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.

NeurIPS 2026

Swimba: Switch Mamba Model Scales State Space Models

Zhixu Du, Krishna Teja Chitty-Venkata, Murali Emani, Venkatram Vishwanath, Hai Li, Yiran Chen

Mixture-of-experts (MoE) is a common approach for increasing parameter capacity, but applying MoE to state space model (SSM) token mixers can multiply the cost of the recurrent state update. We study how to introduce expert specialization into selective SSMs while preserving computational efficiency. We show that MoE--SSM can refer to two designs: (1) MoE over separated SSMs, which maintains multiple state trajectories and thus scales compute with the number of experts; and (2) MoE-parameterized SSM, which mixes experts in parameter space, maintains a single state trajectory, and evaluates the recurrence once. Our method, Switch Mamba (Swimba), follows the second design by routing over expert-produced SSM streams. Theoretically, we establish well-definedness and stability for MoE-parameterized SSMs and characterize the relationship between the two designs. Empirically, we evaluate Swimba on standard benchmark tasks and measure real-time throughput and latency. Under matched FLOPs, Swimba achieves slightly better average performance than the baseline, with a small slowdown in real-time latency and throughput. Overall, these results suggest that parameter-space MoE can increase SSM capacity while keeping the dominant recurrence cost fixed.

NeurIPS 2026

Sustainability in the Loop: AI Model Development Should Be Multi-Objective

Matteo Mugnai, Francesco Pistolesi

This position paper argues that environmental cost should be part of the objectives used to train, select, and deploy AI models. Today, sustainability is mainly measured after design choices have been made, while architectures, data, hyperparameters, and serving strategies are chosen through accuracy, latency, and other proxies. This separation weakens model development. In training, newer models can move toward higher emissions without a comparable gain in performance. In inference, small differences in energy per query can become large lifecycle costs at scale. FLOPs, parameter counts, and latency do not capture these effects, because the real cost depends on hardware, datacenter efficiency, energy mix, water demand, and deployment volume. We call for multiobjective model development where performance and lifecycle environmental cost guide decisions together. The paper explains how to distinguish sustainable progress from costlier forms of progress, addresses alternative views, and outlines research directions for objectives, benchmarks, and model selection practices that make sustainability part of optimization.

NeurIPS 2026

Susceptibilities for Neural Networks Learning from Physical Data

Rohan Hitchcock, Gary W Delaney, Jonathan H Manton, Richard Scalzo, Jingge Zhu

Neural networks that are trained on data arising from a physical system must somehow learn regularities induced by the underlying physical laws. In this setting, concepts from statistical physics provide powerful tools for analysing how physical laws influence the learning process. In this paper we explain how *susceptibilities* --- which measure the response of a neural network to perturbations of a parameter of the data distribution --- can be applied when learning from physical data. We show that such susceptibilities can identify the conditions under which specific input features are most informative for learning, guiding data selection, a prediction we validate experimentally. For distributions lacking a natural parameter, we propose introducing one via an arbitrary scalar function of the physical state, and demonstrate that susceptibilities track the emergence of specific capabilities (such as collision detection) during training.

NeurIPS 2026

Survive or Collapse: The Asymmetric Roles of Data Gating and Reward Grounding in Self-Play RL

Sophia Xiao Pu, Zhaotian Weng, Chengzhi Liu, Jayanth Srinivasa, Gaowen Liu, William Yang Wang, Xin Wang

Self-play reinforcement learning trains language models on their own generated tasks, co-evolving a proposer and solver without human labels. Recent systems report strong reasoning gains, but collapse and instability are widely observed and poorly understood. The dominant response treats this as a reward-design problem. We argue instead that self-play stability is governed by two distinct levers: a data-level gate that decides which proposer-generated tasks enter the training pool, and the reward signal that updates the policy on tasks already admitted. Through controlled experiments on a Python output-prediction task and a deterministic-DSL twin task that strips pretraining priors, output ambiguity, and executor noise, we find the two levers are asymmetric. A strict gate is sufficient for stability under every reward variant we test, including a self-consistency reward with no access to ground truth; while no reward variant is sufficient once the gate is removed. This asymmetry exposes a counter-intuitive coupling we call the Grounded Proposer Paradox: a proposer with ground-truth access accelerates collapse faster than an ungrounded one when paired with a self-consistency solver, by concentrating training on clean tasks that form the fastest path to a spurious self-consistent attractor. Replacing the binary gate with a continuous strictness parameter $\varepsilon$ further reveals a two-stage phase transition: training-side metrics decouple at low $\varepsilon$, while validation accuracy holds until $\varepsilon$ is much higher. Data-level gating, not reward calibration, is the binding constraint on self-play stability.

