Multimodal Optimization

Follow this topic Ask about this topic

Momentum

7 papers in the last four weeks, with none the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 21

Sep 23, 2026cs.LG

Confidence Falls Short: Asymmetric Certainty Gains from Optimization Hinder Multimodal Classification

Multimodal learning (MML) falls into the optimization dilemma due to the modality imbalance phenomenon, leading to suboptimal overall performance in practice. While many attempts primarily focus on balancing the optimization dynamics across modalities to address this issue, we identify a subtle yet critical flaw: optimization yields asymmetric gains in predictive certainty, with the strong modality more confident than the weak one, driving imbalanced modality contributions. In this paper, our analysis reveals that this flaw stems from unimodal characteristics rather than multimodal learning, and this confidence discrepancy can be corrected by positive cross-modal intervention. Based on this insight, we propose multimodal Max Confidence Regularization (MaxCR) to dynamically intervene in modality semantic confidence. Specifically, the semantic confidence of each modality is tracked using a nonlinear sparsity measure. We then design max suppression and max excitation based on this measure to regularize strong and weak modalities, respectively. They penalize and encourage the top-1 confidence, thereby constraining multimodal prediction. To this end, strong and weak modalities are expected to make calibrated confidence, thereby improving the overall performance. Empirical experiments on widely used datasets reveal the superiority of our method through comparison with various state-of-the-art (SOTA) multimodal learning baselines.

Longfei Huang, Xiangyu Wu, Yang Yang

Nanjing University of Science and Technology · Alibaba Group

Modality Imbalance Multimodal Optimization Multimodal Classification Multimodal Fusion

Sep 23, 2026cs.LG

VCMM: Variance-Calibrated Momentum for Multimodal Learning

Multimodal joint training often suffers from modality imbalance, where a dominant modality suppresses the optimization of others. Existing methods mainly balance modality learning by modulating gradient magnitudes or directions, modifying optimization objectives, or adjusting training strategies, with most interventions focusing on the current update. However, when combined with widely used momentum-based optimizers, the update also incorporates accumulated information from previous gradients, which is not explicitly addressed by current-step modulation alone. To address this issue, we propose Variance-Calibrated MomentuM (VCMM), which adapts gradient memory to modality-specific gradient dynamics. Specifically, VCMM estimates minibatch noise and temporal drift online and uses their relative strength to determine modality-specific momentum through a Kalman-inspired controller. We further center the control signal across modalities and apply exact bias correction for the time-varying first moment, enabling adaptive gradient memory without extra network passes or explicit learning-rate scaling. Experiments on four multimodal benchmarks demonstrate consistent improvements with modest training overhead.

Zhongjing Gu, Chenyang Huang, Yufa Feng +3

Multimodal Optimization Adaptive Gradient Methods Multimodal Learning

Sep 20, 2026cs.CV

GeoBalance: Geometry-Aware Monitoring and Reconstruction with Asymmetric Optimization for Balanced Multimodal Learning

Multimodal classifiers can converge to modality-dominant solutions in which one modality dominates the joint prediction, suppressing the learning of others. Existing balancing methods mainly adjust losses, gradients, or modality contributions, largely treating modality imbalance as an optimization problem while implicitly treating the weak modality as under-optimized but representationally intact. In this work, we find that this assumption does not always hold, as persistent modality dominance can induce a representation-level collapse of the weak modality, which we term \emph{manifold modality collapse} (MMC). MMC manifests as a coupled geometric degradation in which weak-modality representations collapse onto fewer directions within each class and become less separable across classes. Motivated by this observation, we propose \emph{GeoBalance}, a geometry-aware framework that monitors these two geometric properties and reconstructs the weak modality representation only when it exhibits signs of MMC. Once triggered, GeoBalance uses a fixed Simplex-ETF class scaffold and spectral regularization to restore class separation while preventing collapse onto a few feature directions. To preserve reconstruction during joint training, asymmetric gradient projection removes the joint-gradient component conflicting with reconstruction, leaving non-conflicting optimization unchanged. Extensive experiments across six multimodal benchmarks demonstrate great improvements over competitive balancing methods, validating its effectiveness.

