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.

ICML 2026

Can VLMs Diagnose and Recover from VLA Manipulation Faults?

Bowen Yan, Jiahao Xiao, Kehui Liu, Jianbo Zhang, Zicheng Zhang, Qi Jia, Zhongjie Jia, Haoming Song, Chunyi Li, Bin Zhao, Guangtao Zhai

Existing VLA models frequently fail in robotic manipulation tasks, with poorly structured fault types that often require expert diagnosis. While VLMs offer strong explanatory capabilities, their effectiveness in assisting VLAs is limited by their unclear role in diagnostics and inadequate collaboration mechanisms. To address this, we introduce VLA-FixBench, a fault evaluation dataset that spans perception, planning, and control failures, and provides annotations for task stages, fault types, and spatiotemporal repair strategies. We further propose FaultEval, a static-to-dynamic-to-real evaluation framework that benchmarks 20 VLMs across multiple fault-related dimensions. Building on these insights, we design a VLM–VLA collaboration mechanism that localizes spatiotemporal deviations and rolls back task execution to enable targeted recovery. Experiments show that FaultEval reliably characterizes VLM-based closed-loop diagnosis and repair. The upper-bound analysis using human expert intervention shows that an idealized feedback loop can improve task success rates by 13\% on LIBERO and 35\% on real-world robots. Our code, benchmark, and project page will be publicly released at: https://kakigo.github.io/VLA-FixBench/

ICML 2026

CLAA: Cross-Layer Attention Aggregation for Accelerating LLM Prefill

Bradley McDanel, Steven Li, Harshit Khaitan

Token-ranking heuristics accelerate the prefill bottleneck in long-context LLM inference by selectively processing semantically relevant tokens. However, current evaluation relies on end-to-end benchmarks, making it difficult to isolate the quality of the token ranking itself. To address this, we introduce an Answer-Informed Reference framework with two variants: a Model Reference (Model-Ref) that measures token importance using the model generated answer, and a Ground-Truth Reference (GT-Ref) that uses human reference answers. Using GT-Ref, we establish that as few as 10% of prompt tokens suffice to match full-context performance on LongBench across all three evaluated models. The framework also reveals that existing heuristics exhibit variance across layers, with rankings degrading sharply at specific layers. Motivated by this instability, we propose Cross-Layer Attention Aggregation (CLAA), which aggregates importance scores across consecutive layers, eliminating the layer-dependent accuracy collapse observed in single-layer methods. A meaningful gap remains between the best heuristic and GT-Ref, indicating theoretical room for improved token selection.

ICML 2026

When RAG Hurts: Diagnosing and Mitigating Attention Distraction in Retrieval-Augmented LVLMs

Beidi Zhao, Wenlong Deng, Xinting Liao, Yushu Li, Nazim Shaikh, Yao Nie, Xiaoxiao Li

While Retrieval-Augmented Generation (RAG) is one of the dominant paradigms for enhancing Large Vision-Language Models (LVLMs) on knowledge-based VQA tasks, recent work attributes RAG failures to insufficient attention towards the retrieved context, proposing to reduce the attention allocated to image tokens. In this work, we identify a distinct failure mode that previous study overlooked: Attention Distraction (AD). When the retrieved context is sufficient (highly relevant or including the correct answer), the retrieved text suppresses the visual attention globally, and the attention on image tokens shifts away from question-relevant regions. This leads to failures on questions the model could originally answer correctly without the retrieved text. To mitigate this issue, we propose MAD-RAG, a training-free intervention that decouples visual grounding from context integration through a dual-question formulation, combined with attention mixing to preserve image-conditioned evidence. Extensive experiments on OK-VQA, E-VQA, and InfoSeek demonstrate that MAD-RAG consistently outperforms existing baselines across different model families, yielding absolute gains of up to 4.76%, 9.20%, and 6.18% over the vanilla RAG baseline. Notably, MAD-RAG rectifies up to 74.68% of failure cases with negligible computational overhead.

