Multimodal Large Language Models

While Multimodal Large Language Models (MLLMs) have become adept at recognizing objects, they often lack the intuitive, human-like understanding of the world's underlying physical and social principles. This high-level vision-grounded semantics, which we term visual knowledge, forms a bridge between perception and reasoning, yet remains an underexplored area in current MLLMs. To systematically evaluate this capability, we present VKnowU, a comprehensive benchmark featuring 1,680 questions in 1,249 videos, covering 8 core types of visual knowledge spanning both world-centric (e.g., intuitive physics) and human-centric (e.g., subjective intentions). Evaluation of 28 SOTA MLLMs reveals that leading models still fall short of human performance, with particularly notable gaps in the world-centric. To bridge this gap, we introduce a new dataset, VKnowQA, and VideoKnow+, a baseline model that explicitly incorporates visual knowledge into MLLMs. VideoKnow+ follows a structured See-Think-Answer paradigm and adopts reinforcement learning with visual knowledge reward, achieving a +3.7% improvement on VKnowU and consistent gains on MVBench (+5.4%), Video-MME (+7.0%), and MMVU (+5.7%). Our work highlights visual knowledge as a missing cornerstone for developing more generalizable MLLMs that can not only see but also truly understand our worlds.

Multimodal large language models (MLLMs) can inadvertently memorize privacy-sensitive information during training. While existing unlearning methods can remove such content, they often severely degrade the model's foundational capabilities, such as general image understanding. This critical shortfall motivates our investigation into benign memory forgetting, the precise removal of targeted, privacy-sensitive knowledge while rigorously preserving unrelated capabilities. To pioneer and evaluate progress toward this objective, we introduce S-MLLMUn Bench, the first benchmark designed to jointly and quantitatively assess an unlearning method's efficacy in knowledge erasure and the preservation of image understanding. Furthermore, we propose the Sculpted Memory Forgetting Adapter (SMFA), a new framework that enables benign memory forgetting. SMFA confines forgetting to designated memory regions, maintaining overall model performance. By initially fine-tuning the model to replace sensitive outputs with refusals, SMFA generates a memory forgetting adapter, followed by a retaining anchor-guided masking mechanism that safeguards unrelated knowledge. Extensive experiments on S-MLLMUn Bench demonstrate that existing methods fail to achieve benign forgetting, whereas our proposed SMFA serves as an effective baseline, successfully achieving targeted knowledge erasure without compromising the model's foundational visual capabilities. Code and data are available at https://github.com/zeng-zhen/S-MLLMUn.

Recent advancements in multimodal large language models (MLLMs) have shown strong understanding of driving scenes, drawing interest in their application to autonomous driving. However, high-level reasoning in safety-critical scenarios, where avoiding one traffic risk can create another, remains a major challenge. Such reasoning is often infeasible with only a single front view and requires a comprehensive view of the environment, which we achieve through multi-view inputs. We define Safety-Critical Reasoning as a new task that leverages multi-view inputs to address this challenge. Then, we distill Safety-Critical Reasoning into two stages: first resolve the immediate risk, then mitigate the decision-induced downstream risks. To support this, we introduce WaymoQA, a dataset of 35,000 human-annotated question-answer pairs covering complex, high-risk driving scenarios. The dataset includes multiple-choice and open-ended formats across both image and video modalities. Experiments reveal that existing MLLMs underperform in safety-critical scenarios compared to normal scenes, but fine-tuning with WaymoQA significantly improves their reasoning ability, highlighting the effectiveness of our dataset in developing safer and more reasoning-capable driving agents. Our code and data are provided in https://github.com/sjyu001/WaymoQA

In this work, we define Foresight Intelligence as the capability to anticipate and interpret future events-an ability essential for applications such as autonomous driving, yet largely overlooked by existing research. To bridge this gap, we introduce FSU-QA, a new Visual Question-Answering (VQA) dataset specifically designed to elicit and evaluate Foresight Intelligence. Using FSU-QA, we conduct the first comprehensive study of state-of-the-art Vision-Language Models (VLMs) under foresight-oriented tasks, revealing that current models still struggle to reason about future situations. Beyond serving as a benchmark, FSU-QA also enables the assessment of world models by measuring the semantic coherence of their generated predictions, quantified through performance gains when VLMs are augmented with such outputs. Our experiments further demonstrate that FSU-QA can effectively enhance foresight reasoning: even small VLMs fine-tuned on FSU-QA surpass much larger, advanced models by a substantial margin. Together, these findings position FSU-QA as a principled foundation for developing next-generation models capable of truly anticipating and understanding future events. Furthermore, beyond model performance, we examine whether WM-generated predictions remain semantically consistent by using VLM-based proxy judges, and validate this evaluation protocol through shuffled control experiments. Fine-tuning models on FSU-QA leads to substantial improvements in foresight understanding, demonstrating the dataset's effectiveness and offering a principled foundation for future research.

