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

Message Tuning Outshines Graph Prompt Tuning: A Prismatic Space Perspective

Yancheng Chen, Dun Ma, Shuai Zhang, Yang Liu, Xixun Lin, Xiangyu Zhao, Wenguo Yang, Wei Chen, Chuan Zhou

Graph Foundation Models (GFMs), built upon the *Pre-training and Adaptation* paradigm, have emerged as a research hotspot in graph learning. For GNN-based GFMs, graph prompt tuning has become the prevailing adaptation method for downstream tasks. Although recent methods explain why graph prompt tuning works, how to rigorously measure its adaptation capacity remains an open problem. Addressing this problem is critical for understanding the capability limits of graph prompt tuning and for developing more powerful adaptation methods. In this paper, we propose Prismatic Space Theory (PS-Theory), a novel mathematical framework to quantify the capacity of adaptation methods, while focusing on establishing the upper bound for the adaptation capacity of graph prompt tuning. Building upon the proposed PS-Theory, we further introduce **M**essage **T**uning for **G**FMs (MTG), a lightweight approach that injects a small set of learnable message prototypes into each layer of the GNN backbone to adaptively guide message fusion without updating pre-trained weights. Through our PS-Theory, we prove that the adaptation capacity of MTG can exceed the theoretical upper bound of graph prompt tuning. Extensive experiments demonstrate that MTG consistently outperforms graph prompt baselines across diverse benchmark datasets, providing strong empirical support for our theoretical findings.

ICML 2026

Reflect-then-Correct: Rebalancing Task Optimization for Generalizable Meta-Reinforcement Learning via Distributional Value Error Reduction

Min Wang, Xin Li, Ye He, Mingzhong Wang, Yonggang Zhang

Meta-Reinforcement Learning (Meta-RL) faces significant challenges in non-parametric settings, where vastly different return scales across diverse tasks cause severe gradient interference. Existing categorical solutions attempt to normalize these scales but often fail due to rigid discretization and quantization errors. To address this, we propose Reflect-then-Correct (RTC), a framework that models meta-values using Sinkhorn divergence. By treating distributions as adaptive floating particles, RTC achieves a geometry-aware alignment of distinct meta-task structures. However, while Sinkhorn updates harmonize gradients, they introduce statistical bias via sampling estimation. RTC overcomes this issue by "reflecting'' on the temporal accumulation of Bellman inconsistencies through a recursive error model and "correcting'' the optimization via adaptive importance weights, which prioritize more accurate transitions for meta-value estimation. We provide theoretical guarantees for this reweighting strategy and demonstrate that RTC outperforms existing baselines on the challenging Meta-World ML-10 and ML-45 benchmarks.

ICML 2026

Deep Pre-Alignment for VLMs

Tianyu Yu, Kechen Fang, Zihao Wan, Kaidong Zhang, Yicheng Zhang, Jun Song, Bo Zheng, Yuan Yao

Most Vision Language Models (VLMs) directly map outputs from ViT encoders to the LLM via a lightweight projector. While effective, recent analysis suggests this architecture suffers from an alignment challenge: visual features remain distant from the text space in the initial layers of the LLM, forcing the model to waste critical depth on superficial modality alignment rather than deep understanding and complex reasoning. In this work, we propose Deep Pre-Alignment (DPA), a novel architecture that replaces the standard ViT encoder with a small VLM as perceiver, ensuring visual features are deeply aligned with the text space of the target large language model. Comprehensive experiments demonstrate the effectiveness of DPA. On the 4B parameter scale, DPA outperforms baselines by 1.9 points across 8 multimodal benchmarks, with gains widening to 3.0 points at the 32B scale. Moreover, by offloading alignment to the perceiver, DPA achieves a 32.9\% reduction in language capability forgetting over 3 text benchmarks. We further demonstrate that these gains are consistent across different LLM families including Qwen3 and LLaMA 3.2, highlighting the generality of our approach. Beyond performance, DPA also offers a seamless upgrade path for current VLM development, requiring only a modular replacement for the visual encoder with marginal computation overhead.

