arXiv subjects

Zhenbo Luo

Publications and source records attributed to Zhenbo Luo.

51 records · Page 3Linked to original sources

arXiv2025

TimeViper: A Hybrid Mamba-Transformer Vision-Language Model for Efficient Long Video Understanding

We introduce TimeViper, a hybrid vision-language model designed to tackle challenges of long video understanding. Processing long videos demands both an efficient model architecture and an effective mechanism for handling extended temporal contexts. To this end, TimeViper adopts a hybrid Mamba-Transformer backbone that combines the efficiency of state-space models with the expressivity of attention mechanisms. Through this hybrid design, we reveal the vision-to-text information aggregation phenomenon, where information progressively flows from vision tokens to text tokens across increasing LLM depth, resulting in severe vision token redundancy. Motivated by this observation, we propose TransV, a token information transfer module that transfers and compresses vision tokens into instruction tokens while maintaining multimodal understanding capabilities. This design enables TimeViper to process hour-long videos exceeding 10,000 frames. Extensive experiments across multiple benchmarks demonstrate that TimeViper competes with state-of-the-art models while extending frame numbers. We further analyze attention behaviors of both Mamba and Transformer layers, offering new insights into hybrid model interpretability. This work represents an initial step towards developing, interpreting, and compressing hybrid Mamba-Transformer architectures.

cs.CV↗

arXiv2025

Cook and Clean Together: Teaching Embodied Agents for Parallel Task Execution

Task scheduling is critical for embodied AI, enabling agents to follow natural language instructions and execute actions efficiently in 3D physical worlds. However, existing datasets often simplify task planning by ignoring operations research (OR) knowledge and 3D spatial grounding. In this work, we propose Operations Research knowledge-based 3D Grounded Task Scheduling (ORS3D), a new task that requires the synergy of language understanding, 3D grounding, and efficiency optimization. Unlike prior settings, ORS3D demands that agents minimize total completion time by leveraging parallelizable subtasks, e.g., cleaning the sink while the microwave operates. To facilitate research on ORS3D, we construct ORS3D-60K, a large-scale dataset comprising 60K composite tasks across 4K real-world scenes. Furthermore, we propose GRANT, an embodied multi-modal large language model equipped with a simple yet effective scheduling token mechanism to generate efficient task schedules and grounded actions. Extensive experiments on ORS3D-60K validate the effectiveness of GRANT across language understanding, 3D grounding, and scheduling efficiency. The code is available at https://github.com/H-EmbodVis/GRANT

cs.CV↗

arXiv2025

AutoLink: Autonomous Schema Exploration and Expansion for Scalable Schema Linking in Text-to-SQL at Scale

For industrial-scale text-to-SQL, supplying the entire database schema to Large Language Models (LLMs) is impractical due to context window limits and irrelevant noise. Schema linking, which filters the schema to a relevant subset, is therefore critical. However, existing methods incur prohibitive costs, struggle to trade off recall and noise, and scale poorly to large databases. We present \textbf{AutoLink}, an autonomous agent framework that reformulates schema linking as an iterative, agent-driven process. Guided by an LLM, AutoLink dynamically explores and expands the linked schema subset, progressively identifying necessary schema components without inputting the full database schema. Our experiments demonstrate AutoLink's superior performance, achieving state-of-the-art strict schema linking recall of \textbf{97.4\%} on Bird-Dev and \textbf{91.2\%} on Spider-2.0-Lite, with competitive execution accuracy, i.e., \textbf{68.7\%} EX on Bird-Dev (better than CHESS) and \textbf{34.9\%} EX on Spider-2.0-Lite (ranking 2nd on the official leaderboard). Crucially, AutoLink exhibits \textbf{exceptional scalability}, \textbf{maintaining high recall}, \textbf{efficient token consumption}, and \textbf{robust execution accuracy} on large schemas (e.g., over 3,000 columns) where existing methods severely degrade-making it a highly scalable, high-recall schema-linking solution for industrial text-to-SQL systems.

