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

The Power of Power Law: Asymmetry Enables Compositional Reasoning

Zixuan Wang, Xingyu Dang, Jason D. Lee, Kaifeng Lyu

Natural language data follows a power-law distribution, with most knowledge and skills appearing at very low frequency. While a common intuition suggests that reweighting or curating data toward a uniform distribution may help models better learn these long-tail skills, we find a counterintuitive result: across a wide range of compositional reasoning tasks, such as state tracking and multi-step arithmetic, training under power-law distributions consistently outperforms training under uniform distributions. To understand this advantage, we introduce a minimalist skill-composition task and show that learning under a power-law distribution provably requires significantly less training data. Our theoretical analysis reveals that power law sampling induces a beneficial asymmetry that improves the pathological loss landscape, which enables models to first acquire high-frequency skill compositions with low data complexity, which in turn serves as a stepping stone to efficiently learn rare long-tailed skills. Our results offer an alternative perspective on what constitutes an effective data distribution for training models.

ICML 2026

Meta Flow Maps enable scalable reward alignment

Peter Potaptchik, Adhi Saravanan, Abbas Mammadov, Alvaro Prat, Michael Samuel Albergo, Yee Whye Teh

Controlling generative models—whether via inference-time steering or fine-tuning—is expensive. Control relies on estimating the value function—typically necessitating costly trajectory simulations. To eliminate this bottleneck, we introduce *Meta Flow Maps (MFMs)*, stochastic extensions of consistency models and flow maps. MFMs are trained to perform \textbf{one-step posterior sampling}, generating arbitrarily many i.i.d. draws of clean data $x_1$ from any noisy state $x_t$. Crucially, these samples are differentiable in the conditioning state $x_t$, unlocking efficient estimation of the value function gradient. We leverage this capability to enable both **inference-time steering** without inner rollouts, and unbiased, off-policy **fine-tuning** to general rewards. Among our fine-tuning and steering experiments on ImageNet, we highlight that our single-particle steered-MFM sampler outperforms a Best-of-1000 baseline across multiple rewards at a fraction of the compute.

ICML 2026

Token Sample Complexity of Attention

Léa Bohbot, Cyril Letrouit, Gabriel Peyré, François-Xavier Vialard

As context windows in large language models continue to expand, it is essential to characterize how attention behaves at extreme sequence lengths. We introduce token sample complexity: the rate at which attention computed on $n$ tokens converges to its infinite-token limit. We estimate finite-$n$ convergence bounds at two levels: pointwise uniform convergence of the attention map, and convergence of moments for the transformed token distribution. For compactly supported (and more generally sub-Gaussian) distributions, our first result shows that the attention map converges uniformly on a ball of radius $R$ at rate $C(R)/\sqrt{n}$, where $C(R)$ grows exponentially with $R$. For large $R$, this estimate loses practical value, and our second result addresses this issue by establishing convergence rates for the moments of the transformed distribution (the token output of the attention layer). In this case, the rate is $C'(R)/n^{\beta}$ with $\beta<\tfrac{1}{2}$, and $C'(R)$ depends polynomially on the size of the support of the distribution. The exponent $\beta$ depends on the attention geometry and the spectral properties of the token distribution. We also examine the regime in which the attention parameter tends to infinity and the softmax approaches a hardmax, and in this setting, we establish a logarithmic rate of convergence. Experiments on synthetic and real data support our predictions and show that the predicted slowdown is reflected in downstream accuracy.

ICML 2026

EVMbench: Evaluating AI Agents on Smart Contract Security

Justin Wang, Andreas Bigger, Xiaohai Xu, Justin W Lin, Andy Applebaum, Tejal Patwardhan, Alpin Yukseloglu, Olivia Watkins

Smart contracts on public blockchains now manage large amounts of value, and vulnerabilities in these systems can lead to substantial losses. As AI agents become more capable at reading, writing, and running code, it is natural to ask how well they can already navigate this landscape, both in ways that improve security and in ways that might increase risk. We introduce EVMbench, an evaluation that measures the ability of agents to detect, patch, and exploit smart contract vulnerabilities. EVMbench draws on 117 curated vulnerabilities from 40 repositories and, in the most realistic setting, uses programmatic grading based on tests and blockchain state under a local Ethereum execution environment. We evaluate a range of frontier agents and find that they are capable of discovering and exploiting vulnerabilities end-to-end against live blockchain instances. We release code, tasks, and tooling to support continued measurement of these capabilities and future work on security.

ICML 2026

One-Step Graph-Structured Neural Flows for Irregular Multivariate Time Series Classification

Mengzhou Gao, kaiwei wang, Pengfei Jiao

Neural Flows efficiently model irregular multivariate time series by directly learning ODE solution trajectories with neural networks, bypassing step-by-step numerical solvers. Despite their efficiency, many existing approaches treat variables independently, leaving inter-variable interactions underexplored. Moreover, their one-step mapping makes interaction modeling inherently challenging, as it removes the iterative refinement of interactions during learning. To address this challenge, we propose one-step Graph-Structured Neural Flows (GSNF), which introduce two auxiliary-trajectory self-supervision strategies to strengthen interaction learning: (i) interaction-aware trajectory generation via re-initialization, which induces trajectory divergence to expose graph-induced interactions, with a theoretically derived lower bound on divergence; and (ii) reverse-time trajectory generation, which enforces forward–backward consistency to regularize graph learning, enabled by flow invertibility. Experiments on five real-world datasets show that GSNF achieves state-of-the-art classification performance with highly competitive training time and memory usage. The code is available at https://github.com/mzgaooo/GSNF.