ICML 2026

Multi-Objective Preference Optimization: Improving Human Alignment of Generative Models

Akhil Agnihotri, Rahul Jain, Deepak Ramachandran, Zheng Wen

Post-training LLMs with RLHF and preference optimization methods (e.g., DPO, IPO) has greatly improved alignment, yet these approaches assume a single objective. In reality, humans express multiple, often conflicting objectives, such as helpfulness and harmlessness, with no natural scalarization. We study the multi-objective preference alignment problem, where a policy must balance several objectives simultaneously. We propose Multi-Objective Preference Optimization (MOPO), a constrained KL-regularized framework that maximizes a primary objective while enforcing lower bounds on secondary objectives via tunable safety thresholds. MOPO operates directly on pairwise preferences without point-wise rewards, and admits simple closed-form iterative updates. Empirically, MOPO recovers Pareto-optimal policies on synthetic benchmarks and, when fine-tuned on human-preference data, yields multi-billion parameter models that achieve higher rewards and Pareto-dominate baselines, with stable and robust optimization dynamics.

ICML 2026

On Testing Conditional Mean Independence for Manifold-Valued Data

Meiling Zeng, Jinhong You, Jicai Liu, Shouxia Wang

This paper introduces a nonparametric test for conditional mean independence between a manifold‑valued $Y$ and Euclidean predictors $X$. The test is built on a new measure called the Manifold Martingale Difference Divergence (MMDD), which characterizes conditional mean dependence by projecting observations onto the tangent space via the logarithmic map. We provide an empirical estimator for the MMDD, establish its asymptotic null distribution, and implement a wild bootstrap procedure for finite‑sample inference. Simulations on three representative manifolds demonstrate that the proposed test maintains correct size under the null even when the distribution of $Y$ depends on $X$, in contrast to the severe size distortion exhibited by the distance covariance (dCov) test. At the same time, it achieves competitive power across a range of alternatives. An application to real data illustrates its practical utility.

ICML 2026

Don't Drop Dropout: Optimizing Layer Sparsity for Efficient LLM Training and Inference

Mostafa Elhoushi, Alexander D. Pretko, Nolan Simran Dey, Bin Claire Zhang, Gavia Gray, Gurpreet Gosal, Abdulrahman Mahmoud, Shane Bergsma, Joel Hestness

Layer dropout (a.k.a.\ stochastic depth) has been shown to enable faster training, higher accuracy, and robustness to zero-shot layer pruning in both language and vision transformers. However, as models and datasets have scaled, dropout---particularly layer dropout---has largely disappeared from LLM pre-training recipes. While some prior work has reported that dropout can degrade accuracy, no comprehensive study has quantified, let alone mitigated, this effect. In this study, we show that layer dropout **should** be used in state-of-the-art LLM training, establishing best practices and scaling analysis for both training and post-training benefits. Concretely, with optimal layer distribution, time schedule, and optimizer hyperparameters, LLM can achieve lower or similar validation loss while saving upto 20\% of training FLOPs. Moreover, layer dropout enables significant post-training optimizations, such as early exit, intermediate-layer skipping, and self-speculative decoding, yielding up to 1.4x inference speedup with negligible accuracy loss. All pre-training experiments were run on Cerebras CS-3 systems.

ICML 2026

Formal Concept Lattices are Good Semantic Scaffolds for Concept-Based Learning

Deepika Vemuri, Sayanta Adhikari, Ankit Saha, Krishn Vishwas Kher, Vineeth N. Balasubramanian

Learning semantics is essential for deep learning models to be interpretable and better aligned with human reasoning. Concept-based models approach this by representing classes through meaningful semantic abstractions, but typically treat all concepts as a flat, unstructured set learned at a single neural network layer. This overlooks a fundamental property of human semantic understanding: concepts being organized hierarchically, from general to specific. While deep networks do learn a hierarchy of visual features, this structure is rarely aligned with explicit semantic hierarchies. Drawing on Formal Concept Analysis, we demonstrate that formal concept lattices provide principled semantic scaffolds to guide neural network learning. These lattices naturally identify where in the network concepts should be learned based on their level of generality. This allows the model to develop staged, semantically grounded representations throughout its depth. Empirical results on real-world datasets show that our models produce more interpretable embeddings, support more effective interventions, and learn concept representations that are both meaningful and hierarchically structured.

