论文检索

Optimization · Learning for Optimization

Xinyu Yuan, Yan Qiao, Zonghui Wang, Wenzhi CHEN

The multi-commodity flow (MCF) problem is a fundamental topic in network flow and combinatorial optimization, with broad applications in transportation, communication, and logistics, etc. Nowadays, the rapid expansion of allocation systems has posed challenges for existing optimization engines in balancing optimality and tractability. In this paper, we present Pram, the first ML-based method that leverages the reasoning power of multimodal language models (MLMs) for addressing the trade-off dilemma—a great need of service providers. As part of our proposal, Pram (i) quickly computes high-quality allocations by dividing the original problem into local subproblems, which are then resolved by an MLM-powered "agent", and (ii) ensures global consistency by harmonizing these subproblems via a multi-agent reinforcement learning algorithm. Theoretically, we show that Pram, which learns to perform gradient descent in context, provably converges to the optimum within the family of MCF problems. Empirically, on real-world datasets and public topologies, Pram achieves performance comparable to, and in some cases even surpassing, linear programming solvers (very close to the optimal solution), and substantially lower runtimes (one to two orders of magnitude faster). Moreover, Pram exhibits strong robustness (<10\% performance degradation under failures or bursts), demonstrating MLM's generalization ability to unforeseen events. Pram is objective-agnostic and seamlessly integrates with mainstream allocation systems, providing a practical and scalable solution for future networks.

Deep Learning · Generative Models and Autoencoders

Devang Acharya, Mohammad Hammoud

Compact pretrained bidirectional encoders remain the backbone of industrial NLP under tight compute and memory budgets. Their effectiveness stems from self-attention’s ability to deliver high-quality bidirectional contextualization with sequence-level parallelism, as popularized by BERT-style architectures. Recently, **Avey** was introduced as an autoregressive, attention-free alternative that naturally admits an encoder-only adaptation. In this paper, we reformulate Avey for the encoder-only paradigm and propose several innovations to its architecture, including decoupled static and dynamic parameterizations, stability-oriented normalization, and neural compression. Results show that this reformulated architecture compares favorably to four widely used Transformer-based encoders, consistently outperforming them on standard token-classification and information-retrieval benchmarks while scaling more efficiently to long contexts.

Deep Learning · Generative Models and Autoencoders

Edgardo Solano Carrillo, Sreerag Vadakkemeppully Naveenachandran, Julia Niebling

Score-based generative modeling through differential equations has driven breakthroughs in high-fidelity image synthesis, offering modular model design and efficient sampling. However, this success has not been widely translated to timeseries forecasting yet. This gap stems from the sequential nature of time series, in contrast to the unordered structure of images. Here, we extend the theoretical formulation used for images to explicitly address sequential structures. We propose a diffusion-based forecasting framework (TEDM) that adapts score estimation to temporal settings and elucidates its design space. Such a design allows empirical computation of noise and signal scaling directly from data, avoiding external schedules. Notably, this reduces sampling complexity to linear in the forecast horizon. Without elaborate preprocessing, TEDM sets new state-of-the-art results on multiple forecasting benchmarks. These results illustrate the growing potential of diffusion models beyond vision. TEDM generates low-latency forecasts using a lightweight architecture, making it ideal for real-time deployment.

Fan Liu, Xiaozhao Zeng, Hao Liu

Recent advances in large language models (LLMs) have enabled agents that automate scientific discovery by interpreting data, generating analysis pipelines, and executing them with computational tools. However, existing benchmarks remain largely limited to unimodal datasets and slice-level tasks, overlooking the fact that real discovery requires multimodal integration, modeling, and hypothesis-driven reasoning. To address this gap, we introduce MoSciBench, the first benchmark for multimodal scientific discovery, constructed from peer-reviewed studies through a principled four-stage pipeline. MoSciBench spans six scientific domains, seven data modalities, and five categories of discovery questions, yielding 88 individual, end-to-end, data-driven tasks. Each task is designed as a cross-modal hypothesis verification workflow, requiring agents to align and integrate heterogeneous datasets before modeling and reasoning. We further evaluate four representative agent frameworks across multiple LLM families. Results show that multimodal discovery is substantially harder than unimodal tasks: even the strongest agents achieve only 48.94\% accuracy, with over 60\% of failures due to cross-modal alignment. Lightweight workflow scaffolding consistently improves performance, reducing alignment errors by 5–10\% and raising accuracy by 5.7\% on average. Our benchmark and evaluation framework thus establish a rigorous testbed for advancing LLM agents toward realistic, multimodal scientific discovery.

