25 papers
Is This Your Agent? Identity Watermarking for Agent Systems in Dynamic Environments
Yuwei Zhong, Yu Cheng, Jiuan Zhou +5
Agent systems deployed in dynamic environments continuously update their memories, skills, and runtime configurations, leading to evolving trajectories and challenges for persisten…
SafeCoEvo: Co-Evolving Safety Harnesses and Guards for LLM Agents at Test-Time
Yu Cheng, Yongkang Hu, Shuaijie Ma +12
LLM agents deployed in real-world environments continually encounter new tasks and safety risks, while execution feedback typically becomes available only after each task is comple…
HarnessX: A Composable, Adaptive, and Evolvable Agent Harness Foundry
Tingyang Chen, Shuo Lu, Kang Zhao +11
AI agent performance depends critically on the runtime harness, comprising the prompts, tools, memory, and control flow that mediate how a model observes, reasons, and acts. Yet to…
VideoSearcher: Empowering Video Deep Research with Multi-Tool Agentic Reasoning via Reinforcement Learning
Zhenkun Gao, Yicheng Bao, Jinlong Peng +13
Video understanding is moving beyond closed-context perception toward open-world evidence exploration, a paradigm formalized as Video Deep Research (VDR). However, existing multimo…
GSCompleter: A Distillation-Free Plugin for Metric-Aware 3D Gaussian Splatting Completion in Seconds
Ao Gao, Jingyu Gong, Xin Tan +3
3D Gaussian Splatting (3DGS) has revolutionized high-fidelity neural rendering with its explicit representation and efficiency. However, reconstructing scenes from sparse viewpoint…
World2Minecraft: Occupancy-Driven Simulated Scenes Construction
Lechao Zhang, Haoran Xu, Jingyu Gong +3
Embodied intelligence requires high-fidelity simulation environments to support perception and decision-making, yet existing platforms often suffer from data contamination and limi…
ProMMSearchAgent: A Generalizable Multimodal Search Agent Trained with Process-Oriented Rewards
Wentao Yan, Shengqin Wang, Huichi Zhou +4
Training multimodal agents via reinforcement learning for knowledge-intensive visual reasoning is fundamentally hindered by the extreme sparsity of outcome-based supervision and th…
DR-MMSearchAgent: Deepening Reasoning in Multimodal Search Agents
Shengqin Wang, Wentao Yan, Huichi Zhou +4
Agentic multimodal models have garnered significant attention for their ability to leverage external tools to tackle complex tasks. However, it is observed that such agents often m…
Memory Intelligence Agent
Jingyang Qiao, Weicheng Meng, Yu Cheng +6
Deep research agents (DRAs) integrate LLM reasoning with external tools. Memory systems enable DRAs to leverage historical experiences, which are essential for efficient reasoning…
DiPO: Disentangled Perplexity Policy Optimization for Fine-grained Exploration-Exploitation Trade-Off
Xiaofan Li, Ming Yang, Zhiyuan Ma +9
Reinforcement Learning with Verifiable Rewards (RLVR) has catalyzed significant advances in the reasoning capabilities of Large Language Models (LLMs). However, effectively managin…
DailyArt: Discovering Articulation from Single Static Images via Latent Dynamics
Hang Zhang, Qijian Tian, Jingyu Gong +4
Articulated objects are essential for embodied AI and world models, yet inferring their kinematics from a single closed-state image remains challenging because crucial motion cues…
Direct Segmentation without Logits Optimization for Training-Free Open-Vocabulary Semantic Segmentation
Jiahao Li, Yang Lu, Yachao Zhang +3
Open-vocabulary semantic segmentation (OVSS) aims to segment arbitrary category regions in images using open-vocabulary prompts, necessitating that existing methods possess pixel-l…
PC-CrossDiff: Point-Cluster Dual-Level Cross-Modal Differential Attention for Unified 3D Referring and Segmentation
Wenbin Tan, Jiawen Lin, Fangyong Wang +4
3D Visual Grounding (3DVG) aims to localize the referent of natural language referring expressions through two core tasks: Referring Expression Comprehension (3DREC) and Segmentati…
S2GS: Streaming Semantic Gaussian Splatting for Online Scene Understanding and Reconstruction
Renhe Zhang, Yuyang Tan, Jingyu Gong +4
Existing offline feed-forward methods for joint scene understanding and reconstruction on long image streams often repeatedly perform global computation over an ever-growing set of…
Zero-Shot Robotic Manipulation via 3D Gaussian Splatting-Enhanced Multimodal Retrieval-Augmented Generation
Zilong Xie, Jingyu Gong, Xin Tan +2
Existing end-to-end approaches of robotic manipulation often lack generalization to unseen objects or tasks due to limited data and poor interpretability. While recent Multimodal L…
TPRU: Advancing Temporal and Procedural Understanding in Large Multimodal Models
Zhenkun Gao, Xuhong Wang, Xin Tan +1
Multimodal Large Language Models (MLLMs), particularly smaller, deployable variants, exhibit a critical deficiency in understanding temporal and procedural visual data, a bottlenec…
Camera-Aware Cross-View Alignment for Referring 3D Gaussian Splatting Segmentation
Yuwen Tao, Kanglei Zhou, Xin Tan +1
Referring 3D Gaussian Splatting Segmentation (R3DGS) aims to ground free-form language queries in 3D Gaussian fields. However, existing methods rely on single-view pseudo supervisi…
Switchable Token-Specific Codebook Quantization For Face Image Compression
Yongbo Wang, Haonan Wang, Guodong Mu +7
With the ever-increasing volume of visual data, the efficient and lossless transmission, along with its subsequent interpretation and understanding, has become a critical bottlenec…
CompassNav: Steering From Path Imitation To Decision Understanding In Navigation
LinFeng Li, Jian Zhao, Yuan Xie +2
The dominant paradigm for training Large Vision-Language Models (LVLMs) in navigation relies on imitating expert trajectories. This approach reduces the complex navigation task to…
T2S: Tokenized Skill Scaling for Lifelong Imitation Learning
Hongquan Zhang, Jingyu Gong, Zhizhong Zhang +3
The main challenge in lifelong imitation learning lies in the balance between mitigating catastrophic forgetting of previous skills while maintaining sufficient capacity for acquir…
NaviMaster: Learning a Unified Policy for GUI and Embodied Navigation Tasks
Zhihao Luo, Wentao Yan, Jingyu Gong +5
Recent advances in Graphical User Interface (GUI) and embodied navigation have driven progress, yet these domains have largely evolved in isolation, with disparate datasets and tra…
YouTube-Occ: Learning Indoor 3D Semantic Occupancy Prediction from YouTube Videos
Haoming Chen, Lichen Yuan, TianFang Sun +5
3D semantic occupancy prediction is crucial for fine-grained scene understanding, yet its advancement in privacy-sensitive indoor environments is fundamentally hindered by the scar…
FMLGS: Fast Multilevel Language Embedded Gaussians for Part-level Interactive Agents
Xin Tan, Yuzhou Ji, He Zhu +1
The semantically interactive radiance field has long been a promising backbone for 3D real-world applications, such as embodied AI to achieve scene understanding and manipulation.…
IDMR: Towards Instance-Driven Precise Visual Correspondence in Multimodal Retrieval
Bangwei Liu, Yicheng Bao, Shaohui Lin +5
Multimodal retrieval systems are becoming increasingly vital for cutting-edge AI technologies, such as embodied AI and AI-driven digital content industries. However, current multim…