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

Safety Alignment of LMs via Non-cooperative Games

Anselm Paulus, Ilia Kulikov, Brandon Amos, Rémi Munos, Ivan Evtimov, Kamalika Chaudhuri, Arman Zharmagambetov

Ensuring the safety of language models (LMs) while maintaining their usefulness remains a critical challenge in AI alignment. Current approaches rely on sequential adversarial training: generating adversarial prompts and fine-tuning LMs to defend against them. We introduce a different paradigm: framing safety alignment as a non-zero-sum game between an Attacker LM and a Defender LM trained jointly via online reinforcement learning. Each LM continuously adapts to the other's evolving strategies, driving iterative improvement. Our method uses a preference-based reward signal derived from pairwise comparisons instead of point-wise scores, providing more robust supervision and potentially reducing reward hacking. Our RL recipe, AdvGame, shifts the Pareto frontier of safety and utility, yielding a Defender LM that is simultaneously more helpful and more resilient to adversarial attacks. In addition, the resulting Attacker LM converges into a strong, general-purpose red-teaming agent that can be directly deployed to probe arbitrary target models. Code at github.com/facebookresearch/advgame.

ICML 2026

Riemannian MeanFlow

Dongyeop Woo, Marta Skreta, Seonghyun Park, Kirill Neklyudov, Sungsoo Ahn

Diffusion and flow models have become the dominant paradigm for generative modeling on Riemannian manifolds, with successful applications in protein backbone generation and DNA sequence design. However, these methods require tens to hundreds of neural network evaluations at inference time, which can become a computational bottleneck in large-scale scientific sampling workflows. We introduce Riemannian MeanFlow (RMF), a framework for learning flow maps directly on manifolds, enabling high-quality generations with as few as one forward pass. We derive three equivalent characterizations of the manifold average velocity (Eulerian, Lagrangian, and semigroup identities), and analyze parameterizations and stabilization techniques to improve training on high-dimensional manifolds. In promoter DNA design and protein backbone generation settings, RMF achieves comparable sample quality to prior methods while requiring up to 10$\times$ fewer function evaluations. Finally, we show that few-step flow maps enable efficient reward-guided design through reward look-ahead, where terminal states can be predicted from intermediate steps at minimal additional cost.

ICML 2026

Scaling Inference-Time Computation via Opponent Simulation: Enabling Online Strategic Adaptation in Repeated Negotiation

Xiangyu Liu, Di Wang, Zhe Feng, Aranyak Mehta

While large language models (LLMs) have emerged as powerful decision-makers across a wide range of single-agent and stationary environments, fewer efforts have been devoted to settings where LLMs must engage in \emph{repeated} and \emph{strategic} interactions with unknown or dynamic opponents. In such settings, recipes built upon \emph{offline} pre-training or fine-tuning, though robust against worst-case adversaries, do not fully exploit the capability of LLMs to adapt \emph{online} based on interaction feedback. Instead, we explore the more natural perspective of \emph{scaling inference-time computation} as a mechanism for adaptation, embedding the principles of a classical game-theoretical learning dynamic, \emph{smooth Fictitious Play (sFP)}, into LLM inference: (i) for belief formation, we employ an auxiliary opponent model that in-context learns to imitate the \emph{time-averaged} behavior of the opponent; (ii) for best response, we advance best-of-$N$ (BoN) sampling by simulating against the opponent model. Empirical evaluations on two distinct forms of repeated negotiation games demonstrate that our method enables significant performance improvement over online interaction compared to various baselines, offering a scalable and principled approach to strategic decision-making without any parameter updates.