Multimodal Large Language Models (MLLMs) show promising results as decision-making engines for embodied agents operating in complex, physical environments. However, existing benchmarks often prioritize high-level planning or spatial reasoning, leaving the fine-grained action intelligence required for embodied physical interaction underexplored. To address this gap, we introduce CFG-Bench, a new benchmark designed to systematically evaluate this crucial capability. CFG-Bench consists of 1,368 curated videos paired with 19,562 question-answer pairs spanning three evaluation paradigms targeting four cognitive abilities: 1) Physical Interaction, 2) Temporal-Causal Relation, 3) Intentional Understanding, and 4) Evaluative Judgment. Together, these dimensions provide a systematic framework for assessing a model's ability to translate visual observations into actionable knowledge, moving beyond mere surface-level recognition. Our comprehensive evaluation on CFG-Bench reveals that leading MLLMs struggle to produce detailed instructions for physical interactions and exhibit profound limitations in the higher-order reasoning of intention and evaluation. Moreover, supervised fine-tuning (SFT) on our data demonstrates that teaching an MLLMs to articulate fine-grained actions directly translates to significant performance gains on established embodied benchmarks. Our analysis highlights these limitations and offers insights for developing more capable and grounded embodied agents. Project page: https://cfg-bench.github.io/

Multimodal large language models (MLLMs) have demonstrated powerful capabilities in general spatial understanding and reasoning. However, their fine-grained spatial understanding and reasoning capabilities in complex urban scenarios have not received significant attention in the fields of both research and industry. To fill this gap, we focus primarily on road markings as a typical example of fine-grained spatial elements under urban scenarios, given the essential role of the integrated road traffic network they form within cities. Around road markings and urban traffic systems, we propose \textbf{RoadBench}, a systematic benchmark that comprehensively evaluates MLLMs' fine-grained spatial understanding and reasoning capabilities using Bird's-Eye View (BEV) and First-Person View (FPV) image inputs. This benchmark comprises eight tasks consisting of 3,040 strictly manually verified test cases, constructed from 2,137 unique BEV images and 721 unique FPV images collected from five Chinese cities with relatively consistent traffic conventions. These tasks form a systematic evaluation framework that bridges understanding at local spatial scopes to global reasoning. They not only test MLLMs' capabilities in recognition, joint understanding, and reasoning but also assess their ability to integrate image information with domain knowledge. After evaluating 20 mainstream MLLMs, we confirm that RoadBench is a challenging benchmark for MLLMs while revealing significant shortcomings in existing MLLMs' fine-grained spatial understanding and reasoning capabilities within urban scenarios. In certain tasks, their performance even falls short of simple rule-based or random selection baselines. These findings, along with RoadBench itself, will contribute to the comprehensive advancement of spatial understanding capabilities for MLLMs.

Chain-of-Thought (CoT) prompting has proven remarkably effective for eliciting complex reasoning in large language models (LLMs). Yet, its potential in multimodal large language models (MLLMs) remains largely untapped, hindered by the absence of large-scale datasets that capture the rich, spatially grounded reasoning intrinsic to visual understanding. Existing visual-CoT resources are typically small, domain-specific, or lack the human-like stepwise structure necessary for compositional visual reasoning. In this paper, we introduce VisReason, a large-scale dataset designed to advance visual Chain-of-Thought reasoning. VisReason comprises 489K annotated examples spanning four diverse domains, each featuring multi-round, human-like rationales that guide MLLMs through interpretable visual reasoning steps. Building upon this, we curate VisReason-Pro, a 165K subset produced with a stronger expert-level GPT annotator, enriched with detailed reasoning traces and 3D spatial grounding via depth-informed annotations. Fine-tuning the state-of-the-art Qwen2.5-VL model on VisReason and VisReason-Pro yields substantial improvements in step-by-step visual reasoning accuracy, interpretability, and cross-benchmark generalization. These results demonstrate that VisReason equips MLLMs with more systematic and generalizable reasoning capabilities. We envision VisReason as a cornerstone for cultivating human-like visual reasoning, paving the way toward the next generation of multimodal intelligence.

Multimodal large language models (MLLMs) have achieved remarkable progress in vision-language tasks, but continue to struggle with spatial reasoning. Existing spatial MLLMs rely on large-scale datasets, explicit 3D inputs, architecture-specific modifications, or sparse Reinforcement Learning (RL) methods that provide insufficient guidance for spatially-grounded reasoning. We introduce SpatialThinker. To our knowledge, it is the first MLLM unifying Scene Graph Generation (SGG) and visual reasoning in a single pass via online RL. The model simulates human-like spatial perception by constructing a mental scene graph of task-relevant objects and relations, and reasoning toward an answer via dense spatial rewards. Our contributions are threefold: (1) SGG-grounded reasoning: integrating SGG directly within the reasoning chain rather than as a disjoint preprocessing step; (2) STVQA-7K: a high-quality spatial VQA training dataset via a scalable synthesis pipeline; and (3) a dense spatial reward design that enforces structured grounding during RL and generalizes to improve broad visual perception. SpatialThinker-7B achieves 3.6$\times$ larger gains over SFT and $1.7\times$ better in- and out-of-distribution generalization than sparse RL. Trained on only 7K samples, SpatialThinker-7B matches GPT-5 and outperforms GPT-4o, while SpatialThinker-30B surpasses both GPT-5 and Claude 4 Sonnet on average across 14 spatial and real-world benchmarks, demonstrating that structured spatial grounding with reward-aligned reasoning enables robust spatial understanding with limited data.

Fine-grained cross-modal alignment aims to establish precise local correspondences between vision and language, forming a cornerstone for visual question answering and related multimodal applications. Current approaches face challenges in addressing patch redundancy and ambiguity, which arise from the inherent information density disparities across modalities. Recently, Multimodal Large Language Models (MLLMs) have emerged as promising solutions to bridge this gap through their robust semantic generation capabilities. However, the dense textual outputs from MLLMs may introduce conflicts with the original sparse captions. Furthermore, accurately quantifying semantic relevance between rich visual patches and concise textual descriptions remains a core challenge. To overcome these limitations, we introduce the Semantic-Enhanced Patch Slimming (SEPS) framework, which systematically addresses patch redundancy and ambiguity. Our approach employs a two-stage mechanism to integrate unified semantics from both dense and sparse texts, enabling the identification of salient visual patches. Additionally, it leverages relevance-aware selection with mean value computation to highlight crucial patch-word correspondences, thereby improving cross-modal similarity assessment. Comprehensive experiments on Flickr30K and MS-COCO datasets validate that SEPS achieves superior performance, surpassing existing approaches by 23%-86% in rSum across diverse model architectures, with notable enhancements in text-to-image retrieval scenarios. Our implementation is available at https://github.com/Sweet4tars/seps.git.

