20 citations · 39 across the 46 of their papers we have counts for
54 papers
AVC-Reward: Event-Centric Audio-Video Consistency Evaluation
Yuruo Wu, Kaihang Pan, Kai Shen +6
As joint audio-video generation models become more capable, they can generate audio-visual scenes exhibiting three forms of complexity: multi-event composition, multi-layer audio m…
Beyond the Remembered World: Predictive 4D Belief for Persistent Navigation in Evolving Worlds
Mingjian Gao, Zhaocheng Li, Haoyang Huang +7
Persistent spatial memory enables embodied agents to navigate familiar environments across repeated visits. However, targets may move while unobserved, including during navigation,…
RoboSPA: Can VLA Models Go Beyond Simple Scenes and Short-Horizon Tasks?
Zhenxuan Fan, Bo Zhang, Yutong Lin +9
Vision-Language-Action (VLA) models have shown promising progress in language-conditioned robotic manipulation. However, existing datasets and benchmarks mainly evaluate task compl…
Iron: Intent-Aligned and Retrospective Dual Learning Framework for Enhancing Generalist Virtual Agents
Jiahe Ying, Wendong Bu, Kaihang Pan +6
Achieving virtual agents capable of automating tasks across diverse digital environments remains a pivotal challenge in Embodied AI. While Multimodal Large Language Models (MLLMs)…
UniPhysGen: Unified Physical Grounding for Simulation-Ready 3D Assets
Xian Li, Rong Wei, Lujie Yang +6
Physically grounded 3D assets are increasingly important for embodied AI and robotic simulation. However, most existing 3D assets lack unified physical semantics, including articul…
SCOPE: Evolving Symbolic World for Planning in Open-Ended Environments
Yundaichuan Zhan, Minghe Gao, Zhongqi Yue +7
Recent works have explored integrating Vision-Language Models (VLMs) with classical planners that rely on symbolic representations of planning problems to generate long-horizon pla…
InstructSAM: Segment Any Instance with Any Instructions
Yuqian Yuan, Wentong Li, Zhaocheng Li +6
In this paper, we introduce InstructSAM, a unified and streamlined framework designed for multi-instance segmentation under arbitrary instructions. We formulates instruction-driven…
Learning to Adapt: Self-Improving Web Agent via Cognitive-Aware Exploration
Weile Chen, Bingchen Miao, Qifan Yu +6
Recent advances in Multimodal Large Language Models (MLLMs) have led to promising progress in web agents. However, existing web agents often rely on handcrafted execution pipelines…
VisualThink-VLA: Visual Intermediate Reasoning for Effective and Low-Latency Vision-Language-Action Policies
Mingjian Gao, Wenqiao Zhang, Yuqian Yuan +9
Recent work has begun to equip vision-language-action (VLA) policies with explicit intermediate reasoning. In embodied control, however, textual chain-of-thought is a poor fit: irr…
CrossView Suite: Harnessing Cross-view Spatial Intelligence of MLLMs with Dataset, Model and Benchmark
Wei Wang, Yuqian Yuan, Tianwei Lin +4
Spatial intelligence requires multimodal large language models (MLLMs) to move beyond single-view perception and reason consistently about objects, visibility, geometry, and intera…
BELIEF: Structured Evidence Modeling and Uncertainty-Aware Fusion for Biomedical Question Answering
Chang Zong, Hao Ning, Siliang Tang +2
Biomedical question answering often requires decisions from retrieved literature whose relevance, quality, and support for candidate answers are uneven. Most retrieval-augmented la…
SpatialFusion: Endowing Unified Image Generation with Intrinsic 3D Geometric Awareness
Haiyi Qiu, Kaihang Pan, Jiacheng Li +3
Recent unified image generation models have achieved remarkable success by employing MLLMs for semantic understanding and diffusion backbones for image generation. However, these m…
OmniWeaving: Towards Unified Video Generation with Free-form Composition and Reasoning
Kaihang Pan, Qi Tian, Jianwei Zhang +12
While proprietary systems such as Seedance-2.0 have achieved remarkable success in omni-capable video generation, the academic research community lags far behind: most of its model…
CoMoL: Efficient Mixture of LoRA Experts via Dynamic Core Space Merging
Jie Cao, Zhenxuan Fan, Zhuonan Wang +8
Large language models (LLMs) achieve remarkable performance on diverse downstream and domain-specific tasks via parameter-efficient fine-tuning (PEFT). However, existing PEFT metho…
Draft-Thinking: Learning Efficient Reasoning in Long Chain-of-Thought LLMs
Jie Cao, Tianwei Lin, Zhenxuan Fan +7
Long chain-of-thought~(CoT) reasoning improves the problem-solving capability of large reasoning models~(LRMs), but often incurs substantial inference cost and overthinking. Existi…
CORE: Code-based Inverse Self-Training Framework with Graph Expansion for Virtual Agents
Keyu Wang, Bingchen Miao, Wendong Bu +7
The development of Multimodal Virtual Agents has made significant progress through the integration of Multimodal Large Language Models. However, mainstream training paradigms face…
OmniMoGen: Unifying Human Motion Generation via Learning from Interleaved Text-Motion Instructions
Wendong Bu, Kaihang Pan, Yuze Lin +6
Large language models (LLMs) have unified diverse linguistic tasks within a single framework, yet such unification remains unexplored in human motion generation. Existing methods a…
WiseEdit: Benchmarking Cognition- and Creativity-Informed Image Editing
Kaihang Pan, Weile Chen, Haiyi Qiu +6
Recent image editing models boast next-level intelligent capabilities, facilitating cognition- and creativity-informed image editing. Yet, existing benchmarks provide too narrow a…
Arcadia: Toward a Full-Lifecycle Framework for Embodied Lifelong Learning
Minghe Gao, Juncheng Li, Yuze Lin +15
We contend that embodied learning is fundamentally a lifecycle problem rather than a single-stage optimization. Systems that optimize only one link (data collection, simulation, le…
WEAVE: Unleashing and Benchmarking the In-context Interleaved Comprehension and Generation
Wei Chow, Jiachun Pan, Yongyuan Liang +10
Recent advances in unified multimodal models (UMMs) have enabled impressive progress in visual comprehension and generation. However, existing datasets and benchmarks focus primari…
Towards Physically Executable 3D Gaussian for Embodied Navigation
Bingchen Miao, Rong Wei, Zhiqi Ge +8
3D Gaussian Splatting (3DGS), a 3D representation method with photorealistic real-time rendering capabilities, is regarded as an effective tool for narrowing the sim-to-real gap. H…
Fast Thinking for Large Language Models
Haoyu Zheng, Zhuonan Wang, Yuqian Yuan +7
Reasoning-oriented Large Language Models (LLMs) often rely on generating explicit tokens step by step, and their effectiveness typically hinges on large-scale supervised fine-tunin…
Towards Meta-Cognitive Knowledge Editing for Multimodal LLMs
Zhaoyu Fan, Kaihang Pan, Mingze Zhou +7
Knowledge editing enables multimodal large language models (MLLMs) to efficiently update outdated or incorrect information. However, existing benchmarks primarily emphasize cogniti…
Graft: Integrating the Domain Knowledge via Efficient Parameter Synergy for MLLMs
Yang Dai, Jianxiang An, Tianwei Lin +6
Multimodal Large Language Models (MLLMs) have achieved success across various domains. However, their applicability tends to degrade when confronted with different types of data in…