Zechang Xiong, Da Li, Rong Yin +7

Beihang University, Beijing, China · Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China · Amap, Alibaba Group, Beijing, China +3

Modality Imbalance Geometric Representation Learning Multimodal Optimization Multimodal Classification

Sep 16, 2026cs.MM

From Models to Systems: A Comprehensive Survey of Efficient Multimodal Learning

The rapid expansion of multimodal models has surfaced formidable bottlenecks in computation, memory, and deployment, catalyzing the rise of Efficient Multimodal Learning (EML) as a pivotal research frontier. Despite intensive progress, a cohesive understanding of what, how, and where efficiency is manifested across the learning stack remains fragmented. This survey systematizes the EML landscape by introducing the first structured, model-to-system taxonomy. We distill insights from over 300 seminal works into three hierarchical levels--model, algorithm, and system--addressing architectural parsimony, execution refinement, and hardware-aware orchestration, respectively. Moving beyond a purely categorical review, we offer a methodological synthesis of the vertical synergies between these layers, elucidating how cross-layer co-design contributes to the fundamental "Efficiency-Utility-Privacy" trade-off. Through an integrative case study of Multimodal Large Language Models (MLLMs), we trace the field's evolutionary trajectory from initial structural adjustments to modern full-stack resource orchestration. Furthermore, we provide a holistic discussion and application-specific optimization blueprints for diverse domains and posit a paradigm shift toward self-regulating intelligence, where efficiency is an intrinsic, emergent property of the model's fundamental design rather than a post-hoc constraint. Finally, we present open challenges and future directions that will define the trajectory of EML research. This survey establishes a structured framework for multimodal systems that are not only high-performing and generalizable but natively efficient and ready for ubiquitous deployment. A continuously updated version is available at https://github.com/pwang322/Efficient-Multimodal-Learning-Survey.

Pan Wang, Siwei Song, Hui Ji +12

University of Pittsburgh · New York University · Carnegie Mellon University +6

Efficient Multimodal Inference Multimodal Optimization Multimodal Learning

Sep 14, 2026cs.CV

PACE: Progressive Angular-to-Norm Contrastive Embedding

Multimodal embedding models encode heterogeneous inputs into a shared embedding space, enabling efficient similarity computation across modalities and tasks. Most existing methods optimize cosine-based contrastive objectives, which promote stable training but restrict semantic compatibility to angular geometry, precluding embedding norms from serving as an additional semantic signal. However, directly optimizing the more expressive dot-product similarity, which leverages both angular and norm information, underperforms cosine-based training and exhibits unstable training dynamics. We attribute this discrepancy to premature optimization-space expansion, manifested as angular--norm entanglement and directional anisotropy in the representation space and further compounded by full-parameter fine-tuning. In this paper, we propose PACE, a two-stage framework that progressively expands both the representation and trainable parameter spaces. Stage I combines cosine-based objective with low-rank adaptation to establish a reliable angular geometry within constrained optimization spaces. Stage II switches to dot-product similarity and full-parameter fine-tuning, enabling embedding directions and norms to jointly encode semantic information. We further introduce Focal Embedding Loss, a confidence-adaptive objective that downweights queries with high positive retrieval confidence while emphasizing ambiguous queries with competitive negatives. Experiments across multiple backbone scales and diverse multimodal embedding tasks consistently validate the effectiveness of PACE.

Yanping Li, Wei Zhou, Yawen Liu +7

The Hong Kong University of Science and Technology · Alibaba Group · Huazhong University of Science and Technology +1

Cross-Modal Representation Learning Multimodal Embedding Multimodal Optimization Multimodal Contrastive Learning

Sep 14, 2026cs.AI

Tracing and Coordinating Cross-Layer Influence for Multimodal Model Merging

Multimodal model merging aims to consolidate task experts into a single model that retains their complementary capabilities. Most unimodal model merging methods combine expert updates within individual layers, and multimodal approaches largely follow this design. However, an expert update changes the representations passed to subsequent layers, allowing its influence to propagate across depth and affect how visual and textual information interact. When visual and language updates are combined, later updates act on inputs already modified by earlier ones, coupling their effects. This poses two challenges: (1) how to characterize the multimodal influence of individual expert updates across depth, and (2) how to jointly combine expert updates based on their multimodal influence. To address these challenges, we propose TAC-Merge for tracing and coordinating cross-layer influence in multimodal model merging. It contains two modules, i.e., multimodal influence mapping (MIM) and coupled merge control (CMC). MIM constructs graphs of update effects and uses Ricci curvature together with expert predictions to define a shared fusion objective. CMC models interactions among coefficient adjustments and jointly optimizes regional weights to synthesize one shared model. Experiments across diverse multimodal tasks demonstrate the effectiveness of TAC-Merge in consolidating complementary expert capabilities and supporting generalization to unseen tasks.