ICML 2026

XRPO: Pushing the Limits of GRPO with Targeted Exploration and Exploitation

Udbhav Bamba, Minghao Fang, Yifan Yu, Haizhong Zheng, Fan Lai

Reinforcement learning algorithms such as GRPO have driven recent advances in large language model (LLM) reasoning. While scaling the number of rollouts stabilizes training, existing approaches suffer from limited exploration on challenging prompts and leave informative feedback signals underexploited, due to context-independent rollout allocation across prompts (e.g., generating 16 rollouts per prompt) and relying heavily on sparse rewards. This paper presents XRPO (eXplore–eXploit GRPO), a unified framework that recasts policy optimization through the principled lens of rollout exploration–exploitation. To enhance exploration, XRPO introduces a mathematically grounded rollout allocator that adaptively prioritizes prompts with higher potential for uncertainty reduction. It further addresses stagnation on zero-reward prompts through an in-context seeding strategy that injects curated exemplars, steering the model into more difficult reasoning trajectories. To strengthen exploitation, XRPO develops a group-relative, novelty-aware advantage sharpening mechanism that leverages sequence likelihoods to amplify low-probability yet correct responses, thereby extending the policy’s reach beyond sparse rewards. Experiments across diverse math and coding benchmarks on both reasoning and non-reasoning models demonstrate that XRPO outperforms existing advances (e.g., GRPO and GSPO) up to 4% pass@1 and 6% cons@32, while accelerating training convergence by up to 2.7x.

ICML 2026

On the Infinite Width and Depth Limits of Predictive Coding Networks

Francesco Innocenti, El Mehdi Achour, Rafal Bogacz

Predictive coding (PC) is a biologically plausible alternative to standard backpropagation (BP) that minimises an energy function with respect to network activities before updating weights. Recent work has improved the training stability of deep PC networks (PCNs) by leveraging some BP-inspired reparameterisations. However, the full scalability and theoretical basis of these methods remain unclear. To address this gap, we study the infinite width and depth limits of PCNs. For linear residual networks, we show that the set of width- and depth-stable feature-learning parameterisations for PC is exactly the same as for BP. Moreover, under any of these parameterisations, the PC energy with equilibrated activities converges to the quadratic BP loss when the model width is much larger than the depth, resulting in PC computing the same gradients as BP. Experiments show that, as long as an activity equilibrium is reached, convergence to BP holds for nonlinear models including convolutional networks and transformers. Overall, this work constrains the types of parameterisation that are scalable with PC, while showing a way in which BP can be effectively implemented with only local updates in much wider than deep networks like the brain.

ICML 2026

Adaptive Personalized Federated Learning via Multi-task Averaging of Kernel Mean Embeddings

Jean-Baptiste Fermanian, Batiste Le Bars, Aurélien Bellet

Personalized Federated Learning enables a collection of agents to collaboratively learn individual models without sharing raw data. We propose a new approach in which each agent optimizes a weighted combination of all agents' empirical risks, with the weights learned from data rather than specified a priori. The novelty of our method lies in formulating the estimation of these collaborative weights as a kernel mean embedding estimation problem with multiple data sources, leveraging tools from multi-task averaging to capture statistical relationships between agents. This perspective yields a fully adaptive procedure that requires no prior knowledge of data heterogeneity and automatically transitions between global and local learning regimes. By recasting the objective as a high-dimensional mean estimation problem, we derive finite-sample guarantees on local excess risks for a broad class of distributions, explicitly quantifying the statistical gains of collaboration. To address communication constraints inherent to federated settings, we also propose a practical implementation based on random Fourier features, which allows one to trade communication cost for statistical efficiency. Numerical experiments validate our theoretical results.

