paperlist.ai

AI conference papers

AI conference paper library

Search papers from 30+ top conferences, including NeurIPS, ICLR, ICML, CVPR, ACL and AAAI. Filter by keyword, then open any paper for its abstract, authors and links.

IJCAI 2026

Music Atelier: Exploring the Knowing–Doing Gap in LLM Creativity via Symbolic Music Composition

Zhejing Hu, Yan Liu, Zhi Zhang, Sean Fontaine, Gong Chen

The knowing--doing gap, the mismatch between ideas articulated during model reasoning and the realized creative artifact, remains a fundamental challenge in creative AI and persists in LLM-based artistic creation. This paper responds to this gap by introducing a systematic and interpretable framework for examining how user intent is articulated during model reasoning and selectively realized, or lost, during action in LLMs, using symbolic music composition as an analytical lens. We present a realizational process theory that formalizes creative generation and localizes the knowing--doing gap at the realization stage. We instantiate this theory with Music Atelier (Mutelier), an LLM-as-a-Judge framework that operationalizes idea-level realization analysis and makes the gap observable and analyzable in practice. Across diverse evaluation settings, we show that Mutelier reveals reliable, previously invisible failure modes in which intent-aligned ideas are articulated during reasoning but fail to materialize in the final artifact. By reframing artistic creation as a realizational process, this work provides a principled process-level foundation for understanding how knowing--doing gaps emerge in machine creativity.

IJCAI 2026

Semantics-Guided Representation Learning for Long-Tailed ECG Classification

Fengyi Guo, Ying An, Jianxin Wang

Deep learning has achieved remarkable success in automated electrocardiogram (ECG) diagnosis. However, the long-tailed distribution of real-world ECG data remains a critical challenge. Existing methods mainly operate at the signal feature level and fail to exploit semantic relationships among diagnostic labels, which limits their ability to effectively recognize rare categories. To address this issue, we propose a Semantics-Guided Representation Learning (SGRL) framework, designed to leverage semantic priors to guide feature learning and thereby correct feature bias under long-tailed distributions. Specifically, we propose a Label Semantic Prompt Adaptation (LSPA) strategy, which introduces ECG-calibrated learnable parameters into label prompts to generate adaptive label semantic embeddings under a semantic-consistency constraint, thereby overcoming the limitations of coarse-grained label prompts in characterizing fine-grained intra-class morphological variations. Subsequently, we propose Semantic-Guided Representation Decorrelation (SGRD) that fuses ECG embeddings with adaptive label semantics and suppresses inter-class semantic correlations to obtain discriminative class semantic anchors, thereby improving tail-class separability. Extensive experiments on multiple public datasets demonstrate the significant superiority of SGRL in long-tailed ECG classification tasks. Our code is available on https://github.com/gfywudi/SGRL.

IJCAI 2026

SPOTR: Spatio-temporal Pooling One-Token Reconstruction for Universal Physiological Signal Self-supervised Learning

Yiyu Gui, Mingzhi Chen, Yuesheng Zhu, Guibo Luo, Yuchao Yang

Physiological signals such as EEG, ECG, and PPG are widely used in clinical monitoring. Recent self-supervised learning (SSL) methods offer an attractive way to leverage unlabeled recordings, yet they still fall short in practice. In particular, current SSL methods struggle across heterogeneous datasets, often distorting clinically meaningful structures or learning shortcuts from temporal and cross-channel redundancy. Consequently, existing SSL methods often deliver limited performance under linear probing, a lightweight adaptation setting that better matches real-world medical scenarios. Moreover, most Transformer-based SSL models encode a flattened spatiotemporal token sequence, incurring high computation and memory cost, and are typically developed within a single modality. To address these limitations, we present SPOTR (Spatio-temporal Pooling One-Token Reconstruction), a compress-reconstruct pretraining framework that introduces a single-token global bottleneck for physiological signals. SPOTR compresses each waveform into a single-token representation and reconstructs the signal conditioned only on this representation. Meanwhile, SPOTR introduces an efficient spatio-temporal compaction module to reduce computation and memory cost. Pretrained on 20 datasets spanning EEG, iEEG, ECG, and PPG, SPOTR consistently outperforms the strongest baseline under linear probing, improving average AUC by 18.49%, 21.71%, 17.86%, and 4.64%, respectively. Compared with a representative general-purpose time-series foundation model, SPOTR achieves around 78% lower latency and 52% lower peak GPU memory on average. The code and supplementary material can be found at https://github.com/5GYYYYY/SPOTR.

