14 papers
Evidence-RL: Towards Evidence-intensive Visual Reasoning
Haojie Huang, Xinlei Yu, Chengming Xu +6
Vision-Language Models (VLMs) should answer from concrete image evidence rather than language priors, dataset shortcuts, or irrelevant visual context. Existing perception-aware pos…
ToolArtist: Tool-Using Unified Multimodal Models for Agentic Image Generation
Jiahao Zhao, Xiaomin Yu, Zhongxiang Sun +5
Text-to-image (T2I) models can produce visually compelling images, yet they remain limited on open-world tasks that require complex semantic understanding, multi-step reasoning, an…
SPEAR: Selection-aware Personalized End-to-end Adaptive Rewriting and Retrieval for Community Search
Wenbin Wu, Yuzhong Wu, Yufan Xu +4
Query reformulation bridges user intent and retrieval in e-commerce search, yet production systems optimize rewrite quality and retrieval effectiveness separately, leaving the two…
Dual Latent Memory in Vision-Language-Action Models for Robotic Manipulation
Hongyu Qu, Jianzhe Gao, Xiaobin Hu +6
Mainstream Vision-Language-Action (VLA) models predict actions primarily from the current observation under a Markovian assumption, thus struggling with long-horizon, temporally de…
SPOT-E: Test-Time Entropy Shaping with Visual Spotlights for Frozen VLMs
Bo Yin, Xiaobin Hu, Chengming Xu +6
Vision-language models (VLMs) often underperform on evidence intensive tasks because decisive visual evidence are small, localized, and easy to overlook, leading to failures in evi…
Last But Not Least: Boundary Attention CalibratiON for Multimodal KV Cache Compression
Tianhao Chen, Yuheng Wu, Kelu Yao +3
Multimodal Large Language Models (MLLMs) achieve strong vision-language reasoning but incur large KV caches and high decoding latency with long visual contexts. Existing compressio…
TouchThinker: Scaling Tactile Commonsense Reasoning to the Open World with Large-scale Data and Action-aware Representation
Kailin Lyu, Di Wu, Pengwei Zhang +12
Touch is a key modality for embodied agents to understand the physical world. Although recent work has incorporated tactile signals into language systems for tactile commonsense re…
Audio Interaction Model
Zhifei Xie, Zihang Liu, Ze An +8
Audio is continuous and interactive, yet most Large Audio Language Models (LALMs) remain offline and streaming systems usually specialize in ASR or spoken dialogue. We formalize th…
4DThinker: Thinking with 4D Imagery for Dynamic Spatial Understanding
Zhangquan Chen, Manyuan Zhang, Xinlei Yu +9
Dynamic spatial reasoning from monocular video is essential for bridging visual intelligence and the physical world, yet remains challenging for vision-language models (VLMs). Prio…
Anisotropic Modality Align
Xiaomin Yu, Yijiang Li, Yuhui Zhang +8
Training multimodal large language models has long been limited by the scarcity of high-quality paired multimodal data. Recent studies show that the shared representation space of…
SkillGraph: Self-Evolving Multi-Agent Collaboration with Multimodal Graph Topology
Zheng Nie, Ruolin Shen, Xinlei Yu +3
Scaling vision-language models into Visual Multiagent Systems (VMAS) is hindered by two coupled issues. First, communication topologies are fixed before inference, leaving them bli…
The Latent Space: Foundation, Evolution, Mechanism, Ability, and Outlook
Xinlei Yu, Zhangquan Chen, Yongbo He +36
Latent space is rapidly emerging as a native substrate for language-based models. While modern systems are still commonly understood through explicit token-level generation, an inc…
Modality Gap-Driven Subspace Alignment Training Paradigm For Multimodal Large Language Models
Xiaomin Yu, Yi Xin, Yuhui Zhang +12
Despite the success of multimodal contrastive learning in aligning visual and linguistic representations, a persistent geometric anomaly, the Modality Gap, remains: embeddings of d…
Watching, Reasoning, and Searching: A Video Deep Research Benchmark on Open Web for Agentic Video Reasoning
Chengwen Liu, Xiaomin Yu, Zhuoyue Chang +15
In real-world video question answering scenarios, videos often provide only localized visual cues, while verifiable answers are distributed across the open web; models therefore ne…