Deep Learning · Algorithms

Wittawat Jitkrittum, Harikrishna Narasimhan, Ankit Singh Rawat, Jeevesh Juneja, Congchao Wang, Zifeng Wang, Alec Go, Chen-Yu Lee, Pradeep Shenoy, Rina Panigrahy 等

Model routing is a simple technique for reducing the inference cost of large language models (LLMs), wherein one maintains a pool of candidate LLMs, and learns to route each prompt to the smallest feasible LLM. Existing works focus on learning a router for a fixed pool of LLMs. In this paper, we consider the problem of dynamic routing, where new, previously unobserved LLMs are available at test time. We propose UniRoute, a new approach to this problem that relies on representing each LLM as afeature vector, derived based on predictions on a set of representative prompts. Based on this, we detail two effective instantiations of UniRoute, relying on cluster-based routing and a learned cluster map respectively. We show that these are estimates of a theoretically optimal routing rule, and quantify their errors via an excess risk bound. Experiments on a range of public benchmarks show the effectiveness of UniRoute in routing amongst more than 30 unseen LLMs.

Shahaf Bassan, Xuanxiang Huang, Guy Katz

Previous work has explored the computational complexity of deriving two fundamental types of explanations for ML model predictions: (1) *sufficient reasons*, which are subsets of input features that, when fixed, determine a prediction, and (2) *contrastive reasons*, which are subsets of input features that, when modified, alter a prediction. Prior studies have examined these explanations in different contexts, such as non-probabilistic versus probabilistic frameworks and local versus global settings. In this study, we introduce a unified framework for analyzing these explanations, demonstrating that they can all be characterized through the minimization of a unified probabilistic value function. We then prove that the complexity of these computations is influenced by three key properties of the value function: (1) *monotonicity*, (2) *submodularity*, and (3) *supermodularity* - which are three fundamental properties in *combinatorial optimization*. Our findings uncover some counterintuitive results regarding the nature of these properties within the explanation settings examined. For instance, although the *local* value functions do not exhibit monotonicity or submodularity/supermodularity whatsoever, we demonstrate that the *global* value functions do possess these properties. This distinction enables us to prove a series of novel polynomial-time results for computing various explanations with provable guarantees in the global explainability setting, across a range of ML models that span the interpretability spectrum, such as neural networks, decision trees, and tree ensembles. In contrast, we show that even highly simplified versions of these explanations become NP-hard to compute in the corresponding local explainability setting.

Applications · Everything Else

Yunlun Li, Sinno Jialin Pan

Symbolic regression (SR) aims to automate scientific discovery, but often truncates the hypothetico–deductive cycle, focusing on hypothesis and experiment while lacking systematic analysis. We introduce RESTART, a framework that closes this loop by adding a principled analysis stage to diagnose and correct structural errors. RESTART features two core mechanisms: a short-term refinement process that uses boosting to identify unexplained signals and guide an LLM toward targeted corrections, and a long-term structure library that distills successful refinements into reusable code snippets for cumulative knowledge. On LLM-SRBench across Physics, Biology, and Materials Science, RESTART achieves lower error and higher accuracy than state-of-the-art baselines. It also generalizes robustly, recovering near-exact functional forms on out-of-distribution data, representing a significant advance toward fully automated scientific discovery.

Deep Learning · Generative Models and Autoencoders

Wenyang Luo, Haina Qin, Bing Li, Jiwen Lu, Xin Tao, Pengfei Wan, Kun Gai

Video autoregressive generation (VideoAR) sequentially predicts future frames conditioned on history frames. Despite the advance of recent diffusion-based VideoAR, the role of conditioning signal—internal representations of history frames—remains underexplored. Inspired by the success of strong condition representations in text-conditioned generation, we investigate: \textit{Can better internal representations of history frames improve VideoAR performance?} Through systematic analysis, we show that history representation quality positively correlates with VideoAR, and that enhancing these representations provides gains that cannot be achieved by refining future frames representations alone. Based on these insights, we propose \textbf{MiMo} (Masked History Modeling), a novel framework that seamlessly integrates representation learning into diffusion-based VideoAR. MiMo applies masks to history frame tokens and trains the model to predict masked tokens of current and future frames alongside the diffusion objective, yielding predictive and robust history representations without relying on vision foundation models (VFMs) or heavy architectural changes. Extensive experiments demonstrate that MiMo achieves competitive performance in video prediction and generation tasks while substantially improving training efficiency. Our work underscores the importance of history representations in VideoAR.