IJCAI 2026

Toward Synthesizability-Aware Multi-Step Retrosynthetic Planning

yujie Chen, AJie Lin, Tengfei Ma, Shu Wu, Leyi Wei, Yiping Liu, xiangxiang Zeng

Multi-step retrosynthetic planning aims to decompose target molecules into available starting materials by iteratively invoking single-step prediction models within a search algorithm. The success of retrosynthetic planning depends on the joint guidance of single-step reasoning and global search across steps. However, most existing frameworks make step-wise decisions based only on the current molecular state, without explicitly modeling synthesizability signals that reflect long-range reachability. In this work, we propose GuideRetro, a synthesizability-aware framework for multi-step retrosynthetic planning that integrates global synthesizability knowledge into step-wise retrosynthetic prediction. GuideRetro learns transferable knowledge from large-scale reaction networks by modeling the evolution of synthetic complexity along reaction pathways. During planning, a route-aware synthesis state modeling module combines the evolving retrosynthetic route with retrieved global signals to guide reactant generation at each step. Experiments on benchmark datasets show that GuideRetro achieves state-of-the-art performance. The integration of global synthesizability knowledge and route-aware modeling improves planning accuracy and search efficiency under realistic retrosynthetic settings. The code is available at: https://github.com/L-AJ/GuideRetro.

IJCAI 2026

UniPocket: Physics-Aware Geometric Graph Learning with Manifold Completeness for Ligand-Specific Binding Site Prediction

Kangxin Chen, Jieyu Zhao, Jinli Hu, Min Xie

Predicting ligand binding sites on protein surfaces requires capturing complex local geometries and satisfying physical constraints. Existing voxel-based methods suffer from high computational costs and rotation sensitivity, while standard point-cloud GNNs often lack geometric completeness—failing to distinguish chiral structures or subtle topological variations. In this work, we propose UniPocket, a novel E(3)-equivariant surface graph neural network. Inspired by recent advances in efficient geometric completeness, UniPocket constructs a Manifold-Aware Surface Encoder that utilizes local surface normals as virtual reference frames to capture complete geometric invariants without expensive high-order tensor products. Furthermore, we introduce a Ligand-Gated Message Passing mechanism to condition the surface features on the chemical semantics of the target ligand, and a Physics-Aware Vector Rejection Module that enforces steric constraints via orthogonal vector decomposition. Experimental results on standard benchmarks (PDBbind, COACH420, Holo4k) demonstrate that UniPocket achieves state-of-the-art performance, validating that geometric completeness and physical inductive biases are key to precise binding site detection.

IJCAI 2026

LogicFusion: Differentiable Logical Rule Learning for Cancer Driver Gene Identification

Bang Chen, Lijun Guo, Wentao He, Guang Cao, Rong Zhang

Identifying cancer driver genes (CDGs) requires integrating heterogeneous biological networks, each encoding distinct mechanistic insights into tumorigenesis. Existing multi-network methods typically fuse views at the feature level or enforce uniform representations, which obscures network-specific signals and limits interpretability. To address this, we propose LogicFusion, a novel differentiable framework that treats each biological network as an independent probabilistic evidence source and explicitly learns how to combine them using logical reasoning. Specifically, LogicFusion maps the output of each view into probabilistic space as independent evidence, and learns a set of logical rules in a differentiable manner. These rules adaptively select and fuse these view evidences through logical conjunction (AND) and disjunction (OR). The final prediction is then obtained via gene-specific weighting. LogicFusion enables both high-accuracy CDG identification and interpretable attribution of predictions to specific networks. Experiments on pan-cancer and cancer-specific datasets show that LogicFusion consistently outperforms state-of-the-art methods, while providing transparency in multi-view genomic reasoning through learned logical rules.

