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

Self-Supervised Uncertainty Estimation For Super-Resolution of Satellite Images

Zhe Zheng, Valery Dewil, Pablo Arias

Super-resolution (SR) of satellite imagery is challenging due to the lack of paired low-/high-resolution data. Recent self-supervised SR methods overcome this limitation by exploiting the temporal redundancy in burst observations, but they lack a mechanism to quantify uncertainty in the reconstruction. In this work, we introduce a novel self-supervised loss that allows to estimate uncertainty in image super-resolution without ever accessing the ground-truth high-resolution data. We adopt a decision-theoretic perspective and show that minimizing the corresponding Bayesian risk yields the posterior mean and variance as optimal estimators. We validate our approach on a synthetic dataset with both white and signal dependent noise and demonstrate that it produces calibrated uncertainty estimates comparable to supervised methods. We further apply our method on real SkySat satellite data and validate its performance through an unsupervised coverage test. Our work bridges self-supervised restoration with uncertainty quantification, making a practical framework for uncertainty-aware image reconstruction.

UAI 2026

SeSE: Black-Box Uncertainty Quantification for Large Language Models Based on Structural Information Theory

Xingtao Zhao, Hao Peng, Dingli Su, Xianghua Zeng, Chunyang Liu, Jinzhi Liao, Philip S. Yu

Reliable uncertainty quantification (UQ) is essential for deploying large language models (LLMs) in safety-critical scenarios, as it enables them to abstain from responding when uncertain, thereby avoiding hallucinations, i.e., plausible yet factually incorrect responses. However, while current semantic UQ methods have achieved state-of-the-art performance, they inherently overlook latent semantic structural information that could enable more precise uncertainty estimates. In this paper, we propose Semantic Structural Entropy (SeSE), a principled black-box UQ framework applicable to both open- and closed-source LLMs. To reveal the intrinsic structure of the LLM semantic space, SeSE constructs its hierarchical abstraction based on the principle of structural entropy minimization. The structural entropy of the resulting optimal hierarchical abstraction thus quantifies the inherent uncertainty within the semantic space after optimal compression. Additionally, unlike existing methods that primarily focus on simple short-form generation, we extend SeSE to provide interpretable and granular uncertainty estimation for long-form outputs. We theoretically prove that SeSE generalizes semantic entropy, the gold standard for UQ in LLMs, and empirically demonstrate its superior performance over baselines across 24 model-dataset combinations.

UAI 2026

Efficient Decentralized Learning of Generalized Quantal Response Equilibrium

Zehao Zhao, Apurv Shukla, Rahul Jain, Vijay G Subramanian

We study a solution concept for bounded rational agents in finite normal-form general-sum games called Generalized Quantal Response Equilibrium (GQRE) which generalizes a Quantal Response Equilibrium (McKelvey and Palfrey, 1995). In our setup, each player can individually maximize a smooth, regularized expected utility of the mixed profiles used, reflecting both bounded rationality that subsumes stochastic choice, and also individual choice of behaviors. After establishing existence under mild conditions, we present a computationally efficient no-regret decentralized learning algorithm that uses a smoothened version of the Frank–Wolfe algorithm coupled with a computationally efficient projection step. Our algorithm uses noisy gradient estimates via bandit-feedback from a simulation oracle that reports on repeated plays of the game. We analyze finite-time convergence properties of our algorithm under assumptions that ensure uniqueness of equilibrium, using a novel class of gap functions that generalize the Nash gap function. We end by demonstrating the effectiveness of our method on a set of complex general-sum games such as high-rank two-player games, large action two-player games, and known examples of difficult multi-player games.