Pengyang Zhou, Xiaobin Tu, Zhengxi Liu +7

Alibaba Cloud

Multimodal Optimization Language Model Merging Multimodal Fusion

Sep 11, 2026cs.CL

The Illusion of Balanced Multimodal Sentiment Analysis: Beyond the Limits of Optimization-Based Methods

Multimodal Sentiment Analysis (MSA) remains constrained by modality imbalance, yet the field continues to rely on optimization-based balancing methods that promise more than they deliver. We provide three contributions: 1) a unified evaluation framework testing gradient and loss-based balancing strategies under controlled settings; 2) a theoretical diagnosis explaining why these methods fail, as they conflate fitting speed with discriminative contribution; and 3) a research agenda toward held-out discriminative modality valuation. Experiments on CMU-MOSI and CMU-MOSEI reveal three shortcomings: no strategy reliably outperforms Late Concatenation; performance is sensitive to hyperparameters; and even ratio calibration fails to yield consistent gains. The core issue is fundamental: loss is not utility, and gradients are not importance. Modality imbalance remains unresolved, motivating utility estimation from held-out performance.

Ioanna Kaffeza, Efthymios Georgiou, Alexandros Potamianos

PERSEE Center, Mines Paris-PSL University, Sophia-Antipolis, France · National Technical University of Athens, Athens, Greece · University of Bern, Bern, Switzerland +2

Modality Imbalance Multimodal Optimization Multimodal Sentiment Analysis Multimodal Fusion Multimodal Model Evaluation

Jul 23, 2026cs.AI

Beyond Independent Optimization: Compression, MoE Routing, and Quantization Interactions in Multimodal Edge Intelligence

Efficient multimodal inference is increasingly constrained not only by model quality or FLOP count, but also by the cost of preserving, moving, routing, caching, and quantizing multimodal representations under latency, memory, and energy constraints. This paper reviews recent advances in efficient vision-language and multimodal large language models, covering visual token compression, video token management, KV-cache optimization, Mixture-of-Experts (MoE) routing, low-bit quantization, edge deployment, and hardware-aware benchmarking. We argue that these techniques cannot be treated as independent optimizations. Visual token compression alters downstream feature distributions and MoE routing decisions, routing behavior affects expert utilization and quantization sensitivity, quantized router logits influence expert assignment, KV-cache policies determine retained multimodal evidence, and hardware constraints often transform computational savings into memory and communication bottlenecks. We organize the literature around these interactions and identify key design trade-offs, including accuracy versus token budget, static versus adaptive compression, sparse routing efficiency versus expert collapse, and low-bit inference versus modality-specific degradation. Finally, we introduce Temporal Routing Consistency as a diagnostic for video MoE models and highlight open research directions in routing-aware compression, cross-modal cache management, hardware-aware co-design, and unified benchmarking for multimodal edge intelligence.

Jay Gor, Karm Dave, Akshita Abrol +3

Nirma University · Singapore Institute of Technology, Singapore · Department of CE-AI and Big Data, Marwadi University

Efficient Multimodal Inference VLM Quantization Multimodal Optimization Expert Routing Multimodal Token Compression Edge AI

Jul 23, 2026cs.AI

OPOD: On-Policy Omni Distillation

Omni-modal models provide a unified interface for text, images, and audio. However, improving these abilities together remains difficult, as post-training on pooled multimodal data often fails to preserve the strengths of modality teachers. On-policy distillation (OPD) has recently become popular in model post-training. It samples responses from the current student and compares the teacher's and student's next-token distributions along those responses, yielding dense supervision while reducing the mismatch between training and inference. Despite these advantages, standard OPD does not readily extend to several modality teachers. Their guidance may favor conflicting changes to the shared model, while matching each teacher's next-token distribution can prevent the student from moving beyond that teacher. To address these challenges, we propose On-Policy Omni Distillation (OPOD), which consolidates text, image, and audio teachers into one omni model. OPOD routes each response to the corresponding teacher, controls the teachers independently, and applies guidance only when the teacher assigns a higher probability to the generated token. The selected teacher also evaluates answer confidence and whether the reasoning increases support for the answer. Extensive experiments on twelve benchmarks show that OPOD achieves the best average at three model scales, reaching 70.8, 51.7, and 46.2 and outperforming the strongest comparator by 2.1, 1.8, and 1.7 points. At 30B, it surpasses the base model and pooled RL training on all twelve benchmarks, and ranks first or second on eleven even when the teachers are included. Only the student is retained for deployment.

