Systematic Abductive Reasoning via Diverse Relation Representations in Vector-symbolic Architecture

In abstract visual reasoning, monolithic deep learning models suffer from limited interpretability and generalization, while existing neuro-symbolic approaches fall short in capturing the diversity and systematicity of attributes and relation representations. To address these challenges, we propose a Systematic Abductive Reasoning model with diverse relation representations (Rel-SAR) in Vector-symbolic Architecture (VSA) to solve Raven's Progressive Matrices (RPM). To derive attribute representations with symbolic reasoning potential, we introduce not only various types of atomic vectors that represent numeric, periodic and logical semantics, but also the structured high-dimentional representation (SHDR) for the overall Grid component. For systematic reasoning, we propose novel numerical and logical relation functions and perform rule abduction and execution in a unified framework that integrates these relation representations. Experimental results demonstrate that Rel-SAR achieves significant improvement on RPM tasks and exhibits robust out-of-distribution generalization. Rel-SAR leverages the synergy between HD attribute representations and symbolic reasoning to achieve systematic abductive reasoning with both interpretable and computable semantics.

VARGPT: Unified Understanding and Generation in a Visual Autoregressive Multimodal Large Language Model

We present VARGPT, a novel multimodal large language model (MLLM) that unifies visual understanding and generation within a single autoregressive framework. VARGPT employs a next-token prediction paradigm for visual understanding and a next-scale prediction paradigm for visual autoregressive generation. VARGPT innovatively extends the LLaVA architecture, achieving efficient scale-wise autoregressive visual generation within MLLMs while seamlessly accommodating mixed-modal input and output within a single model framework. Our VARGPT undergoes a three-stage unified training process on specially curated datasets, comprising a pre-training phase and two mixed visual instruction-tuning phases. The unified training strategy are designed to achieve alignment between visual and textual features, enhance instruction following for both understanding and generation, and improve visual generation quality, respectively. Despite its LLAVA-based architecture for multimodel understanding, VARGPT significantly outperforms LLaVA-1.5 across various vision-centric benchmarks, such as visual question-answering and reasoning tasks. Notably, VARGPT naturally supports capabilities in autoregressive visual generation and instruction-to-image synthesis, showcasing its versatility in both visual understanding and generation tasks. Project page is at: \url{https://vargpt-1.github.io/}

MMVU: Measuring Expert-Level Multi-Discipline Video Understanding

We introduce MMVU, a comprehensive expert-level, multi-discipline benchmark for evaluating foundation models in video understanding. MMVU includes 3,000 expert-annotated questions spanning 27 subjects across four core disciplines: Science, Healthcare, Humanities & Social Sciences, and Engineering. Compared to prior benchmarks, MMVU features three key advancements. First, it challenges models to apply domain-specific knowledge and perform expert-level reasoning to analyze specialized-domain videos, moving beyond the basic visual perception typically assessed in current video benchmarks. Second, each example is annotated by human experts from scratch. We implement strict data quality controls to ensure the high quality of the dataset. Finally, each example is enriched with expert-annotated reasoning rationals and relevant domain knowledge, facilitating in-depth analysis. We conduct an extensive evaluation of 32 frontier multimodal foundation models on MMVU. The latest System-2-capable models, o1 and Gemini 2.0 Flash Thinking, achieve the highest performance among the tested models. However, they still fall short of matching human expertise. Through in-depth error analyses and case studies, we offer actionable insights for future advancements in expert-level, knowledge-intensive video understanding for specialized domains.

GLAM: Global-Local Variation Awareness in Mamba-based World Model

Mimicking the real interaction trajectory in the inference of the world model has been shown to improve the sample efficiency of model-based reinforcement learning (MBRL) algorithms. Many methods directly use known state sequences for reasoning. However, this approach fails to enhance the quality of reasoning by capturing the subtle variation between states. Much like how humans infer trends in event development from this variation, in this work, we introduce Global-Local variation Awareness Mamba-based world model (GLAM) that improves reasoning quality by perceiving and predicting variation between states. GLAM comprises two Mambabased parallel reasoning modules, GMamba and LMamba, which focus on perceiving variation from global and local perspectives, respectively, during the reasoning process. GMamba focuses on identifying patterns of variation between states in the input sequence and leverages these patterns to enhance the prediction of future state variation. LMamba emphasizes reasoning about unknown information, such as rewards, termination signals, and visual representations, by perceiving variation in adjacent states. By integrating the strengths of the two modules, GLAM accounts for highervalue variation in environmental changes, providing the agent with more efficient imagination-based training. We demonstrate that our method outperforms existing methods in normalized human scores on the Atari 100k benchmark.