UAI 2026

Gungnir: Exploiting Stylistic Features in Images for Backdoor Attacks on Diffusion Models

Lei Zhang, Yu Pan, Bingrong Dai, Lin Wang

Diffusion Models (DMs) have achieved remarkable success in image generation, yet recent studies reveal their vulnerability to backdoor attacks, where adversaries manipulate outputs via covert triggers embedded in inputs. Existing defenses, such as backdoor detection and trigger inversion, are largely effective because prior attacks rely on limited input spaces and low-dimensional triggers that are visually conspicuous or easily captured by neural detectors. To broaden the threat landscape, we propose Gungnir, a novel backdoor attack that activates malicious behaviors through style-based triggers embedded in input images. Unlike explicit visual patches or textual cues, stylistic features serve as stealthy, high-level triggers. We introduce Reconstructing-Adversarial Noise (RAN) and Short-Term Timesteps-Retention (STTR) to preserve trigger-consistent diffusion dynamics in image-to-image tasks. The resulting trigger-embedded samples are perceptually indistinguishable from clean images, evading both manual and automated detection. Extensive experiments show that Gungnir bypasses state-of-the-art defenses with an extremely low backdoor detection rate (BDR) and remains effective under fine-tuning-based purification, revealing previously underexplored vulnerabilities in diffusion models.

UAI 2026

Instrumental and Proximal Causal Inference with Gaussian Processes

Yuqi Zhang, Krikamol Muandet, Dino Sejdinovic, Edwin Fong, Siu Lun Chau

Instrumental variable (IV) and proximal causal learning (Proxy) methods are central frameworks for causal inference in the presence of unobserved confounding. Despite substantial methodological advances, existing approaches rarely provide reliable epistemic uncertainty (EU) quantification. We address this gap through a Deconditional Gaussian Process (GP) framework for uncertainty-aware causal learning. Our formulation recovers popular kernel estimators as the posterior mean, ensuring predictive precision, while the posterior variance yields principled and well-calibrated EU. Moreover, the probabilistic structure enables systematic model selection via marginal log-likelihood optimization. Empirical results demonstrate strong predictive performance alongside informative EU quantification, evaluated via empirical coverage frequencies and decision-aware accuracy–rejection curves. Together, our approach provides a unified, practical solution for causal inference under unobserved confounding with reliable uncertainty.

UAI 2026

Not All Queries Need Deep Thought: CoFiCot for Adaptive Coarse-to-fine Stateful Refinement

Dongxu Zhang, Hongqiang Lin, Yiding Sun, Pengyu Wang, Qirui Wang, Ning Yang, Jihua Zhu

Scaling test-time computation enhances LLM reasoning ability but faces a uniform computation paradox. Allocating identical resources leads to over-correction on simple tasks and insufficient refinement on complex ones. To address this, we propose CoFiCot, a coarse-to-fine adaptive framework that dynamically tailors inference strategies to problem difficulty. Specifically, we implement a multi-metric classifier that triages queries by synthesizing semantic entropy, consensus reliability, and predicted reasoning depth . This enables a differentiated refinement stage that applies efficient aggregation for simple queries while routing complex ones to a context-aware correction loop . We formalize correction as a stateful sequential propagation process , where each repair is strictly conditioned on the verified history of prior rectifications. By integrating Process Reward Models (PRMs) within this state-dependent trajectory, CoFiCot effectively bridges the gap between granular error localization and global logical coherence, preventing the context fragmentation typical of stateless refinement methods.

UAI 2026

FedSteer: Taming Extreme Gradient Staleness in Federated Learning with Corrective Projections and Caching

Haoran Zhang, Cainã Figueiredo Pereira, Marie Siew, Xutong Liu, Carlee Joe-Wong, Rachid El-Azouzi