NeurIPS 2026

SurvivalPFN: Amortizing Survival Prediction via In-Context Bayesian Inference

Shi-ang Qi, Vahid Balazadeh Meresht, Michael Cooper, Russell Greiner, Rahul Krishnan

Survival analysis provides a powerful statistical framework for modeling time-to-event outcomes in the presence of censoring. However, selecting an appropriate estimator from the many specialized survival approaches often requires substantial methodological and domain expertise. We introduce SurvivalPFN, a prior-data fitted network that amortizes Bayesian inference for censored observations through in-context learning. SurvivalPFN is pretrained on a diverse family of synthetic, identifiable, and right-censored data-generating processes, enabling it to amortize survival analysis in a single forward pass during inference. As a result, the model adapts to the effective complexity of each dataset without task-specific training or hyperparameter tuning, avoids restrictive parametric assumptions, and produces calibrated survival distributions. In a large-scale benchmark spanning 61 survival datasets, 21 methods, and 5 evaluation metrics, SurvivalPFN achieves strong predictive performance and often improves upon established survival models. These results suggest that SurvivalPFN offers a principled and practical foundation model for survival analysis, with potential applications in high-impact domains such as healthcare, finance, and engineering.

NeurIPS 2026

Survival Transformers for Longitudinal Data Analysis: Application to Atrial Fibrillation Risk from ECG

Rafael Silva, Maxime Sermesant

Atrial fibrillation (AFib) is the most common sustained cardiac arrhythmia and a major risk factor for stroke, yet it often remains undetected until a first clinical event. Existing deep learning approaches typically estimate AFib risk from a single, cross-sectional ECG, discarding the longitudinal information contained in serial recordings. We propose a transformer-based survival model, SurviFormer, that leverages sequences of ECG representations to model patient-specific AFib risk over time. Our approach encodes irregular inter-visit time gaps as pairwise relative attention biases within a causally masked transformer, and outputs a discrete hazard function trained with a multi-landmark strategy. We train and evaluate our model on the CODE dataset (140k patients, 517k ECGs), with external validation on MIMIC-IV. Compared to static baselines (DeepSurv and DeepHit applied to ResNet-50 embeddings) and a dynamic competing-risk model (DynamicDeepHit), our model achieves a C-index of 0.853, a mean TD-AUC of 0.867, and an IBS of 0.030 on the internal test set, and a C-index of 0.805, a mean TD-AUC of 0.848, and an IBS of 0.106 on the external cohort, demonstrating that longitudinal ECG trajectories provide prognostic value beyond a single recording.

NeurIPS 2026

SurvCancel: A Longitudinal Dataset and Benchmark for Dynamic Order Cancellation Prediction in On-Demand Ride-Sharing Systems

Huayang Liu, Mingyu Zheng, Wei Zhang, Yijun Bian, Kai Wang

Passenger-order cancellation is a critical source of uncertainty in on-demand ride-sharing systems, where requests, assignments, and vehicle routes evolve continuously in real time. Due to shared capacity and coupled routes, a single cancellation may propagate through downstream matching and routing decisions, degrading system efficiency and service reliability. However, cancellation prediction in on-demand ride-sharing remains difficult to study systematically due to the lack of large-scale longitudinal datasets, standardized evaluation protocols, and fine-grained real-time benchmarks. In this work, we introduce SurvCancel, a real-world longitudinal dataset and benchmark for dynamic passenger-order cancellation prediction in on-demand ride-sharing systems. Constructed from operational logs collected across four service regions in the real world, SurvCancel contains 173K released orders and 7.9M time-dependent snapshots. Each order is represented as a longitudinal sequence of system states, capturing both order-level attributes and the evolving supply-demand environment throughout its lifecycle. We formulate cancellation prediction as a stage-conditioned dynamic survival task: at each landmark time, models estimate short-term cancellation risk from the historical state sequence observed so far. We evaluate representative survival and dynamic-risk models under both in-distribution and distribution-shift protocols. Our results show stage-dependent model behavior in the in-distribution setting and reveal distinct robustness patterns under regional and temporal distribution shifts.

