AIM: Adaptive Inference of Multi-Modal LLMs via Token Merging and Pruning

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, under 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 will be available at https://github.com/LaVi-Lab/AIM.

Omni-IML: Towards Unified Image Manipulation Localization

Image manipulation can lead to misinterpretation of visual content, posing significant risks to information security. Image Manipulation Localization (IML) has thus received increasing attention. However, existing IML methods rely heavily on task-specific designs, making them perform well only on one target image type but are mostly random guessing on other image types, and even joint training on multiple image types causes significant performance degradation. This hinders the deployment for real applications as it notably increases maintenance costs and the misclassification of image types leads to serious error accumulation. To this end, we propose Omni-IML, the first generalist model to unify diverse IML tasks. Specifically, Omni-IML achieves generalism by adopting the Modal Gate Encoder and the Dynamic Weight Decoder to adaptively determine the optimal encoding modality and the optimal decoder filters for each sample. We additionally propose an Anomaly Enhancement module that enhances the features of tampered regions with box supervision and helps the generalist model to extract common features across different IML tasks. We validate our approach on IML tasks across three major scenarios: natural images, document images, and face images. Without bells and whistles, our Omni-IML achieves state-of-the-art performance on all three tasks with a single unified model, providing valuable strategies and insights for real-world application and future research in generalist image forensics. Our code will be publicly available.

TemporalBench: Benchmarking Fine-grained Temporal Understanding for Multimodal Video Models

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.

Enhancing Temporal Modeling of Video LLMs via Time Gating

Video Large Language Models (Video LLMs) have achieved impressive performance on video-and-language tasks, such as video question answering. However, most existing Video LLMs neglect temporal information in video data, leading to struggles with temporal-aware video understanding. To address this gap, we propose a Time Gating Video LLM (TG-Vid) designed to enhance temporal modeling through a novel Time Gating module (TG). The TG module employs a time gating mechanism on its sub-modules, comprising gating spatial attention, gating temporal attention, and gating MLP. This architecture enables our model to achieve a robust understanding of temporal information within videos. Extensive evaluation of temporal-sensitive video benchmarks (i.e., MVBench, TempCompass, and NExT-QA) demonstrates that our TG-Vid model significantly outperforms the existing Video LLMs. Further, comprehensive ablation studies validate that the performance gains are attributed to the designs of our TG module. Our code is available at https://github.com/LaVi-Lab/TG-Vid.

Generalized Tampered Scene Text Detection in the era of Generative AI

The rapid advancements of generative AI have fueled the potential of generative text image editing while simultaneously escalating the threat of misinformation spreading. However, existing forensics methods struggle to detect unseen forgery types that they have not been trained on, leaving the development of a model capable of generalized detection of tampered scene text as an unresolved issue. 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 pre-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 will be open-source.

Beyond Embeddings: The Promise of Visual Table in Multi-Modal Models

Visual representation learning has been a cornerstone in computer vision, evolving from supervised learning with human-annotated labels to aligning image-text pairs from the Internet. Despite recent advancements in multi-modal large language models (MLLMs), the visual representations they rely on, such as CLIP embeddings, often lack access to external world knowledge critical for real-world visual reasoning. In this work, we propose Visual Table, a novel visual representation tailored for MLLMs. It provides hierarchical text descriptions of holistic visual scenes, consisting of a scene description and multiple object-centric descriptions that encompass categories, attributes, and knowledge at instance level. We further develop a scalable generator for visual table generation and train it on small-scale annotations from GPT4V. Extensive evaluations demonstrate that, with generated visual tables as additional visual representations, our model can consistently outperform the state-of-the-art (SOTA) MLLMs across diverse benchmarks. When visual tables serve as standalone visual representations, our model can closely match or even beat the SOTA MLLMs that are built on CLIP visual embeddings. Our code is available at https://github.com/LaVi-Lab/Visual-Table.

Towards Learning a Generalist Model for Embodied Navigation

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.

GPT-4V in Wonderland: Large Multimodal Models for Zero-Shot Smartphone GUI Navigation

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.

Robust and Interpretable Medical Image Classifiers via Concept Bottleneck Models

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.

Learning Concise and Descriptive Attributes for Visual Recognition

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.