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.

UAI 2026

Robustness Quantification for Discriminative Models: a New Robustness Metric and its Application to Dynamic Classifier Selection

Rodrigo F L Lassance, Jasper De Bock

Among the different possible strategies for evaluating the reliability of individual predictions of classifiers, robustness quantification stands out as a method that evaluates how much uncertainty a classifier could cope with before changing its prediction. However, its applicability is more limited than some of its alternatives, since it requires the use of generative models and restricts the analyses either to specific model architectures or discrete features. In this work, we propose a new robustness metric applicable to any probabilistic discriminative classifier and any type of features. We demonstrate that this new metric is capable of distinguishing between reliable and unreliable predictions, and use this observation to develop new strategies for dynamic classifier selection.

UAI 2026

KMM-CP: Practical Conformal Prediction under Covariate Shift via Selective Kernel Mean Matching

Siddhartha Laghuvarapu, Rohan Deb, Jimeng Sun

Uncertainty quantification is essential for deploying machine learning models in high-stakes domains such as scientific discovery and healthcare. Conformal Prediction (CP) provides finite-sample coverage guarantees under exchangeability, an assumption often violated in practice due to distribution shift. Under covariate shift, restoring validity requires importance weighting, yet accurate density-ratio estimation becomes unstable when training and test distributions exhibit limited support overlap. We propose KMM-CP, a conformal prediction framework based on Kernel Mean Matching (KMM) for covariate-shift correction. We show that KMM directly controls the bias–variance components governing conformal coverage error by minimizing RKHS moment discrepancy under explicit weight constraints, and establish asymptotic coverage guarantees under mild conditions. We then introduce a selective extension that identifies regions of reliable support overlap and restricts conformal correction to this subset, further improving stability in low-overlap regimes. Experiments on molecular property prediction benchmarks with realistic distribution shifts show that KMM-CP reduces coverage gap by over 50

UAI 2026

Controlling Path Dependence in Gradient Ascent Unlearning through Forget-Set Ordering

Varun Sampath Kumar, Esmaeil S. Nadimi, Vinay Chakravarthi Gogineni

Machine unlearning aims to selectively remove the influence of designated training data from a trained model. Gradient ascent-based unlearning methods are widely used in machine unlearning, but are often observed to exhibit instability and sensitivity to optimization hyperparameters. In this work, we show that the ordering of forget-set samples during ascent materially influences the resulting optimization trajectory, yielding markedly different forgetting–retention trade-offs under identical optimization budgets. We provide a local second-order analysis illustrating how non-commutativity of ascent updates induces path dependence, and we propose a simple ordering strategy that processes forget samples from low to high predictive uncertainty. By deferring high-uncertainty samples, this strategy attenuates early parameter drift and leads to more stable trajectories. Across image classification benchmarks with convolutional and vision transformer architectures, as well as text classification tasks, we observe that this ordering consistently achieves effective forgetting while better preserving retain-set utility compared to random ordering. In the retain-data-free regime, this trajectory-aware modification substantially strengthens vanilla gradient ascent, improving its position on the forgetting–retention Pareto frontier relative to naive ascent and several retain-data-free unlearning baselines. In general, our results identify sample ordering as a practically meaningful and previously under explored degree of freedom in machine unlearning, highlighting the importance of trajectory-aware design and evaluation.

UAI 2026

Decomposing Ensemble Spread in Lorenz ’96 with Learned Stochastic Parameterizations

Birgit Kühbacher, Daan Crommelin, Niki Kilbertus

Weather and climate forecasts are inherently uncertain due to chaotic dynamics, imperfect initial conditions, and incomplete representation of the underlying physical processes. Operational ensemble forecasts aim to represent these uncertainties through forecast spread, yet many approaches yield underdispersive estimates, with spread that grows too slowly relative to forecast error. Using the two-scale Lorenz ’96 system as a widely used, controlled testbed, we design a systematic approach to disentangle intrinsic variability, initial-condition perturbations, and stochastic model uncertainty. We compare multiple ensemble configurations and parameterization strategies, including existing deterministic and autoregressive as well as novel Bayesian and flow-based approaches. Our results show that ensemble perturbations do not increase the system’s long-term variance; rather, they regulate how rapidly trajectories decorrelate and explore the invariant measure. Stochastic parameterizations, particularly those with temporally persistent structure, enhance early spread growth and improve spread-error consistency. Overall, we bring clarity to how different sources of uncertainty interact in a chaotic system and provide guidance for the design and evaluation of stochastic parameterizations in weather and climate models.