NeurIPS 2026

Surrogate Calibration for Transferable Adversarial Attacks against Black-Box MLLMs

Zhewen Yao, Yao Zhu, Xiangyang Ji, Shiliang Zhang

Transfer-based attacks expose serious adversarial vulnerabilities in closed-source Multimodal Large Language Models (MLLMs) by crafting adversarial examples on off-the-shelf surrogate models. However, this paradigm often drives adversarial examples toward surrogate-specific local optima, where they deceive only the surrogate model but fail to transfer to black-box MLLMs. Although existing methods mitigate this issue at the attack level, they leave the surrogate itself unchanged. To address this gap, we propose Surrogate Calibration (SCal), a novel model-level refinement that enhances downstream transfer-based adversarial attacks in a plug-and-play manner. Specifically, SCal employs a feature-preserving loss to maintain the surrogate's representational utility, while a distributional regularizer encourages its gradient field to stay closer to the natural data manifold. With calibrated surrogates, downstream attacks generate update directions that exhibit superior generalization across black-box MLLMs. Extensive experiments demonstrate that SCal boosts current attacks to new heights across various surrogates. For instance, it elevates baseline M-Attack's ASR on GPT-5.4 Mini to 53.5\%, substantially surpassing the state-of-the-art MPCAttack (29.7\%). These results expose critical vulnerabilities that must be addressed for trustworthy multimodal systems. Code is at: https://anonymous.4open.science/r/SCal_code-B0BC

NeurIPS 2026

Surprisingly consistent failures of post-hoc OOD detectors reveal security concerns in open-set recognition with modern CNNs and ViTs, stemming from representation mismatch

Kamil Szyc, Tomasz Walkowiak, Henryk Maciejewski

Although many OOD detection methods have been proposed, no clear winner can be identified as winners are benchmark-specific. One problem with evaluating OOD detectors is the imprecise definition of the "out" distribution, as many commonly used OOD datasets designed to test for 'semantic shift' contain a substantial proportion of 'covariate shift' samples. Moreover, recent work finds that, on carefully crafted benchmarks focused on semantic shift, modern OOD detectors yield little improvement over the baseline MSP. We analyzed a vast number of post-hoc OOD detectors on these benchmarks. We found that they consistently misclassify a common, substantial subset of samples across modern CNN and ViT architectures. We showed that failures across all OOD detectors on this benchmark are primarily due to learned feature representations: we observe that feature extractors map many semantically distant OOD samples closer to ImageNet classes than some in-distribution samples. This misalignment raises safety concerns about DNNs operating in open-set recognition scenarios. We publish a new benchmark, along with a reproducible construction protocol, that focuses on shared hard examples drawn from semantically distinct datasets, including NINCO and ImageNet-OoD. Our new benchmark can reveal fundamental security gaps in current DNNs, as they fail to reliably distinguish semantically distant OOD samples from in-distribution samples.

NeurIPS 2026

SurgVista: Long-Horizon Surgical World Modeling with Plausible Instrument-Tissue Dynamics

Wentao Pan, Wuyang Li, Shengyuan Liu, Xinyu Liu, Hengyu Liu, Yixuan Yuan

Scaling robot policy learning for autonomous surgery is challenging, as expert demonstrations are expensive and in vivo exploration poses substantial safety risks. Surgical world models address this by generating realistic, action-conditioned future frames from an initial observation, but existing methods exhibit two persistent failure modes: *spatial interaction incoherence*, where visible instrument contact fails to induce spatially consistent tissue deformation, and *temporal fidelity collapse*, where prediction errors compound across autoregressive rollouts and progressively corrupt visual quality. We present **SurgVista**, a surgical world model that mitigates both failures through two training recipes. *Deformation Consistency Regularization* extracts scene-point trajectories from training videos and enforces cross-frame coherence through latent contrastive learning, strengthening physically consistent instrument-tissue dynamics. *Drift Adaptation Training* mitigates long-horizon drift by perturbing conditioning frames with online prediction residuals and photometric augmentations calibrated to long-horizon drift statistics, sustaining visual fidelity over extended rollouts. To enable rigorous evaluation, we further introduce **SurgWorld-Bench**, featuring diverse procedure types, long-range rollouts, and decoupled metrics for instrument-motion accuracy and tissue-response fidelity. Extensive experiments show that SurgVista consistently outperforms state-of-the-art methods across visual quality, temporal consistency, and interaction fidelity, with gains widening as the prediction horizon grows.