ICML 2026

RSPO: Regularized Self-Play Alignment of Large Language Models

Xiaohang Tang, Sangwoong Yoon, Seongho Son, Huizhuo Yuan, Quanquan Gu, Ilija Bogunovic

Self-play-based policy optimization has emerged as an effective approach for fine-tuning large language models (LLMs), formulating preference optimization as a two-player game. However, the regularization with respect to the reference policy, which is crucial for mitigating over-optimization, has been insufficiently investigated in self-play alignment. To study the impact of different regularization strategies, we propose \textbf{Regularized Self-Play Policy Optimization (RSPO)}, a novel framework that unifies prior methods and enables simple plug-and-play regularizers, meanwhile preserving convergence to Nash equilibrium of the corresponding regularized game. We empirically show that RSPO with appropriate regularizers can substantially improve the length-controlled win rate (LCWR) on AlpacaEval-2 across a range of base models, while also achieving consistently superior performance on Arena-Hard, MT-Bench, ArmoRM, and response diversity. In particular, RSPO improves unregularized self-play baseline (SPPO) on AlpacaEval-2 LCWR from $28.5\%$ to $ 35.4\%$ with base model Mistral-7B, from $38.77\%$ to $43.66\%$ with LLaMA-8B, and from $50.54\%$ to $51.83\%$ with Gemma-2B. Combining simplicity, convergence guarantees, and significant empirical gains, RSPO offers a strong foundation for exploring regularized self-play in alignment.

ICML 2026

Do Language Models Track Entities Across State Changes?

Zilu Tang, Qiao Zhao, Gabriel Franco, Derry Tanti Wijaya, Aaron Mueller, Sebastian Schuster, Najoung Kim

Entity tracking (ET), the ability to keep track of states, is a fundamental skill that underlies complex reasoning. An increasing amount of work investigates how transformer language models (LMs) solve entity binding *without* state changes. However, there is limited understanding of how non-toy LMs address ET problems of realistic difficulties expressed in natural language. To this end, we investigate the mechanisms underlying ET in more complex scenarios featuring multiple state-changing operations. We find that LMs do not incrementally track world states across tokens or query-relevant states across layers, but simply aggregate relevant information in parallel at the last token when the query becomes evident. We further investigate mechanisms of individual operations (`PUT`, `REMOVE`, `MOVE`) to characterize this non-incremental ET mechanism. Surprisingly, LMs implement the `REMOVE` operation with a fragile global suppression tag; this global removal mechanism predicts various failure modes that we confirm behaviorally. We provide a mechanistic solution of nullifying this tag to partially address this issue. Overall, our findings reveal that LMs solve a fundamentally sequential task using a non-sequential strategy. More broadly, our work illustrates how behavioral and mechanistic analyses can fruitfully interact. Behavioral results inform mechanistic hypotheses, and insights from mechanistic analyses help build stronger behavioral evaluations by predicting failure modes missing from existing evaluations.

ICML 2026

MaMi-HOI: Harmonizing Global Kinematics and Local Geometry for Human-Object Interaction Generation

Hao Wang, Shiqi Wang, Qi Liu

Generating realistic 3D Human-Object Interactions (HOI) is a fundamental task for applications ranging from embodied AI to virtual content creation, which requires harmonizing high-level semantic intent with strict low-level physical constraints. Existing methods excel at semantic alignment, however, they struggle to maintain precise object contact. We reveal a key finding termed $\textit{Geometric Forgetting}$: as diffusion model depth increases, semantic feature tend to overshadow object geometry feature, causing the model to lose its perception to object geometry. To address this, we propose MaMi-HOI, a hierarchical framework reconciling Macro-level kinematic fluidity with Micro-level spatial precision. First, to counteract geometric forgetting, we introduce the Geometry-Aware Proximity Adapter (GAPA), which explicitly re-injects dense object details to perform residual snapping corrections for precise contact. Nevertheless, such aggressive local enforcement can disrupt global dynamics, leading to robotic stiffness. In response, we introduce the Kinematic Harmony Adapter (KHA), which proactively aligns whole-body posture with spatial objectives, ensuring the skeleton actively accommodates constraints without compromising naturalness. Extensive experiments validate that MaMi-HOI simultaneously achieves natural motion and precise contact. Crucially, it extends generation capabilities to long-term tasks with complex trajectories, effectively bridging the gap between global navigation and high-fidelity manipulation in 3D scenes.