Graphical user interface (GUI) grounding is a key capability for computer-use agents, mapping natural-language instructions to actionable regions on the screen. Existing Multimodal Large Language Model (MLLM) approaches typically formulate GUI grounding as a text-based coordinate generation task. However, directly generating precise coordinates from visual inputs is challenging and often data-intensive. A more intuitive strategy is to first identify instruction-relevant visual patches and then determine the exact click location within them. Motivated by recent observations that general MLLMs exhibit native grounding ability embedded in their attention maps, we propose GUI-AIMA, an attention-based and coordinate-free supervised fine-tuning framework for efficient GUI grounding. GUI-AIMA aligns the intrinsic multimodal attention of MLLMs with patch-wise grounding signals. These signals are calculated adaptively for diverse user instructions by multi-head aggregation on simplified query-visual attention matrices. Besides, its coordinate-free manner can easily integrate a plug-and-play zoom-in stage. GUI-AIMA-3B was trained with only 509k samples (around 101k screenshots), demonstrating exceptional data efficiency and verifying that light training can trigger the native grounding capability of MLLMs. It achieves state-of-the-art performance among 3B models, attaining an average accuracy of 61.5% on ScreenSpot-Pro, 92.1% on ScreenSpot-v2, 68.1% on OSWorld-G, 79.1% on MMBench-GUI-L2, and 60.0% on UI-Vision. Project page: https://github.com/sjz5202/GUI-AIMA .

Building robots that can perceive, reason, and act in dynamic, unstructured environments remains a central challenge. Recent embodied systems often follow a dual-system paradigm, where System 2 performs high-level reasoning and System 1 handles low-level control. We refer to System 2 as the embodied brain, the cognitive core for decision-making in manipulation. Although evaluating this embodied brain is crucial, existing benchmarks mainly measure execution success or cover only limited aspects of high-level cognition and task realism. We introduce RoboBench, a benchmark for evaluating multimodal large language models (MLLMs) as embodied brains. RoboBench covers five dimensions: Instruction Comprehension, Perception Reasoning, Generalized Planning, Affordance Prediction, and Failure Analysis. It spans 14 capabilities, 25 tasks, and 6,092 QA pairs. To improve realism, it draws from large-scale real robotic data and in-house collection across diverse embodiments, attribute-rich objects, multi-view scenes, and memory-driven navigation. For planning, RoboBench introduces an MLLM-as-world-simulator framework that assesses whether predicted plans can achieve critical object-state changes under physical and visual constraints, enabling more faithful evaluation of long-horizon reasoning than symbolic matching. Experiments on 18 state-of-the-art MLLMs reveal persistent limitations in implicit instruction understanding, spatiotemporal reasoning, cross-scenario planning, fine-grained affordance understanding, and failure diagnosis. We further analyze how embodied cognitive abilities relate to downstream robotic control. RoboBench offers a comprehensive scaffold for quantifying high-level cognition and guiding next-generation MLLMs toward more robust robotic intelligence.

Multimodal large language models (MLLMs) often miss small details and spatial relations in cluttered scenes, leading to errors in fine-grained perceptual grounding. We introduce AttWarp, a lightweight method that allocates more resolution to query-relevant content while compressing less informative areas, all while preserving global context. At test time, the approach uses an MLLM's cross-modal attention to perform rectilinear warping of the input image, reallocating spatial resolution toward regions the model deems important, without changing model weights or architecture. This attention-guided warping preserves all original image information but redistributes it non-uniformly, so small objects and subtle relationships become easier for the same model to read while the global layout remains intact. Across five benchmarks (TextVQA, GQA, DocVQA, POPE, MMMU) and four MLLMs (LLaVA, Qwen-VL, InternVL, and InstructBLIP), AttWarp consistently improves accuracy, strengthens compositional reasoning, and reduces hallucinations, outperforming four competitive baselines that manipulate raw images at test time. Together, these results show that attention-guided warping prioritizes information relevant to the query while preserving context, and that the same MLLMs perform better when given such warped inputs.

Multimodal Large Language Models (MLLMs) often struggle with fine-grained perception, such as identifying small objects in high-resolution images or detecting key moments in long videos. Existing methods typically rely on complex, task-specific fine-tuning, which reduces generalizability and increases system complexity. In this work, we propose an effective, training-free framework that uses an MLLM's intrinsic uncertainty as proactive guidance. Our core insight is that a model's uncertainty decreases when provided with relevant visual information. We introduce a unified mechanism that scores candidate visual inputs by response uncertainty, enabling the model to autonomously focus on the most informative data. We apply this simple principle to three challenging visual tasks: Visual Search, Long Video Understanding, and Temporal Grounding, allowing off-the-shelf MLLMs to achieve performance competitive with specialized, fine-tuned systems. Our results demonstrate that leveraging intrinsic uncertainty is a powerful strategy for improving fine-grained multimodal performance.