cs.CL↗

arXiv2025

BTL-UI: Blink-Think-Link Reasoning Model for GUI Agent

In the field of AI-driven human-GUI interaction automation, while rapid advances in multimodal large language models and reinforcement fine-tuning techniques have yielded remarkable progress, a fundamental challenge persists: their interaction logic significantly deviates from natural human-GUI communication patterns. To fill this gap, we propose "Blink-Think-Link" (BTL), a brain-inspired framework for human-GUI interaction that mimics the human cognitive process between users and graphical interfaces. The system decomposes interactions into three biologically plausible phases: (1) Blink - rapid detection and attention to relevant screen areas, analogous to saccadic eye movements; (2) Think - higher-level reasoning and decision-making, mirroring cognitive planning; and (3) Link - generation of executable commands for precise motor control, emulating human action selection mechanisms. Additionally, we introduce two key technical innovations for the BTL framework: (1) Blink Data Generation - an automated annotation pipeline specifically optimized for blink data, and (2) BTL Reward -- the first rule-based reward mechanism that enables reinforcement learning driven by both process and outcome. Building upon this framework, we develop a GUI agent model named BTL-UI, which demonstrates competitive performance across both static GUI understanding and dynamic interaction tasks in comprehensive benchmarks. These results provide conclusive empirical validation of the framework's efficacy in developing advanced GUI Agents.

cs.CV↗

arXiv2025

SALM: Spatial Audio Language Model with Structured Embeddings for Understanding and Editing

Spatial audio understanding is essential for accurately perceiving and interpreting acoustic environments. However, existing audio-language models exhibit limitations in processing spatial audio and perceiving spatial acoustic scenes. To address this gap, we propose the Spatial Audio Language Model (SALM), a novel framework that bridges spatial audio and language through multi-modal contrastive learning. SALM integrates a text encoder with a dual-branch audio encoder that decomposes spatial sound into semantic and spatial components via structured audio embeddings. Key features of SALM include seamless alignment between spatial audio and natural language, both separate and joint extraction of spatial and semantic representations, zero-shot direction classification, and flexible support for spatial audio editing. Experimental results demonstrate that SALM effectively captures and aligns cross-modal representations, yielding well-structured audio embeddings. Furthermore, SALM enables advanced editing capabilities, such as modifying directional audio using text-based embeddings.

cs.SD↗

arXiv2025

Omni-CLST: Error-aware Curriculum Learning with guided Selective chain-of-Thought for audio question answering

With the rapid progress of large audio-language models (LALMs), audio question answering (AQA) has emerged as a challenging task requiring both fine-grained audio understanding and complex reasoning. While current methods mainly rely on constructing new datasets via captioning or reasoning traces, existing high-quality AQA data remains underutilized. To address this, we propose Omni-CLST, an error-aware Curriculum Learning framework with guided Selective Chain-of-Thought. The framework efficiently leverages existing high-quality dataset through two key strategies: an error-aware curriculum that organizes samples by difficulty, and a guided thought dropout mechanism that focuses reasoning on challenging cases. Experiments show that Omni-CLST achieves 73.80% on MMAU-mini and a new state of the art of 64.30% on MMAR, demonstrating robust generalization in multimodal audio-language understanding.

cs.SD↗

arXiv2025

Q-Frame: Query-aware Frame Selection and Multi-Resolution Adaptation for Video-LLMs

