93 citations · 279 across the 46 of their papers we have counts for
51 papers
SolarWM: Open Data and Scalable Training for Long-Horizon Video World Models
Junchao Huang, Guian Fang, Shengju Qian +15
We introduce SolarWM, a fully open foundation for building interactive video world models from data preparation through long-horizon inference. Training across heterogeneous data s…
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…
Reinforcing Dual-Path Reasoning in Spatial Vision Language Models
Yatai Ji, An-Chieh Cheng, Yang Fu +13
Spatial VLMs have made substantial progress in geometric perception, yet complex spatial reasoning requiring multi-step inference over depth, distance, and scene relations remains…
LongLive-RAG: A General Retrieval-Augmented Framework for Long Video Generation
Qixin Hu, Shuai Yang, Wei Huang +2
Autoregressive (AR) video diffusion enables variable-length synthesis, but long-horizon generation often suffers from accumulated errors and identity drift. For efficiency, existin…
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…
Smaller Models are Natural Explorers for Policy-Level Diversity in GRPO
Yiran Xu, Yiming Ren, Zicheng Lin +8
We identify a new dimension for enhancing rollout diversity in Group Relative Policy Optimization (GRPO) for LLMs. While GRPO relies on diverse rollouts, prevailing strategies prim…
SpatialEdit: Benchmarking Fine-Grained Image Spatial Editing
Yicheng Xiao, Wenhu Zhang, Lin Song +10
Image spatial editing performs geometry-driven transformations, allowing precise control over object layout and camera viewpoints. Current models are insufficient for fine-grained…
TriAttention: Efficient Long Reasoning with Trigonometric KV Compression
Weian Mao, Xi Lin, Wei Huang +5
Extended reasoning in large language models (LLMs) creates severe KV cache memory bottlenecks. Leading KV cache compression methods estimate KV importance using attention scores fr…
Harli: SLO-Aware Co-location of LLM Inference and PEFT-based Finetuning on Model-as-a-Service Platforms
Ao Xu, Han Zhao, Weihao Cui +7
Large language models (LLMs) are increasingly deployed under the Model-as-a-Service (MaaS) paradigm. To meet stringent quality-of-service (QoS) requirements, existing LLM serving s…
OmniVinci: Enhancing Architecture and Data for Omni-Modal Understanding LLM
Hanrong Ye, Chao-Han Huck Yang, Arushi Goel +29
Advancing machine intelligence requires developing the ability to perceive across multiple modalities, much as humans sense the world. We introduce OmniVinci, an initiative to buil…
SparseVILA: Decoupling Visual Sparsity for Efficient VLM Inference
Samir Khaki, Junxian Guo, Jiaming Tang +6
Vision Language Models (VLMs) have rapidly advanced in integrating visual and textual reasoning, powering applications across high-resolution image understanding, long-video analys…
QeRL: Beyond Efficiency -- Quantization-enhanced Reinforcement Learning for LLMs
Wei Huang, Yi Ge, Shuai Yang +11
We propose QeRL, a Quantization-enhanced Reinforcement Learning framework for large language models (LLMs). While RL is essential for LLMs' reasoning capabilities, it is resource-i…
MC#: Mixture Compressor for Mixture-of-Experts Large Models
Wei Huang, Yue Liao, Yukang Chen +6
Mixture-of-Experts (MoE) effectively scales large language models (LLMs) and vision-language models (VLMs) by increasing capacity through sparse activation. However, preloading all…
SANA-Video: Efficient Video Generation with Block Linear Diffusion Transformer
Junsong Chen, Yuyang Zhao, Jincheng Yu +17
We introduce SANA-Video, a small diffusion model that can efficiently generate videos up to 720x1280 resolution and minute-length duration. SANA-Video synthesizes high-resolution,…
StreamingVLM: Real-Time Understanding for Infinite Video Streams
Ruyi Xu, Guangxuan Xiao, Yukang Chen +3
Vision-language models (VLMs) could power real-time assistants and autonomous agents, but they face a critical challenge: understanding near-infinite video streams without escalati…
3D Aware Region Prompted Vision Language Model
An-Chieh Cheng, Yang Fu, Yukang Chen +10
We present Spatial Region 3D (SR-3D) aware vision-language model that connects single-view 2D images and multi-view 3D data through a shared visual token space. SR-3D supports flex…
TTS-VAR: A Test-Time Scaling Framework for Visual Auto-Regressive Generation
Zhekai Chen, Ruihang Chu, Yukang Chen +4
Scaling visual generation models is essential for real-world content creation, yet requires substantial training and computational expenses. Alternatively, test-time scaling has ga…
Scaling RL to Long Videos
Yukang Chen, Wei Huang, Baifeng Shi +11
We introduce a full-stack framework that scales up reasoning in vision-language models (VLMs) to long videos, leveraging reinforcement learning. We address the unique challenges of…
MindOmni: Unleashing Reasoning Generation in Vision Language Models with RGPO
Yicheng Xiao, Lin Song, Yukang Chen +7
Recent text-to-image systems face limitations in handling multimodal inputs and complex reasoning tasks. We introduce MindOmni, a unified multimodal large language model that addre…
TraveLLaMA: A Multimodal Travel Assistant with Large-Scale Dataset and Structured Reasoning
Meng Chu, Yukang Chen, Haokun Gui +3
Tourism and travel planning increasingly rely on digital assistance, yet existing multimodal AI systems often lack specialized knowledge and contextual understanding of urban envir…
Towards High-Goodput LLM Serving with Prefill-decode Multiplexing
Yukang Chen, Weihao Cui, Han Zhao +7
Large Language Model (LLM) serving must meet stringent Service Level Objectives (SLOs) for both the prefill and decode phases. Some existing solutions disaggregate the two phases,…
WorldModelBench: Judging Video Generation Models As World Models
Dacheng Li, Yunhao Fang, Yukang Chen +10
Video generation models have rapidly progressed, positioning themselves as video world models capable of supporting decision-making applications like robotics and autonomous drivin…
Lyra: An Efficient and Speech-Centric Framework for Omni-Cognition
Zhisheng Zhong, Chengyao Wang, Yuqi Liu +12
As Multi-modal Large Language Models (MLLMs) evolve, expanding beyond single-domain capabilities is essential to meet the demands for more versatile and efficient AI. However, prev…
NVILA: Efficient Frontier Visual Language Models
Zhijian Liu, Ligeng Zhu, Baifeng Shi +24
Visual language models (VLMs) have made significant advances in accuracy in recent years. However, their efficiency has received much less attention. This paper introduces NVILA, a…