IJCAI 2026

The Alignment Bottleneck in Decomposition-Based Claim Verification

Mahmud Elahi Akhter, Federico Ruggeri, Iman Munire Bilal, Robert Procter, Maria Liakata

Structured claim decomposition is often proposed as a solution for verifying complex, multi-faceted claims, yet empirical results have been inconsistent. We argue that these inconsistencies stem from two overlooked bottlenecks: evidence alignment and sub-claim error profiles. To better understand these factors, we introduce a new dataset of real-world complex claims, featuring temporally bounded evidence and human-annotated sub-claim evidence spans. We evaluate decomposition under two evidence alignment setups: Sub-claim Aligned Evidence (SAE) and Repeated Claim-level Evidence (SRE). Our results reveal that decomposition brings significant performance improvement only when evidence is granular and strictly aligned. By contrast, standard setups that rely on repeated claim-level evidence (SRE) fail to improve and often degrade performance as shown across different datasets and domains (PHEMEPlus, MMM-Fact, COVID-Fact). Furthermore, we demonstrate that in the presence of noisy sub-claim labels, the nature of the error ends up determining downstream robustness. We find that conservative "abstention" significantly reduces error propagation compared to aggressive but incorrect predictions. These findings suggest that future claim decomposition frameworks must prioritize precise evidence synthesis and calibrate the label bias of sub-claim verification models.

IJCAI 2026

Bi-CoG: Bi-Consistency-Guided Self-Training for Vision-Language Models

Rui Zhu, Song-Lin Lv, Zi-Kang Wang, Lan-Zhe Guo

Exploiting unlabeled data through semi-supervised learning (SSL) or leveraging pre-trained models via fine-tuning are two prevailing paradigms for addressing label-scarce scenarios. Recently, growing attention has been given to combining fine-tuning of pre-trained vision-language models (VLMs) with SSL, forming the emerging paradigm of semi-supervised fine-tuning. However, existing methods often suffer from model bias and hyperparameter sensitivity, due to reliance on prediction consistency or pre-defined confidence thresholds. To address these limitations, we propose a simple yet effective plug-and-play methodology named Bi-Consistency-Guided Self-Training (Bi-CoG), which assigns high-quality and low-bias pseudo-labels, by simultaneously exploiting inter-model and intra-model consistency, along with an error-aware dynamic pseudo-label assignment strategy. Both theoretical analysis and extensive experiments over 14 datasets demonstrate the effectiveness of Bi-CoG, which consistently and significantly improves the performance of existing methods.

IJCAI 2026

Mixture of Clustering Experts with Dual Consistency for Multi-View Clustering

Daidai Zhu, Yang Zhao, Dandan Ma, Ganchao Liu, Zhiyu Jiang

Multi-view clustering aims to discover shared semantic structures from multiple complementary data views to improve clustering performance. However, most existing methods rely on a single clustering representation for each semantic cluster, which limits the ability to model complex cluster structures and diverse patterns in real-world data. To address this limitation, we propose a Mixture of Clustering Experts with Dual Consistency (MoCE-DC). MoCE-DC introduces a set of learnable clustering experts that characterize the same semantic cluster from multiple perspectives within a unified prototype space. A gating mechanism is employed to adaptively select experts for each sample. MoCE-DC decomposes complex semantic clusters into multiple collaborative sub-structures, significantly enhances the ability to model intricate intra-cluster diversity. To further ensure cross-view semantic consistency, we propose a dual-level alignment mechanism that enforces prediction consistency across views while guiding clustering assignments toward a more discriminative direction. In addition, a gating balance regularization strategy is introduced to mitigate expert collapse and promote balanced expert utilization. Extensive experiments on multiple public multi-view clustering benchmarks demonstrate that MoCE-DC outperforms state-of-the-art methods.