General Machine Learning · Causality

Taiyu Ban, Changxin Rong, Xiangyu Wang, Lyuzhou Chen, Yanze Gao, Xin Wang, Huanhuan Chen

Learning instantaneous and time-lagged causal relationships from time-series data is essential for uncovering fine-grained, temporally-aware interactions. Although this problem has been formulated as a continuous optimization task amenable to modern machine learning methods, existing approaches largely neglect the use of coarse-grained, lag-agnostic causal priors, an important form of prior knowledge that is often available in practice. To address this gap, we propose a novel framework for structure learning from time series to integrate lag-agnostic priors, enabling the discovery of lag-specific causal links without requiring precise temporal annotations. We introduce formulations to precisely characterize the lag-agnostic prior, and demonstrate their consequential and process-equivalence to priors, maintaining consistency with the intended semantics of the priors throughout optimization. We further analyze the challenge for optimization due to the increased non-convexity by lag-agnostic prior constraints, and introduce a data-driven initialization to mitigate this issue. Experiments on both synthetic and real-world datasets show that our method effectively incorporates lag-agnostic prior knowledge to enhance the recovery of fine-grained, lag-aware structures.

General Machine Learning · Everything Else

Katherine Collins, Cedegao Zhang, Graham Todd, Lance Ying, Mauricio da Costa, Ryan Liu, Prafull Sharma, Adrian Weller, Ionatan Kuperwajs, Lio Wong 等

Reasoning is not just about solving problems---it is also about evaluating which problems are worth solving at all. Evaluations of artificial intelligence (AI) systems primarily focused on problem solving, historically by studying how models play games such as chess and Go. In this paper, we advocate for a new paradigm that assesses AI systems' evaluation of games. First, we introduce a formalism for evaluating such evaluations. We then leverage a large-scale dataset of over 100 novel board games and over 450 human judgments to compare evaluations produced by modern language and reasoning models against those of people and symbolic computational agents. We consider two kinds of evaluative queries: assessing the payoff (or fairness) and the funness of games. These queries span two dimensions relevant to the design of evaluations of AI evaluations: how complex a query is to compute and how difficult a query is to quantify. Our results show that reasoning models are generally more aligned to people in their evaluations of games than non-reasoning language models. However, we observe a non-monotonic relationship: as models get closer to game-theoretic optimal, their fit to human data weakens. We also observe more "jaggedness" across models for assessing funness, in line with the greater difficulty of quantifying this query. Across queries and games, reasoning models show highly variable and unpredictable resource usage when assessing queries, pointing to the importance of imbuing more resource-rational meta-reasoning in language and reasoning models.

Computer Vision · Image and Video Generation

Jiazi Bu, Pengyang Ling, Yujie Zhou, Yibin Wang, Yuhang Zang, Dahua Lin, Jiaqi Wang

Recent years have witnessed the rapid development of acceleration techniques for diffusion models, especially caching-based acceleration methods. These studies seek to answer two fundamental questions: _"When to cache"_ and _"How to use cache"_, typically relying on predefined empirical laws or dataset-level priors to determine caching timings and adopting handcrafted rules for multi-step cache utilization. However, given the highly dynamic nature of the diffusion process, they often exhibit limited generalizability and fail to cope with diverse samples. In this paper, a strong sample-specific correlation is revealed between the variation patterns of the shallow-layer feature differences in the diffusion model and those of deep-layer features. Moreover, we have observed that the features from different model layers form similar trajectories. Based on these observations, we present **DiCache**, a novel training-free adaptive caching strategy for accelerating diffusion models at runtime, answering both when and how to cache within a unified framework. Specifically, DiCache is composed of two principal components: (1) _Online Probe Profiling Scheme_ leverages a shallow-layer online probe to obtain an on-the-fly indicator for the caching error in real time, enabling the model to dynamically customize the caching schedule for each sample. (2) _Dynamic Cache Trajectory Alignment_ adaptively approximates the deep-layer feature output from multi-step historical caches based on the shallow-layer feature trajectory, facilitating higher visual quality. Extensive experiments validate DiCache’s capability in achieving higher efficiency and improved fidelity over state-of-the-art approaches on various leading diffusion models including WAN 2.1, HunyuanVideo and Flux.