ICML 2026

The Information Geometry of Softmax: Probing and Steering

Kiho Park, Todd Nief, Yo Joong Choe, Victor Veitch

This paper concerns the question of how AI systems encode semantic structure into the geometric structure of their representation spaces. The motivating observation is that the natural geometry of these representation spaces should reflect the way models use representations to produce behavior. We focus on the important special case of representations that define softmax distributions. In this case, we argue that the natural geometry is information geometry. Our focus is on the role of information geometry on semantic encoding and the linear representation hypothesis. As an illustrative application, we develop *dual steering*, a method for robustly steering representations to exhibit a particular concept using linear probes. We prove that dual steering optimally modifies the target concept while minimizing changes to off-target concepts. Empirically, we find that dual steering enhances the controllability and stability of concept manipulation.

ICML 2026

Hyperbolic RQ-VAE enhanced Generative Recommendation with Differential-Length Codebook Strategy

Aoran Zhang, Yu-Bin Yang, Yonghong Yu

Recently, the integration of large language models (LLMs) with generative recommendation (GR) has demonstrated promising potential. However, most existing GR methods adopt residual quantization to implicitly model hierarchical relationships across codebook layers in Euclidean space, which distorts the intrinsic tree-like hierarchy and leads to low codebook utilization. To address these issues, we propose a Hyperbolic RQ-VAE enhanced Generative Recommendation, namely HG-Rec. Specifically, HG-Rec enhances the residual quantization mechanism by embedding the latent discrete representations into hyperbolic space to explicitly model hierarchical relationships across codebook layers. Motivated by the exponential volume growth of hyperbolic space, we further design a differential-length codebook strategy, i.e. the codebook size follows a pyramidal structure, which aligns with the tree-like structure and effectively compresses the codebook size. Hence, benefiting from the alignment of hyperbolic geometry and codebook hierarchy, HG-Rec achieves lower collision rates, more uniform codebook usage, and less training time compared to existing methods. Extensive experiments across multiple benchmark datasets demonstrate that HG-Rec consistently achieves state-of-the-art performance. The code is available in the https://github.com/zar123123/HG-Rec.

ICML 2026

Prism-MoE: Efficient Dense-to-MoE Conversion for Visual Autoregressive Generation

Ying Li, Zefang Wang, Zhaode Wang, Zhiwen Chen, chengfei lv, Huan Wang

Scaling up visual autoregressive models improves generation quality but incurs substantial inference costs. Mixture-of-Experts (MoE) architectures mitigate this issue through sparse activation and have proven effective in large language models. However, training MoE models from scratch remains prohibitively expensive, and dense-to-MoE conversion for visual autoregressive models is still underexplored. To enable *low-cost and high-quality dense-to-MoE conversion*, we propose **Prism-MoE**, an efficient framework for transforming pretrained dense visual autoregressive models into sparse MoE models. Prism-MoE consists of two key components. First, we introduce trajectory-consistent Initialization, which formulates expert initialization as a principled decomposition problem and preserves the generation trajectory of pretrained models. Second, we propose a confidence-adaptive sparse fine-tuning framework that aligns expert specialization with the information density of visual tokens via confidence-aware routing supervision. Experiments show that Prism-MoE achieves dense-to-MoE conversion with less than **10\%** of the standard training budget, while maintaining generation quality comparable to dense baselines with only **37.5\%** active parameters.

ICML 2026

UMEM: Unified Memory Extraction and Management Framework for Generalizable Memory

Yongshi Ye, Hui Jiang, Feihu Jiang, Tian Lan, Yichao Du, Biao Fu, Xiaodong Shi, Qianghuai Jia, Longyue Wang, Weihua Luo

Self-evolving memory serves as the trainable parameters for Large Language Models (LLMs)-based agents, where extraction (distilling insights from experience) and management (updating the memory bank) must be tightly coordinated. Existing methods predominantly optimize memory management while treating memory extraction as a static process, resulting in poor generalization, where agents accumulate instance-specific noise rather than robust memories. To address this, we propose Unified Memory Extraction and Management (UMEM), a self-evolving agent framework that jointly optimizes a LLM to simultaneously extract and manage memories. To mitigate overfitting to specific instances, we introduce Semantic Neighborhood Modeling and optimize the model with a neighborhood-level marginal utility reward via GRPO. This approach ensures memory generalizability by evaluating memory utility across clusters of semantically related queries. Extensive experiments across five benchmarks demonstrate that UMEM significantly outperforms highly competitive baselines, achieving up to 11.49 points improvement in multi-turn interactive tasks. Furthermore, UMEM maintains a stable improvement trend during continuous evolution.