IJCAI 2026

Progressive Adversarial Multi-View Alignment for Unsupervised Embedded Feature Selection with Linear Complexity

Shixuan Zhou, Yi Xiang, Haoxiang Qin, Haining Wang, Yukuan Ma, Han Huang

Standard unsupervised multi-view feature selection (UMFS) methods for large datasets exhibit limitations in modeling the competition between cross-view alignment and intra-view diversity, resulting in suboptimal solutions and expensive computational costs. This challenge is exacerbated by the diverse signals inherent in complex samples, which tend to mask shared patterns, thus complicating the pursuit of an optimal trade-off. In this work, we propose a Progressive Adversarial Feature Selection (ProAd-FS) framework for large-scale multi-view learning, which formulates this static trade-off objective as a dynamic competitive process. To be specific, ProAd-FS develops an adversarial decoupled architecture that assigns these competing objectives to distinct inter-view and intra-view games, guided by a robust gated curriculum to prioritize the learning of underlying structures. The entire framework exhibits linear computational complexity in both sample size and feature dimension, and embeds structural sparse regularization for end-to-end optimization. Extensive experimental results show that ProAd-FS achieves state-of-the-art performance while being highly scalable as well, providing an effective solution for large-scale UMFS tasks.

IJCAI 2026

GBFlow: Grouping Belief-Guided Dual Normalizing Flows for Accurate Spatial Domain Delineation

Fengyi Zhou, Daoyuan Wang, Wenlan Chen, Cheng Liang, Fei Guo

Existing spatial domain identification methods primarily use graph neural networks to model spatial and transcriptional relationships. However, their performance is highly sensitive to noisy affinity graphs. Moreover, graph autoencoders tend to over-constrain latent representations, which limits their ability to capture global variability in spatial multi-omics data. To overcome these issues, we propose a dual-flow latent refinement framework that simultaneously integrates structure-aware and structure-free transformations. Specifically, a graph normalizing flow is employed to enforce relational consistency, while a parallel vanilla normalizing flow preserves global distributional flexibility. Features learned by the two flows are then adaptively fused to obtain a robust and unified latent representations. In addition, we introduce a grouping belief-based affinity refinement strategy to suppress unreliable connections and strengthen confident neighborhood relationships, which provides a more stable structural prior for representation learning. Extensive experiments on multiple spatial multi-omics datasets show that the proposed method consistently outperforms state-of-the-art approaches and achieves more accurate and robust spatial domain identification. The supplementary material is publicly available at https://github.com/LiangSDNULab/GBFlow.

IJCAI 2026

Disentangling Coarse and Fine Latent Dynamics for Probabilistic Time Series Forecasting

Changze Zhou, Ruichu Cai, Shengbin Nie, Juntao Fang, Jie Qiao, Zijian Li

Probabilistic time series forecasting seeks to quantify the uncertainty of future observations. While recent works introduce latent variables to alleviate the spurious dependencies caused by hidden confounders, thereby reducing overly wide confidence intervals, simply incorporating latent factors is not sufficient. When the underlying latent dynamics evolve at multiple temporal scales, existing methods may entangle temporally coarse and fine latent dynamics, which introduces spurious latent transitions and in turn amplifies predictive uncertainty. Therefore, disentangling temporally coarse and fine latent dynamics is essential for achieving sharper and more reliable probabilistic forecasting results. Building on this insight, we propose COFE (COarse And FinE latent dynamics disentanglement), a variational autoencoder–based framework that models the temporal distribution by disentangling and modeling the rapidly changing and slowly varying latent dynamics simultaneously. In particular, the proposed COFE harnesses the independence of estimated noises between adjacent latent states as well as a sparsity constraint on estimated noise to disentangle latent dynamics across different scales effectively. More specifically, we show that the multi-scale latent dynamics are disentangled with rigorous theoretical guarantees. Extensive experiments on 15 benchmark datasets, compared against 12 state-of-the-art baselines, demonstrate that COFE achieves superior uncertainty quantification, validating its effectiveness in a wide range of real-world scenarios. Code is available at https://github.com/polars8948/COFE

