Yiwu Zhong

An Yan, Zhengyuan Yang, Wanrong Zhu et al. · microsoft-research

We present MM-Navigator, a GPT-4V-based agent for the smartphone graphical user interface (GUI) navigation task. MM-Navigator can interact with a smartphone screen as human users, and determine subsequent actions to fulfill given instructions. Our findings demonstrate that large multimodal models (LMMs), specifically GPT-4V, excel in zero-shot GUI navigation through its advanced screen interpretation, action reasoning, and precise action localization capabilities. We first benchmark MM-Navigator on our collected iOS screen dataset. According to human assessments, the system exhibited a 91\% accuracy rate in generating reasonable action descriptions and a 75\% accuracy rate in executing the correct actions for single-step instructions on iOS. Additionally, we evaluate the model on a subset of an Android screen navigation dataset, where the model outperforms previous GUI navigators in a zero-shot fashion. Our benchmark and detailed analyses aim to lay a robust groundwork for future research into the GUI navigation task. The project page is at https://github.com/zzxslp/MM-Navigator.

Jie Huang, Ruixun Liu, Sirui Sun et al.

As multi-modal models advance towards long-form video understanding, memory emerges as a critical capability. Despite substantial efforts in developing video datasets and benchmarks, existing works primarily focus on perception and reasoning, without systematically evaluating memory: what models retain, how faithfully information is preserved, and how robust memory remains under interference. To address this gap, we introduce M$^3$Eval, the first comprehensive evaluation framework and benchmark for probing different memory dimensions in multi-modal models. Grounded in cognitive psychology, our design features carefully constructed tasks that isolate key aspects of memory. Leveraging M$^3$Eval, we conduct extensive experiments across representative multi-modal models, revealing consistent weaknesses and distinctive behaviors. We find that models struggle to maintain disentangled representations when processing parallel video streams, exhibit interference patterns differing substantially from those observed in human memory, ground memory sources more reliably in the spatial domain than the temporal domain, and demonstrate limited symbolic memory. Collectively, our benchmark provides a valuable resource for future research, while our findings highlight memory as a fundamental yet underexplored capability and offer insights for designing more effective memory mechanisms in multi-modal models. Our code and dataset are available at https://pku-value-lab.github.io/m3eval-homepage.

An Yan, Yu Wang, Yiwu Zhong et al.

Recent advances in foundation models present new opportunities for interpretable visual recognition -- one can first query Large Language Models (LLMs) to obtain a set of attributes that describe each class, then apply vision-language models to classify images via these attributes. Pioneering work shows that querying thousands of attributes can achieve performance competitive with image features. However, our further investigation on 8 datasets reveals that LLM-generated attributes in a large quantity perform almost the same as random words. This surprising finding suggests that significant noise may be present in these attributes. We hypothesize that there exist subsets of attributes that can maintain the classification performance with much smaller sizes, and propose a novel learning-to-search method to discover those concise sets of attributes. As a result, on the CUB dataset, our method achieves performance close to that of massive LLM-generated attributes (e.g., 10k attributes for CUB), yet using only 32 attributes in total to distinguish 200 bird species. Furthermore, our new paradigm demonstrates several additional benefits: higher interpretability and interactivity for humans, and the ability to summarize knowledge for a recognition task.

Yiwu Zhong, Licheng Yu, Yang Bai et al.

The abundance of instructional videos and their narrations over the Internet offers an exciting avenue for understanding procedural activities. In this work, we propose to learn video representation that encodes both action steps and their temporal ordering, based on a large-scale dataset of web instructional videos and their narrations, without using human annotations. Our method jointly learns a video representation to encode individual step concepts, and a deep probabilistic model to capture both temporal dependencies and immense individual variations in the step ordering. We empirically demonstrate that learning temporal ordering not only enables new capabilities for procedure reasoning, but also reinforces the recognition of individual steps. Our model significantly advances the state-of-the-art results on step classification (+2.8% / +3.3% on COIN / EPIC-Kitchens) and step forecasting (+7.4% on COIN). Moreover, our model attains promising results in zero-shot inference for step classification and forecasting, as well as in predicting diverse and plausible steps for incomplete procedures. Our code is available at https://github.com/facebookresearch/ProcedureVRL.