Federated learning (FL) is often subject to aggregation variance if clients do not consistently participate in training rounds. While reusing stale model updates from inactive clients is a common technique to reduce this variance, we find that with skewed client participation, the resulting update staleness can become severe enough to destabilize training. To remedy this, we propose FedSteer, a novel method that constructs a gradient subspace from a cache of recent client gradients to serve as a low-dimensional representation of the current optimization landscape. FedSteer projects an active client’s true gradient onto this subspace to find a set of optimal coordinates. For an inactive client, FedSteer reuses these coordinates with the now-evolved subspace drifted by other active clients. This process effectively “steers” outdated gradients toward the current global objective. This is complemented by a selective caching strategy that identifies a representative client subset to form the subspace, reducing server memory. Experiments demonstrate that FedSteer significantly outperforms baselines, preventing performance collapse in challenging scenarios while delivering accuracy gains of over 7

UAI 2026

Interpretable Causal Discovery via Causal-Effect Constraints

Cixuan Zhang, Guy Van den Broeck, Benjie Wang

Causal discovery aims to uncover the underlying causal relationships given data generated from a system. The goal, however, is not merely to predict causal edges given data, but also to be able to interpret and explain either observed or hypothesized phenomena, such as a particularly large causal effect. We consider this task of conditional causal discovery and cast it as a Bayesian inference problem, in which we target the posterior over causal graphs and parameters conditional on an event such as a causal-effect constraint. Unfortunately, this poses a computational challenge: existing approaches to Bayesian causal discovery struggle when the event has small posterior mass. To address this, we adapt rare-event estimation techniques to perform inference the joint graph-parameter space. Our method gradually drives a particle population toward the constrained region while maintaining samples that approximate the conditional posterior. Empirical evaluation on synthetic graphs validates the accuracy of our approach at small and large scales, and we show in a case study on the Sachs protein dataset how our method can be used to aid scientific exploration by providing pathway-level summaries.

UAI 2026

Bounding the Causal Impact of ML-assisted Decision-Making via Counterfactual Correctness

Jonathan Zhang, Erik Skalnes, Jacob M. Chen, Michael Oberst

Predictive machine learning (ML) models are increasingly used to aid human decision-makers across various high-risk domains such as healthcare and criminal justice. There is a growing recognition of the need to evaluate the causal impact of deploying these systems on downstream outcomes, such as patient survival or crime recidivism. Randomized control trials (RCTs) can provide high-quality evidence on the impact of a deployed model, but they run into a challenge: it is often infeasible to run repeated trials when models are updated or retrained to improve predictive performance. In this work, we present a partial-identification approach to using prior RCT data to construct bounds on the causal effect of a new model. The core innovation in our approach is to leverage assumptions relating fine-grained predictive accuracy to downstream outcomes. We do so via two monotonicity assumptions: first, on individual-level ‘counterfactual correctness’ (all else being equal, a correct prediction leads to non-inferior outcomes); and second, on the relation between subgroup predictive performance and outcomes, interpretable as an assumption regarding trust in model outputs. We demonstrate our method with a simulation study, illustrating how incorporating this information can lead to more informative bounds compared to prior work.

UAI 2026

ALIGN: Adversarial Learning for Generalizable Speech Neuroprosthesis

Zhanqi Zhang, Shun Li, Bernardo L. Sabatini, Mikio Christian Aoi, Gal Mishne

Intracortical brain-computer interfaces (BCIs) can decode speech from neural activity with high accuracy when trained on data pooled across recording sessions. In realistic deployment, however, models must generalize to new sessions without labeled data, and performance often degrades due to cross-session nonstationarities (e.g., electrode shifts, neural turnover, and changes in user strategy). In this paper, we propose ALIGN, a session-invariant learning framework based on multi-domain adversarial neural networks for semi-supervised cross-session adaptation. ALIGN trains a feature encoder jointly with a phoneme classifier and a domain classifier operating on the latent representation. Through adversarial optimization, the encoder is encouraged to preserve task-relevant information while suppressing session-specific cues. We evaluate ALIGN on intracortical speech decoding and find that it generalizes consistently better to previously unseen sessions, improving both phoneme error rate and word error rate relative to baselines. These results indicate that adversarial domain alignment is an effective approach for mitigating session-level distribution shift and enabling robust longitudinal BCI decoding.