ICML 2026

$\text{DT}^\text{2}$: Decision-Targeted Digital Twins

Harry Amad, Mihaela van der Schaar

A digital twin (DT) is a virtual model of a real-world system that can assist decision-making by simulating scenarios induced by different policies. However, typical machine learning-based DTs do not optimise for this use case. We prove that, when model capacity is limited, training DTs to minimise one-step transition errors can produce suboptimal models for ranking sets of policies according to a reward function. We further show that this holds empirically, even with expressive model classes. To address this, we introduce DT$^2$, a decision-targeted DT training paradigm. Firstly, DT$^2$ uses fitted Q-evaluation to estimate values of candidate policies from offline data. A DT is then trained to generate rollouts that preserve pairwise policy rankings derived from these proxy ground-truth values with an architecture-agnostic loss function. We empirically demonstrate the efficacy of our method across a range of settings and architectures. DT$^2$ consistently improves policy ranking and reduces decision regret during policy selection relative to conventional DT training, both for policies used during training and for unseen policies, while maintaining a good level of raw simulation fidelity.

ICML 2026

Universal Multiclass Transductive Online Learning

Steve Hanneke, Hongao Wang

We consider the problem of universal transductive online classification with a possibly unbounded label space. This setting considers online learning, with the sequence of instances (without labels) known to the learner in advance. We say a concept class $\mathcal{H}$ is learnable if there is a learning algorithm $\mathcal{A}$, such that for every realizable sequence, the number of mistakes made by $\mathcal{A}$ grows at most sublinearly with the number of predictions. We characterize the learnability of this setting and show that there are only two possible optimal rates for the learnable classes: either bounded or increasing logarithmically. We introduce a new combinatorial structure, called "Level-Constrained-Littlestone-Littlestone (LCLL) tree", which, along with the indifference property, characterizes the learnability. We also extend the learnability result to the agnostic case and the case where only the stochastic process that generates the instance sequence is known.

ICML 2026

When Agents Go Rogue: Activation-Based Detection of Malicious Behaviors in Multi-Agent Systems

Haowen Xu, Xue Tan, Lei Ma, Zhihao Zhang, Chao Wang, Qingze Wang, Ping Chen, Jun Dai, Xiaoyan Sun

While enabling effective collaboration on complex tasks, LLM-based Multi-Agent Systems (MAS) face critical security challenges due to vulnerabilities at the agent and interaction levels. Most existing MAS security defenses are built upon two core assumptions: semantically-explicit malicious attacks and explicit graph-based modeling of the MAS topology and agent-level interactions. In practice, real-world attacks are becoming more semantically stealthy, while MAS execution is typically asynchronous without the temporal alignment assumed by graph-based propagation models. To address these limitations, we propose AcMAS, an activation-based framework for malicious-behavior detection in MAS. By analyzing internal reasoning states in the activation space of local agents, AcMAS detects even stealthy attacks in a synchronization-robust fashion, without relying on explicit interaction graphs. Moreover, our activation analysis provides critical signals to guide AcMAS in restoring the functionality of compromised agents, rather than the disruptive agent isolation commonly used by the state-of-the-art methods. Comprehensive evaluation demonstrates that AcMAS significantly outperforms graph-based baselines against stealthy attacks, by +0.22 F1 in synchronous settings (0.94 vs. 0.72) and by +0.55 F1 in asynchronous settings (0.93 vs. 0.38), with generalization across diverse open-source LLM backbones, attack intensity, and MAS scale.

