109 citations · 318 across the 46 of their papers we have counts for
48 papers
World Tokens: Enhancing Embodied Policies with Training-Time World Modeling
Qu Tang, Benhui Zhuang, Bo Yuan +3
Vision-language-action (VLA) models are a widely adopted paradigm for embodied policies. They excel at efficient closed-loop control but do not explicitly model how physical scenes…
NeuPAT: Neuron-aware Plasticity Allocation Tuning for Language-Preserving MLLMs
Jiayue Jin, Jingwei Zhang, Chen Wang +2
Multimodal expansion of large language models (LLMs) enables new perceptual capabilities but often compromises the language intelligence acquired during pretraining. In this work,…
AtlasVLA: Persistent World-Ego State Modeling for Vision-Language-Action Models
Guiyu Zhao, Longteng Guo, Yanghong Mei +7
While Vision-Language-Action (VLA) models have advanced embodied AI, their fundamentally reactive paradigm severely limits performance in partially observable and long-horizon task…
TimeThink: Reasoning with Time for Video LLMs
Handong Li, Longteng Guo, Zikang Liu +8
Video reasoning requires models to identify and verify temporally localized evidence within long video sequences. Recent Video Large Language Models (Video-LLMs) have shown promisi…
SurveilNav: Collaborative Object Goal Navigation with Robot and Surveillance System
Ming-Ming Yu, Qunbo Wang, Rongtao Xu +5
With the growing deployment of surveillance systems in factories, offices, and homes, integrating them with robots offers a promising direction for collaborative and efficient task…
NavWM: A Unified Navigation World Model for Foresight-Driven Planning
Yanghong Mei, Longteng Guo, Ming-Ming Yu +3
Conventional visual navigation policies often struggle with myopic decision-making and mode collapse in complex environments. While world models offer a promising alternative, exis…
VeriSpace: Spatially Grounded Action Verification for Vision-Language-Action Models
Guiyu Zhao, Longteng Guo, Junyou Zhu +6
Vision-language-action (VLA) models have shown strong promise for robotic manipulation, but their reliability at test time remains limited by one-shot action prediction, where even…
LongSpace: Exploring Long-Horizon Spatial Memory from Perception to Recall in Video
Shiqiang Lang, Jing Liu, Haoyang He +6
Multimodal Large Language Models (MLLMs) have advanced image and video understanding and can increasingly handle longer visual inputs. Long-horizon tasks such as autonomous driving…
Semantic-Enriched Latent Visual Reasoning
Tianrun Xu, Yue Sun, Qixun Wang +8
Multimodal latent-space reasoning aims to replace explicit thinking with images by performing visual reasoning directly in a compact latent space. However, existing approaches larg…
Can MLLMs Reason Beyond Language? VisReason: A Comprehensive Benchmark for Vision-Centric Reasoning
Longteng Guo, Yifan Wang, Pengkang Huo +4
Recent multimodal large language models (MLLMs) achieve strong performance on visual reasoning benchmarks, yet it remains unclear to what extent such performance reflects reasoning…
When Robots Do the Chores: A Benchmark and Agent for Long-Horizon Household Task Execution
Zilin Zhu, Longteng Guo, Yanghong Mei +5
Long-horizon household tasks demand robust high-level planning and sustained reasoning capabilities, which are largely overlooked by existing embodied AI benchmarks that emphasize…
SciVQR: A Multidisciplinary Multimodal Benchmark for Advanced Scientific Reasoning Evaluation
Longteng Guo, Xuanxu Lin, Dongze Hao +5
Scientific reasoning is a key aspect of human intelligence, requiring the integration of multimodal inputs, domain expertise, and multi-step inference across various subjects. Exis…
M-VQA: A Benchmark for Multimodal, Multi-Entity, Multi-Hop Visual Question Answering
Jiatong Ma, Longteng Guo, Yuchen Liu +4
We present M-VQA, a novel knowledge-based Visual Question Answering (VQA) benchmark, to enhance the evaluation of multimodal large language models (MLLMs) in fine-grained multi…
AdaSpark: Adaptive Sparsity for Efficient Long-Video Understanding
Handong Li, Zikang Liu, Longteng Guo +10
Processing long-form videos with Video Large Language Models (Video-LLMs) is computationally prohibitive. Current efficiency methods often compromise fine-grained perception throug…
Thinking in Streaming Video
Zikang Liu, Longteng Guo, Handong Li +7
Real-time understanding of continuous video streams is essential for interactive assistants and multimodal agents operating in dynamic environments. However, most existing video re…
UrbanNav: Learning Language-Guided Urban Navigation from Web-Scale Human Trajectories
Yanghong Mei, Yirong Yang, Longteng Guo +5
Navigating complex urban environments using natural language instructions poses significant challenges for embodied agents, including noisy language instructions, ambiguous spatial…
S1-MMAlign: A Large-Scale, Multi-Disciplinary Dataset for Scientific Figure-Text Understanding
He Wang, Longteng Guo, Pengkang Huo +4
Multimodal learning has revolutionized general domain tasks, yet its application in scientific discovery is hindered by the profound semantic gap between complex scientific imagery…
LaVi: Efficient Large Vision-Language Models via Internal Feature Modulation
Tongtian Yue, Longteng Guo, Yepeng Tang +4
Despite the impressive advancements of Large Vision-Language Models (LVLMs), existing approaches suffer from a fundamental bottleneck: inefficient visual-language integration. Curr…
Prefix Grouper: Efficient GRPO Training through Shared-Prefix Forward
Zikang Liu, Tongtian Yue, Yepeng Tang +5
Group Relative Policy Optimization (GRPO) enhances policy learning by computing gradients from relative comparisons among candidate outputs that share a common input prefix. Despit…
Towards Unified Referring Expression Segmentation Across Omni-Level Visual Target Granularities
Jing Liu, Wenxuan Wang, Yisi Zhang +5
Referring expression segmentation (RES) aims at segmenting the entities' masks that match the descriptive language expression. While traditional RES methods primarily address objec…
Breaking the Encoder Barrier for Seamless Video-Language Understanding
Handong Li, Yiyuan Zhang, Longteng Guo +2
Most Video-Large Language Models (Video-LLMs) adopt an encoder-decoder framework, where a vision encoder extracts frame-wise features for processing by a language model. However, t…
FlexVLN: Flexible Adaptation for Diverse Vision-and-Language Navigation Tasks
Siqi Zhang, Yanyuan Qiao, Qunbo Wang +3
The aspiration of the Vision-and-Language Navigation (VLN) task has long been to develop an embodied agent with robust adaptability, capable of seamlessly transferring its navigati…
Efficient Motion-Aware Video MLLM
Zijia Zhao, Yuqi Huo, Tongtian Yue +5
Most current video MLLMs rely on uniform frame sampling and image-level encoders, resulting in inefficient data processing and limited motion awareness. To address these challenges…
VRoPE: Rotary Position Embedding for Video Large Language Models
Zikang Liu, Longteng Guo, Yepeng Tang +6
Rotary Position Embedding (RoPE) has shown strong performance in text-based Large Language Models (LLMs), but extending it to video remains a challenge due to the intricate spatiot…