ICML 2026

Learning Task-Sufficient World Models by Synergizing Agentic Exploration and Structured Modeling

Fan Feng, Yujia Zheng, Minghao Fu, Yongqiang Chen, Guangyi Chen, Kevin Patrick Murphy, Biwei Huang, Kun Zhang

Learning and planning in imagination using world models provides an effective paradigm for training agents for decision-making. However, existing approaches often rely on high-dimensional latent spaces or generic visual embeddings that retain many factors irrelevant to control, limiting efficiency and generalization across tasks. To this end, we study how agents can learn world models with representations that are task-specific, minimal, and sufficient for decision making. We achieve this via a closed-loop synergy between the agent and the world model, in which structured world-model learning distills task-sufficient representations from informative interaction data. On the agent side, agents perform active probing of the environment to collect informative trajectories that expose task-relevant latent factors, guided by an adaptive curriculum. On the world-model side, we learn structured representations over observations to distill compact, task-sufficient latent states from the collected interaction data. This synergy enables the recovery of task-sufficient latent representations that capture all control-relevant factors empirically. Leveraging these representations, the resulting policies achieve improved sample efficiency generalization, including generalization across skills, object–skill compositions, and previously unseen tasks on standard continuous control and robotic manipulation benchmarks.

ICML 2026

Towards Seed-Robust Safety Alignment in Text-to-Image Models

Zhenyu Wu, Yao Huang, Shouwei Ruan, Xingxing Wei

Text-to-image diffusion models have achieved remarkable success in generating high-quality images, yet existing safety mechanisms exhibit critical cross-seed instability where defense performance varies significantly under different random seed conditions. This instability stems from the fact that a single malicious prompt generates diverse harmful variants across different noise initializations, forming complex distributional clusters that current methods cannot adequately address. We investigate extending Noise Contrastive Alignment (NCA) to diffusion models due to its native capability of handling multiple negative samples through probabilistic weighting, but our theoretical analysis reveals two fundamental flaws in direct extension: gradient reversal caused by positive regularization terms that paradoxically penalize safe content generation, and uniform suppression of harmful samples that ignores severity variations. To tackle these issues, we propose Noise Contrastive Diffusion (NCD), which incorporates targeted algorithmic modifications including elimination of problematic regularization and introduction of pairwise regularization mechanisms that establish individualized preference relationships between safe and harmful variants. Extensive experiments further demonstrate that NCD achieves superior cross-seed stability, reducing attack success rates (ASRs) from 11.1% to 6.2% compared to SOTA methods at the seed level while maintaining exceptional generation quality, exhibiting robust resistance against sophisticated jailbreak prompts and strong generalizability across different T2I architectures. WARNING: This paper may contain examples of harmful texts and images.

ICML 2026

Spatial Conformal Inference through Localized Quantile Regression

Hanyang Jiang, Yao Xie

Reliable uncertainty quantification at unobserved spatial locations is a key challenge in spatial statistics, particularly for complex and heterogeneous datasets. While traditional methods such as Kriging rely on strong distributional assumptions, conformal prediction (CP) offers a distribution-free alternative. However, although non-i.i.d. CP theory is well established for time-series data, a significant gap remains for spatial data, where the lack of a natural ordering and discrete index complicates theoretical guarantees. Existing CP theory for spatial data often relies on exchangeability. We propose Localized Spatial Conformal Prediction (LSCP), a model-agnostic framework that bridges this gap by coupling local quantile regression with conformal calibration. LSCP conditions on spatial neighborhoods to capture local heterogeneity. We show that LSCP retains finite-sample marginal coverage under spatial exchangeability and attains asymptotic conditional coverage under stationarity and spatial mixing. Across synthetic and real datasets, LSCP consistently achieves near-nominal coverage with tighter and more stable prediction intervals than existing methods that fail to capture these spatial dependencies.