Bridging Visualization and Optimization: Multimodal Large Language Models on Graph-Structured Combinatorial Optimization

Graph-structured combinatorial challenges are inherently difficult due to their nonlinear and intricate nature, often rendering traditional computational methods ineffective or expensive. However, these challenges can be more naturally tackled by humans through visual representations that harness our innate ability for spatial reasoning. In this study, we propose transforming graphs into images to preserve their higher-order structural features accurately, revolutionizing the representation used in solving graph-structured combinatorial tasks. This approach allows machines to emulate human-like processing in addressing complex combinatorial challenges. By combining the innovative paradigm powered by multimodal large language models (MLLMs) with simple search techniques, we aim to develop a novel and effective framework for tackling such problems. Our investigation into MLLMs spanned a variety of graph-based tasks, from combinatorial problems like influence maximization to sequential decision-making in network dismantling, as well as addressing six fundamental graph-related issues. Our findings demonstrate that MLLMs exhibit exceptional spatial intelligence and a distinctive capability for handling these problems, significantly advancing the potential for machines to comprehend and analyze graph-structured data with a depth and intuition akin to human cognition. These results also imply that integrating MLLMs with simple optimization strategies could form a novel and efficient approach for navigating graph-structured combinatorial challenges without complex derivations, computationally demanding training and fine-tuning.

EndoChat: Grounded Multimodal Large Language Model for Endoscopic Surgery

Recently, Multimodal Large Language Models (MLLMs) have demonstrated their immense potential in computer-aided diagnosis and decision-making. In the context of robotic-assisted surgery, MLLMs can serve as effective tools for surgical training and guidance. However, there is still a lack of MLLMs specialized for surgical scene understanding in clinical applications. In this work, we introduce EndoChat to address various dialogue paradigms and subtasks in surgical scene understanding that surgeons encounter. To train our EndoChat, we construct the Surg-396K dataset through a novel pipeline that systematically extracts surgical information and generates structured annotations based on collected large-scale endoscopic surgery datasets. Furthermore, we introduce a multi-scale visual token interaction mechanism and a visual contrast-based reasoning mechanism to enhance the model's representation learning and reasoning capabilities. Our model achieves state-of-the-art performance across five dialogue paradigms and eight surgical scene understanding tasks. Additionally, we conduct evaluations with professional surgeons, most of whom provide positive feedback on collaborating with EndoChat. Overall, these results demonstrate that our EndoChat has great potential to significantly advance training and automation in robotic-assisted surgery.

InternLM-XComposer2.5-Reward: A Simple Yet Effective Multi-Modal Reward Model

Despite the promising performance of Large Vision Language Models (LVLMs) in visual understanding, they occasionally generate incorrect outputs. While reward models (RMs) with reinforcement learning or test-time scaling offer the potential for improving generation quality, a critical gap remains: publicly available multi-modal RMs for LVLMs are scarce, and the implementation details of proprietary models are often unclear. We bridge this gap with InternLM-XComposer2.5-Reward (IXC-2.5-Reward), a simple yet effective multi-modal reward model that aligns LVLMs with human preferences. To ensure the robustness and versatility of IXC-2.5-Reward, we set up a high-quality multi-modal preference corpus spanning text, image, and video inputs across diverse domains, such as instruction following, general understanding, text-rich documents, mathematical reasoning, and video understanding. IXC-2.5-Reward achieves excellent results on the latest multi-modal reward model benchmark and shows competitive performance on text-only reward model benchmarks. We further demonstrate three key applications of IXC-2.5-Reward: (1) Providing a supervisory signal for RL training. We integrate IXC-2.5-Reward with Proximal Policy Optimization (PPO) yields IXC-2.5-Chat, which shows consistent improvements in instruction following and multi-modal open-ended dialogue; (2) Selecting the best response from candidate responses for test-time scaling; and (3) Filtering outlier or noisy samples from existing image and video instruction tuning training data. To ensure reproducibility and facilitate further research, we have open-sourced all model weights and training recipes at https://github.com/InternLM/InternLM-XComposer

