Quanlong Zheng

SCOUT: Self-Checking and Recovery-Aware Tool-Thought Agents for Ultra-Long Egocentric Video Reasoning

Keyang Zhong, Kuo Wang, Peng Liu, Quanlong Zheng et autres

Ultra-long egocentric video understanding requires reasoning over temporally sparse evidence distributed across hours or days, challenging current multimodal models with limited context and the grounding of key video segments. While Chain-of-Tool-Thought (CoTT) agent systems enable iterative retrieval and inspection, they suffer from …

X-OmniClaw Technical Report: A Unified Mobile Agent for Multimodal Understanding and Interaction

Xiaoming Ren, Ru Zhen, Chao Li, Yang Song et autres

Inspired by the development of OpenClaw, there is a growing demand for mobile-based personal agents capable of handling complex and intuitive interactions. In this technical report, we introduce X-OmniClaw, a unified mobile agent designed for multimodal understanding and interaction in the Android …

X-OmniClaw Technical Report: A Unified Mobile Agent for Multimodal Understanding and Interaction

Xiaoming Ren, Ru Zhen, Chao Li, Yang Song et autres

Inspired by the development of OpenClaw, there is a growing demand for mobile-based personal agents capable of handling complex and intuitive interactions. In this technical report, we introduce X-OmniClaw, a unified mobile agent designed for multimodal understanding and interaction in the Android …

de (code pays fourni par la source)

Free-Moref: Instantly Multiplexing Context Perception Capabilities of Video-Mllms Within Single Inference

Kuo Wang, Quanlong Zheng, Junlin Xie, Yanhao Zhang et autres

Video Multimodal Large Language Models~(Video-MLLM) have achieved remarkable advancements in video understanding tasks. However, constrained by the context length limitation in the underlying LLMs, existing Video-MLLMs typically exhibit suboptimal performance on long video scenarios. To understand extended input frames, common solutions span …

cn, nl (code pays fourni par la source)

AndesVL Technical Report: An Efficient Mobile-side Multimodal Large Language Model

Xiaohui Song, Nan Wang, Yafei Liu, Chao Li et autres

In recent years, while cloud-based MLLMs such as QwenVL, InternVL, GPT-4o, Gemini, and Claude Sonnet have demonstrated outstanding performance with enormous model sizes reaching hundreds of billions of parameters, they significantly surpass the limitations in memory, power consumption, and computing capacity of …

Dynamic-I2V: Exploring Image-to-Video Generation Models via Multimodal LLM

Peng Liu, Xiaoming Ren, Fengkai Liu, Qingsong Xie et autres

Recent advancements in image-to-video (I2V) generation have shown promising performance in conventional scenarios. However, these methods still encounter significant challenges when dealing with complex scenes that require a deep understanding of nuanced motion and intricate object-action relationships. To address these challenges, we …

H2VU-Benchmark: A Comprehensive Benchmark for Hierarchical Holistic Video Understanding

Qilin Wu, Quanlong Zheng, Yanhao Zhang, Junlin Xie et autres

With the rapid development of multimodal models, the demand for assessing video understanding capabilities has been steadily increasing. However, existing benchmarks for evaluating video understanding exhibit significant limitations in coverage, task diversity, and scene adaptability. These shortcomings hinder the accurate assessment of …

InstructHOI: Context-Aware Instruction for Multi-Modal Reasoning in Human-Object Interaction Detection

Jinguo Luo, Weihong Ren, Quanlong Zheng, Yanhao Zhang et autres

cn, nl (code pays fourni par la source)

Towards Real-world Shadow Removal with a Shadow Simulation Method and a Two-stage Framework

Jianhao Gao, Quanlong Zheng, Yandong Guo

Shadow removal is an important yet challenging restoration task. State-of-the-art shadow removal methods usually require paired datasets for training. Existing shadow removal datasets lack large-scale quantity and scene diversity. Hence, models trained on such datasets have poor generalization ability. This paper proposes …

cn (code pays fourni par la source)

Correction to: Instance-Aware Scene Layout Forecasting

Xiaotian Qiao, Quanlong Zheng, Ying Shan Cao, Rynson W. H. Lau

cn, hk (code pays fourni par la source)

Instance-Aware Scene Layout Forecasting

Xiaotian Qiao, Quanlong Zheng, Ying Shan Cao, Rynson W. H. Lau

cn, hk (code pays fourni par la source)

Distilling Reflection Dynamics for Single-Image Reflection Removal

Quanlong Zheng, Xiaotian Qiao, Ying Shan Cao, Shi Zeng Guo et autres

Single-image reflection removal (SIRR) aims to restore the transmitted image given a single image shot through glass or window. Existing methods rely mainly on information extracted from a single image along with some predefined priors, and fail to give satisfying results on …

hk, ky (code pays fourni par la source)