Chenfan Qu, Yiwu Zhong, Fengjun Guo et al.

The rapid advancements of generative AI have fueled the potential of generative text image editing, meanwhile escalating the threat of misinformation spreading. However, existing forensics methods struggle to detect unseen forgery types that they have not been trained on, underscoring the need for a model capable of generalized detection of tampered scene text. To tackle this, we propose a novel task: open-set tampered scene text detection, which evaluates forensics models on their ability to identify both seen and previously unseen forgery types. We have curated a comprehensive, high-quality dataset, featuring the texts tampered by eight text editing models, to thoroughly assess the open-set generalization capabilities. Further, we introduce a novel and effective training paradigm that subtly alters the texture of selected texts within an image and trains the model to identify these regions. This approach not only mitigates the scarcity of high-quality training data but also enhances models' fine-grained perception and open-set generalization abilities. Additionally, we present DAF, a novel framework that improves open-set generalization by distinguishing between the features of authentic and tampered text, rather than focusing solely on the tampered text's features. Our extensive experiments validate the remarkable efficacy of our methods. For example, our zero-shot performance can even beat the previous state-of-the-art full-shot model by a large margin. Our dataset and code are available at https://github.com/qcf-568/OSTF.

An Yan, Yu Wang, Yiwu Zhong et al.

Medical image classification is a critical problem for healthcare, with the potential to alleviate the workload of doctors and facilitate diagnoses of patients. However, two challenges arise when deploying deep learning models to real-world healthcare applications. First, neural models tend to learn spurious correlations instead of desired features, which could fall short when generalizing to new domains (e.g., patients with different ages). Second, these black-box models lack interpretability. When making diagnostic predictions, it is important to understand why a model makes a decision for trustworthy and safety considerations. In this paper, to address these two limitations, we propose a new paradigm to build robust and interpretable medical image classifiers with natural language concepts. Specifically, we first query clinical concepts from GPT-4, then transform latent image features into explicit concepts with a vision-language model. We systematically evaluate our method on eight medical image classification datasets to verify its effectiveness. On challenging datasets with strong confounding factors, our method can mitigate spurious correlations thus substantially outperform standard visual encoders and other baselines. Finally, we show how classification with a small number of concepts brings a level of interpretability for understanding model decisions through case studies in real medical data.

Yiwu Zhong, Zi-Yuan Hu, Yin Li et al.

Chain-of-thought (CoT) reasoning has been highly successful in solving complex tasks in natural language processing, and recent multimodal large language models (MLLMs) have extended this paradigm to video reasoning. However, these models typically build on lengthy reasoning chains and large numbers of input visual tokens. Motivated by empirical observations from our benchmark study, we hypothesize that concise reasoning combined with a reduced set of visual tokens can be sufficient for effective video reasoning. To evaluate this hypothesis, we design and validate an efficient post-training and inference framework that enhances a video MLLM's reasoning capability. Our framework enables models to operate on compressed visual tokens and generate brief reasoning traces prior to answering. The resulting models achieve substantially improved inference efficiency, deliver competitive performance across diverse benchmarks, and avoid reliance on manual CoT annotations or supervised fine-tuning. Collectively, our results suggest that long, human-like CoT reasoning may not be necessary for general video reasoning, and that concise reasoning can be both effective and efficient. Our code will be released at https://github.com/LaVi-Lab/Rethink_CoT_Video.

Yiwu Zhong, Zhuoming Liu, Yin Li et al.

Large language models (LLMs) have enabled the creation of multi-modal LLMs that exhibit strong comprehension of visual data such as images and videos. However, these models usually rely on extensive visual tokens from visual encoders, leading to high computational demands, which limits their applicability in resource-constrained environments and for long-context tasks. In this work, we propose a training-free adaptive inference method for multi-modal LLMs that can accommodate a broad range of efficiency requirements with a minimum performance drop. Our method consists of a) iterative token merging based on embedding similarity before LLMs, and b) progressive token pruning within LLM layers based on multi-modal importance. With a minimalist design, our method can be applied to both video and image LLMs. Extensive experiments on diverse video and image benchmarks demonstrate that our method substantially reduces computation load (e.g., a $\textbf{7-fold}$ reduction in FLOPs) while preserving the performance of video and image LLMs. Further, at a similar computational cost, our method outperforms the state-of-the-art methods in long video understanding (e.g., $\textbf{+4.6}$ on MLVU). Additionally, our in-depth analysis provides insights into token redundancy and LLM layer behaviors, offering guidance for future research in designing efficient multi-modal LLMs. Our code is available at https://github.com/LaVi-Lab/AIM.