ICML 2026

Logarithmic Switching Regret for Online Convex Optimization

Wenhao Yang, Yibo Wang, Yuanyu Wan, Lijun Zhang

Online convex optimization in non-stationary environments has garnered considerable attention in the literature. Recently, Pasteris et al. (2024) investigate online convex optimization with the optimal switching regret, defined as the sum of the static regret over each segment, where the segmentation is an arbitrary partition of the entire time horizon. For general convex functions, their work has established an optimal switching regret bound. However, it remains open whether similar bounds are attainable for other types of convex functions, such as exponentially concave or strongly convex functions. In this paper, we affirmatively answer this question by proposing a novel meta-algorithm, termed IRESET, which is used to aggregate the decisions from a group of experts. The essence of our method lies in running multiple experts over a set of intervals, and then employing a meta-algorithm equipped with second-order bounds to sequentially combine their decisions. We leverage the segment tree structure to analyze the switching regret over the entire time horizon, and offer new insights into utilizing recursive equations over the segment tree. By choosing appropriate expert-algorithms for IRESET, our methods achieve logarithmic switching regret bounds for exponentially concave or strongly convex functions, respectively.

ICML 2026

Evaluating Contextual Illegality: AI Compliance in Corporate Law Scenarios

Hilal Aka, Joe Kwon, Noam Kolt

While AI models often refuse explicitly unlawful requests, in real-world scenarios illegality often depends on context. We evaluate frontier models on contextual illegality across four corporate law scenarios in which routine actions—editing documents, trading stock, requesting payment, approving communications—become unlawful due to circumstances such as pending investigations or bankruptcy filings. We study both chat and agentic settings and compare results to a human baseline. The best-performing models consistently followed lawful requests and refused unlawful requests, though performance varied substantially between different scenarios and models. We also identify distinct failure modes, such as excessive refusal of lawful requests, and find higher performance in reasoning models and agentic environments. By studying contextual illegality in these controlled environments, we develop a methodology that can be extended to evaluate the legal compliance of AI models in additional scenarios and domains.

ICML 2026

HIAL: Towards Semantics-Aware Hypergraph Active Learning via Dual-Perspective Information Maximization

Yanheng Hou, Xunkai Li, Yanzhe Wen, Zhenjun Li, Bing Zhou, Rong-Hua Li, Guoren Wang

Hypergraph Neural Networks (HNNs) model high-order interactions effectively but rely on costly node annotations, motivating Hypergraph Active Learning (HAL). However, many HAL pipelines adapt graph-based querying through clique expansion, which introduces *structural bias* and can cause *ranking collapse*, making utilities overly determined by hyperedge cardinalities rather than informative high-order context. We propose **HIAL** (**H**ypergraph **I**nfluence-based **A**ctive **L**earning), a training-free framework that formulates hypergraph active learning as influence maximization over a high-order context-based weighted pairwise projection of the hypergraph. HIAL employs a High-Order Interaction-aware propagation mechanism that modulates pairwise influence weights using hyperedge cardinality and feature consistency, yielding a scalable linear diffusion process tailored to homophilic hypergraphs. We further combine feature-space coverage and structural reachability into a monotone submodular selection objective, enabling an efficient lazy greedy solver. Experiments on eight benchmarks demonstrate that HIAL consistently outperforms strong baselines across diverse homophilic hypergraph domains.

ICML 2026

High-Dimensional Sensitivity Analysis for Genomic Studies: An Adversarial Framework for Learning Worst-Case Latent Confounders

Yifan Lin, Kevin Z. Lin

High-dimensional genomics studies are frequently confounded by unmeasured biological processes that obscure disease-specific signals. While existing workflows can estimate these latent confounders, they fail to quantify how robust a discovery is to varying levels of hypothetical confounding. We introduce sensGAN, a deep-learning adversarial framework that systematically explores the confounding spectrum by learning "worst-case" latent variables that nullify the most gene associations under novel predictive-gain constraints. By identifying the minimum confounding strength required to explain away an observed effect, our method shifts the paradigm toward a formal, quantitative sensitivity analysis. In diverse simulations, sensGAN accurately recovers latent structures and outperforms existing methods in identifying confounder-sensitive genes. Applied to human Alzheimer's disease microglia, our framework prioritizes robust disease pathways while successfully isolating signals driven by unmeasured co-occurring neurodegenerative pathologies.