ICML 2026

Beyond Sample-Level Forgetting: Improving Reliability in Multimodal Unlearning

Jianzhou Wang, Yirui Wu, Lixin Yuan, Wenxiao Zhang, Jun Liu

Multimodal unlearning aims to eliminate specific data from pretrained multimodal models, which offers significant advantages in data privacy and model efficiency. Current methods struggle to achieve the desired properties of effectiveness, reliability and locality, due to the complex interdependency of unimodal and multimodal knowledge. By introducing a causal perspective, we propose multimodal unlearning with decoupled knowledge components. To promote fine-grained understanding of multimodal context, we introduce Multimodal Variational Inference (MVI) to infer modal-specific and -consistent factors with incomplete sample observation. With foundation of decoupled knowledge, we propose contrastive semantic editing to regulate multimodal unlearning towards refined forgetting. Experiments on privacy- and copyright-sensitive scenarios validate effectiveness of our method across multiple scenarios, ensuring the unlearned model maintains high reliability and locality.

ICML 2026

Calibrated Knowledge Aggregation in Bayesian Mixture-of-Experts for Continual VQA

Mahsa Mozaffari, Hitesh Sapkota, Yu Kong, Xumin Liu, Qi Yu

Continual learning for visual question answering (VQA) is typically implemented by training one expert per task and routing each query using task-ID supervision. Yet continual VQA tasks overlap substantially: on the VQA-v2 task stream, a non-native expert outperforms the task’s own expert on $49.9\%$ of queries, so hard routing both wastes transferable knowledge and can be confidently wrong when mismatched. We propose a calibrated Bayesian mixture-of-experts that trains parameter-efficient per-task adapters, learns routing by directly maximizing expected VQA utility, and marginalizes expert identity at inference via Bayesian aggregation in a unified answer space; an entropy penalty prevents the utility objective from collapsing to one-hot routing, enabling evidence pooling across plausible experts. We reach $64.16$ accuracy with $0.63$ forgetting on VQA-v2 CL-LS ($+5.74\%$ accuracy, $-2.99$ forgetting vs. the strongest prior method), $78.81$ with $0.40$ forgetting on TDIUC CL-LS ($+3.10$, $-1.74$), and $83.41$ with $3.21$ forgetting on TDIUC CL-VS ($+1.58$, $-0.82$). Calibration also improves on VQA-v2, reducing ECE from $0.15$ to $0.07$.

ICML 2026

RDT2: Exploring the Scaling Limit of UMI Data Towards Zero-Shot Cross-Embodiment Generalization

Songming Liu, Bangguo Li, Kai Ma, Lingxuan Wu, Hengkai Tan, Xiao Ouyang, Hang Su, Jun Zhu

Vision-Language-Action (VLA) models hold promise for generalist robotics but currently struggle with data scarcity, architectural inefficiencies, and the inability to generalize across different hardware platforms. We introduce RDT2, a robotic foundation model built upon a 7B parameter VLM designed to enable zero-shot deployment on novel embodiments for open-vocabulary tasks. To achieve this, we collected one of the largest open-source robotic datasets—over $10,000$ hours of demonstrations in diverse families—using an enhanced, embodiment-agnostic Universal Manipulation Interface (UMI). Our approach employs a novel three-stage training recipe that aligns discrete linguistic knowledge with continuous control via Residual Vector Quantization (RVQ), flow-matching, and distillation for real-time inference. Consequently, RDT2 becomes one of the first models that simultaneously zero-shot generalizes to unseen objects, scenes, instructions, and even robotic platforms. Besides, it outperforms state-of-the-art baselines in dexterous, long-horizon, and dynamic downstream tasks like playing table tennis.