Biao Wu, Yiwu Zhong, Meng Fang et al.

High-quality and diverse multimodal data are essential for improving vision-language models (VLMs), yet existing datasets often contain noisy, redundant, and poorly aligned samples. To address these problems, data filtering is commonly used to enhance the efficiency and performance of multimodal learning, but it introduces extra computational cost because filtering models are usually trained on the same data they are meant to screen. To reduce this cost, we study DOSE, which explores whether off-the-shelf pretrained models that have never seen the target data can be used to select training samples for larger and stronger multimodal models without any task-specific training. Even without fine-tuning, these models can effectively assess text quality and image-text alignment to guide data selection. Based on this, we build a joint quality-alignment distribution and apply adaptive weighted sampling to select informative samples while maintaining long-tail diversity. This approach enhances data diversity, enabling models trained on DOSE-filtered data to match or surpass those trained on the full dataset on standard VQA and math benchmarks. Extensive experiments demonstrate its effectiveness, efficiency, and scalability.

Zhancun Mu, Guangyu Zhao, Yiwu Zhong et al.

One-step offline RL actors are attractive because they avoid backpropagating through long iterative samplers and keep inference cheap, but they still have to improve under a critic without drifting away from actions that the dataset can support. In recent one-step extraction pipelines, a strong iterative teacher provides one target action for each latent draw, and the same student output is asked to do both jobs: move toward higher Q and stay near that paired endpoint. If those two directions disagree, the loss resolves them as a compromise on that same sample, even when a nearby better action remains locally supported by the data. We propose DROL, a latent-conditioned one-step actor trained with top-1 dynamic routing. For each state, the actor samples $K$ candidate actions from a bounded latent prior, assigns each dataset action to its nearest candidate, and updates only that winner with Behavior Cloning and critic guidance. Because the routing is recomputed from the current candidate geometry, ownership of a supported region can shift across candidates over the course of learning. This gives a one-step actor room to make local improvements that pointwise extraction struggles to capture, while retaining single-pass inference at test time. On OGBench and D4RL, DROL is competitive with the one-step FQL baseline, improving many OGBench task groups while remaining strong on both AntMaze and Adroit. Project page: https://muzhancun.github.io/preprints/DROL.

Yiwu Zhong, Zi-Yuan Hu, Michael R. Lyu et al.

Visual representation learning has been a cornerstone in computer vision, involving typical forms such as visual embeddings, structural symbols, and text-based representations. Despite the success of CLIP-type visual embeddings, they often lack access to world knowledge critical for visual reasoning. In this work, we propose Visual Table, a novel form of visual representation tailored for visual reasoning. Visual tables are constructed as hierarchical descriptions of visual scenes, featuring a scene description and multiple object-centric descriptions covering categories, attributes, and knowledge. Thanks to the structural and textual formats, visual tables offer unique advantages over mere visual embeddings, such as interpretability and controllable editing. Furthermore, they deliver instance-level world knowledge and detailed attributes that are essential for visual reasoning. To create visual tables, we develop a generator trained on the dataset with collected, small-scale annotations. Extensive results on 11 visual reasoning benchmarks demonstrate that the generated visual tables significantly outperform previous structural and text-based representations. Moreover, they consistently enhance state-of-the-art multimodal large language models across diverse benchmarks, showcasing their potential for advancing visual reasoning tasks. Our code is available at https://github.com/LaVi-Lab/Visual-Table.

Chenfan Qu, Yiwu Zhong, Fengjun Guo et al.