ICML 2026

Tri-Scale Neural ODEs for Continuous Multi-Omics Disease Modeling

Shohaib Shaffiey, Massimiliano Pierobon

The fields of AI-based disease fingerprinting, drug discovery and repurposing are currently among the emerging frontiers of machine learning applied to medicine. One major challenge is to obtain robust $\textit{in-silico}$ modeling of disease progression while accounting for the vastly different time scales of biochemical interactions, from gene expression to protein abundance and metabolic flux. Discrete sequence models inadequately represent such multi-scale interactions, and standard Neural Ordinary Differential Equations (NODEs) often fail to train stably under stiffness (different time scales). To address this, a Tri-Scale Stiff NODE, defined by hierarchically coupled latent differential equations that model the causal relationships from genes to proteins and metabolites, is introduced and optimized in this paper in terms of reconstruction error and information-theoretic mutual information. This enables continuous-time modeling of cellular responses to identify not only the disease dynamics, but also drug perturbations that act within narrow time windows, often invisible to discrete-time approaches. Lyapunov analysis provides a theoretical guarantee that the modeled trajectories remain stable and well-behaved even under extreme stiffness. The methodology is validated using the STATegra B-cell and Traxler macrophage datasets, with the former utilized for a proof-of-concept drug repurposing pipeline.

ICML 2026

Beyond Test-Time Memory: State-Space Optimal Control for LLM Reasoning

Peihao Wang, Shan Yang, Xijun Wang, Tesi Xiao, Xin Liu, Changlong Yu, Yu Lou, Pan Li, Zhangyang Wang, Ming Lin, Rene Vidal

Associative memory has long underpinned the design of sequential models. Beyond recall, humans reason by *projecting future states and selecting goal-directed actions*, a capability that modern language models increasingly require but do not natively encode. While prior work uses reinforcement learning or test-time training, planning remains external to the model architecture. We formulate reasoning as *optimal control* and introduce the *Test-Time Control (TTC)* layer, which performs finite-horizon *LQR* planning over latent states at inference time, represents a *value function* within neural architectures, and leverages it as the nested objective to enable *planning before prediction*. To ensure scalability, we derive a hardware-efficient LQR solver based on a symplectic formulation and implement it as a fused CUDA kernel, enabling parallel execution with minimal overhead. Integrated as an adapter into pretrained LLMs, TTC layers improve mathematical reasoning performance by up to +27.8% on MATH-500 and 2-3$\times$ Pass@8 improvements on AMC and AIME, demonstrating that embedding optimal control as an architectural component provides an effective and scalable mechanism for reasoning beyond test-time training.

ICML 2026

Path-Coupled Bellman Flows for Distributional Reinforcement Learning

Boyang Xu, Qing Zou, Siqin Yang, Hao Yan

Distributional reinforcement learning (DRL) models the full return distribution, but typically relies on finite-dimensional categorical or quantile approximations, often involving projection or quantile-regression approximations to the Bellman target, together with independently sampled bootstrap targets that obscure transport structure and add variance. We present Path-Coupled Bellman Flows (PCBF), a continuous-time DRL method that encodes Bellman endpoint consistency and pathwise Bellman-coupled geometry within generative flow trajectories. PCBF represents return distributions via flow matching and couples the paths of consecutive states through shared base noise, yielding a geometric Bellman flow relation between velocity fields. This structure enables a $\lambda$-parameterized control-variate target that reduces training variance while preserving the source and Bellman endpoint geometry. Experiments on analytically tractable MRPs, OGBench, and D4RL show improved distributional fidelity, training stability, and competitive offline RL performance.

ICML 2026

Symmetries in PAC-Bayesian Learning

Armin Beck, Peter Ochs

Symmetries are known to improve the empirical performance of machine learning models, yet theoretical guarantees explaining these gains remain limited. Prior work has focused mainly on compact group symmetries and often assumes that the data distribution itself is invariant, an assumption rarely satisfied in real-world applications. In this work, we extend generalization guarantees to the broader setting of non-compact symmetries, such as translations and to non-invariant data distributions. Building on the PAC-Bayes framework, we adapt and tighten existing bounds, demonstrating the approach on McAllester's PAC-Bayes bound while showing that it applies to a wide range of PAC-Bayes bounds. We validate our theory with experiments on several datasets with non-uniform and non-compact transformations, where the derived guarantees not only hold but also improve upon prior results. These findings provide theoretical evidence that, for symmetric data, symmetric models are preferable beyond the narrow setting of compact groups and invariant distributions, opening the way to a more general understanding of symmetries in machine learning.