NeurIPS 2026

Surface Recovery Is Not State Recovery: Pressure–Recovery–Relapse in Multi-turn LLMs

Zixi Huang, Hankun Chang, Xueli Geng, Xutong Mu

Interactive language models should respond to user feedback without blindly conforming to incorrect pressure. Existing evaluations of sycophancy typically measure whether models flip their answers under pressure and treat apparent recovery after pressure removal as robustness. We show that this recovery is often superficial. We introduce the **Pressure--Recovery--Relapse (PRR) protocol**, a multi-turn evaluation framework that disentangles pressure-induced flipping, surface recovery, and relapse under renewed weak pressure. Across factual QA benchmarks and instruction-tuned models, PRR reveals three findings: (1) models can appear to recover at the output level while remaining vulnerable to renewed pressure; (2) surface answer correction can be dissociated from repair of the latent answer state; and (3) different internal components support distinct recovery pathways. Through causal interventions, we show that output-level steering can enforce correct answers without repairing corrupted latent readouts, whereas restoring clean hidden states repairs both surface behavior and latent states. Further component-level restoration shows that residual-stream states enable full repair, while mid-layer attention outputs provide partial latent repair. These results highlight that robust multi-turn reliability requires evaluating recovery stability and latent state repair, not merely apparent answer correctness.

NeurIPS 2026

SurGe: Improved Surface Geometry in Point Maps

Karim Knaebel, Gonzalo Martin Garcia, Christian Schmidt, Ilya Fradlin, Lucas Nunes, Daan de Geus, Bastian Leibe

With impressive progress in architectures, training recipes, and quantity of high-quality data, recent monocular geometry estimation methods estimate global 3D geometry remarkably well. However, they still exhibit surprisingly low quality on surface details, which is clearly visible in qualitative predictions but not reflected in common metrics. To improve this shortcoming, we first formulate a metric that is capable of measuring the surface quality of the estimated geometry via normals derived from the predicted point map. Furthermore, we propose two manners to improve fine-grained local geometry in monocular geometry estimation models: (i) we present an improved point-based gradient loss, and (ii) we introduce a novel decoder based on neighborhood attention. We evaluate our proposed method on eight common zero-shot monocular geometry estimation benchmarks and achieve state-of-the-art results, particularly improving local surface geometry. Extensive ablations validate our design choices. Code and models will be open-sourced.

NeurIPS 2026

Support-Safe Variational Hybrid Filtering for Contact-Mode and Sparse-Law Recovery

Marios Papamichalis, Regina Ruane

Contact-rich robot dynamics are hybrid: a single observation can match several latent states and contact regimes (free, impact, stick--slip). A standard amortized filter that places no probability on a feasible contact transition will permanently lose the branch the robot actually follows. We introduce VHYDRO, a variational hybrid dynamics learner that prevents this branch loss. At each step, VHYDRO mixes the learned proposal with a feasible transition law before sampling and importance weighting. This keeps every feasible contact alternative covered. VHYDRO jointly infers a continuous latent state and a discrete contact mode, and fits a sparse port-Hamiltonian law to each recovered regime. On top of this, three guarantees connect: support coverage stabilizes filtering, the stabilized filter concentrates the discrete contact posterior on coherent regimes, and mode-pure segments admit sparse port-Hamiltonian recovery. The recovery error separates cleanly into filtering, derivative, mode-impurity, and physics-residual parts. Three empirical findings track the same mechanism. Under heavy occlusion the support-safe filter stays usable while a non-defensive proposal collapses. On ManiSkill demonstrations and on four canonical Sawyer/BridgeData task families the discrete state forms temporally coherent contact-regime segments that post-hoc segmenters and mode-free baselines miss. On hybrid systems with known equations the mode-conditioned sparse fit recovers the active physical terms; purely predictive baselines do not.