MAPS: Advancing Multi-Modal Reasoning in Expert-Level Physical Science

Pre-trained on extensive text and image corpora, current Multi-Modal Large Language Models (MLLM) have shown strong capabilities in general visual reasoning tasks. However, their performance is still lacking in physical domains that require understanding diagrams with complex physical structures and quantitative analysis based on multi-modal information. To address this, we develop a new framework, named Multi-Modal Scientific Reasoning with Physics Perception and Simulation (MAPS) based on an MLLM. MAPS decomposes expert-level multi-modal reasoning task into physical diagram understanding via a Physical Perception Model (PPM) and reasoning with physical knowledge via a simulator. The PPM module is obtained by fine-tuning a visual language model using carefully designed synthetic data with paired physical diagrams and corresponding simulation language descriptions. At the inference stage, MAPS integrates the simulation language description of the input diagram provided by PPM and results obtained through a Chain-of-Simulation process with MLLM to derive the underlying rationale and the final answer. Validated using our collected college-level circuit analysis problems, MAPS significantly improves reasoning accuracy of MLLM and outperforms all existing models. The results confirm MAPS offers a promising direction for enhancing multi-modal scientific reasoning ability of MLLMs. We will release our code, model and dataset used for our experiments upon publishing of this paper.

Can Multimodal LLMs do Visual Temporal Understanding and Reasoning? The answer is No!

Multimodal Large Language Models (MLLMs) have achieved significant advancements in tasks like Visual Question Answering (VQA) by leveraging foundational Large Language Models (LLMs). However, their abilities in specific areas such as temporal understanding, which is crucial for comprehending real-world dynamics, remain underexplored. To address this, we propose a challenging evaluation benchmark named TemporalVQA, consisting of two parts: (1) Temporal Order Understanding and (2) Time-lapse Estimation. The first part requires MLLMs to determine the sequence of events by analyzing temporally consecutive video frames. The second part presents image pairs with varying time differences, framed as multiple-choice questions, asking MLLMs to estimate the time-lapse between images with options ranging from seconds to years. Our evaluations of advanced MLLMs, including models like GPT-4o and Gemini-1.5-Pro, reveal significant challenges: GPT-4o achieved only 43.8% average consistent accuracy in temporal order tasks and 70% in time-lapse estimation, with open-source models performing even less effectively. These findings underscore the limitations of current MLLMs in visual temporal understanding and reasoning, highlighting the need for further improvements in their temporal capabilities. Our dataset can be found at https://huggingface.co/datasets/fazliimam/temporal-vqa.

Visual RAG: Expanding MLLM visual knowledge without fine-tuning

Multimodal Large Language Models (MLLMs) have achieved notable performance in computer vision tasks that require reasoning across visual and textual modalities, yet their capabilities are limited to their pre-trained data, requiring extensive fine-tuning for updates. Recent researches have explored the use of In-Context Learning (ICL) to overcome these challenges by providing a set of demonstrating examples as context to augment MLLMs performance in several tasks, showing that many-shot ICL leads to substantial improvements compared to few-shot ICL. However, the reliance on numerous demonstrating examples and the limited MLLMs context windows presents significant obstacles. This paper aims to address these challenges by introducing a novel approach, Visual RAG, that synergically combines the MLLMs capability to learn from the context, with a retrieval mechanism. The crux of this approach is to ensure to augment the MLLM knowledge by selecting only the most relevant demonstrating examples for the query, pushing it to learn by analogy. In this way, relying on the new information provided dynamically during inference time, the resulting system is not limited to the knowledge extracted from the training data, but can be updated rapidly and easily without fine-tuning. Furthermore, this greatly reduces the computational costs for improving the model image classification performance, and augments the model knowledge to new visual domains and tasks it was not trained for. Extensive experiments on eight different datasets in the state of the art spanning several domains and image classification tasks show that the proposed Visual RAG, compared to the most recent state of the art (i.e., many-shot ICL), is able to obtain an accuracy that is very close or even higher (approx. +2% improvement on average) while using a much smaller set of demonstrating examples (approx. only 23% on average).