ICML 2026

Policy Search via Bayesian Optimization with Temporal Difference Gaussian Processes

Armin Lederer, Anuj Srivastava, Marco Bagatella, Andreas Krause

Bayesian optimization (BO) is a method commonly used for policy search in problems with low-dimensional policy parameterizations. While it is generally considered data-efficient, existing BO approaches are agnostic to the sequential structure of the optimization objective induced by policy roll-outs. Thereby, valuable information is discarded that could improve the convergence of BO. We address this inefficiency by developing and rigorously analyzing a novel approach for BO that relies on a temporal difference learning formulation for discounted infinite-horizon value functions based on Gaussian process (GP) regression. We derive learning error bounds for the proposed temporal difference GPs, such that we can exploit upper confidence bounds to analyze the cumulative regret of our BO approach. This analysis is further refined by bounding the maximal information gain for our temporal difference GP model. In a comparison with relevant baseline methods, we demonstrate the practical advantages of our method.

ICML 2026

Variational Adapter for Cross-modal Similarity Representation

WenZhang Wei, Zhipeng Gui, Dehua Peng, Tiandi Ye, Huayi Wu

The core of vision-language models lies in measuring cross-modal similarity within a unified representation space. However, most image-text matching or multi-class image classification datasets lack fine-grained cross-modal matching annotations, forcing the continuous similarity space into binary classification boundaries. This compression induces false negative samples and significantly impairs the generalization performance of cross-modal tasks. While prior research has attempted to mitigate this by modeling intra-modal ambiguity, it often overlooks inherent annotation flaws, leading to suboptimal uncertainty allocation. To address these challenges, we propose a Variational Adapter for Cross-modal Similarity Representation (VACSR). This approach reformulates image-text matching with fine-grained semantic scarcity as a variational inference problem. It constructs a latent space for cross-modal similarity and uses regularization techniques to mitigate overfitting to binary annotations. Experiments on image-text retrieval, domain generalization, and base-to-novel generalization demonstrate the proposed method’s effectiveness and robust generalization ability.

ICML 2026

CVE-Factory: Scaling Expert-Level Agentic Tasks for Code Security Vulnerability

Xianzhen Luo, Jingyuan Zhang, Shiqi Zhou, JinYang Huang, Chuan Xiao, Qingfu Zhu, Zhiyuan Ma, Yue Xing, Yang Yue, Wencong Zeng, Wanxiang Che

Evaluating and improving the security capabilities of code agents requires high-quality, executable vulnerability tasks. However, existing works rely on costly, unscalable manual reproduction and suffer from outdated data distributions. To address these, we present CVE-Factory, the first multi-agent framework to achieve expert-level quality in automatically transforming sparse CVE metadata into fully executable agentic tasks. Cross-validation against human expert reproductions shows that CVE-Factory achieves 95\% solution correctness and 96\% environment fidelity, confirming its expert-level quality. It is also evaluated on the latest realistic vulnerabilities and achieves a 66.2\% verified success. This automation enables two downstream contributions. First, we construct LiveCVEBench, a continuously updated benchmark of 190 tasks spanning 14 languages and 153 repositories that captures emerging threats including AI-tooling vulnerabilities. Second, we synthesize over 1,000 executable training environments, the first large-scale scaling of agentic tasks in code security. Fine-tuned Qwen3-32B improves from 5.3\% to 35.8\% on LiveCVEBench, surpassing Claude 4.5 Sonnet, with gains generalizing to Terminal Bench (12.5\% to 31.3\%). We open-source all code, data, and models.