Tong Zhao, Yuyang Hu, Yutao Zhu +5

1Renmin University of China · 2Tencent

Cross-Modal Knowledge Distillation Unified Multimodal Models Multimodal Optimization Multi-Teacher Knowledge Distillation On-Policy Distillation Multimodal Foundation Models+1

Jul 15, 2026cs.NE

S-CARD-CMSA: A Score-Aware Candidate Archive with Density-Filtered Reporting for Multimodal Optimization

Multimodal optimization aims to locate multiple globally optimal or near-optimal solutions in a single run. This paper presents \emph{S-CARD-CMSA}, a score-aware candidate-archive and density-filtered reporting framework built on the covariance matrix self-adaptation evolution strategy with repelling subpopulations (RS-CMSA-ESII). The method is developed for the IEEE CEC 2026 Competition on Benchmarking Niching Methods for Multimodal Optimization. Rather than modifying the core search dynamics of RS-CMSA-ESII, S-CARD-CMSA preserves its sampling, covariance adaptation, taboo-region update, restart, and termination mechanisms. Two conservative extensions are introduced. First, a passive secondary candidate archive records the restart-level best candidates without influencing the search trajectory. Second, a score-aware density-filtered reporting rule constructs the final solution set by balancing robust peak ratio and precision-driven F1-score. Development experiments show that the density-filtered rule preserves the peak coverage obtained by a medium score-aware rule while reducing redundant reports. On a broader validation subset, it maintains the same mean RPR while improving mean precision, F1-score, and the official-score-oriented average. The method does not use true global-minimum locations during optimization; such information is used only for offline development analysis and post-run scoring. The source code of S-CARD-CMSA is available at https://github.com/ChauhanDikshit.

Dikshit Chauhan

Department of Electrical and Computer Engineering, National University of Singapore

Evolutionary Optimization Multimodal Optimization

Jul 4, 2026cs.AI

Bridging Interleaved Multi-Modal Reasoning as a Unified Decision Process

Unified multi-modal models (UMMs) have shown promising interleaved text-image reasoning capabilities, yet effectively optimizing such multi-turn generation via reinforcement learning (RL) remains an open challenge. Existing approaches apply RL exclusively to text steps, relegating image generation to supervised surrogates, preventing policy gradients from propagating through the full interleaved trajectory across heterogeneous modalities. This leaves the potential of RL for UMMs largely untapped. In the paper, we introduce \textbf{BRAID} (\textbf{B}ridging inte\textbf{R}le\textbf{A}ved mult\textbf{I}-modal reasoning as a unified \textbf{D}ecision process), a simple framework that casts multi-turn text-image-text reasoning as a unified Markov decision process (MDP), enabling joint optimization of textual and visual generation via a single, principled RL objective. BRAID computes a shared trajectory-level advantage and propagates it coherently into both text tokens and image denoising paths, each optimized through its modality-native policy gradient mechanism. To further address long-horizon credit assignment, BRAID employs a vision-language model (VLM) judge that scores each intermediate image on its reasoning utility, supplying dense turn-level feedback to sharpen learning at critical visual branches. Experiments on spatial reasoning and visual perception benchmarks show that BRAID consistently outperforms various baselines, confirming that a unified MDP formulation with vision-thinking guidance is essential for effective multi-modal reasoning.