Large Language Models (LLMs) with multimodal capabilities have revolutionized vision-language tasks, but their deployment often requires huge memory and computational resources. Post-training quantization (PTQ) has successfully compressed language models to as low as 1-bit precision, its effectiveness for multimodal LLMs (MLLMs) remains unexplored. In this paper, we present the first method for ultra-low-bit (<4-bit) quantization of MLLMs. Our analysis reveals that multimodal tokens and intermediate layer activations produced by them exhibit significantly higher entropy compared to text tokens, indicating greater functional complexity that makes MLLMs less tolerant to ultra-low bit quantization. However, this entropy varies significantly across layers, with some layers producing lower-entropy activation distributions that we empirically show can better tolerate ultra-low bit quantization. Existing PTQ methods optimize weight quantization within each layer but apply the same target precision uniformly, ignoring this variation in complexity across layers. Building on this insight, we propose LUQ: Layerwise Ultra-Low Bit Quantization, which characterizes each transformer layer's functional complexity via its output activation entropy and selectively applies ultra-low bit quantization to layers encoding simpler, more compressible functions. We also show that multimodal calibration (image and text tokens) boosts VQA performance in the ultra-low bit regime. Evaluated on LLaVA-1.5 and Qwen-2.5-VL across 9 VQA benchmarks, LUQ models use 40% and 31% less memory than their 4-bit counterparts while exhibiting less than 10% degradation on MME.

Multimodal large language models (MLLMs) have achieved strong vision-language performance, yet their token-level visual evidence remains difficult to inspect. Recent logit-lens attribution methods project each visual-token hidden state into the vocabulary space to explain generated words, but this token-wise readout introduces a mismatch: visual tokens are context-mixed by the model, while the attribution score is decoded independently at each token location. This often produces fragmented attribution maps and can be further affected by autoregressive context signals from preceding text tokens. We propose ERCR, an attribution framework built from Evidence Recomposition (ER) and Predictive Context Residualization (PCR). ER aggregates target evidence across multiple views with different token-to-region assignments, reducing attribution fragmentation caused by a single readout grid. PCR estimates a preceding-token context map with RBO-based rank relevance and subtracts its fitted component from the ER map to suppress context-token interference. Experiments on LLaVA, Qwen2-VL, and InternVL families across COCO Caption, GranDf, and OpenPSG show that ERCR improves visual evidence for target tokens and mitigates preceding-token context interference under the existing evaluation protocol. On Qwen2-VL-2B, ERCR improves TAM F1-IoU from 39.10 to 44.45 on COCO Caption and from 30.83 to 37.20 on GranDf. Overall, ERCR provides a practical refinement for token-level visual evidence inspection.

Multimodal large language models (MLLMs) have recently demonstrated remarkable reasoning abilities under reinforcement learning (RL) paradigm. However, most existing multimodal medical reasoning models focus on basic reasoning, which refers to shallow inference based on visual feature matching. In contrast, real-world clinical diagnosis extends beyond basic reasoning, demanding complex reasoning that integrates heterogeneous clinical information (such as chief complaints and medical history) with multimodal medical imaging data. To bridge this gap, we introduce MM-Retinal-Reason, an ophthalmic multimodal dataset covering the full spectrum of perception and reasoning. Specifically, it is the first dataset in ophthalmology to encompass both basic and complex reasoning tasks with Chain-of-Thought (CoT) trajectories, aiming to enhance visual-centric reasoning and emulate realistic clinical decision-making. Building upon MM-Retinal-Reason, we propose OphthaReason, the first RL-enhanced ophthalmic multimodal reasoning model with step-by-step reasoning traces. To enable flexible adaptation to both basic and complex reasoning tasks, we further introduce Uncertainty-Aware Dynamic Thinking (UADT), which estimates sample-level uncertainty via entropy and dynamically modulates exploration depth through a shaped advantage mechanism. Comprehensive experiments demonstrate the effectiveness of our model on both basic and complex reasoning tasks, outperforming general-purpose MLLMs, medical MLLMs, RL-based medical MLLMs, and ophthalmic MLLMs by at least 15.47%. Project Page: link.

While Multimodal Large Language Models (MLLMs) demonstrate remarkable capabilities across diverse domains, their application to specialized anomaly detection (AD) remains constrained by domain adaptation challenges. Existing Group Relative Policy Optimization (GRPO) based approaches suffer from two critical limitations: inadequate training data utilization when models produce uniform responses, and insufficient supervision over reasoning processes that encourage immediate binary decisions without deliberative analysis. We propose a comprehensive framework addressing these limitations through two synergistic innovations. First, we introduce a multi-stage deliberative reasoning process that guides models from region identification to focused examination, generating diverse response patterns essential for GRPO optimization while enabling structured supervision over analytical workflows. Second, we develop a fine-grained reward mechanism incorporating classification accuracy and localization supervision, transforming binary feedback into continuous signals that distinguish genuine analytical insight from spurious correctness. Comprehensive evaluation across multiple industrial datasets demonstrates substantial performance improvements in adapting general vision-language models to specialized anomaly detection. Our method achieves superior accuracy with efficient adaptation of existing annotations, effectively bridging the gap between general-purpose MLLM capabilities and the fine-grained visual discrimination required for detecting subtle manufacturing defects and structural irregularities.

Text-to-image (T2I) generation models have made significant strides but still struggle with prompt sensitivity: even minor changes in prompt wording can yield inconsistent or inaccurate outputs. To address this challenge, we introduce a closed-loop, test-time prompt refinement framework that requires no additional training of the underlying T2I model, termed TIR. In our approach, each generation step is followed by a refinement step, where a pretrained multimodal large language model (MLLM) analyzes the output image and the user's prompt. The MLLM detects misalignments (e.g., missing objects, incorrect attributes) and produces a refined and physically grounded prompt for the next round of image generation. By iteratively refining the prompt and verifying alignment between the prompt and the image, TIR corrects errors, mirroring the iterative refinement process of human artists. We demonstrate that this closed-loop strategy improves alignment and visual coherence across multiple benchmark datasets, all while maintaining plug-and-play integration with black-box T2I models. Code is available at https://github.com/hafeezkhan909/Test-time-Image-Refinement.