IJCAI 2026

Beyond the Mean: Gaussian Distributional Successor Features for Zero-Shot Non-Linear Reward Adaptation

Yong Zhao, Wen Sun, Jianhua He, Peng Wang, Qubeijian Wang

Zero-shot transfer for offline reinforcement learning involves generalizing to a wide range of tasks that are often risk-sensitive, without new interaction. We show here that although Successor Features (SFs) provide a principled framework for transfer through abstracting dynamics from rewards, their typical form is restricted to expected cumulative returns and is thus indifferent to variance in returns. We contend that such a mean-centric approach introduces bias by conflating risky and safe trajectories with identical expected outcomes, as it ignores outcome dispersion critical for risk-aware evaluation. Additionally, we note that distributional methods can be employed to model outcome distributions, but frequently do so at a high computational cost due to the need for discretization or elaborate sampling. To overcome this problem, we introduce a form of successor representation that incorporates an uncertainty envelope over states: Gaussian Distributional Successor Features (GDSF). Rather than inferring an implicit generative process, GDSF learns to approximate the distribution of cumulative outcomes with a Gaussian through recursive moment-matching. We present this framework for efficient representation of aleatoric uncertainty, without resorting to computationally expensive existing distributional methods. We also introduce Latent Outcome Optimization, an inference procedure which finds high-reward outcomes in the data support and drives a goal-conditioned policy. This dual-mode design allows the agent to transfer to non-linear objectives in a zero-shot way while preserving closed-form efficiency for linear tasks. Experiments on the D4RL benchmark show that GDSF yields better performance in risk-sensitive tasks while achieving at least competitive results in standard linear regimes.

IJCAI 2026

Uncertainty-Guided Adaptive Local Adversarial Perturbation for Reliable Molecular Property Prediction

Xuxin Zhao, Wen Zhang, Shichao Liu

Molecular property prediction is a fundamental task with wide-ranging applications in chemistry, materials science, and drug discovery. Beyond predictive accuracy, the reliability of model predictions, particularly their uncertainty awareness, is critical for high-stakes downstream applications. However, most existing methods predominantly optimize performance metrics while overlooking prediction reliability, often producing results that are both inaccurate and overconfident. To address this challenge, we propose an uncertainty-guided framework that integrates adaptive local adversarial perturbation with evidential deep learning for reliable molecular property prediction. The proposed method identifies sensitive molecular regions through gradient-based sensitivity analysis and applies locally adaptive perturbations whose magnitudes are dynamically modulated by predictive uncertainty. This approach explicitly challenges the model to preserve predictive stability under structure-aware perturbations, thereby enhancing its sensitivity to critical molecular substructures. Furthermore, we introduce an evidential calibration strategy that aligns uncertainty with the prediction discrepancy between clean and adversarial molecular views, enabling the learned evidence to faithfully reflect prediction stability. Extensive experiments on benchmark molecular property prediction datasets demonstrate that our approach achieves state-of-the-art predictive performance while providing more reliable uncertainty estimates than widely used uncertainty quantification methods. These results highlight the potential of the proposed framework as a reliable tool for risk-sensitive virtual screening and molecular decision-making. Our code is available at https://github.com/Ubehind/ugap.