Existing Image Manipulation Localization (IML) methods mostly rely heavily on task-specific designs, making them perform well only on the target IML task, while joint training on multiple IML tasks causes significant performance degradation, hindering real applications. To this end, we propose Omni-IML, the first generalist model designed to unify IML across diverse tasks. Specifically, Omni-IML achieves generalization through three key components: (1) a Modal Gate Encoder, which adaptively selects the optimal encoding modality per sample, (2) a Dynamic Weight Decoder, which dynamically adjusts decoder filters to the task at hand, and (3) an Anomaly Enhancement module that leverages box supervision to highlight the tampered regions and facilitate the learning of task-agnostic features. Beyond localization, to support interpretation of the tampered images, we construct Omni-273k, a large high-quality dataset that includes natural language descriptions of tampered artifact. It is annotated through our automatic, chain-of-thoughts annotation technique. We also design a simple-yet-effective interpretation module to better utilize these descriptive annotations. Our extensive experiments show that our single Omni-IML model achieves state-of-the-art performance across all four major IML tasks, providing a valuable solution for practical deployment and a promising direction of generalist models in image forensics. Our code and dataset will be publicly available.

Zhuoming Liu, Yiquan Li, Khoi Duc Nguyen et al.

Pre-trained video large language models (Video LLMs) exhibit remarkable reasoning capabilities, yet adapting these models to new tasks involving additional modalities or data types (e.g., audio or 3D information) remains challenging. In this paper, we present PAVE, a flexible framework for adapting pre-trained Video LLMs to downstream tasks with side-channel signals, such as audio, 3D cues, or multi-view videos. PAVE introduces lightweight adapters, referred to as "patches," which add a small number of parameters and operations to a base model without modifying its architecture or pre-trained weights. In doing so, PAVE can effectively adapt the pre-trained base model to support diverse downstream tasks, including audio-visual question answering, 3D reasoning, multi-view video recognition, and high frame rate video understanding. Across these tasks, PAVE significantly enhances the performance of the base model, surpassing state-of-the-art task-specific models while incurring a minor cost of ~0.1% additional FLOPs and parameters. Further, PAVE supports multi-task learning and generalizes well across different Video LLMs. Our code is available at https://github.com/dragonlzm/PAVE.

Chenfan Qu, Yiwu Zhong, Bin Li et al.

Images manipulated using image editing tools can mislead viewers and pose significant risks to social security. However, accurately localizing the manipulated regions within an image remains a challenging problem. One of the main barriers in this area is the high cost of data acquisition and the severe lack of high-quality annotated datasets. To address this challenge, we introduce novel methods that mitigate data scarcity by leveraging readily available web data. We utilize a large collection of manually forged images from the web, as well as automatically generated annotations derived from a simpler auxiliary task, constrained image manipulation localization. Specifically, we introduce a new paradigm CAAAv2, which automatically and accurately annotates manipulated regions at the pixel level. To further improve annotation quality, we propose a novel metric, QES, which filters out unreliable annotations. Through CAAA v2 and QES, we construct MIMLv2, a large-scale, diverse, and high-quality dataset containing 246,212 manually forged images with pixel-level mask annotations. This is over 120x larger than existing handcrafted datasets like IMD20. Additionally, we introduce Object Jitter, a technique that further enhances model training by generating high-quality manipulation artifacts. Building on these advances, we develop a new model, Web-IML, designed to effectively leverage web-scale supervision for the image manipulation localization task. Extensive experiments demonstrate that our approach substantially alleviates the data scarcity problem and significantly improves the performance of various models on multiple real-world forgery benchmarks. With the proposed web supervision, Web-IML achieves a striking performance gain of 31% and surpasses previous SOTA TruFor by 24.1 average IoU points. The dataset and code will be made publicly available at https://github.com/qcf-568/MIML.

Shuo Liang, Yiwu Zhong, Zi-Yuan Hu et al.

Spatiotemporal video grounding aims to localize target entities in videos based on textual queries. While existing research has made significant progress in exocentric videos, the egocentric setting remains relatively underexplored, despite its growing importance in applications such as augmented reality and robotics. In this work, we conduct a systematic analysis of the discrepancies between egocentric and exocentric videos, revealing key challenges such as shorter object durations, sparser trajectories, smaller object sizes, and larger positional shifts. To address these challenges, we introduce EgoMask, the first pixel-level benchmark for fine-grained spatiotemporal grounding in egocentric videos. It is constructed by our proposed automatic annotation pipeline, which annotates referring expressions and object masks across short-, medium-, and long-term videos. Additionally, we create EgoMask-Train, a large-scale training dataset to facilitate model development. Experiments demonstrate that the state-of-the-art spatiotemporal grounding models perform poorly on our benchmark EgoMask, but fine-tuning on EgoMask-Train yields significant improvements, while preserving performance on exocentric datasets. Our work thus provides essential resources and insights for advancing egocentric video understanding. Our code is available at https://github.com/LaVi-Lab/EgoMask .