UAI 2026

Who to Trust? Aggregating Client Predictions in Federated Distillation.

Viktor Kovalchuk, Denis Son, Arman Bolatov, Mohsen Guizani, Samuel Horváth, Maxim Panov, Martin Takac, Eduard Gorbunov, Nikita Kotelevskii

Federated Distillation enables distributed learning for clients with heterogeneous model architectures. In this paradigm, the server and clients exchange predictions on a shared unlabeled public dataset, rather than model parameters or gradients.

UAI 2026

Controlling Uncertainty and Hallucination Risk in Multi-Agent Fact Verification

Adam Kostka, Jaroslaw A. Chudziak

Multi-agent language systems are increasingly relied upon for high-stakes decision support. Many systems use consensus among agents as a measure of confidence. However, such a model is prone to failure if aligned agents have the same biases and propagate the same error. Under sycophantic consensus, correlated errors resemble strong agreement, and hallucination manifests as a consequence of uncalibrated uncertainty. While current measures provide useful heuristics, they lack statistical safety bounds at deployment time. This work reinterprets hallucination control as an uncertainty quantification problem. We contribute a Score Deviation penalty that directly lowers confidence when the factual disagreement within the ensemble rises. A Learn-Then-Test calibration procedure converts these penalized scores into a certified decision threshold that provably bounds the expected False Discovery Rate. The results show that this deviation-penalized method reduces the conservatism of the calibration process, achieving 71.7

UAI 2026

Maximally Robust Satisficing Bayesian Optimization

Samuli Kinnunen, Petrus Mikkola, Antti Niskanen, Arto Klami

Many design tasks can be cast as black-box function optimization, enabling use of Bayesian optimization to find an ideal design with minimal number of trials. However, often we do not actually need the optimum but instead a sufficiently good solution is enough, for instance a material that is durable enough for its intended use.In most cases there are multiple satisfactory solutions, forming a superlevel set of the function, raising a key question of which one to prefer. We answer this by explaining why robustness to input perturbations that may occur when the solution is deployed is a good criterion and by introduce a Bayesian optimization method that efficiently finds satisficing solutions that are robust to maximally large perturbations. In contrast to previous works, we assume the inputs can be accurately controlled during optimization, but will be perturbed after the deployment.

UAI 2026

Same Benchmark, Same Subspace: Task-Selective Convergence in LLM Representations

JaeSeong Kim, Suan Lee

Benchmark scores are the dominant lens through which progress in large language models is assessed, yet the implicit assumption that different benchmarks read out a shared internal structure has never been verified at the representation level. We introduce readout subspace analysis, a framework that extracts the low-dimensional subspace a benchmark uses to linearly discriminate correct answers from a model’s frozen hidden representations, and compares these subspaces across models and tasks via a coordinate-invariant Gram cosine metric. Analyzing 50 models spanning six architecture families and varied fine-tuning strategies (SFT, DPO, RLHF, model merging) on three benchmarks (MMLU, MedQA, AGIEval), we find that readout geometry is governed by the benchmark, not the model. Within the same benchmark, readout subspaces are strongly aligned even across architecturally unrelated models (Gram cosine up to 0.87 versus a random baseline of ∼10^-3), while subspaces across different benchmarks are nearly orthogonal. This convergence is graded: benchmarks sharing cognitive demands partially overlap in readout subspace, whereas those requiring qualitatively different reasoning occupy orthogonal regions. Furthermore, probe accuracy consistently meets or exceeds generation accuracy, indicating that benchmark scores reflect not only representational structure but also decoding efficiency. These findings recast benchmarks from passive measurement instruments to active structural constraints that selectively activate specific regions of representation space.