Computer Vision · Vision Models & Multimodal

Brandon Huang, Hang Hua, Zhuoran Yu, trevor darrell, Rogerio Feris, Roei Herzig

While Vision–language models (VLMs) have demonstrated remarkable performance across multi-modal tasks, their choice of vision encoders presents a fundamental weakness: their low-level features lack the robust structural and spatial information essential for document understanding and web agents. To bridge this gap, we introduce DAVE, a vision encoder purpose-built for VLMs and tailored for these tasks. Our training pipeline is designed to leverage abundant unlabeled data to bypass the need for costly large-scale annotations for document and web images. We begin with a self-supervised pretraining stage on unlabeled images, followed by a supervised autoregressive pretraining stage, where the model learns tasks like parsing and localization from limited, high-quality data. Within the supervised stage, we adopt two strategies to improve our encoder’s alignment with both general visual knowledge and diverse document and web agentic tasks: (i) We introduce a novel model-merging scheme, combining encoders trained with different text decoders to ensure broad compatibility with different web agentic architectures. (ii) We use ensemble training to fuse features from pretrained generalist encoders (e.g., SigLIP2) with our own document and web-specific representations. Extensive experiments on classic document tasks, VQAs, web localization, and agent-based benchmarks validate the effectiveness of our approach, establishing DAVE as a strong vision encoder for document and web applications.

Deep Learning · Everything Else

Chuiyang Meng, Ming Tang, Vincent Wong

Parameter-efficient fine-tuning techniques such as low-rank adaptation (LoRA) enable large language models (LLMs) to adapt to downstream tasks efficiently. Federated learning (FL) further facilitates this process by enabling collaborative fine-tuning across distributed clients without sharing private data. However, the use of two separate low-rank matrices in LoRA for federated fine-tuning introduces two types of challenges. First, aggregation error can arise from separately aggregating the two low-rank matrices. Second, even if the server aggregates the product of two low-rank matrices, it needs to decompose the aggregated matrix back into low-rank matrices. Since the decomposition is not unique, it can lead to decomposition drift. To tackle the aforementioned challenges, we propose federated low-rank Gram-matrix aggregation (FLoRG), a federated fine-tuning framework which employs a single low-rank matrix for fine-tuning and aggregates its Gram matrix (i.e., the matrix of inner products of its column vectors). FLoRG can eliminate the aggregation error and reduce the communication overhead. It also minimizes the decomposition drift by introducing a Procrustes alignment approach which aligns the decomposed matrix between consecutive fine-tuning rounds for consistent updates. We theoretically analyze the convergence of FLoRG and prove that adopting the Procrustes alignment results in a tighter convergence bound. Experimental results across multiple LLM fine-tuning benchmarks demonstrate that FLoRG outperforms five state-of-the-art baseline schemes by providing higher downstream task accuracy and can reduce the communication overhead by up to 2041$\times$.

sina alemohammad, Zhangyang Wang, Richard Baraniuk

Scaling generative AI models is bottlenecked by the scarcity of high-quality training data. The ease of synthesizing from a generative model suggests using (unverified) synthetic data to augment a limited corpus of real data for the purpose of fine-tuning in the hope of improving performance. Unfortunately, however, the resulting positive feedback loop leads to model autophagy disorder (MAD, aka model collapse) that results in a rapid degradation in sample quality and/or diversity. In this paper, we introduce Neon (for Negative Extrapolation frOm self-traiNing), a new learning method that turns the degradation from self-training into a powerful signal for self-improvement. Given a base model, Neon first fine-tunes it on its own self-synthesized data but then, counterintuitively, reverses its gradient updates to extrapolate away from the degraded weights. We prove that Neon works because typical inference samplers that favor high-probability regions create a predictable anti-alignment between the synthetic and real data population gradients, which negative extrapolation corrects to better align the model with the true data distribution. Neon is remarkably easy to implement via a simple post-hoc merge that requires no new real data, works effectively with as few as 1k synthetic samples, and typically uses less than 1\% additional training compute. We demonstrate Neon’s universality across a range of architectures (diffusion, flow matching, autoregressive, and inductive moment matching models) and datasets (ImageNet, CIFAR-10, and FFHQ). In particular, on ImageNet 256x256, Neon elevates the xAR-L model to a new state-of-the-art FID of 1.02 with only 0.36\% additional training compute.