Zican Hu, Xuyang Hu, Yiming Liu +10

Nanjing University · Shanghai AI Laboratory · Tsinghua University +5

Unified Multimodal Models Multimodal Reasoning Multimodal Optimization Multimodal Generation Multimodal Foundation Models RL for VLMs+1

Jun 24, 2026cs.LG

\chisao{}: A GPU-Native Parallel Optimizer for Multimodal Black-Box Functions via Convergence-Anticonvergence Oscillation

Finding all modes of a multimodal black-box function is a fundamental challenge in optimization, Bayesian inference, and scientific computing. Existing approaches -- basin-hopping, CMA-ES, multistart gradient descent -- operate sequentially and cannot exploit the massive parallelism of modern GPU hardware. We introduce \chisao{} (\textbf{C}onvergence-\textbf{H}alt-\textbf{I}nvert-\textbf{S}tick-\textbf{A}nd-\textbf{O}scillate), a GPU-native population optimizer that runs an entire sample batch simultaneously and exploits a deliberate convergence-anticonvergence oscillation cycle to escape local traps while freezing confirmed modes. The structural move is asymmetric: samples that reach true peaks are frozen (``stuck'') and preserved, while the rest keep exploring via momentum-based anti-convergence and stochastically smoothed gradients. Adaptive reseeding via two complementary strategies (Repulse Monkey and Golden Rooster) maintains population diversity throughout. On all 42 functions of the Simon Fraser University optimization benchmark suite across dimensions

d \in \{2, 4, 8, 16, 32, 64\}

, \chisao{} achieves \textbf{100%} mode recovery where all CPU baselines collapse at

d \geq 8

on the hardest multimodal functions, at up to \textbf{

34\times

} speedup over basin-hopping on functions where all methods succeed (Michalewicz

d=64

) and up to \textbf{

39\times

} on unimodal functions (Rotated Hyper-Ellipsoid

d=64

, pure GPU dividend). All benchmarks evaluate the objective by value alone -- gradients come from finite differences -- so the reported speedups are a derivative-free worst case. Under substantial likelihood noise (

σ_{\mathrm{noise}}

up to 1.0), mode detection remains 100% reliable. The algorithm is available as a standalone open-source Python package on PyPI.

Ira Wolfson

Department of Electronics and Electrical Engineering Braude College of Engineering, Karmiel, Israel

GPU Acceleration Black-Box Optimization High-Performance Computing Zeroth-Order Optimization Metaheuristic Optimization Global Optimization+2

Jun 14, 2026cs.NE

MSC-CMA-ES: Structure-Aware Restarts for CMA-ES via Cyclic Nearest-Better Basin Discovery

CMA-ES is, per run, a local optimizer; multimodal search relies on restart strategies such as IPOP and BIPOP, which draw every restart uniformly and reuse no information from previous evaluations. Multi-Start Clustering CMA-ES (MSC-CMA-ES) makes restarts structure-aware: in alternating cycles, a Sobol pre-sample is partitioned into approximate basins of attraction by nearest-better clustering, restarts are seeded basin by basin with locally scaled step sizes and population sizes, redundant basin visits are detected and excluded, and the remaining budget is spent on an unbounded local refinement of the best-so-far solution. We evaluate the method on four CEC suites (CEC2014, CEC2017, CEC2020, CEC2022) at their official budgets, across ten (suite, dimension) cells with dimensions 5-30, 51 runs per function, against BIPOP-CMA-ES and five differential-evolution algorithms (ARRDE, jSO, j2020, NL-SHADE-RSP, LSRTDE). Read per function class, MSC-CMA-ES leads on one class, is mixed on a second, and trails on the third. On composition functions, MSC-CMA-ES attains the best value on all four aggregate measures, with 2.7x the fixed-budget target coverage of BIPOP-CMA-ES - the highest composition coverage of any algorithm evaluated. On basic functions, it achieves the best (lowest) median error but exhibits a lower deep-target coverage - the measured price of spending budget on landscape discovery. On hybrid functions both CMA variants trail the leading DE algorithms; the deficit belongs to the CMA family, not to the restart mechanism. All results and scripts are publicly available.

Dimitar Nedanovski, Svetoslav Nenov, Dimitar Pilev

Faculty of Mathematics and Informatics Sofia University St. Kliment Ohridski James Baucher Blvd., 1164 Sofia, Bulgaria · Department of Mathematics University of Chemical Technology and Metallurgy Sofia, Bulgaria · Department of Informatics University of Chemical Technology and Metallurgy Sofia, Bulgaria

Evolutionary Optimization Covariance Matrix Adaptation Evolution Strategy Multimodal Optimization