Yiwu Zhong, Jianwei Yang, Pengchuan Zhang et al.

Contrastive language-image pretraining (CLIP) using image-text pairs has achieved impressive results on image classification in both zero-shot and transfer learning settings. However, we show that directly applying such models to recognize image regions for object detection leads to poor performance due to a domain shift: CLIP was trained to match an image as a whole to a text description, without capturing the fine-grained alignment between image regions and text spans. To mitigate this issue, we propose a new method called RegionCLIP that significantly extends CLIP to learn region-level visual representations, thus enabling fine-grained alignment between image regions and textual concepts. Our method leverages a CLIP model to match image regions with template captions and then pretrains our model to align these region-text pairs in the feature space. When transferring our pretrained model to the open-vocabulary object detection tasks, our method significantly outperforms the state of the art by 3.8 AP50 and 2.2 AP for novel categories on COCO and LVIS datasets, respectively. Moreoever, the learned region representations support zero-shot inference for object detection, showing promising results on both COCO and LVIS datasets. Our code is available at https://github.com/microsoft/RegionCLIP.

Liunian Harold Li, Pengchuan Zhang, Haotian Zhang et al.

This paper presents a grounded language-image pre-training (GLIP) model for learning object-level, language-aware, and semantic-rich visual representations. GLIP unifies object detection and phrase grounding for pre-training. The unification brings two benefits: 1) it allows GLIP to learn from both detection and grounding data to improve both tasks and bootstrap a good grounding model; 2) GLIP can leverage massive image-text pairs by generating grounding boxes in a self-training fashion, making the learned representation semantic-rich. In our experiments, we pre-train GLIP on 27M grounding data, including 3M human-annotated and 24M web-crawled image-text pairs. The learned representations demonstrate strong zero-shot and few-shot transferability to various object-level recognition tasks. 1) When directly evaluated on COCO and LVIS (without seeing any images in COCO during pre-training), GLIP achieves 49.8 AP and 26.9 AP, respectively, surpassing many supervised baselines. 2) After fine-tuned on COCO, GLIP achieves 60.8 AP on val and 61.5 AP on test-dev, surpassing prior SoTA. 3) When transferred to 13 downstream object detection tasks, a 1-shot GLIP rivals with a fully-supervised Dynamic Head. Code is released at https://github.com/microsoft/GLIP.

Yiwu Zhong, Jing Shi, Jianwei Yang et al.

Learning from image-text data has demonstrated recent success for many recognition tasks, yet is currently limited to visual features or individual visual concepts such as objects. In this paper, we propose one of the first methods that learn from image-sentence pairs to extract a graphical representation of localized objects and their relationships within an image, known as scene graph. To bridge the gap between images and texts, we leverage an off-the-shelf object detector to identify and localize object instances, match labels of detected regions to concepts parsed from captions, and thus create "pseudo" labels for learning scene graph. Further, we design a Transformer-based model to predict these "pseudo" labels via a masked token prediction task. Learning from only image-sentence pairs, our model achieves 30% relative gain over a latest method trained with human-annotated unlocalized scene graphs. Our model also shows strong results for weakly and fully supervised scene graph generation. In addition, we explore an open-vocabulary setting for detecting scene graphs, and present the first result for open-set scene graph generation. Our code is available at https://github.com/YiwuZhong/SGG_from_NLS.

Duo Zheng, Shijia Huang, Lin Zhao et al.

Building a generalist agent that can interact with the world is the intriguing target of AI systems, thus spurring the research for embodied navigation, where an agent is required to navigate according to instructions or respond to queries. Despite the major progress attained, previous works primarily focus on task-specific agents and lack generalizability to unseen scenarios. Recently, LLMs have presented remarkable capabilities across various fields, and provided a promising opportunity for embodied navigation. Drawing on this, we propose the first generalist model for embodied navigation, NaviLLM. It adapts LLMs to embodied navigation by introducing schema-based instruction. The schema-based instruction flexibly casts various tasks into generation problems, thereby unifying a wide range of tasks. This approach allows us to integrate diverse data sources from various datasets into the training, equipping NaviLLM with a wide range of capabilities required by embodied navigation. We conduct extensive experiments to evaluate the performance and generalizability of our model. The experimental results demonstrate that our unified model achieves state-of-the-art performance on CVDN, SOON, and ScanQA. Specifically, it surpasses the previous stats-of-the-art method by a significant margin of 29% in goal progress on CVDN. Moreover, our model also demonstrates strong generalizability and presents impressive results on unseen tasks, e.g., embodied question answering and 3D captioning.