ICML 2026

Online Rubrics Elicitation from Pairwise Comparisons

MohammadHossein Rezaei, Robert Vacareanu, Zihao Wang, Clinton Wang, Bing Liu, Yunzhong He, Afra Feyza Akyürek

Rubrics provide a flexible way to train LLMs on open-ended long-form answers where verifiable rewards are not applicable and human preferences provide coarse signals. Prior work shows that reinforcement learning with rubric-based rewards leads to consistent gains in LLM post-training. Most existing approaches rely on rubrics that remain static over the course of training. Such static rubrics, however, are vulnerable to reward-hacking type behaviors and fail to capture emergent desiderata that arise during training. We introduce Online Rubrics Elicitation (OnlineRubrics), a method that dynamically curates evaluation criteria in an online manner through pairwise comparisons of responses from current and reference policies. This online process enables continuous identification and mitigation of errors as training proceeds. Empirically, this approach yields consistent improvements of up to 8% over training exclusively with static rubrics across AlpacaEval, GPQA, ArenaHard as well as the validation sets of expert questions and rubrics. We qualitatively analyze the elicited criteria and identify prominent themes such as transparency, practicality, organization, and reasoning.

ICML 2026

EigenCache: Rethinking Diffusion Acceleration as Covariance-Optimal Forecasting and Submodular Information Allocation

Chenyang Xu, Dezhen Wang, Lin Chen, Kepeng Lin, Hao Wang

Accelerating diffusion models via feature caching has progressed from static feature reuse to polynomial extrapolation, yet current cache-then-forecast strategies still rely on hand-crafted approximation families (e.g., Taylor or Hermite bases) that can misalign with the non-stationary, layer-specific dynamics of generative features. This paper introduces EigenCache, a training-free framework that re-frames diffusion acceleration as covariance-adaptive feature forecasting and uncertainty-aware temporal design. EigenCache models cached feature trajectories as time-indexed stochastic processes and estimates layer-wise temporal kernels from a small calibration set. Under the resulting scalar temporal-kernel approximation, the Gaussian-process posterior mean, i.e., Kriging, is risk-optimal within the scalar-weighted linear predictor class; under joint Gaussianity, it further coincides with the MMSE estimator. This formulation generalizes fixed-basis forecasting from a covariance-adaptive perspective while providing a closed-form posterior-variance proxy for prediction uncertainty. Leveraging this proxy, EigenCache selects computation anchors by maximizing a log-determinant information-gain objective over denoising timesteps, a monotone submodular objective with a near-optimal greedy solution. Across image, video, transformer, U-Net, and LoRA-adapted diffusion models, EigenCache achieves a strong speed--fidelity Pareto frontier and provides a principled mechanism for robust compute allocation.

ICML 2026

Risk-Averse and Optimistic Advertiser Incentive Compatibility in Auto-bidding

Christopher Liaw, Wennan Zhu

The rise of auto-bidding in online advertising has created new challenges for ensuring advertiser incentive compatibility, particularly when advertisers delegate bidding to agents with high-level constraints. One challenge is the multiplicity of equilibria with reported constraints. Alimohammadi et al. (2023) proposed a notion of Auto-bidding Incentive Compatibility (AIC) which serves to highlight that standard auctions may not incentivize truthful reporting of these constraints. However, their definition of AIC is very stringent as it requires that the worst-case outcome of an advertiser's truthful report is at least as good as the best-case outcome of any of the advertiser's possible deviations. In this paper, we introduce two refined and relaxed concepts: Risk-Averse Auto-bidding Incentive Compatibility (RAIC) and Optimistic Auto-bidding Incentive Compatibility (OAIC). RAIC (OAIC) stipulates that truthful reporting is preferred if its least (most) favorable equilibrium outcome is no worse than the least (most) favorable equilibrium outcome from any misreport. We demonstrate that SPA satisfies both RAIC and OAIC. These findings clarify SPA's incentive properties under auto-bidding, specifically regarding advertiser perspectives on equilibrium selection.