May 29, 2026cs.LG

GLENS: Global Search via Learning from Solver Iterates with Diffusion Models

We consider the problem of generating a large collection of initial guesses for local minima of multimodal non-convex continuous optimization problems. The goal is for these initial guesses to be high-quality (i.e., a numerical solver converges quickly) and diverse (i.e., represent many different local minima). Identifying multiple locally optimal solutions enables flexible downstream decision-making, but typically requires expensive global search. Existing data-driven methods predict initial guesses using only the final converged optima from offline solver runs, which discards information about the local neighborhoods of solutions and limits the available training data. We propose GLENS (Global Search via Learning from Solver Iterates), a data-efficient global search method that leverages intermediate solver iterates as free data augmentation. GLENS consists of two components: a neighborhood structure model that uses diffusion models to learn the local geometry around optima conditioned on problem parameters, and a solver behavior model that learns refinement directions to further guide samples towards nearby optima during diffusion sampling. Experiments on modified non-convex benchmark problems and a two-robot obstacle-avoidance navigation problem show that GLENS generates high-quality initial guesses while preserving the multimodal distribution of diverse local optima. The resulting initial guesses lead to faster solver convergence across different problem settings and solvers. We also analyze how key hyperparameter choices affect the performance.

Anjian Li, Bartolomeo Stellato, Ryne Beeson

Department of Electrical and Computer Engineering, Princeton University, Princeton, 08544, NJ, USA. · Department of Operations Research and Financial Engineering, Princeton University, Princeton, 08544, NJ, USA. · Department of Mechanical and Aerospace Engineering, Princeton University, Princeton, 08544, NJ, USA.

Learning to Optimize Diffusion Sampling Global Optimization Multimodal Optimization Nonconvex Optimization

May 25, 2026cs.CV

DIVA: Harnessing the Representation Divergence in Unified Multimodal Models for Mutual Reinforcement

Unified Multimodal models (UMMs) built on a single architecture have shown impressive performance in both understanding and generation. We identify a fundamental challenge that lies in inductive biases induced by distinct supervision signals: generation branch prefers high-fidelity, fine-grained representations capable of reconstruction, while the understanding favours semantically discriminative embeddings that remain invariant to task-irrelevant factors. Consequently, optimizing these complementary but non-equivalent objectives within a monolithic backbone leads to mutual impairment instead of enhancement. In this paper, we first analyze the root cause of this interference in unified backbones and reveal a complementary structure in their internal representations. Motivated by the observation, we propose DIVA, a self-improved post-training framework that transforms the representation divergence into interior synergy. By explicitly factorizing the visual representation into shared and unique components based on two complementary information flow, DIVA enables both the understanding and generation branches to achieve beneficial transferring while preserving the integrity of unique information from cross-flow interference via mutual information estimation. Despite its generality, our method consistently achieves improvements across visual understanding (+7.82%) and generation (+8.46%). The official code is available at: https://github.com/Jayyy-H/DIVA.

Renjie Lu, Xulong Zhang, Xiaoyang Qu +2

Ping An Technology (Shenzhen) Co., Ltd., Shenzhen, China · University of Science and Technology of China, Hefei, China.

Multimodal Disentangled Representation Learning Unified Multimodal Models Representation Disentanglement Multimodal Optimization Multimodal Generation Multimodal Foundation Models+2

May 18, 2026cs.NE

Mapping the Fitness Landscape: A Structure-Guided Approach to Multi-Modal Optimization

Multimodal optimization requires finding many optima rather than merely keeping a diverse population. Yet most niching-based evolutionary algorithms rely on distances or density estimators without explicitly recovering the underlying peak--basin organization in the decision space, which can lead to pseudo-multimodality: many distinct individuals ultimately collapse into only a few basins. We introduce Chaotic Landscape-Decoding Evolution (CLDE), a decision-space-centric framework that turns multimodal search into a closed loop of decode--value--allocate--refine. CLDE injects controlled global exploration via a logistic chaotic map with a decaying step size, then builds a

k

-nearest-neighbor graph on a decoding canvas and performs persistence-guided basin growing that merges peaks only when they are not separated by deep valleys. An adaptive persistence threshold continuously tunes the decoding resolution online to avoid over-fragmentation and over-merging. Guided by the decoded structure, CLDE carries out basin-wise selection and refinement to improve solution quality while preserving basin coverage. We instantiate CLDE as CLDE-S and CLDE-M for single- and multi-objective multimodal optimization. Experiments on 20 CEC2013 functions show that CLDE-S achieves strong peak ratio under the same evaluation budget, while on DTLZ and MMMOP suites CLDE-M attains competitive IGD/IGDx, with pronounced gains on strongly multimodal problems.

