limitations…
UniScene: Unified Occupancy-centric Driving Scene Generation
Bohan Li, Jiazhe Guo, Hongsi Liu +14
Generating high-fidelity, controllable, and annotated training data is critical for autonomous driving. Existing methods typically generate a single data form directly from a coars…