Multimodal Large Language Models (MLLMs) have demonstrated significant success in visual understanding tasks. However, challenges persist in adapting these models for video comprehension due to the large volume of data and temporal complexity. Existing Video-LLMs using uniform frame sampling often struggle to capture the query-related crucial spatiotemporal clues of videos effectively. In this paper, we introduce Q-Frame, a novel approach for adaptive frame selection and multi-resolution scaling tailored to the video's content and the specific query. Q-Frame employs a training-free, plug-and-play strategy generated by a text-image matching network like CLIP, utilizing the Gumbel-Max trick for efficient frame selection. Q-Frame allows Video-LLMs to process more frames without exceeding computational limits, thereby preserving critical temporal and spatial information. We demonstrate Q-Frame's effectiveness through extensive experiments on benchmark datasets, including MLVU, LongVideoBench, and Video-MME, illustrating its superiority over existing methods and its applicability across various video understanding tasks.

cs.CV↗

arXiv2025

Time-R1: Post-Training Large Vision Language Model for Temporal Video Grounding

Temporal Video Grounding (TVG), the task of locating specific video segments based on language queries, is a core challenge in long-form video understanding. While recent Large Vision-Language Models (LVLMs) have shown early promise in tackling TVG through supervised fine-tuning (SFT), their abilities to generalize remain limited. To address this, we propose a novel post-training framework that enhances the generalization capabilities of LVLMs via reinforcement learning (RL). Specifically, our contributions span three key directions: (1) Time-R1: we introduce a reasoning-guided post-training framework via RL with verifiable reward to enhance the capabilities of LVLMs on the TVG task. (2) TimeRFT: we explore data-efficient post-training strategies on our curated RL-friendly dataset, which trains the model to progressively comprehend difficult samples, leading to better generalization. (3) TVGBench: we carefully construct a small yet comprehensive benchmark for LVLM evaluation, assessing 11 types of queries and featuring balanced distributions across both videos and queries. Extensive experiments demonstrate that Time-R1 achieves state-of-the-art performance across multiple downstream datasets using only 2.5K training data, while improving its general video understanding capabilities.

cs.CV↗

arXiv2025

MiMo-VL Technical Report

We open-source MiMo-VL-7B-SFT and MiMo-VL-7B-RL, two powerful vision-language models delivering state-of-the-art performance in both general visual understanding and multimodal reasoning. MiMo-VL-7B-RL outperforms Qwen2.5-VL-7B on 35 out of 40 evaluated tasks, and scores 59.4 on OlympiadBench, surpassing models with up to 78B parameters. For GUI grounding applications, it sets a new standard with 56.1 on OSWorld-G, even outperforming specialized models such as UI-TARS. Our training combines four-stage pre-training (2.4 trillion tokens) with Mixed On-policy Reinforcement Learning (MORL) integrating diverse reward signals. We identify the importance of incorporating high-quality reasoning data with long Chain-of-Thought into pre-training stages, and the benefits of mixed RL despite challenges in simultaneous multi-domain optimization. We also contribute a comprehensive evaluation suite covering 50+ tasks to promote reproducibility and advance the field. The model checkpoints and full evaluation suite are available at https://github.com/XiaomiMiMo/MiMo-VL.

cs.CL↗

arXiv2022

Multi Receptive Field Network for Semantic Segmentation

Semantic segmentation is one of the key tasks in computer vision, which is to assign a category label to each pixel in an image. Despite significant progress achieved recently, most existing methods still suffer from two challenging issues: 1) the size of objects and stuff in an image can be very diverse, demanding for incorporating multi-scale features into the fully convolutional networks (FCNs); 2) the pixels close to or at the boundaries of object/stuff are hard to classify due to the intrinsic weakness of convolutional networks. To address the first issue, we propose a new Multi-Receptive Field Module (MRFM), explicitly taking multi-scale features into account. For the second issue, we design an edge-aware loss which is effective in distinguishing the boundaries of object/stuff. With these two designs, our Multi Receptive Field Network achieves new state-of-the-art results on two widely-used semantic segmentation benchmark datasets. Specifically, we achieve a mean IoU of 83.0 on the Cityscapes dataset and 88.4 mean IoU on the Pascal VOC2012 dataset.