UAI 2026

Model Merging is Secretly Certifiable: Non-Vacuous Generalisation Bounds for Low-Shot Learning

Taehoon Kim, Henry Gouk, Minyoung Kim, Timothy Hospedales

Certifying the IID generalisation ability of deep networks is the first of many requirements for trusting AI in high-stakes applications from medicine to security. However, when instantiating generalisation bounds for deep networks it remains challenging to obtain non-vacuous guarantees, especially when applying contemporary large models on the small scale data prevalent in such high-stakes fields. In this paper, we draw a novel connection between a family of learning methods based on model fusion and generalisation certificates, and surprisingly show that with minor adjustment several existing learning strategies already provide non-trivial generalisation guarantees. Essentially, by focusing on data-driven learning of downstream tasks by fusion rather than fine-tuning, the certified generalisation gap becomes tiny and independent of the base network size, facilitating its certification. Our results show for the first time non-trivial generalisation guarantees for learning with as low as 100 examples, while using vision models such as VIT-B and language models such as mistral-7B. This observation is significant as it has immediate implications for facilitating the certification of existing systems as trustworthy, and opens up new directions for research at the intersection of practice and theory.

UAI 2026

On Causal Representation Learning with Internal Auxiliaries

Kwonho Kim, Heejeong Nam, Inwoo Hwang, Sanghack Lee

Causal representation learning typically achieves identifiability using auxiliary variables external to the mixing process. This fails when observable sources act as internal mixing inputs whose entanglement invalidates standard volume-change proofs. We introduce a framework that treats observable sources as internal auxiliaries. We establish identifiability when all observed internal sources are used as conditioning variables. Under a volume-preserving mixing assumption, suitable variability conditions, and additional alignment conditions on the learned model, the unobserved source subspaces are identifiable up to an Independent Subspace Analysis (ISA)-style equivalence class—a permutation of conditionally independent subspaces with within-subspace invertible transformations. In practice, we approximate the volume-preserving restriction with encoders that stabilize the induced distortion. Leveraging the known causal graph, we further propose a scheme that selects conditioning sources so as to preserve fine-grained factorizations of the unobserved sources. Experiments show improved recovery over representative auxiliary-based baselines in settings where treating internal sources as external conditioners can induce cross-factor leakage.

UAI 2026

Residual Koopman Spectral Profiling for Predicting and Preventing Transformer Training Instability

Bum Jun Kim, Shohei Taniguchi, Makoto Kawano, Yusuke Iwasawa, Yutaka Matsuo

Training divergence in transformers wastes compute, yet practitioners discover instability only after expensive runs begin. They therefore need an initialization-time signal for identifying risky training configurations. We study Residual Koopman Spectral Profiling (RKSP), a fixed, single-forward-pass spectral risk score. RKSP extracts Koopman spectral features by applying whitened dynamic mode decomposition to layer-wise residual snapshots. Our central diagnostic, the near-unit spectral mass, quantifies the fraction of modes concentrated near the unit circle, which captures instability risk. For predicting divergence across extensive configurations, this score achieves an AUROC of 0.995, outperforming the best gradient baseline. When calibrated probabilities are required for a target configuration distribution, a held-out one-dimensional calibrator maps the same scalar score to probabilities. We further make the diagnostic actionable through Koopman Spectral Shaping (KSS), which reshapes spectra during training. In the challenging high learning rate regime without normalization layers, KSS reduces the divergence rate from 66.7

UAI 2026

A Model-Free Universal AI

Yegon Kim, Juho Lee

In general reinforcement learning, all established optimal agents, including AIXI, are model-based, explicitly maintaining and using environment models. This paper introduces Universal AI with Q-Induction (AIQI), the first model-free agent proven to be asymptotically ε-optimal in general RL. AIQI performs universal induction over distributional action-value functions, instead of policies or environments like previous works. Under a grain of truth condition, we prove that AIQI is strong asymptotically ε-optimal and asymptotically ε-Bayes-optimal. We also apply our novel proof techniques to show asymptotic ε-optimality of Self-AIXI without any ad-hoc assumptions. Our results significantly expand the diversity of known universal agents.

