6 citations · 8 across the 19 of their papers we have counts for
25 papers
Orbia: Do Generated Videos Form a Consistent 3D World?
Dongyue Lu, Guian Fang, Hur Lim +20
Video generators serve as interactive worlds for exploration and simulation, yet realistic and visually appealing frames do not necessarily depict a consistent 3D world. Existing b…
RAR: Rate-Adaptive Rollout for Time-Consistent Interactive World Models
Yaoyang Liu, Dongyu Yan, Yihua Du +5
Video-based interactive world models aim to enable real-time, user-controllable environments. Yet most existing systems are trained and rolled out at a fixed temporal rate, limitin…
Remembering What Matters for Long-Horizon Robotic World Models
Hao Wu, Tianyu Shao, Shengju Qian +10
Autoregressive robot video world models based on discrete visual tokens remain unreliable over long rollout horizons. Retaining the entire generated history does not necessarily im…
FutureWorlds: Learning Robotic World Models from Alternative Futures
Hao Wu, Shengju Qian, Weiyan Wang +5
Robotic world models predict action-conditioned future scenes, providing a foundation for understanding action outcomes. However, turning alternative predictions into useful learni…
RAGCell: Retrieval-Augmented Generation as Supervision for Versatile Single-cell Analysis
Tianyu Liu, Fan Zhang, Jiayuan Chen +10
Single-cell foundation models (scFMs) are transforming computational biology by enabling generalizable, task-agnostic representations for versatile single-cell analysis. Despite th…
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…
CoverPrune: Coverage-Driven Token Pruning for 3D VLMs via Optimal Transport
Peng Ling, Yingda Yin, Lingting Zhu +5
While 3D Vision-Language Models (3D VLMs) have demonstrated remarkable spatial reasoning capabilities, they suffer from massive visual token counts that create severe computational…
MemVLN: Episodic and Procedural Memory for Vision-and-Language Navigation
Yuqi Liu, Shengju Qian, Tianyuan Qu +5
Vision-and-Language Navigation in Continuous Environments (VLN-CE) requires agents to maintain long-horizon visual history for trajectory consistency while executing actions with l…
Orchestra-o1: Omnimodal Agent Orchestration
Fan Zhang, Vireo Zhang, Shengju Qian +8
The recent success of agent swarms has shifted the paradigm of large language model (LLM)-based agents from single-agent workflows to multi-agent systems, highlighting the importan…
OmniGameArena: A Unified UE5 Benchmark for VLM Game Agents with Improvement Dynamics
Mingxian Lin, Shengju Qian, Yuqi Liu +9
Vision-language model (VLM) agents are increasingly deployed in interactive game environments. Yet game benchmarks for VLM agents typically report a single first-attempt score per…
Policy and World Modeling Co-Training for Language Agents
Ning Lu, Baijiong Lin, Shengcai Liu +9
Reinforcement learning (RL) improves large language model (LLM) agents by teaching them which actions lead to high rewards, but provides little supervision on what those actions do…
On-Policy Adversarial Flow Distillation for Autoregressive Video Generation
Yang Luo, Shengju Qian, Xiaohang Tang +4
Autoregressive video generators are attractive for streaming, long-horizon, and interactive applications, but distilling strong black-box teachers into causal students remains diff…
SAP: Segment Any 4K Panorama
Lutao Jiang, Zidong Cao, Weikai Chen +14
Promptable instance segmentation is widely adopted in embodied and AR systems, yet the performance of foundation models trained on perspective imagery often degrades on 360° panora…
CoSMo3D: Open-World Promptable 3D Semantic Part Segmentation through LLM-Guided Canonical Spatial Modeling
Li Jin, Weikai Chen, Yujie Wang +7
Open-world promptable 3D semantic segmentation remains brittle as semantics are inferred in the input sensor coordinates. Yet, humans, in contrast, interpret parts via functional r…
AssetFormer: Modular 3D Assets Generation with Autoregressive Transformer
Lingting Zhu, Shengju Qian, Haidi Fan +6
The digital industry demands high-quality, diverse modular 3D assets, especially for user-generated content~(UGC). In this work, we introduce AssetFormer, an autoregressive Transfo…
ReVSeg: Incentivizing the Reasoning Chain for Video Segmentation with Reinforcement Learning
Yifan Li, Yingda Yin, Lingting Zhu +4
Reasoning-centric video object segmentation is an inherently complex task: the query often refers to dynamics, causality, and temporal interactions, rather than static appearances.…
V-ReasonBench: Toward Unified Reasoning Benchmark Suite for Video Generation Models
Yang Luo, Xuanlei Zhao, Baijiong Lin +7
Recent progress in generative video models, such as Veo-3, has shown surprising zero-shot reasoning abilities, creating a growing need for systematic and reliable evaluation. We in…
Rethinking Facial Expression Recognition in the Era of Multimodal Large Language Models: Benchmark, Datasets, and Beyond
Fan Zhang, Haoxuan Li, Shengju Qian +9
Multimodal Large Language Models (MLLMs) have revolutionized numerous research fields, including computer vision and affective computing. As a pivotal challenge in this interdiscip…
Light-SQ: Structure-aware Shape Abstraction with Superquadrics for Generated Meshes
Yuhan Wang, Weikai Chen, Zeyu Hu +19
In user-generated-content (UGC) applications, non-expert users often rely on image-to-3D generative models to create 3D assets. In this context, primitive-based shape abstraction o…
EmbRACE-3K: Embodied Reasoning and Action in Complex Environments
Mingxian Lin, Wei Huang, Yitang Li +6
Recent advanced vision-language models(VLMs) have demonstrated strong performance on passive, offline image and video understanding tasks. However, their effectiveness in embodied…
StyleAR: Customizing Multimodal Autoregressive Model for Style-Aligned Text-to-Image Generation
Yi Wu, Lingting Zhu, Shengju Qian +4
In the current research landscape, multimodal autoregressive (AR) models have shown exceptional capabilities across various domains, including visual understanding and generation.…
MAR-3D: Progressive Masked Auto-regressor for High-Resolution 3D Generation
Jinnan Chen, Lingting Zhu, Zeyu Hu +4
Recent advances in auto-regressive transformers have revolutionized generative modeling across different domains, from language processing to visual generation, demonstrating remar…
MuMA: 3D PBR Texturing via Multi-Channel Multi-View Generation and Agentic Post-Processing
Lingting Zhu, Jingrui Ye, Runze Zhang +8
Current methods for 3D generation still fall short in physically based rendering (PBR) texturing, primarily due to limited data and challenges in modeling multi-channel materials.…
Text-Animator: Controllable Visual Text Video Generation
Lin Liu, Quande Liu, Shengju Qian +5
Video generation is a challenging yet pivotal task in various industries, such as gaming, e-commerce, and advertising. One significant unresolved aspect within T2V is the effective…