The rapid advancement of large language models (LLMs) has intensified the need for effective mechanisms to transform continuous multimodal data into discrete representations suitable for language-based processing. Discrete tokenization, with vector quantization (VQ) as a central approach, offers both computational efficiency and compatibility with LLM architectures. Despite its growing importance, there is a lack of a comprehensive survey that systematically examines VQ techniques in the context of LLM-based systems. This work fills this gap by presenting the first structured taxonomy and analysis of discrete tokenization methods designed for LLMs. We categorize 8 representative VQ variants that span classical and modern paradigms and analyze their algorithmic principles, training dynamics, and integration challenges with LLM pipelines. Beyond algorithm-level investigation, we discuss existing research in terms of classical applications without LLMs, LLM-based single-modality systems, and LLM-based multimodal systems, highlighting how quantization strategies influence alignment, reasoning, and generation performance. In addition, we identify key challenges including codebook collapse, unstable gradient estimation, and modality-specific encoding constraints. Finally, we discuss emerging research directions such as dynamic and task-adaptive quantization, unified tokenization frameworks, and biologically inspired codebook learning. This survey bridges the gap between traditional vector quantization and modern LLM applications, serving as a foundational reference for the development of efficient and generalizable multimodal systems. A continuously updated version is available at: https://github.com/jindongli-Ai/LLM-Discrete-Tokenization-Survey.

Current CT report generation frameworks predominantly rely on global feature representations, often failing to capture region-specific details and potentially missing certain abnormalities. To overcome this limitation, we propose MedRegion-CT, a region-focused multimodal large language model framework featuring three key innovations. First, we revisit the SlowFast strategy to jointly model global and fine-grained information and adapt it to the medical domain via a Region-based SlowFast Tokenizer that extracts tokens guided by clinically meaningful regions. Second, generated pseudo-masks guide the model to attend to diagnostically important anatomical regions, facilitating a systematic understanding of the overall scan context. Third, quantitative lesion information, including size, diameter, and spatial location, is encoded as structured textual prompts, enabling context-aware and clinically informed report generation. To enable rigorous evaluation, we validate our framework on multi-institutional structured report generation benchmarks. Experimental results demonstrate that MedRegion-CT achieves state-of-the-art performance, outperforming existing approaches in both linguistic quality and clinical accuracy. All code is publicly available at: https://github.com/babbu3682/MedRegion-CT.

While Multimodal Large Language Models (MLLMs) demonstrate impressive performance in benign scenarios, their cognitive reliability deteriorates significantly in complex scenes under adverse conditions. In these settings, models often rely on implicit inference without sufficient visual evidence, leading to a disconnect between perception and reasoning. Meanwhile, existing outcome-oriented benchmarks evaluate only final predictions and fail to diagnose failures in the underlying reasoning process. To address this gap, the authors propose AD2-Bench, which introduces a Hierarchical Visual Diagnosis framework that decomposes reasoning into a structured Chain of Evidence (CoE). This fine-grained diagnosis reveals that robust multimodal reasoning fundamentally depends on accurate evidence acquisition. Building on this perspective, the authors formulate reasoning from a probabilistic viewpoint and identify two primary causes of reasoning failure: Spatial Ambiguity, where models fail to distinguish target objects from background clutter, resulting in localization errors; and Semantic Uncertainty, where degraded visual features lead to incorrect semantic interpretation, resulting in understanding errors. To overcome these evidence deficiencies, they further propose Evidence-grounded Visual Reasoning (EGVOR), which replaces implicit reasoning with the explicit generation of Evidence Atoms - structured spatial-semantic triplets that enforce tight alignment between localization and semantic understanding. The model is trained through a hierarchical curriculum that progresses from reflective supervision construction to reinforcement learning, where reducing reasoning variance is explicitly rewarded. Extensive experiments demonstrate that EGVOR substantially improves reasoning stability under adverse conditions, providing a more robust framework for trustworthy multimodal cognition.

Multimodal Large Language Models (MLLMs) have demonstrated impressive capabilities in understanding common visual elements, largely due to their large-scale datasets and advanced training strategies. However, their effectiveness in medical applications remains limited due to the inherent discrepancies between data and tasks in medical scenarios and those in the general domain. Concretely, existing medical MLLMs face the following critical limitations: (1) limited coverage of medical knowledge beyond imaging, (2) heightened susceptibility to hallucinations due to suboptimal data curation processes, (3) lack of reasoning capabilities tailored for complex medical scenarios. To address these challenges, we first propose a comprehensive data curation procedure that (1) efficiently acquires rich medical knowledge data not only from medical imaging but also from extensive medical texts and general-domain data; and (2) synthesizes accurate medical captions, visual question answering (VQA), and reasoning samples. As a result, we build a multimodal dataset enriched with extensive medical knowledge. Building on the curated data, we introduce our medical-specialized MLLM: Lingshu. Lingshu undergoes multi-stage training to embed medical expertise and enhance its task-solving capabilities progressively. Besides, we preliminarily explore the potential of applying reinforcement learning with verifiable rewards paradigm to enhance Lingshu's medical reasoning ability. Additionally, we develop MedEvalKit, a unified evaluation framework that consolidates leading multimodal and textual medical benchmarks for standardized, fair, and efficient model assessment. We evaluate the performance of Lingshu on three fundamental medical tasks, multimodal QA, text-based QA, and medical report generation. The results show that Lingshu consistently outperforms the existing open-source multimodal models on most tasks ...