ICML 2026

When Single Answer Is Not Enough: Rethinking Single-Step Retrosynthesis Benchmarks for LLMs

Bogdan Zagribelnyy, Ivan Ilin, Maksim Kuznetsov, Nikita Bondarev, Roman Schutski, Thomas MacDougall, Rim Shayakhmetov, Zulfat Miftahutdinov, Mikolaj Mizera, Vladimir Aladinskiy, Alex Aliper, Alex Zhavoronkov

Recent progress has expanded the use of large language models (LLMs) in drug discovery, including synthesis planning. However, objective evaluation of retrosynthesis performance remains limited. Existing benchmarks and metrics typically rely on published synthetic procedures and Top-K accuracy based on single ground-truth, which does not capture the open-ended nature of real-world synthesis planning. We propose a new benchmarking framework for single-step retrosynthesis that evaluates both general-purpose and chemistry-specialized LLMs using ChemCensor, a novel metric for chemical plausibility. By emphasizing plausibility over exact match, this approach better aligns with human synthesis planning practices. We also introduce CREED, a novel dataset comprising millions of ChemCensor-validated reaction records for LLM training, and use it to train a model that improves over the LLM baselines under this benchmark.

ICML 2026

Align Your Trajectory Tangent: Training Better Consistency Models via Manifold-Aligned Tangents

Beomsu Kim, ByungHee Cha, Jong Chul Ye

With diffusion and flow matching models achieving state-of-the-art generating performance, the interest of the community now turned to reducing the inference time without sacrificing sample quality. Consistency Models (CMs), which are trained to be consistent on diffusion or probability flow ordinary differential equation (PF-ODE) trajectories, enable one or two-step flow or diffusion sampling. However, CMs typically require prolonged training with large batch sizes to obtain competitive sample quality. In this paper, we examine the training dynamics of CMs near convergence and discover that CM trajectory tangents -- CM output update directions -- are quite oscillatory, in the sense that they move parallel to the data manifold, not towards the manifold. To mitigate oscillatory trajectory tangents, we propose a new loss function, called the {\em manifold feature distance (MFD)}, which provides manifold-aligned trajectory tangents that point toward the data manifold. Consequently, our method -- dubbed {\em Align Your Trajectory Tangent (AYT)} -- can accelerate CM training by orders of magnitude and even out-perform the learned perceptual image patch similarity metric (LPIPS). Furthermore, we find that our loss enables training with extremely small batch sizes without compromising sample quality. Code is available at \url{https://github.com/1202kbs/AYT}

ICML 2026

IdEst: Assessing Self-Supervised Learning Representations via Intrinsic Dimension

Julie Mordacq, Vicky Kalogeiton, Steve Oudot

Self-supervised learning (SSL) has emerged as a powerful paradigm for learning meaningful representations from unlabeled data. However, the standard protocol for evaluating these representations, linear probing, is computationally expensive, sensitive to hyperparameters, and provides limited insight into the geometric structure of the representation space. In this work, motivated by connections between neural network generalization and intrinsic dimension (ID) we propose IdEst, a method for estimating the ID of SSL representations via the Minimum Spanning Tree dimension estimator ($\mathrm{dim}_\mathrm{MST}$). Across diverse datasets, architectures, and SSL pretraining objectives, we show that IdEst strongly correlates with downstream linear probe performances. Furthermore, we demonstrate that IdEst enables efficient hyperparameter selection, significantly reducing the computational cost compared to supervised alternatives. Our results highlight intrinsic dimensionality as a principled geometric proxy for assessing SSL representations, complementing standard supervised probing protocols.

ICML 2026

PhysHanDI: Physics-Based Reconstruction of Hand-Deformable Object Interactions

Jihyun Lee, Changmin Lee, Donghwan Kim, Tae-Kyun Kim

While existing methods for reconstructing hand–object interactions have made impressive progress, they either focus on rigid or part-wise rigid objects—limiting their ability to model real-world objects (e.g., cloth, stuffed animals) that exhibit highly non-rigid deformations—or model deformable objects without full 3D hand reconstruction. To bridge this gap, we present PhysHanDI (Physics-based Reconstruction of Hand and Deformable Object Interactions), a framework that enables full 3D reconstruction of both interacting hands and non-rigid objects. Our key idea is to physically simulate object deformations driven by forces induced from densely reconstructed 3D hand motions, ensuring that the reconstructed object dynamics are both physically plausible and coherent with the interacting hand movements. Furthermore, we demonstrate that such simulation of object deformations can, in turn, refine and improve hand reconstruction via inverse physics. In experiments, PhysHanDI outperforms the state-of-the-art baseline across reconstruction and future prediction.