Ziqi Jiang, Yanghao Wang, Long Chen

Aligning features from different modalities is one of the most fundamental challenges for cross-modal tasks. Although pre-trained vision-language models can achieve a general alignment between image and text, they often require parameter-efficient fine-tuning (PEFT) for further adjustment. Today’s PEFT methods (e.g., prompt tuning, LoRA-based, or adapter-based) always selectively fine-tune a subset of parameters, which can slightly adjust either visual or textual features, and avoid overfitting. In this paper, we are the first to highlight that all existing PEFT methods perform one-step adjustment and are insufficient for complex (or difficult) datasets, where features of different modalities are highly entangled. To this end, we propose the first model-agnostic multi-step adjustment approach by learning a cross-modal velocity field: Flow Matching Alignment (FMA). Specifically, to ensure the correspondence between categories during training, we first utilize a fixed coupling strategy. Then, we propose a noise augmentation strategy to alleviate the data scarcity issue. Finally, we design an early-stopping solver, which terminates the transformation process earlier, improving both efficiency and accuracy. Compared with one-step PEFT methods, FMA has the multi-step rectification ability to achieve more precise and robust alignment. Extensive results have shown that FMA can consistently yield significant performance gains across various benchmarks and backbones, especially on difficult datasets.

Social Aspects · Trustworthy Machine Learning

Tianyu Chen, Jian Lou, Wenjie Wang

As Retrieval-Augmented Generation (RAG) evolves into service-oriented platforms (Rag-as-a-Service) with shared knowledge bases, protecting the copyright of contributed data becomes essential. Existing watermarking methods in RAG focus solely on textual knowledge, leaving image knowledge unprotected. In this work, we propose \textit{AQUA}, the first watermark framework for image knowledge protection in Multimodal RAG systems. \textit{AQUA} embeds semantic signals into synthetic images using two complementary methods: acronym-based triggers and spatial relationship cues. These techniques ensure watermark signals survive indirect watermark propagation from image retriever to textual generator, being efficient, effective and imperceptible. Experiments across diverse models and datasets show that \textit{AQUA} enables robust, stealthy, and reliable copyright tracing, filling a key gap in multimodal RAG protection.

Computer Vision · Vision Models & Multimodal

Hulingxiao He, Zijun Geng, Yuxin Peng

Any entity in the visual world can be hierarchically grouped based on shared characteristics and mapped to fine-grained sub-categories. While Multi-modal Large Language Models (MLLMs) achieve strong performance on coarse-grained visual tasks, they often struggle with Fine-Grained Visual Recognition (FGVR). Adapting general-purpose MLLMs to FGVR typically requires large amounts of annotated data, which is costly to obtain, leaving a substantial performance gap compared to contrastive CLIP models dedicated for discriminative tasks. Moreover, MLLMs tend to overfit to seen sub-categories and generalize poorly to unseen ones. To address these challenges, we propose Fine-R1, an MLLM tailored for FGVR through an R1-style training framework: (1) Chain-of-Thought Supervised Fine-tuning, where we construct a high-quality FGVR CoT dataset with rationales of "visual analysis, candidate sub-categories, comparison, and prediction”, transition the model into a strong open-world classifier; and (2) Triplet Augmented Policy Optimization, where Intra-class Augmentation mixes trajectories from anchor and positive images within the same category to improve robustness to intra-class variance, while Inter-class Augmentation maximizes the response distinction conditioned on images across sub-categories to enhance discriminative ability. With only 4-shot training, Fine-R1 outperforms existing general MLLMs, reasoning MLLMs, and even contrastive CLIP models in identifying both seen and unseen sub-categories, showing promise in working in knowledge-intensive domains where gathering expert annotations for all sub-categories is arduous. Code is available at [https://github.com/PKU-ICST-MIPL/FineR1_ICLR2026](https://github.com/PKU-ICST-MIPL/FineR1\_ICLR2026).