A recent line of research on spoken language assessment (SLA) employs neural models such as BERT and wav2vec 2.0 (W2V) to evaluate speaking proficiency across linguistic and acoustic modalities. Although both models effectively capture features relevant to oral competence, each exhibits modality-specific limitations. BERT-based methods rely on ASR transcripts, which often fail to capture prosodic and phonetic cues for SLA. In contrast, W2V-based methods excel at modeling acoustic features but lack semantic interpretability. To overcome these limitations, we propose a system that integrates W2V with Phi-4 multimodal large language model (MLLM) through a score fusion strategy. The proposed system achieves a root mean square error (RMSE) of 0.375 on the official test set of the Speak & Improve Challenge 2025, securing second place in the competition. For comparison, the RMSEs of the top-ranked, third-ranked, and official baseline systems are 0.364, 0.384, and 0.444, respectively.

Humans develop object orientation understanding progressively, from recognizing which way an object faces to reasoning about orientations across multiple objects. Yet existing vision-language benchmarks largely conflate orientation with broader spatial reasoning. We introduce Discriminative Orientation Reasoning Intelligence (DORI), a cognition-informed hierarchical benchmark that establishes object orientation as the primary evaluation target. DORI decomposes orientation into four dimensions, each evaluated at coarse (categorical) and granular (metric) levels, yielding 33,656 multiple-choice questions over 13,652 real-world and synthetic images from 14 sources. Its design isolates orientation from confounding factors through object isolation, standardized reference frames, and structured prompts. Evaluating 26 state-of-the-art vision-language models reveals a consistent limitation: models strong on general spatial benchmarks remain near-random on object-centric orientation reasoning. The best model achieves only 64.2% on coarse and 42.9% on granular judgments, with the largest drops on compound rotations and inter-object reference frame shifts. Large coarse-to-granular performance gaps further indicate reliance on categorical heuristics rather than geometric reasoning. These results establish object orientation understanding as a fundamental open challenge for multimodal systems. Dataset: https://huggingface.co/datasets/appledora/DORI-Benchmark

Decoding language from the human brain remains a grand challenge for Brain-Computer Interfaces (BCIs). Current approaches typically rely on unimodal brain representations, neglecting the brain's inherently multimodal processing. Inspired by the brain's associative mechanisms, where viewing an image can evoke related sounds and linguistic representations, we propose a unified framework that leverages Multimodal Large Language Models (MLLMs) to align brain signals with a shared semantic space encompassing text, images, and audio. A router module dynamically selects and fuses modality-specific brain features according to the characteristics of each stimulus. Experiments on various fMRI datasets with textual, visual, and auditory stimuli demonstrate state-of-the-art performance, achieving an 8.48% improvement on the most commonly used benchmark. We further extend our framework to EEG and MEG data, demonstrating flexibility and robustness across varying temporal and spatial resolutions. To our knowledge, this is the first unified BCI architecture capable of robustly decoding multimodal brain activity across diverse brain signals and stimulus types, offering a flexible solution for real-world applications.

The steady improvements of text-to-image (T2I) generative models lead to slow deprecation of automatic evaluation benchmarks that rely on static datasets, motivating researchers to seek alternative ways to evaluate T2I progress. We present Multimodal Text-to-Image Eval (MT2IE), an evaluation framework in which a single multimodal large language model (MLLM) acts as an evaluator agent, iteratively generating the evaluation prompts and scoring the resulting images. We show that MT2IE's image-text consistency scores have higher correlation with human judgment than metrics previously introduced in the literature. MT2IE generates prompts that are efficient at probing T2I model performance: closely recovering the official T2I model rankings of three structurally distinct benchmarks from just 20 generated evaluation prompts, 28-105x fewer than the benchmarks' own prompt sets. When compared to existing evaluation metrics such as CLIPScore, VIEScore, and VQAScore, MT2IE's T2I model rankings are more faithful and far more consistent across multiple evaluation seeds when using the same number of prompts. MT2IE can also adapt evaluation to the model being tested: rewriting each prompt based on the model's own measured performance to produce a bespoke per-model benchmark that still recovers the official rankings and keeps the evaluated model in an informative scoring range. We hope that these results will encourage the development of dynamic and interactive evaluation frameworks, and mitigate the deprecation of automatic evaluation benchmarks.

Text-to-Image (T2I) diffusion models have made rapid progress on semantic alignment (generating what is described in the prompt), yet users still lack reliable control over aesthetic composition (how visual elements are put together). Prior work often treats aesthetics as a single, preference-driven notion (e.g., "high quality", "detailed", "breathtaking"), which does not map cleanly to compositional intent. We propose Aesthetic Alignment: aligning generated images to explicit, user-specified compositional constraints. We operationalize these constraints using the Principles of Art (PoA)-e.g., Balance, Rhythm, and Emphasis-commonly used in art education to describe composition. To support this task, we introduce CompArt, a dataset of 80,032 WikiArt images augmented with captions and PoA analyses produced by a multimodal LLM under structured prompting. We further propose ArtDapter, a lightweight and disentangled adapter that enables steering a pretrained T2I model along 10 PoA dimensions while retaining the base model's semantic capability. Experiments on CompArt show improved adherence to PoA controls over strong baselines under a dual evaluation protocol.