Meng Xiang, Pei Yan

University of Aizu Aizuwakamatsu, Japan

Evolutionary Optimization Multi-Objective Evolutionary Optimization Multimodal Optimization

May 15, 2026cs.CV

Second-Order Multi-Level Variance Correction for Modality Competition in Multimodal Models

Autoregressive next-token training offers a unified formulation for image generation and text understanding, but it also creates strong modality competition that destabilizes optimization and limits large-batch scaling. We show that first-order optimizers such as AdamW are vulnerable to cross-modality gradient heterogeneity, while second-order preconditioning, particularly SOAP, provides a more stable basis for multimodal alignment. Building on this insight, we propose \emph{ML-FOP-SOAP}, a second-order optimization framework with Multi-Level Variance Correction. Our Fisher-Orthogonal Projection suppresses variance-induced modality conflicts, reducing the trade-off between visual generation and textual understanding. To make this practical under large gradient accumulation, we introduce a hierarchical folding strategy that captures fine-grained variance with low micro-step overhead. Experiments on Janus and Emu3 show consistent gains across both modalities and stable training at batch size 8192. Compared with AdamW, our method improves sample efficiency by up to

1.4\times

and accelerates wall-clock training by up to

1.5\times

, offering a robust optimizer for scaling multimodal foundation models.

Yishun Lu, Wes Armour

University of Oxford, Oxford, United Kingdom

Second-Order Optimization Multimodal Optimization Multimodal Foundation Models Multimodal Learning Multimodal Understanding

May 12, 2026cs.AI

MM-OptBench: A Solver-Grounded Benchmark for Multimodal Optimization Modeling

Optimization modeling translates real decision-making problems into mathematical optimization models and solver-executable implementations. Although language models are increasingly used to generate optimization formulations and solver code, existing benchmarks are almost entirely text-only. This omits many optimization-modeling tasks that arise in operational practice, where requirements are described in text but instance information is conveyed through visual artifacts such as tables, graphs, maps, schedules, and dashboards. We introduce multimodal optimization modeling, a benchmark setting in which models must construct both a mathematical formulation and executable solver code from a text-and-visual problem specification. To evaluate this setting, we develop a solver-grounded framework that generates structured optimization instances, verifies each with an exact solver, and builds both the model-facing inputs and hidden reference files from the same verified source. We instantiate the framework as MM-OptBench, a benchmark of 780 solver-verified instances spanning 6 optimization families, 26 subcategories, and 3 structural difficulty levels. We evaluate 9 multimodal large language models (MLLMs), including 6 frontier general-purpose models and 3 math-specialized models, with aggregate, family-level, difficulty-level, and failure-mode analyses. The results show that the task remains far from solved: the best two models reach 52.1% and 51.3% pass@1, while on average across the six general-purpose MLLMs, pass@1 is 43.4% on easy instances and 15.9% on hard instances. All three math-specialized MLLMs solve 0/780 instances. Failure attribution shows that errors arise both when extracting instance data from text and visuals and when turning extracted data into solver-correct formulations and code. MM-OptBench provides a testbed for solver-grounded, decision-oriented multimodal intelligence.

Zhong Li, Qi Huang, Yuxuan Zhu +6

Great Bay University · Leiden University · Rensselaer Polytechnic Institute +1

Multimodal Optimization Synthetic Benchmark Generation Multimodal Model Evaluation Natural Language to Optimization Modeling

Apr 17, 2026cs.AI

Stein Variational Black-Box Combinatorial Optimization

Combinatorial black-box optimization in high-dimensional settings demands a careful trade-off between exploiting promising regions of the search space and preserving sufficient exploration to identify multiple optima. Although Estimation-of-Distribution Algorithms (EDAs) provide a powerful model-based framework, they often concentrate on a single region of interest, which may result in premature convergence when facing complex or multimodal objective landscapes. In this work, we incorporate the Stein operator to introduce a repulsive mechanism among particles in the parameter space, thereby encouraging the population to disperse and jointly explore several modes of the fitness landscape. Empirical evaluations across diverse benchmark problems show that the proposed method achieves performance competitive with, and in several cases superior to, leading state-of-the-art approaches, particularly on large-scale instances. These findings highlight the potential of Stein variational gradient descent as a promising direction for addressing large, computationally expensive, discrete black-box optimization problems.