ICML 2026

Benchmarking at the Edge of Comprehension

Samuele Marro, Jialin Yu, Emanuele La Malfa, Oishi Deb, Jiawei Li, Yibo Yang, Ebey Abraham, Sunando Sengupta, Eric Sommerlade, Michael J. Wooldridge, Philip Torr

As frontier Large Language Models (LLMs) increasingly saturate new benchmarks shortly after they are published, benchmarking itself is at a juncture: if frontier models keep improving, it will become increasingly hard for humans to generate discriminative tasks, provide accurate ground-truth answers, or evaluate complex solutions. If benchmarking becomes infeasible, our ability to measure any progress in AI is at stake. We refer to this scenario as the *post-comprehension regime*. In this work, we propose Critique-Resilient Benchmarking, an adversarial framework designed to compare models even when full human understanding is infeasible. Our technique relies on the notion of *critique-resilient correctness*: an answer is deemed correct if no adversary has convincingly proved otherwise. Unlike standard benchmarking, humans serve as bounded verifiers and focus on localized claims, which preserves evaluation integrity beyond full comprehension of the task. Using an itemized bipartite Bradley-Terry model, we jointly rank LLMs by their ability to solve challenging tasks and to generate difficult yet solvable questions. We showcase the effectiveness of our method in the mathematical domain across eight frontier LLMs, showing that the resulting scores are stable and correlate with external capability measures. Our framework reformulates benchmarking as an adversarial generation-evaluation game in which humans serve as final adjudicators.

ICML 2026

Active Curriculum Refinement for Reinforcement Learning

Zhenya Liu, Yuxin Chen

In many RL domains, environments are linked by prerequisite relations—e.g., difficulty-increasing edits or parameter increments—which induce a directed acyclic curriculum graph (DAG). In practice, this structure is often exploited only implicitly, yet it can yield clear gains in training. We introduce PATH, a curriculum learning framework that performs active learning on the curriculum graph. PATH first expands coverage by sampling diverse curriculum paths, then reallocates training toward regions that remain unmastered. Experiments show that PATH leverages the graph structure to achieve strong robustness and generalization across diverse environments.

ICML 2026

PolicyGuard: Towards Test-time and Step-level Adversary Defense for Reinforcement Learning Agent

Junfeng Guo, Heng Huang

While real-world applications of reinforcement learning (RL) are becoming increasingly popular, the security of RL systems deserve more attention and exploration. In particular, recent work has revealed that RL agents are vulnerable to backdoor attacks, where a victim agent behaves normally under standard conditions but executes malicious actions when a specific trigger is activated. Existing backdoor defenses for RL either require access to the agent’s internal parameters, operate only at the model or trajectory level, or are limited to specific attack types. To ensure the security of RL agents, we propose PolicyGuard, a test-time step-level backdoor defense which leverages Gaussian Process (GP) posterior variance and adapts pseudo trajectories to enable uncertainty computation for individual time step. Besides, we also provide theoretical foundations to explain the efficacy of GP posterior variance. Extensive experiments across seven RL games demonstrate that PolicyGuard achieves state-of-the-art detection performance in most cases, with average AUROC of 0.856 for perturbation-based attacks and 0.859 for adversary-agent attacks.

ICML 2026

Efficient numeracy in language models through single-token number embeddings

Linus Kreitner, Paul Hager, Jonathan Mengedoht, Georgios Kaissis, Daniel Rueckert, Martin J. Menten

To drive progress in science and engineering, large language models (LLMs) must be able to process large amounts of numerical data and solve long calculations efficiently. This is currently only possible through the use of external tools or extensive reasoning chains, either weakening the numerical representations of LLMs or limiting the length of problems they can solve. We show that frontier LLMs require excessive amounts of reasoning tokens to solve even basic calculations, which is exacerbated by their tokenization strategies that split single numbers into multiple tokens. This motivates the need for efficient and effective single-token number encodings. We introduce a set of desiderata for such encodings and show that existing approaches fail to fulfill them. To address these shortcomings, we propose BitTokens, a novel encoding strategy that represents any number as a single token using its IEEE 754 binary floating-point representation. Through extensive experiments we show that our BitTokens allow even small language models to learn algorithms that solve basic arithmetic operations nearly perfectly. This newly gained efficiency could expand the length and complexity of problems language models can solve.

Keep browsing

More papers from top AI conferences

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