ICML 2026

PGT: Procedurally Generated Tasks for improving visual grounding in MLLMs

Rim Assouel, Amir Bar, Michal Drozdzal, Adriana Romero-Soriano

Despite remarkable progress in Multimodal Large Language Models (MLLMs), these models still struggle with fine-grained understanding tasks. In this work, we propose **Procedurally Generated Tasks (PGT)** a simple data-driven framework that serves a dual purpose: inducing fine-grained visual understanding and acting as a low-cost diagnostic tool to identify the source of perception failures. By overlaying unambiguous geometric primitives on images, PGT generate additional dense supervision that disentangles visual grounding capability from semantic priors. Extensive experiments on relational, quantitative, and 3D/depth understanding benchmarks show that PGT yields remarkable gains across diverse architectures. Instruction tuning MLLMs on LLaVA-v1.5-Instruct augmented with PGT data results in improvements of up to +20\% on the What’sUp benchmark and +13.3\% on CV-Bench-2D, while maintaining general perception capabilities. Moreover, finetuning state-of-the-art MLLMs on PGT data leads to boosts of up to +5.5\% on What’sUp and +8.3\% on CV-Bench-2D. These findings demonstrate that PGT effectively address the bottleneck of fine-grained perception, revealing that many spatial reasoning deficits stem from inadequate supervision signals rather than inherent architectural or resolution limitations.

ICML 2026

Personalized Additive Modeling for Multi-level Federated Learning

Shutong Chen, Guodong Long, Tianyi Zhou, Jie Ma, Jing Jiang, Chengqi Zhang

Contemporary AI faces the challenge of balancing generality with user-specific personalization. In federated learning (FL), this challenge is amplified by highly heterogeneous client data with complex non-IID patterns beyond standard modeling assumptions. Many existing FL methods are designed for relatively restricted heterogeneity settings (e.g., a fixed number of clusters or a fixed form of personalization), limiting their robustness under complex structures. In this work, we study FL from a \emph{multi-level non-IID} perspective, where client similarity is approximated by multiple granularities of shared knowledge: global, subgroup, and client-specific components. This view captures coarse-to-fine relationships while requiring less prior knowledge of task boundaries. Building on this insight, we propose \emph{Federated Multi-level Additive Modeling} (FeMAM), which learns multiple levels of shareable models and constructs personalized predictors via additive composition across levels. To move beyond a fixed structure, FeMAM allows models to grow and be pruned dynamically during training, adapting to diverse federated scenarios. Despite employing multiple models, FeMAM remains cost-friendly by activating only a small subset (one level) of models for training at a time. Extensive experiments show that FeMAM effectively approximates complex non-IID structures and consistently outperforms representative clustered and personalized FL baselines.

ICML 2026

CAMP: Coherent Alignment of Multimodal Prototypes for Explainable Complementary Learning

Alvaro Lopez Pellicer, Eoin M. Kenny, Simran Lamba, Shubham Sharma, Plamen P Angelov, Saumitra Mishra

Most multimodal learning assumes redundant views (such as image–caption pairs), yet many applications require combining complementary modalities that provide distinct evidence (such as an X-ray and medical history). We term this setting *Complementary Multimodal Classification* (CMC). In CMC, existing explainable-by-design methods often force an accuracy–interpretability trade-off because single shared similarity metrics fail under asymmetric, class-conditional evidence. To address this, we propose Coherent Alignment of Multimodal Prototypes (CAMP). CAMP enforces coherent multimodal reasoning by aligning class-wise evidence via optimal transport and imposing geometric constraints to counter modality dominance and representation collapse. We provide theoretical guarantees showing that these mechanisms eliminate such degeneracies without restricting expressivity. Empirically, across 16 public CMC datasets, CAMP matches or exceeds large ($>$100M parameter) AutoML baselines with fewer than 1M trainable parameters, and when fine-tuned end-to-end it achieves state-of-the-art performance. To the best of our knowledge, this work is the first modality-agnostic prototype-learning framework designed for complementary multimodal tasks.

Keep browsing

More papers from top AI conferences

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