Unimodal vision models are known to rely on spurious correlations, but it remains unclear to what extent Multimodal Large Language Models (MLLMs) exhibit similar biases despite language supervision. In this paper, we investigate spurious bias in MLLMs and introduce SpurLens, a pipeline that leverages GPT-4 and open-set object detectors to automatically identify spurious visual cues without human supervision. Our findings reveal that spurious correlations cause two major failure modes in MLLMs: (1) over-reliance on spurious cues for object recognition, where removing these cues reduces accuracy, and (2) object hallucination, where spurious cues amplify the hallucination by over 10x. We validate our findings in various MLLMs and datasets. Beyond diagnosing these failures, we explore potential mitigation strategies, such as prompt ensembling and reasoning-based prompting, and conduct ablation studies to examine the root causes of spurious bias in MLLMs. By exposing the persistence of spurious correlations, our study calls for more rigorous evaluation methods and mitigation strategies to enhance the reliability of MLLMs.

To overcome the black-box nature of predictive AI and the hallucination risks of generative models, retrieval-based models offer an interpretable, evidence-based paradigm for pathology clinical workflow. However, real-world clinical queries are inherently interleaved (e.g., pathology images and text). Current dual-encoders suffer from an \textbf{Architectural Mismatch}, lacking the mechanism to fuse such composed queries. To address this, we formalize the task of Pathology Composed Retrieval (PCR). While Multimodal Large Language Models (MLLMs) offer deep-fusion capabilities, directly applying them exposes a \textbf{Task Mismatch} and a \textbf{Domain Mismatch}. To resolve these challenges, we propose HOMIE, a model-agnostic adaptation framework that transforms any generative MLLM into a specialized pathology retrieval expert. Evaluated on our newly introduced PCR Benchmark, a lightweight 2B-parameter HOMIE variant substantially outperforms existing paradigms, surpassing specialized 7B pathology MLLMs and dual-encoders by large margins on composed retrieval, while maintaining strong performance on traditional simple retrieval. The project page is available at https://qfchou.github.io/HOMIE_page/.

Semantic role labeling (SRL) is a central natural language processing task for understanding predicate-argument structures within texts and enabling downstream applications. Despite extensive research, comprehensive surveys that critically synthesize the field from a unified perspective remain lacking. This survey makes several contributions beyond organizing existing work. We propose a unified four-dimensional taxonomy that categorizes SRL research along model architectures, syntax feature modeling, application scenarios, and multimodal extensions. We provide a critical analysis of when and why syntactic features help, identifying conditions under which syntax-aided approaches provide consistent gains over syntax-free counterparts. We offer the first systematic treatment of SRL in the era of large language models, examining the complementary roles of LLMs and specialized SRL systems and identifying directions for hybrid approaches. We extend the scope of SRL surveys to cover multimodal settings including visual, video, and speech modalities, and analyze structural differences in evaluation across these modalities. Literature was collected through systematic searches of the ACL Anthology, IEEE Xplore, the ACM Digital Library, and Google Scholar, covering publications from 2000 to 2025 and applying explicit inclusion and exclusion criteria to yield approximately 200 primary references. SRL benchmarks, evaluation metrics, and paradigm modeling approaches are discussed alongside practical applications across domains. Future research directions are analyzed, addressing the evolving role of SRL with large language models and broader NLP impact.

Large language models (LLMs) are widely applied in various fields of society due to their powerful reasoning, understanding, and generation capabilities. However, the security issues associated with these models are becoming increasingly severe. Jailbreaking attacks, as an important method for detecting vulnerabilities in LLMs, have been explored by researchers who attempt to induce these models to generate harmful content through various attack methods. Nevertheless, existing jailbreaking methods face numerous limitations, such as excessive query counts, limited coverage of jailbreak modalities, low attack success rates, and simplistic evaluation methods. To overcome these constraints, this paper proposes a multimodal jailbreaking method: JMLLM. This method integrates multiple strategies to perform comprehensive jailbreak attacks across text, visual, and auditory modalities. Additionally, we contribute a new and comprehensive dataset for multimodal jailbreaking research: TriJail, which includes jailbreak prompts for all three modalities. Experiments on the TriJail dataset and the benchmark dataset AdvBench, conducted on 13 popular LLMs, demonstrate advanced attack success rates and significant reduction in time overhead.

Previous studies on federated learning (FL) often encounter performance degradation due to data heterogeneity among different clients. In light of the recent advances in multimodal large language models (MLLMs), such as GPT-4v and LLaVA, which demonstrate their exceptional proficiency in multimodal tasks, such as image captioning and multimodal question answering. We introduce a novel federated learning framework, named Multimodal Large Language Model Assisted Federated Learning (MLLM-LLaVA-FL), which employs powerful MLLMs at the server end to address the heterogeneous and long-tailed challenges. Owing to the advanced cross-modality representation capabilities and the extensive open-vocabulary prior knowledge of MLLMs, our framework is adept at harnessing the extensive, yet previously underexploited, open-source data accessible from websites and powerful server-side computational resources. Hence, the MLLM-LLaVA-FL not only enhances the performance but also avoids increasing the risk of privacy leakage and the computational burden on local devices, distinguishing it from prior methodologies. Our framework has three key stages. Initially, we conduct global visual-text pretraining of the model. This pretraining is facilitated by utilizing the extensive open-source data available online, with the assistance of MLLMs. Subsequently, the pretrained model is distributed among various clients for local training. Finally, once the locally trained models are transmitted back to the server, a global alignment is carried out under the supervision of MLLMs to further enhance the performance. Experimental evaluations on established benchmarks, show that our framework delivers promising performance in the typical scenarios with data heterogeneity and long-tail distribution across different clients in FL.