Thomas Landais, Olivier Goudet, Adrien Goëffon +2

LERIA, Université d’Angers, 2 Boulevard Lavoisier, Angers 49045, France

Stochastic Optimization Black-Box Optimization Combinatorial Optimization Multimodal Optimization Stein Variational Gradient Descent

Mar 12, 2026cs.CV

Less Data, Faster Convergence: Goal-Driven Data Optimization for Multimodal Instruction Tuning

Multimodal instruction tuning is often compute-inefficient because training budgets are spread across large mixed image-video pools whose utility is highly uneven. We present Goal-Driven Data Optimization (GDO), a framework that computes six sample descriptors for each candidate and constructs optimized 1

\times

training subsets for different goals. Under a fixed one-epoch Qwen3-VL-8B-Instruct training and evaluation recipe on 8 H20 GPUs, GDO uses far fewer training samples than the Uni-10x baseline while converging faster and achieving higher accuracy. Relative to the fixed 512k-sample Uni-10x baseline, GDO reaches the Uni-10x reference after 35.4k samples on MVBench, 26.6k on VideoMME, 27.3k on MLVU, and 34.7k on LVBench, while improving Accuracy by +1.38, +1.67, +3.08, and +0.84 percentage points, respectively. The gains are largest on MVBench and MLVU, while LVBench improves more modestly, consistent with its ultra-long-video setting and the mismatch between that benchmark and the short-video/image-dominant training pool. Across MinLoss, Diverse, Temp, and Temp+, stronger temporal emphasis yields steadily better long-video understanding behavior. Overall, GDO provides a goal-driven data optimization framework that enables faster convergence with fewer training samples under a fixed training protocol. Code is available at https://github.com/rujiewu/GDO.

Rujie Wu, Haozhe Zhao, Hai Ci +1

School of Computer Science, Peking University, Beijing, China · Institute for Artificial Intelligence, Peking University, Beijing, China · State Key Laboratory of General Artificial Intelligence, Peking University, Beijing, China +2

Video Understanding Instruction-Tuning Data Selection Training Data Selection Multimodal Optimization Multimodal Foundation Models Multimodal Instruction Tuning

Date pendingcs.LG

CAT-GS: Balanced Multimodal Learning via Calibrated Gating and Fusion Surgery

End-to-end training of multimodal neural networks often exhibits unstable neural dynamics characterized by three coupled failure modes that degrade learning: (i) modality imbalance, where one branch dominates gradient-based optimization; (ii) unstable gating, where noisy confidence cues induce erratic modality selection; and (iii) fusion interference, where modality-specific gradients conflict at the shared fusion layer. We propose CAT-GS (Calibrated, Adaptive, Thresholded Gating with Fusion Surgery), a neural dynamics-based optimization controller for intelligent computing applications. CAT-GS operates during backpropagation without modifying model architectures, fusion modules, or task losses. Through calibration of teacher-derived reliability via temperature scaling and EMA smoothing, CAT-GS stabilizes neural dynamics using a margin-thresholded policy to switch between warm-up dropout, weak-modality prioritization, and weak-biased blending, stabilizes gradient magnitudes under aggressive gating via capped gradient-budget renormalization, and applies fusion-only PCGrad to reduce destructive cross-modal interference at the primary shared bottleneck. We evaluate CAT-GS on audio--visual multimodal pattern recognition benchmarks (CREMA-D, AV-MNIST, and VGGSound), a tri-modal setting (UR-FUNNY), controlled synthetic data (CG-MNIST), and additional cross-domain benchmarks (AVE and CMU-MOSI). CAT-GS improves or matches fused multimodal accuracy against strong imbalance-aware baselines (including OGM-GE, G

^2

D, and UMT) across settings, and yields smoother gating behavior with fewer conflicting fusion gradients.

Mahir Shahriar Tamim, Sharjil Khan, Md. Samiul Alim +3

Department of Electrical and Computer Engineering, North South University, Dhaka, Bangladesh

Cross-Modal Learning Modality Imbalance Gradient Interference Multimodal Optimization Multimodal Fusion Multimodal Learning+1