cs.CV↗

arXiv2020

VOC-ReID: Vehicle Re-identification based on Vehicle-Orientation-Camera

Vehicle re-identification is a challenging task due to high intra-class variances and small inter-class variances. In this work, we focus on the failure cases caused by similar background and shape. They pose serve bias on similarity, making it easier to neglect fine-grained information. To reduce the bias, we propose an approach named VOC-ReID, taking the triplet vehicle-orientation-camera as a whole and reforming background/shape similarity as camera/orientation re-identification. At first, we train models for vehicle, orientation and camera re-identification respectively. Then we use orientation and camera similarity as penalty to get final similarity. Besides, we propose a high performance baseline boosted by bag of tricks and weakly supervised data augmentation. Our algorithm achieves the second place in vehicle re-identification at the NVIDIA AI City Challenge 2020.

cs.CV↗

arXiv2019

Arbitrary Shape Scene Text Detection with Adaptive Text Region Representation

Scene text detection attracts much attention in computer vision, because it can be widely used in many applications such as real-time text translation, automatic information entry, blind person assistance, robot sensing and so on. Though many methods have been proposed for horizontal and oriented texts, detecting irregular shape texts such as curved texts is still a challenging problem. To solve the problem, we propose a robust scene text detection method with adaptive text region representation. Given an input image, a text region proposal network is first used for extracting text proposals. Then, these proposals are verified and refined with a refinement network. Here, recurrent neural network based adaptive text region representation is proposed for text region refinement, where a pair of boundary points are predicted each time step until no new points are found. In this way, text regions of arbitrary shapes are detected and represented with adaptive number of boundary points. This gives more accurate description of text regions. Experimental results on five benchmarks, namely, CTW1500, TotalText, ICDAR2013, ICDAR2015 and MSRATD500, show that the proposed method achieves state-of-the-art in scene text detection.

cs.CV↗

arXiv2017

Deep Residual Text Detection Network for Scene Text

Scene text detection is a challenging problem in computer vision. In this paper, we propose a novel text detection network based on prevalent object detection frameworks. In order to obtain stronger semantic feature, we adopt ResNet as feature extraction layers and exploit multi-level feature by combining hierarchical convolutional networks. A vertical proposal mechanism is utilized to avoid proposal classification, while regression layer remains working to improve localization accuracy. Our approach evaluated on ICDAR2013 dataset achieves F-measure of 0.91, which outperforms previous state-of-the-art results in scene text detection.

cs.CV↗

arXiv2017

R2CNN: Rotational Region CNN for Orientation Robust Scene Text Detection

In this paper, we propose a novel method called Rotational Region CNN (R2CNN) for detecting arbitrary-oriented texts in natural scene images. The framework is based on Faster R-CNN [1] architecture. First, we use the Region Proposal Network (RPN) to generate axis-aligned bounding boxes that enclose the texts with different orientations. Second, for each axis-aligned text box proposed by RPN, we extract its pooled features with different pooled sizes and the concatenated features are used to simultaneously predict the text/non-text score, axis-aligned box and inclined minimum area box. At last, we use an inclined non-maximum suppression to get the detection results. Our approach achieves competitive results on text detection benchmarks: ICDAR 2015 and ICDAR 2013.

cs.CV↗

arXiv2017

Auto-painter: Cartoon Image Generation from Sketch by Using Conditional Generative Adversarial Networks

Recently, realistic image generation using deep neural networks has become a hot topic in machine learning and computer vision. Images can be generated at the pixel level by learning from a large collection of images. Learning to generate colorful cartoon images from black-and-white sketches is not only an interesting research problem, but also a potential application in digital entertainment. In this paper, we investigate the sketch-to-image synthesis problem by using conditional generative adversarial networks (cGAN). We propose the auto-painter model which can automatically generate compatible colors for a sketch. The new model is not only capable of painting hand-draw sketch with proper colors, but also allowing users to indicate preferred colors. Experimental results on two sketch datasets show that the auto-painter performs better that existing image-to-image methods.

cs.CV↗