NeurIPS 2026

Support Mismatch as a Benchmark Failure Mode for In-Context Prediction

Jie Liu, Lanlan Liang, Qinan Bao, ZiXi Yan, Linghao Meng, Wenbo Gong

We analyze support mismatch in language-model in-context prediction as a frozen-prior Bayes benchmark with finite discrete support. The goal is diagnostic rather than literal: we do not identify production LMs with exact Bayesian updating, but characterize a failure mode whose signatures can be checked in learned in-context predictors. Our main theorem gives the finite-sample predictor-risk bound $R_k^\pi \le C e^{-k\rho_{\min}} + 2\varepsilon_{\mathrm{approx}}^2$, so risk decomposes into an exponentially decaying transient and a nonvanishing support-mismatch floor under exponential-moment control of log-likelihood ratios. In scalar and aligned Gaussian location families, exact two-component analyses match the upper exponent up to a tight factor 2 and show a regime change at $\mu_2=3\mu_1$. Controlled learned-model experiments track the benchmark near crossover. Decoder-only LM diagnostics then test the benchmark signatures: restricted support creates a persistent high-error regime; restoring the missing support sharply lowers error; and modern size-matched distractor controls on Qwen and Llama show that adding a wrong same-cardinality candidate does not reproduce this gain. Multiple-choice, instruction-tuned, cross-family, calibration, null-control, and near-tie checks preserve the same diagnostic picture.

NeurIPS 2026

Support Before Frequency in Discrete Diffusion

Adrian Müller, Antoine Gonon, Zebang Shen, Ya-Ping Hsieh, Niao He

Discrete diffusion models are increasingly competitive for language modeling, yet it remains unclear how their denoising objectives organize learning. Although these objectives target the full data distribution, we show that the exact reverse process induces a hierarchy between coarse *support* information and finer *frequency* information. For uniform and absorbing (a.k.a. masking) diffusion, we prove that, in the small-noise regime of the final denoising steps, each single-token reverse edit decomposes into a leading scale, determined by whether it moves toward the data *support* (e.g., grammatically valid sentences), and a finer coefficient, determining *relative probabilities* within the same scale. Thus, recovering validity structure only requires learning the correct order of magnitude of reverse probabilities, whereas recovering data frequencies requires coefficient-level estimation. The separation is mechanism-dependent: uniform diffusion exhibits a trichotomy into validity-improving, validity-preserving, and validity-worsening edits, while absorbing diffusion places its leading-order mass on validity-improving moves. Experiments on a masked language diffusion model and synthetic regular-language tasks support these predictions: support-localization emerges earlier than within-support frequency ranking, and the contrast between uniform and absorbing diffusion matches the predicted rate separation. Together, our results suggest that discrete diffusion models learn data support before data frequencies.

NeurIPS 2026

Supervision Recovery for Time Series Anomaly Detection via Counterfactual Pairing

Yifei Gao, Tian Lan, Yimeng Lu, Xuming An, Meng Wang, Wenjun He, Yijie Li, Chen Zhang

Time series anomaly detection (TSAD) remains challenging not only because anomaly labels are scarce, but also because temporal anomalies are highly context-dependent. Existing methods often rely on unsupervised or surrogate objectives, producing anomaly scores indirectly rather than learning explicit normal--anomalous distinctions. We propose Counterfactual Pairing with Anomaly Semantics (CAPS), a supervision-recovery framework for TSAD. CAPS formulates temporal anomalies as mechanism-induced effects on normal temporal evolution and recovers matched supervision without target-domain anomaly labels. It learns transferable anomaly semantics from simulated normal--anomalous pairs, disentangles them from normal temporal structure, and organizes them into family-wise modes. Instead of directly using simulated anomalies as target positives, CAPS instantiates the learned semantics as residual-form anomaly effects on target-domain reference trajectories via residual MoE generation. The resulting matched counterparts provide supervision-aligned signals for boundary-oriented detector learning. Experiments on nine benchmark datasets show that CAPS outperforms unsupervised and injection-based baselines, is competitive with supervised-reference baselines, and provides interpretable evidence through anomaly-effect generation and expert association.

NeurIPS 2026

Supervised Distributional Reduction via Optimal Transport and Dependence Maximization

Sai-Aakash Ramesh, Archit Sood, Andrew Corbett, Tim Dodwell

Learning representations that capture both intrinsic data geometry and target-relevant structure remains a fundamental challenge, particularly in settings where data reduction must balance compression with predictive fidelity. While distributional reduction—encompassing joint clustering and dimensionality reduction—offers a principled way to summarize data, its supervised variants remain relatively underexplored, despite the importance of retaining task-relevant signal for downstream prediction and decision-making. We propose Supervised Distributional Reduction (SDR), an algorithm for learning target-aware representations by combining optimal transport with explicit dependence maximization. SDR builds on the Fused Gromov–Wasserstein (FGW) objective to align the relational structure of the input distribution with a set of representative points, while augmenting it with a direct dependence term that encourages the learned embeddings to capture predictive signal more explicitly. This results in compact representations that reflect both geometric structure and supervision. Beyond representation learning, SDR naturally induces a data-dependent, non-stationary geometry that can be leveraged for settings such as Gaussian Process (GP) modelling. By redefining distances through target-aware distributional alignment, SDR enables the construction of adaptive kernels that respond to local variations in both data geometry and supervision, offering an optimal transport-based perspective on non-stationary kernel design.

