10 papers
LiAuto-MindViT: A Hybrid Vision Backbone with Adaptive Bidirectional Mamba
Lifu Mu, Shuai Chen, Wen Zheng +7
While Mamba-based models have shown strong potential for long sequence modeling, adapting them to vision is challenging due to the requirement of local neighborhood correlations an…
ChainSpace: A Chained-Reasoning Paradigm for Spatial Intelligence
Xiaohan Zhang, Feng Gu, Xudong Rao +4
Spatial intelligence requires foundation models to maintain coherent spatial state across interactions with the physical world. However, existing data-centric approaches typically…
LiAuto-GeoX: Efficient Grounded Driving Transformer
Jiawei Lian, Haoyi Sun, Yang Wu +8
Dense 3D reconstruction has demonstrated immense potential for spatial understanding, yet its viability as a real-time, onboard representation for autonomous driving remains an ope…
ERGeoBench:A Comprehensive Benchmark for Embodied Reasoning and Geo-localization in Multimodal Large Language Models
Kaiwen Xue, Tao Wei, Guoxin Zhang +5
Multimodal large language models (MLLMs) have shown strong potential as embodied agents, yet embodied geo-localization remains underexplored due to the lack of fine-grained evaluat…
Evaluating the Search Agent in a Parallel World
Jiawei Chen, Xintian Shen, Lihao Zheng +7
Integrating web search tools has significantly extended the capability of LLMs to address open-world, real-time, and long-tail problems. However, evaluating these Search Agents pre…
CGC: Compositional Grounded Contrast for Fine-Grained Multi-Image Understanding
Lihao Zheng, Zhenwei Shao, Yu Zhou +5
Although Multimodal Large Language Models (MLLMs) have advanced rapidly, they still face notable challenges in fine-grained multi-image understanding, often exhibiting spatial hall…
StreamingClaw Technical Report
Jiawei Chen, Zhe Chen, Chaoqun Du +21
Emerging applications such as embodied intelligence, AI hardware, autonomous driving, and intelligent cockpits rely on a real-time perception-decision-action closed loop, posing st…
Evolving from Tool User to Creator via Training-Free Experience Reuse in Multimodal Reasoning
Xintian Shen, Jiawei Chen, Lihao Zheng +3
Existing Tool-Integrated Reasoning (TIR) models have effectively extended the question-answering capabilities of LLMs by incorporating external tools. However, real-world scenarios…
MindWatcher: Toward Smarter Multimodal Tool-Integrated Reasoning
Jiawei Chen, Xintian Shen, Lihao Zheng +43
Traditional workflow-based agents exhibit limited intelligence when addressing real-world problems requiring tool invocation. Tool-integrated reasoning (TIR) agents capable of auto…
MIRG-RL: Multi-Image Reasoning and Grounding with Reinforcement Learning
Lihao Zheng, Jiawei Chen, Xintian Shen +2
Multi-image reasoning and grounding require understanding complex cross-image relationships at both object levels and image levels. Current Large Visual Language Models (LVLMs) fac…