UAI 2026

Structural Drift Repair in Decision Trees via Bayesian Model-Based Diagnosis

Yoav Zelinger, Meir Kalech

Decision trees are widely used in machine learning due to their interpretability. However, when the underlying data distribution changes—a phenomenon known as concept drift—their performance can degrade significantly. Retraining the model from scratch discards the learned structure and offers no insight into which nodes were actually affected. Prior work, APPETITE, used spectrum-based fault localization to identify and modify a single faulty node, but cannot handle drift that affects multiple nodes simultaneously or that demands structural changes to the tree. We propose BTAD (Bayesian Tree Adaptation for Drift), which formalizes the Decision Tree Concept Drift Problem as a Model-Based Diagnosis task and employs BARINEL, a Bayesian algorithm that ranks multi-node fault hypotheses across the entire tree. For repair, BTAD applies Subtree Re-fitting, replacing affected subtrees with ones fitted to the post-drift distribution. BTAD relies on lightweight node-level statistics and requires no access to the original training data. Experiments show that BTAD outperforms APPETITE in both recovery and localization, achieving accuracy comparable to full retraining—which provides no drift insight and requires the original data.

UAI 2026

A Debiased LASSO Estimator for Design Matrices with Non-zero Mean Elements

Ashish Zantye, Ajit Rajwade*, Radhendushka Srivastava

The LASSO estimator has been popular in diverse fields such as statistics, bio-informatics and compressed sensing for estimation of sparse signals from under-sampled measurements. As the LASSO does not provide confidence intervals for the estimates of the individual elements, techniques such as the debiased LASSO have been developed that provide such confidence intervals and also mitigate the inherent bias in the LASSO estimates. However the theoretical guarantees underlying the debiased LASSO have been developed for a design or measurement matrix whose elements have zero mean. On the other hand, many commonly used measurement matrices in sparse regression applications in optical imaging or pooled biological testing involve non-negative, particularly binary, matrices whose elements have a non-zero mean. In this paper, we propose a debiased LASSO technique based on computing differences between different row subsets of the underlying design matrix iteratively which effectively converts the design matrix into one with zero-mean elements. We show analytically that this results in lower variances for the individual elements of the debiased LASSO estimate as compared to the standard debiased LASSO. We also provide numerical results to support our theory.

UAI 2026

On the Equivalence of Random Network Distillation, Deep Ensembles, and Bayesian Inference

Moritz Akiya Zanger, Yijun Wu, Pascal R. van der Vaart, Wendelin Böhmer, Matthijs T. J. Spaan

Uncertainty quantification is central to safe and efficient deployments of deep learning models, yet many computationally practical methods lack lacking rigorous theoretical motivation. Random network distillation (RND) is a lightweight technique that measures novelty via prediction errors against a fixed random target. While empirically effective, it has remained unclear what uncertainties RND measures and how its estimates relate to other approaches, e.g., Bayesian inference or deep ensembles. We establish these missing theoretical connections by analyzing RND within the neural tangent kernel framework in the limit of infinite network width. Our analysis reveals two central findings in this limit: (1) The uncertainty signal from RND—its squared self-predictive error—is equivalent to the predictive variance of a deep ensemble. (2) By constructing a specific RND target function, we show that the RND error distribution can be made to mirror the centered posterior predictive distribution of Bayesian inference with wide neural networks. Based on this equivalence, we moreover devise a posterior sampling algorithm that generates i.i.d. samples from an exact Bayesian posterior predictive distribution using this modified Bayesian RND model. Collectively, our findings provide a unified theoretical perspective that places RND within the principled frameworks of deep ensembles and Bayesian inference, and offer new avenues for efficient yet theoretically grounded uncertainty quantification methods.