UAI 2026

Beyond Bounds: Quantifying the Probability of Counterfactual Fairness

Taehan Kim, Minyoung Cho, Sanghack Lee

Counterfactual fairness is a rigorous criterion for algorithmic decision-making but remains fundamentally unidentifiable from observational data alone. Existing partial identification methods address this by deriving bounds for fairness measures; however, these intervals are often wide, limiting their practical utility. To address this limitation, we propose a framework that quantifies the probability that a black-box model satisfies counterfactual fairness, under a stated prior over the structural causal models compatible with the observed data. By exploiting conditional independencies to reduce the parameter space, we demonstrate that the set of causal parameters compatible with the observed data forms a convex polytope. We further show that, given domain-specific priors on exogenous distributions, this prior-dependent probability can be estimated via Hit-and-Run Monte Carlo integration. Our approach provides a practical tool that complements worst-case bounds, offering a prior-dependent probabilistic summary for auditing model fairness.

UAI 2026

Don’t Test What You Can Deduce: Causal Discovery with Logical Inference

Jonghwan Kim, Sanghack Lee

Constraint-based causal discovery relies on conditional independence tests (CITs), which are highly unstable in high-dimensional settings. As the conditioning set grows, CITs suffer from low statistical power, leading to frequent false negatives. In the context of structure learning, this causes error propagation that degrades the accuracy of the estimated graph. We propose DF-PC (Deduce-First PC), a theoretically sound framework that integrates graphoid-based reasoning into the PC algorithm. Unlike prior approaches that primarily utilize deduction for conflict resolution or additive checks, DF-PC adopts a proactive “Deduce-First” strategy: it prioritizes logical deduction from strictly lower-order tests to preemptively replace high-order CITs. This "Deduce-First" strategy enables structure learning with potentially fewer CITs while improving performance. Empirical evaluations across various settings demonstrate that DF-PC achieves competitive learning performance and computational efficiency.

UAI 2026

Capacity and Redundancy Trade-offs in Multi-Task Learning

Asif Khan

In multi-task learning (MTL) negative transfer is often considered as an optimization artifact, but it can also be viewed as a consequence of limited shared capacity and weak task redundancy. We investigate this effect through a Capacity–Redundancy (CR) identity that decomposes the sum of per-task predictive informations into joint predictive information that includes label redundancy defined via total correlation, and a residual coupling term that quantifies interference left unresolved by the shared representation. Additionally, we show two key results: (i) a clustering-gap decomposition that gives a necessary and sufficient condition for clustered sharing to outperform global sharing, and (ii) a gradient–TC bridge in a Gaussian multi-task model that formally justifies gradient cosine similarity as a proxy for redundancy ordering. Empirically, we estimate Δ from validation residual correlations, showing that clustered LoRA substantially reduces Δ, outperforms size-matched random partitions, and results in statistically significant gains with multi-seed confidence intervals.

UAI 2026

Conformal Risk Sharing: Certified Cost Allocation with Participation Guarantees

Ieva Kazlauskaite

Sharing the financial impact of rare adverse events across a group can soften extreme individual burdens, but any participant made worse off by the arrangement has reason to leave. A credible mechanism must therefore provide each agent with a trustworthy cap on their future obligation and should be deployed only if the aggregate harm across participants is bounded. We formalise this as the Certified Allocation Problem: from finite data and without distributional assumptions, find a redistribution rule, produce obligation caps for every participant, and verify that no participant is made materially worse off. We propose Conformal Risk Sharing, which solves this problem by pairing an interpretable sharing policy with split conformal calibration. The sharing intensity is tuned on training data, while held-out calibration data produces distribution-free per-agent guarantees (valid under exchangeability). Experiments on synthetic and real-world data, including precipitation and energy-cooperative data, confirm that the framework can substantially reduce extreme obligations for high-risk agents while controlling harm to others.