IJCAI 2026

Multi-view Regression Clustering via Low-Rank Manifold Decomposition

Xiaowei Zhao, Xinyu Kou, Yan Chen, Linrui Xie, Qiang Zhang, Liang Du

Similarity-graph-based multi-view clustering is effective in capturing non-Gaussian cluster structures, yet it suffers from an inherent conflict between scalability and geometry-consistent cluster assignment. In particular, cluster labels are typically inferred via secondary clustering rather than being learned directly from the underlying data geometry. Although anchor-based extensions alleviate the computational burden, they introduce the challenge of anchor-number selection. To address these limitations, we propose Multi-view Clustering via Manifold Decomposition (MvMD), which directly infers cluster labels from multi-view data without explicit similarity graph construction or anchor selection. MvMD reformulates multi-view clustering as a unified multi-view regression problem, where cluster labels are optimized as model variables. To improve robustness against missing small clusters, a global balance regularization is incorporated. Meanwhile, local geometric consistency and the low-rank structure of cluster assignments are jointly enforced through a symmetric matrix factorization scheme, which is efficiently realized via a truncated SVD-based low-rank approximation. Extensive experiments on benchmark datasets validate the effectiveness and efficiency of the proposed MvMD. The code is available at https://github.com/Vince-Doit/MvMD.

IJCAI 2026

Spot-Adaptive Structural Rectification for Spatially Resolved Transcriptomics Data Clustering

Huanjia Zhao, Shanghui Deng, Shunfan Li, Kun Sun, Weiqing Yan, Chang Tang

Spatially resolved transcriptomics integrates gene expression with spatial coordinates to decode tissue microenvironments. Existing methods predominantly utilize graph structures to model relationships between spots. However, their performance is bottlenecked by the reliability of gene feature graph, facing the following hurdles: (1) ubiquitous housekeeping genes cause high-expression spots to densely connect with heterogeneous spots, leading to a skewed graph structure; (2) information reduction during Highly Variable Gene (HVG) selection results in the loss of intrinsic local structures. To address these challenges, we propose a Spot-Adaptive Structural Rectification method, called SASR. Specifically, SASR employs a hyperspherical expansion constraint that projects gene expression profiles onto a unit hypersphere to maximize angular distances, effectively separating spots falsely clustered by high total counts. Simultaneously, a topological consistency constraint repairs structural fractures caused by HVG selection via aligning latent embeddings with the local structures of the raw full-gene space. The complementary synergy balances angular discriminability with topological fidelity for accurate clustering. Experiments demonstrate that SASR effectively corrects structural biases and surpasses state-of-the-art methods in spatial clustering.

IJCAI 2026

Similarity-Guided Structural Matching Learning for Graph Dataset Condensation

Yiyang Zhang, Yutong Ye, Yingbo Zhou, Nan Zhang, Xiang Lian, Mingsong Chen

As graph repositories grow in scale and diversity, training Graph Neural Networks (GNNs) becomes computationally demanding. However, existing graph condensation methods often fail to retain the intrinsic structural patterns of the original graphs, which are essential in graph-based learning. Therefore, these methods suffer from limited performance and poor generalization in downstream tasks due to the loss of structural information. To address this, we propose Similarity-guided Structural Matching Learning for Graph Dataset Condensation (SSGDC), which efficiently reduces repository size while maintaining both task performance and structural information. Our approach introduces a similarity-based graph selector to identify high-quality subsets for condensation. The condensed graphs are optimized using a dual-objective loss that combines gradient-matching for task alignment with a metric-learning loss for structural preservation within the selected subset. This ensures that the condensed dataset retains both task-relevant information and the essential relational topology that supports GNN training and enhances generalization. Experiments demonstrate that our method achieves higher accuracy and better structure retention across varying condensation ratios, highlighting the critical role of structural preservation in graph dataset condensation.