UAI 2026

Optimizing Likelihoods via Mutual Information: Bridging Simulation-Based Inference and Bayesian Optimal Experimental Design

Vincent D. Zaballa, Elliot E. Hui

Simulation-based inference (SBI) depends on expensive simulators, so inference and experimental design must operate under fixed simulation budgets. Bayesian optimal experimental design (BOED) maximizes expected information gain (EIG), but is often implemented with a separate mutual-information critic, used only as a diagnostic, or restricted to differentiable simulators. We show that the InfoNCE lower bound on EIG becomes a principled SBI training objective when the critic is a normalized conditional density model. Maximizing the bound is equivalent to fitting a surrogate likelihood by minimizing a KL divergence plus a marginal-likelihood term, so each simulator call can improve both inference and design. We propose SBI-BOED, a single stochastic-gradient procedure that jointly trains a conditional normalizing-flow likelihood and optimizes designs without simulator differentiability. The same MI view also yields simulation active learning under fixed designs via epistemic predictive information gain (EPIG). With an InfoNCE-λ objective and practical stabilizers, SBI-BOED improves posterior calibration and predictive accuracy over strong BOED baselines on synthetic benchmarks and scientific simulators at matched simulation budgets.

UAI 2026

MMG: Mutual Information Estimation via the MMSE Gap in Diffusion

Longxuan Yu, Xing Shi, Xianghao Kong, Tong Jia, Greg Ver Steeg

Mutual information is one of the most general ways to measure relationships between random variables, but estimating this quantity for complex systems is challenging. Denoising diffusion models have recently set a new bar for density estimation, so it is natural to consider whether these methods could also be used to improve mutual information estimation. Using the recently introduced information-theoretic formulation of denoising diffusion models, we show that diffusion models can be used in a straightforward way to estimate mutual information. In particular, the mutual information corresponds to half the gap in the minimum mean square error between conditional and unconditional diffusion, integrated over all signal-to-noise ratios in the noising process. Our approach not only passes self-consistency tests but also outperforms traditional and score-based diffusion estimators. Furthermore, our method leverages adaptive importance sampling to achieve scalable estimation, while maintaining strong performance even when the mutual information is high. Code to reproduce our experiments is available at <https://github.com/fengsxy/Diffusion_MI>, and the unified mutual information estimation library is available at <https://github.com/fengsxy/Diffusion-MI>.

UAI 2026

Neural Value Iteration

Yang You, Ufuk Çakır, Alex Schutz, Nick Hawes

The value function of a POMDP exhibits the piecewise-linear-convex (PWLC) property and can be represented as a finite set of hyperplanes, known as α-vectors. Most state-of-the-art POMDP solvers (offline planners) follow the point-based value iteration scheme, which performs Bellman backups on α-vectors at reachable belief points until convergence. However, since each α-vector is |S|-dimensional, these methods quickly become intractable for large-scale problems due to the prohibitive computational cost of Bellman backups. In this work, we demonstrate that the PWLC representation of POMDP value functions can be generalized by replacing the alpha-vector sets with a finite set of neural networks. This insight enables a novel POMDP planning algorithm, called *Neural Value Iteration*, which combines the generalization capability of neural networks with the classical value iteration framework. Requiring only a black-box simulator, our approach scales to extremely large POMDPs that are intractable for existing offline solvers.

UAI 2026

Estimating Interventional Outcomes over Time with Causal Normalizing Flow

Yoonseok Yeom, Jonghwan Kim, Taehui Yun, Juhyun Lyu, Jung-Hee Kim, Sangmin Lee, Jinseok Yang, Hyemin Jung, Woohyung Lim, Sanghack Lee

Estimating outcome distributions under time-varying treatments is an essential task for personalized decision-making, particularly in domains such as healthcare. Most prior work in this area focuses on point predictions, which fail to capture the inherent variability in outcomes. Recent efforts in causal inference have begun integrating generative models to address this limitation by estimating interventional distributions. However, existing approaches—including causal normalizing flows—are generally restricted to static settings and are not well suited to sequential, time-dependent data. In this work, we propose a novel framework that extends causal normalizing flows to time-series, enabling simulation-based interventional density estimation over time. Our method learns representations of treatment and covariate history that capture temporal dependencies. Conditioned on these representations and guided by a causal graph, our flow-based model generates interventional samples, allowing for the simulation of outcome trajectories under alternative treatment strategies. We evaluate our approach on both linear and non-linear synthetic time-series as well as on a simulated tumor growth dataset, demonstrating that it achieves performance competitive with state-of-the-art baselines, while accommodating a broader spectrum of causal queries.