UAI 2026

Adaptive Cumulative Mass Calibration with Conformal Prediction

Daniil Kazantsev, Eric Moulines, Maxim Panov, Nikita Kotelevskii, Mohsen Guizani

Reliable probability estimates by classifiers are essential in high-risk applications. In practice, however, predicted probabilities are often miscalibrated, and many existing post-hoc calibration methods typically lack guarantees that a specific notion of calibration is achieved after the correction procedure is applied. We introduce a *set-based* perspective on calibration through the notion of *cumulative mass calibration* and the corresponding error measures. We propose a new calibration procedure based on conformal prediction that forms cumulative probabilities with guaranteed marginal coverage. We introduce an __adaptive temperature scaling algorithm__, with the temperature tuned for each input to satisfy the conformal coverage constraint. As we show, this procedure can be efficiently implemented. Across image classification tasks, particularly in settings with many classes, our method improves newly introduced calibration error measures (__CMCE__ and α__-CMCE__) *and* standard metrics (such as ECE, cw-ECE, MCE) over the existing baselines.

UAI 2026

Joint MDPs and Reinforcement Learning in Coupled-Dynamics Environments

Ege Can Kaya, Mahsa Ghasemi, Abolfazl Hashemi

Many distributional quantities in reinforcement learning are intrinsically joint across actions, including distributions of gaps and probabilities of superiority. However, the classical Markov decision process (MDP) formalism specifies only marginal laws and leaves the joint law of counterfactual one-step outcomes across multiple possible actions at a state unspecified. We study coupled-dynamics environments with a multi-action generative interface which can sample counterfactual one-step outcomes for multiple actions under shared exogenous randomness. We propose joint MDPs (JMDPs) as a formalism for such environments by augmenting an MDP with a multi-action sample transition model which specifies a coupling of one-step counterfactual outcomes, while preserving standard MDP interaction as marginal observations. We adopt and formalize a one-step coupling regime where dependence across actions is confined to immediate counterfactual outcomes at the queried state. In this regime, we derive Bellman operators for nth-order return moments, providing dynamic programming and incremental algorithms with convergence guarantees.

UAI 2026

Stochastic Dominance Driven First-Order Policy Optimization for Multi-Objective Reinforcement Learning

Ege Can Kaya, Kadierdan Kaheman, Jason M Cloud, Abolfazl Hashemi

We study multi-objective reinforcement learning with stochastic, vector-valued returns and propose a policy improvement principle based on multivariate kth-order stochastic dominance in the lower-orthant sense. Rather than scalarizing objectives or comparing only expected values, we compare entire return distributions using kth-order integrated cumulative distribution functions (cdfs). This yields a max-violation objective that measures the worst-case dominance gap of a candidate policy relative to the incumbent policy. Under some regularity assumptions, we show that the Orthant Dominance Policy Optimization (ORDO) algorithm we introduce drives this objective to a point that certifies ϵ-almost non-dominatedness, meaning that no policy in the class can improve the incumbent by more than ϵ. We also propose smoothing approaches for the hinge structure inherent in integrated cdfs, which improve stability and enable stable stochastic gradients in optimization.

UAI 2026

General Bayesian Policy Learning

Masahiro Kato

This study proposes the General Bayes framework for policy learning. We consider decision problems in which a decision-maker chooses an action from an action set to maximize its expected welfare. Typical examples include treatment choice and portfolio selection. In such problems, the statistical target is a decision rule, and the prediction of each outcome Y(a) is not necessarily of primary interest. We formulate this policy learning problem by loss-based Bayesian updating. Our main technical device is a squared-loss surrogate for welfare maximization. We show that maximizing empirical welfare over a policy class is equivalent to minimizing a scaled squared error in the outcome difference, up to a quadratic regularization controlled by a tuning parameter ζ>0. This rewriting yields a General Bayes posterior over decision rules that admits a Gaussian pseudo-likelihood interpretation. We clarify two Bayesian interpretations of the resulting generalized posterior, a working Gaussian view and a decision-theoretic loss-based view. As one implementation example, we introduce neural networks with tanh-squashed outputs. Finally, we provide theoretical guarantees in a PAC-Bayes style.

Keep browsing

More papers from top AI conferences

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