IJCAI 2026

DCIL: DropConnect-based Causal Imitation Learning Under Environment Heterogeneity

Xinyu Zhang, Shihua Li, Rongjie Liu

In many real-world scenarios, agents operate across heterogeneous environments where the underlying dynamics and data-generating processes vary. Standard reinforcement learning and imitation learning methods often fail in such settings as they typically assume stationarity and learn policies that overfit to environment-specific correlations. A key challenge is the presence of spurious correlations as observed states often contain both causal and non-causal features, with the latter introducing environment-specific biases that undermine generalization. To address this problem, we propose DropConnect-based Causal Imitation Learning (DCIL), a novel offline imitation learning framework designed to identify and exploit stable causal mechanisms across diverse environments. DCIL introduces a gradient alignment constraint that encourages the policy to align with causal structures shared across training environments. To further mitigate overfitting to spurious correlations, DCIL involves DropConnect-based regularization, injecting stochastic perturbations into network weights to simulate parameter uncertainty and reduce reliance on unstable features. We evaluate DCIL on synthetic benchmarks derived from OpenAI Gym control tasks, where non-causal features exhibiting spurious correlations are explicitly injected to simulate environmental heterogeneity. Experimental results show that DCIL outperforms state-of-the-art imitation learning baselines, achieving superior generalization to unseen environments. These findings highlight the importance of incorporating causal reasoning and structured regularization into policy learning for robust performance under environment shift.

IJCAI 2026

FedFINFO: A General Full-Informativeness Federated Graph Learning from Open Cross-Domain Data

Wan Zhang, Xiaoqian Jiang, Ye Wang, zhiqiang xu, Jing Zhang

Open cross-domain federated graph learning facilitates collaborative learning among clients from distinct graph domains while preserving privacy. However, severe structure and feature heterogeneity in open scenarios exacerbates the multiplicative amplification of structural and feature noises within graph neural network encoders, leading to significant negative transfer. Existing methods addressing partial heterogeneity are insufficient. We theoretically reveal this amplification mechanism and propose a novel learning method FedFINFO, which leverages full-informativeness shared knowledge. Specifically, we construct an aligned and general feature space integrating node semantic and structural roles. We proposed a counterfactual multi-view framework to explicitly learn a structure masker for extracting consensus subgraphs. These jointly suppress the mutual amplification of noises at the source. We also propose a history-aware adaptive multi-channel aggregation mechanism to enable dynamic and personalized sharing driven by channel similarity while preventing collaborative oscillation. FedFINFO effectively reconciles common knowledge sharing with personalized knowledge retention, significantly mitigating negative transfer. Extensive experiments under cross-dataset and cross-domain settings demonstrate the superiority of our method.

IJCAI 2026

MOBO: A Merging-Oriented Bi-Level Optimization Framework for Class Incremental Learning

Siyu Zhang, Wen Wang, Wenju Sun, Qingyong Li, Yangliao Geng

Class-Incremental Learning (CIL) aims to enable models to sequentially learn new tasks while retaining knowledge from previous ones. Recently, merging-based pre-trained CIL methods have gained significant attention due to their competitive performance and high inference efficiency. However, most existing approaches decouple training from merging, neglecting the compatibility among task-specific adapters. This incompatibility introduces severe conflicts during integration, resulting in catastrophic forgetting and notable performance degradation. To address this limitation, we propose MOBO, a Merging-Oriented Bi-Level Optimization framework that synergizes the optimization of the current task model with the performance of the final merged model. At the upper level, we introduce a global loss that anticipates the merged model's behavior, guiding the current task parameters toward a solution space that facilitates effective merging. At the lower level, we employ a dynamic weighted merging strategy to optimize merging coefficients and update the merged model. By alternately optimizing the task-specific and merged models, MOBO effectively mitigates the performance loss caused by incompatible adapter integration. Comprehensive experiments on CIFAR-100, CUB-200, ImageNet-R, ImageNet-A, and VTAB demonstrate the superiority of our approach, highlighting its robustness and scalability, particularly on long task sequences.

Keep browsing

More papers from top AI conferences

30+ top conferences, by conference, year, and topic.