NeurIPS 2026

Sup-Norm Error under Proportional Asymptotics: Phase Transitions under Linear Regression

Lin Liu, Debarghya Mukherjee, Rajarshi Mukherjee, Zixiao Jolene Wang

This paper characterizes the sharp asymptotics of the $\ell_{\infty}$-norm estimation error for estimating the coefficient vector in linear regression under proportional asymptotics. While $\ell_2$-error is well-documented, we demonstrate that the $\ell_{\infty}$-error exhibits a distinct phase transition governed by the structure of the underlying signal. We explore this through the lens of a class of estimators that include ridge-regularized estimators, a method-of-moments estimator, and the ordinary least squares estimator for the under-parametrized regime. Our results provide a comparative study of these estimators and characterize regimes (as identified by the maximal signal component, number of large signals, total signal strength, and noise variance) where one estimator is preferable to the others. As a by-product, we obtain new double descent curves in $\ell_{\infty}$-error metric for the ridgeless regression, as well as ingredients for uniform confidence intervals for the signal coordinates. Our theoretical results are supported by extensive numerical simulations that confirm the predicted phase transitions and error limits.

NeurIPS 2026

SudoBench: A Contextual Authorization Benchmark for LLM Agents

Vincent Siu, Tianneng Shi, Shangding Gu, Zhun Wang, Dawn Song, Chenguang Wang

Secure LLM agents should take actions for authorized users in authorized environments. However, current agents' (e.g., OpenClaw) runtimes expose neither user nor environment authorization and existing agent security benchmarks similarly evaluate models without relevant authorization context. We propose SudoBench, a benchmark of 135 paired scenarios in a synthetic consulting universe with a static access control list, spanning user authorization (confused deputy), environment authorization (source-label indirect prompt injection), and both (scope-check indirect prompt injection). For each pair of scenarios, the authorization context is flipped such that an identical prompt should be appropriately complied with or refused. We score each pair as a joint pass requiring the model to produce the correct outcome on both paired scenarios. Across ten frontier closed- and open-weight LLMs, joint pass rate without authorization context sits below 16\% on every model. Adding user and environment authorization raises joint pass to as high as 67--73\%. Even with this authorization context, frontier models remain far from reliably handling contextual authorization, framing authorization context as an important research agenda for agent security.

NeurIPS 2026

Subspace-Guided Continual Learning: Hessian Based Stable–Plastic Decomposition for Exemplar-Free Class-Incremental Learning

Qi Zhu, Ziang Gan, Wanting Zhang, Libao Zhang

Exemplar-Free Class-Incremental Learning (EFCIL) is a challenging continual learning paradigm where a model must learn new classes sequentially without access to old data, making it susceptible to catastrophic forgetting. The core difficulty lies in balancing stability (preserving old knowledge) and plasticity (acquiring new knowledge). We propose Subspace-Guided Continual Learning (SGCL), a novel method that tackles this dilemma from a geometric perspective. SGCL decomposes the feature space into two orthogonal subspaces: a ```stable subspace``` containing directions critical for previous tasks, and a ```plastic subspace``` where new knowledge can be learned with minimal interference. This decomposition is efficiently identified via the feature-space Hessian, where high-curvature eigendirections define the stable subspace. Building on this, SGCL introduces two synergistic components: 1) Subspace-Guided Regularization (SGR), which imposes curvature-weighted penalties on feature drifts within the stable subspace, and 2) Subspace-Guided Prototype Alignment (SGPA), which adaptively corrects the shift of old-class prototypes to recalibrate the classifier. Extensive experiments on standard benchmarks show that SGCL consistently achieves competitive or superior performance compared to existing state-of-the-art methods, offering a principled approach to mitigating forgetting through loss landscape analysis.

Keep browsing

More papers from top AI conferences

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