Social Aspects · Trustworthy Machine Learning

Wonjeong Choi, Sejong Ryu, JungMoon Lee, Dong-Jun Han, Jaekyun Moon

Recent vision-language models (VLMs), such as CLIP, have demonstrated remarkable transferability across a wide range of downstream tasks by effectively leveraging the joint text-image embedding space, even with only a few data samples. Despite their impressive performance, these models remain vulnerable to adversarial attacks, raising significant concerns about their security and reliability in practical deployments. To address this issue, we propose Adversarial Mask Tuning (AdvMask), a method that effectively enhances the robustness of VLMs without directly modifying their pre-trained weights. Instead, our AdvMask learns a set of binary masks that selectively deactivate model parameters vulnerable to adversarial perturbations. By identifying robust neural pathways within the vision encoder, AdvMask facilitates the generation of features and predictions that are resistant to adversarial attacks. Furthermore, we introduce a Layer-wise Adaptive Feature Alignment (LAFA) loss, specifically designed to optimize AdvMask in few-shot scenarios. The LAFA loss adaptively aligns intermediate-layer features from clean and adversarial samples across each transformer block, enhancing the representational robustness of the model. Experimental results across multiple benchmarks confirm that our AdvMask approach substantially outperforms existing adversarial tuning techniques for VLMs, especially in few-shot settings.

Guibin Zhang, Junhao Wang, Junjie Chen, Wangchunshu Zhou, Kun Wang, Shuicheng YAN

Large Language Model (LLM)-based agentic systems, often comprising multiple models, complex tool invocations, and orchestration protocols, substantially outperform monolithic agents. Yet this very sophistication amplifies their fragility, making them more prone to system failure. Pinpointing the specific agent or step responsible for an error within long execution traces defines the task of \textbf{agentic system failure attribution}. Current state-of-the-art reasoning LLMs, however, remain strikingly inadequate for this challenge, with accuracy generally below $10\\%$. To address this gap, we propose AgenTracer, the first automated framework for annotating failed multi-agent trajectories via counterfactual replay and programmed fault injection, producing the curated dataset TracerTraj. Leveraging this resource, we develop AgenTracer-8B, a lightweight failure tracer trained with multi-granular reinforcement learning, capable of efficiently diagnosing errors in verbose multi-agent interactions. On {Who\&When} benchmark, AgenTracer-8B outperforms giant proprietary LLMs like Gemini-2.5-Pro and Claude-4-Sonnet by up $18.18\\%$, setting a new standard in LLM agentic failure attribution. More importantly, AgenTracer-8B delivers actionable feedback to off-the-shelf multi-agent systems like MetaGPT and MaAS with $4.8\sim14.2\\%$ performance gains, empowering self-correcting and self-evolving agentic AI.

Social Aspects · Fairness, Equity, Justice and Safety

Jiyuan Fu, Kaixun Jiang, Lingyi Hong, Jinglun Li, HaiJing Guo, Dingkang Yang, Zhaoyu Chen, Wenqiang Zhang

Multimodal Large Language Models (MLLMs) have shown great promise but require substantial computational resources during inference. Attackers can exploit this by inducing excessive output, leading to resource exhaustion and service degradation. Prior energy-latency attacks aim to increase generation time by broadly shifting the output token distribution away from the EOS token, but they neglect the influence of token-level Part-of-Speech (POS) characteristics on EOS and sentence-level structural patterns on output counts, limiting their efficacy. To address this, we propose \textbf{LingoLoop}, an attack designed to induce MLLMs to generate excessively verbose and repetitive sequences. First, we find that the POS tag of a token strongly affects the likelihood of generating an EOS token. Based on this insight, we propose a \textbf{POS-Aware Delay Mechanism} to postpone EOS token generation by adjusting attention weights guided by POS information. Second, we identify that constraining output diversity to induce repetitive loops is effective for sustained generation. We introduce a \textbf{Generative Path Pruning Mechanism} that limits the magnitude of hidden states, encouraging the model to produce persistent loops. Extensive experiments on models like Qwen2.5-VL-3B demonstrate LingoLoop's powerful ability to trap them in generative loops; it consistently drives them to their generation limits and, when those limits are relaxed, can induce outputs with up to \textbf{367$\times$} more tokens than clean inputs, triggering a commensurate surge in energy consumption. These findings expose significant MLLMs' vulnerabilities, posing challenges for their reliable deployment.