ICML 2026

Minibatch Optimal Transport and Perplexity Bound Estimation in Discrete Flow Matching

Etrit Haxholli, Yeti Z. Gurbuz, Oğul Can, Eli Waxman

Discrete flow matching, a recent framework for modeling categorical data, has shown competitive performance with autoregressive models. However, unlike continuous flow matching, the rectification strategy cannot be applied due to the stochasticity of discrete paths, necessitating alternative methods to minimize state transitions. We propose a dynamic-optimal-transport-like minimization objective and derive its Kantorovich formulation for discrete flows with convex interpolants, where transport cost depends solely on inter-state dissimilarity and can be optimized via minibatch strategies. We show that such methods can reduce the number of transitions up to 32 times (1024 to 32) to reach the same generative perplexity without compromising diversity. Additionally, path nondeterminism in discrete flows precludes an instantaneous change-of-variables analogue, preventing precise probability estimation available to continuous flows. We therefore propose two upper bounds on perplexity, enabling principled training, evaluation and model comparison. Finally, we introduce Multimask Flows which outperform masked flows in generative perplexity without compromising diversity, particularly when utilizing minibatch Optimal Transport.

ICML 2026

A Theoretical Framework for Statistical Evaluability of Generative Models

Shashaank Aiyer, Yishay Mansour, Shay Moran, Han Shao

Statistical evaluation aims to estimate the generalization performance of a model using held-out i.i.d. test data sampled from the ground-truth distribution. In supervised learning settings such as classification, performance metrics such as error rate are well-defined, and test error reliably approximates population error given sufficiently large datasets. In contrast, evaluation is more challenging for generative models due to their open-ended nature: it is unclear which metrics are appropriate and whether such metrics can be reliably evaluated from finite samples. In this work, we introduce a theoretical framework for evaluating language models and establish evaluability results for commonly used metrics. We study two categories of metrics: test-based metrics, including integral probability metrics (IPMs), and similarity-based metrics, including Rényi and KL divergences. We show that IPMs with respect to any bounded test class can be evaluated from finite samples up to multiplicative and additive approximation errors. Moreover, when the test class has finite fat-shattering dimension, IPMs can be evaluated with arbitrary precision. In contrast, similarity-based metrics, including Rényi and KL divergences, are not evaluable from finite samples, as their values can be critically determined by rare events. We also analyze the potential and limitations of perplexity as an evaluation method.

ICML 2026

$L^3$: Large Lookup Layers

Albert Tseng, Christopher De Sa

Modern sparse language models typically achieve sparsity through Mixture-of-Experts (MoE) layers, which dynamically route tokens to dense MLP "experts." However, dynamic hard routing has a number of drawbacks, such as potentially poor hardware efficiency and needing auxiliary losses for stable training. In contrast, the tokenizer embedding table, which is natively sparse, largely avoids these issues by selecting a single embedding per token at the cost of not having contextual information. In this work, we introduce the Large Lookup Layer (L3), which generalizes embedding tables to model decoder layers as a means of further scaling sparsity. L3 layers use static token-based routing to aggregate a *set* of learned embeddings per token in a *context-dependent way*, allowing the model to efficiently balance memory and compute by caching information in embeddings. L3 has two main components: (1) a systems-friendly architecture that allows for fast training and CPU-offloaded inference with no overhead, and (2) an information-theoretic embedding allocation algorithm that effectively balances speed and quality. We empirically test L3 by training transformers with up to 2.6B active parameters and find that L3 strongly outperforms both dense models and iso-sparse MoEs in both language modeling and downstream tasks.

Keep browsing

More papers from top AI conferences

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