Chenfan Qu, Yiwu Zhong, Jian Liu et al.

The growing prevalence of tampered images poses serious security threats, highlighting the urgent need for reliable detection methods. Multimodal large language models (MLLMs) demonstrate strong potential in analyzing tampered images and generating interpretations. However, they still struggle with identifying micro-level artifacts, exhibit low accuracy in localizing tampered text regions, and heavily rely on expensive annotations for forgery interpretation. To this end, we introduce TextShield-R1, the first reinforcement learning based MLLM solution for tampered text detection and reasoning. Specifically, our approach introduces Forensic Continual Pre-training, an easy-to-hard curriculum that well prepares the MLLM for tampered text detection by harnessing the large-scale cheap data from natural image forensic and OCR tasks. During fine-tuning, we perform Group Relative Policy Optimization with novel reward functions to reduce annotation dependency and improve reasoning capabilities. At inference time, we enhance localization accuracy via OCR Rectification, a method that leverages the MLLM's strong text recognition abilities to refine its predictions. Furthermore, to support rigorous evaluation, we introduce the Text Forensics Reasoning (TFR) benchmark, comprising over 45k real and tampered images across 16 languages, 10 tampering techniques, and diverse domains. Rich reasoning-style annotations are included, allowing for comprehensive assessment. Our TFR benchmark simultaneously addresses seven major limitations of existing benchmarks and enables robust evaluation under cross-style, cross-method, and cross-language conditions. Extensive experiments demonstrate that TextShield-R1 significantly advances the state of the art in interpretable tampered text detection.

Mu Cai, Reuben Tan, Jianrui Zhang et al.

Understanding fine-grained temporal dynamics is crucial for multimodal video comprehension and generation. Due to the lack of fine-grained temporal annotations, existing video benchmarks mostly resemble static image benchmarks and are incompetent at evaluating models for temporal understanding. In this paper, we introduce TemporalBench, a new benchmark dedicated to evaluating fine-grained temporal understanding in videos. TemporalBench consists of ~10K video question-answer pairs, derived from ~2K high-quality human annotations detailing the temporal dynamics in video clips. As a result, our benchmark provides a unique testbed for evaluating various temporal understanding and reasoning abilities such as action frequency, motion magnitude, event order, etc. Moreover, it enables evaluations on various tasks like both video question answering and captioning, both short and long video understanding, as well as different models such as multimodal video embedding models and text generation models. Results show that state-of-the-art models like GPT-4o achieve only 38.5% question answering accuracy on TemporalBench, demonstrating a significant gap (~30%) between humans and AI in temporal understanding. Furthermore, we notice a critical pitfall for multi-choice QA where LLMs can detect the subtle changes in negative captions and find a centralized description as a cue for its prediction, where we propose Multiple Binary Accuracy (MBA) to correct such bias. We hope that TemporalBench can foster research on improving models' temporal reasoning capabilities. Both dataset and evaluation code will be made available.

Yiwu Zhong, Liwei Wang, Jianshu Chen et al.

We address the challenging problem of image captioning by revisiting the representation of image scene graph. At the core of our method lies the decomposition of a scene graph into a set of sub-graphs, with each sub-graph capturing a semantic component of the input image. We design a deep model to select important sub-graphs, and to decode each selected sub-graph into a single target sentence. By using sub-graphs, our model is able to attend to different components of the image. Our method thus accounts for accurate, diverse, grounded and controllable captioning at the same time. We present extensive experiments to demonstrate the benefits of our comprehensive captioning model. Our method establishes new state-of-the-art results in caption diversity, grounding, and controllability, and compares favourably to latest methods in caption quality. Our project website can be found at http://pages.cs.wisc.edu/~yiwuzhong/Sub-GC.html.