Radiology report generation (RRG) has attracted significant attention due to its potential to reduce the workload of radiologists. The performance of current RRG approaches remains unsatisfactory against clinical standards. This paper introduces a novel RRG method, MLLM-RRG, that integrates multimodal large language models (MLLMs) with various types of clinical knowledge to generate accurate and comprehensive chest X-ray reports. Our method first designs a referring anatomical feature extractor that leverages anatomical knowledge to analyze different regions of the chest X-ray image and extract visual features without explicitly detecting regions. Next, based on the MLLM's decoder, we develop a multimodal report generator that leverages multimodal prompts constructed from dedicated visual features and textual instructions to produce the radiology report in an auto-regressive way. Finally, we introduce a disease-oriented clinical classification and alignment scheme in a multi-task learning manner to leverage disease knowledge to better preserve the clinical relevance among the generated reports. Once the model is trained, we also introduce a novel clinical quality reinforcement learning strategy to enhance the MLLM with report knowledge, further refining the tones of the generated reports towards radiologists. Extensive experiments on the MIMIC-CXR and IU X-Ray datasets demonstrate the superiority of our method over the state of the art. Our codes will be available at https://github.com/viscom-tongji/MLLM-RRG.

Multimodal Large Language Models (MLLMs) suffer from cross-modal hallucinations, where one modality inappropriately influences generation about another, leading to fabricated output. This exposes a more fundamental deficiency in modality-interaction control. To address this, we propose Modality-Adaptive Decoding (MAD), a training-free method that adaptively weights modality-specific decoding branches based on task requirements. MAD leverages the model's inherent ability to self-assess modality relevance by querying which modalities are needed for each task. The extracted modality probabilities are then used to adaptively weight contrastive decoding branches, enabling the model to focus on relevant information while suppressing cross-modal interference. Extensive experiments on CMM and AVHBench demonstrate that MAD significantly reduces cross-modal hallucinations across multiple audio-visual language models (7.8% and 2.0% improvements for VideoLLaMA2-AV, 8.7% and 4.7% improvements for Qwen2.5-Omni). Our approach demonstrates that explicit modality awareness through self-assessment is crucial for robust multimodal reasoning, offering a principled extension to existing contrastive decoding methods. Our code is available at https://github.com/top-yun/MAD

External text can override conflicting image evidence in multimodal large language models, a failure we call multimodal contextual sycophancy. We introduce a 998-case diagnostic that independently varies visual evidence, commonsense priors, and external text, and probe when this failure arises by moving the information boundary around a context-blind visual witness. On abnormal images paired with Gemini-generated false text, GPT-5.1 scores 7.9% under joint conditioning, 49.7% when the context-blind witness report is scored directly, 63.7% under a matched two-call witness-arbiter pipeline that exposes the witness to the text, and 84.2% under System-2 Visual Arbitration (S2VA), which withholds the text from the witness. Across six models, S2VA improves over the direct witness report by 19.7 to 44.1 points, with all paired 95% confidence intervals excluding zero. The best information boundary is not uniform: textual context scaffolds some models, and a GPT-4o-regenerated subset changes the relative ordering of joint conditioning, Witness-Only, and S2VA. Contextual sycophancy is therefore sensitive to when text is introduced, as well as to the model and context source.

Multimodal large language models (MLLM) for surgical scene understanding typically inject hundreds of dense visual tokens into a language model, leading to costly inference and limited spatial traceability for generated answers. We present Slot2Text, a dual-mode surgical MLLM that replaces dense representations of visual input with a compact set of regions encoded as slot latents. Instead of relying on contrastive alignment of the visual encoder with language, Slot2Text groups self-supervised vision features into a few regions--slots that are consumed by the language model as area-labeled visual tokens. Slot2Text-Fast uses the slot prefix to answer surgical questions. Slot2Text-Reason also identifies and locates areas relevant for reasoning, linking language outputs to corresponding slot tokens, masks or regions. Experiments on multiple visual question answering and visual grounding benchmarks show that Slot2Text-Fast is competitive with state-of-the-art baseline at a much lower cost, reducing the average total token consumption by a 91.8% and the visual prefix from 1,295 to 47 tokens (a 96.4% reduction). Slot2Text-Reason trades additional tokens and latency for explicit area identities, locations, and traceable spatial evidence. These results establish compact slot latents as an efficient default visual interface for surgical MLLMs, with grounded reasoning invoked when greater spatial traceability is required.

MLLMs are increasingly deployed in multi-turn settings, where attackers can escalate unsafe intent through the evolving visual-text history and exploit long-context safety decay. Yet safety alignment is still dominated by single-turn data and fixed-template dialogues, leaving a mismatch between training and deployment. To bridge this gap, we propose SaFeR-Steer, a progressive multi-turn alignment framework that combines staged synthetic bootstrapping with tutor-in-the-loop GRPO to train a single student under adaptive, on-policy attacks. We also introduce Trajectory-Consistent Summative Reward (TCSR), which aggregates the historical minimum and average of turn rewards so that any low-quality turn affects the trajectory-level return. I. Dataset. We release STEER, a multi-turn multimodal safety dataset with STEER-SFT (12,934), STEER-RL (2,000), and STEER-Bench (3,227) dialogues spanning 1-10 turns. II. Experiment. Starting from Qwen2.5-VL-3B/7B, SaFeR-Steer substantially improves Safety/Helpfulness on both single-turn (48.30/45.86 $\rightarrow$ 81.84/70.77 for 3B; 56.21/60.32 $\rightarrow$ 87.89/77.40 for 7B) and multi-turn benchmarks (12.55/27.13 $\rightarrow$ 55.58/70.27 for 3B; 24.66/46.48 $\rightarrow$ 64.89/72.35 for 7B), shifting failures to later turns and yielding robustness beyond scaling alone. Code is available at https://github.com/Ed-Bg/SaFeR-Steer-full