UAI 2026

When Can Transformers Count to n?

Gilad Yehudai, Haim Kaplan, Guy Dar, Royi Rassin, Asma Ghandeharioun, Mor Geva, Amir Globerson

Large language models based on the transformer architecture can solve highly complex tasks, yet their fundamental limitations on simple algorithmic problems remain poorly understood. In this work, we focus on basic counting tasks and investigate how the difficulty of these tasks scales with the transformer embedding dimension, the context length, and the vocabulary size. We reveal a sharp theoretical phase transition governed by the relationship between the embedding dimension and the vocabulary size. When the dimension is at least as large as the vocabulary, transformers can perfectly maintain token counts. However, when the vocabulary exceeds the embedding dimension, the interference between non-orthogonal token representations forces the network weights to scale polynomially. This renders the exact counting algorithm numerically unstable and practically unlearnable. We empirically validate this bottleneck by training transformers from scratch, demonstrating a strict performance drop at the theoretical threshold and catastrophic out of distribution failure when scaling the vocabulary or context length. Furthermore, we show that state-of-the-art pretrained models suffer from similar failure cases. Our work reveals a critical blind spot absent from the current literature regarding the connection among these three parameters, proving that vocabulary size fundamentally dictates the difficulty of counting tasks.

UAI 2026

Near-Exponential Convergence Rates for kNN Classifications based on Boltzmann Margin

Luyuan Yang, Shayan Shafaei, Chao Lan

Convergence-rate analysis for classifiers is often conducted under either Tsybakov margin or Massart margin. The former is a relatively weak condition that typically yields polynomial rates, while the latter is substantially stronger but can guarantee exponential rates. In this paper, we introduce a new condition, called *Boltzmann margin*, that bridges the gap between these two regimes. It is weaker than Massart margin, generally stronger than Tsybakov margin, and can imply many of their properties under suitable conditions. We apply Boltzmann margin to the analysis of kNN classifiers and establish the first *near-exponential* convergence rates for kNN classification. We also present extensions of the main results and provide numerical evidence supporting the main theoretical implications.

UAI 2026

Evaluating the Role of Great Pre-trained Diffusion Models in Few-shot Phase: Warm-up and Acceleration

Ruofeng Yang, Yongcan Li, Bo Jiang, Cheng Chen, Shuai Li

Due to the customized requirements, few-shot diffusion models have attracted much attention. However, only a few works analyze few-shot models, and none involve the fast few-shot optimization process, which is important for quickly responding to users. In this work, we evaluate the role of each operation in the optimization process and prove the convergence guarantee for few-shot diffusion models. A standard operation for the few-shot model is only fine-tuning some key parameters to avoid overfitting the limited target dataset. We first show that this operation is insufficient from empirical and theoretical perspectives. Empirically, we conduct real-world few-shot fine-tuning experiments with underfitting and overfitting bad pre-trained models and show that the results are heavily influenced by these bad models. Theoretically, we also prove that the few-shot phase can not learn the ground-truth parameters and suffers from a small gradient when using a bad pre-trained model. Based on these results, we highlight the importance of a great pre-trained model by showing it can warm up few-shot models and lead to a strongly convex landscape for few-shot diffusion models. As a result, the few-shot model fast converges to the ground-truth parameters. In contrast, we show that with a bad initialization, the pretraining phase requires large optimization steps to converge.

Keep browsing

More papers from top AI conferences

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