ICML 2026

GIST: Targeted Data Selection for Instruction Tuning via Coupled Optimization Geometry

Guanghui Min, Tianhao Huang, Ke Wan, Chen Chen

Targeted data selection has emerged as a crucial paradigm for efficient instruction tuning, aiming to identify a small yet influential subset of training examples for a specific target task. In practice, influence is often measured through the effect of an example on parameter updates. To make selection scalable, many approaches leverage optimizer statistics (e.g., Adam states) as an axis-aligned surrogate for update geometry (i.e., diagonal precondition), implicitly treating parameters as coordinate-wise independent. We show that this assumption breaks down in parameter-efficient fine-tuning (PEFT) methods such as LoRA. In this setting, the induced optimization geometry exhibits strong cross-parameter coupling with non-trivial off-diagonal interactions, while the task-relevant update directions are confined to a low-dimensional subspace. Motivated by this mismatch, we propose **GIST** (Gradient Isometric Subspace Transformation), a simple yet principled alternative that replaces axis-aligned scaling with robust subspace alignment. **GIST** recovers a task-specific subspace from validation gradients via singular value decomposition (SVD), projects training gradients into this coupled subspace, and scores examples by their alignment with target directions. Extensive experiments have demonstrated that **GIST** matches or outperforms the state-of-the-art baseline with only 0.29% of the storage and 25% of the computational time under the same selection budget.

ICML 2026

Strategic Candidacy in Generative AI Arenas

Chris Hays, Rachel Li, Bailey Flanigan, Manish Raghavan

AI arenas, which rank generative models from pairwise preferences of users, are a popular method for measuring the relative performance of models in the course of their organic use. Because rankings are computed from noisy preferences, there is a concern that model producers can exploit this randomness by submitting many models (e.g., multiple variants of essentially the same model) and thereby artificially improve the rank of their top models. This can lead to degradations in the quality, and therefore the usefulness, of the ranking. In this paper, we begin by establishing, both theoretically and in simulations calibrated to data from the platform Arena (formerly LMArena, Chatbot Arena), conditions under which producers can benefit from submitting clones when their goal is to be ranked highly. We then propose a new mechanism for ranking models from pairwise comparisons, called You-Rank-We-Rank (YRWR). It requires that producers submit rankings over their own models and uses these rankings to correct statistical estimates of model quality. We prove that this mecha-nism is approximately clone-robust, in the sense that a producer cannot improve their rank much by doing anything other than submitting each of their unique models exactly once. Moreover, to the extent that model producers are able to correctly rank their own models, YRWR improves overall ranking accuracy. In further simulations, we show that indeed the mechanism is approximately clone-robust and quantify improvements to ranking accuracy, even under producer mis-ranking.

ICML 2026

Loss-Aware Distributionally Robust Optimization via Trainable Optimal Transport Ambiguity Sets

Jonas Ohnemus, Marta Fochesato, Riccardo Zuliani, John Lygeros

Optimal-transport distributionally robust optimization (OT-DRO) robustifies data-driven decision-making under uncertainty by capturing the sampling-induced statistical error via optimal transport ambiguity sets. The standard OT-DRO pipeline consists of a two-step procedure, where the ambiguity set is first designed and subsequently embedded into the downstream OT-DRO problem. However, this separation between uncertainty quantification and optimization may lead to excessive conservatism. We introduce an end-to-end pipeline to automatically learn decision-focused ambiguity sets for OT-DRO problems, where the loss function informs the shape of the ambiguity set, leading to less conservative decisions whose distributional robustness is enforced via data-driven bootstrapping. We formulate the learning problem as a bilevel optimization program and solve it via a hypergradient-based method. By leveraging the recently introduced nonsmooth conservative implicit function theorem, we establish convergence to a critical point of the bilevel problem. We present experiments validating our method on standard portfolio optimization and linear regression tasks.

ICML 2026

MAVRL: Learning Reward Functions from Multiple Feedback Types with Amortized Variational Inference

Raphaël Baur, Yannick Metz, Maria Gkoulta, Mennatallah El-Assady, Giorgia Ramponi, Thomas Kleine Buening

Reward learning typically relies on a single feedback type or combines multiple feedback types using manually weighted loss terms. Currently, it remains unclear how to jointly learn reward functions from heterogeneous feedback types such as demonstrations, comparisons, ratings, rankings, and stops that provide qualitatively different signals. We address this challenge by formulating reward learning from multiple feedback types as Bayesian inference over a shared latent reward function, where each feedback type contributes information through an explicit likelihood. We introduce a scalable amortized variational inference approach that learns a shared reward encoder and feedback-specific likelihood decoders and is trained by optimizing a single evidence lower bound. Our approach avoids reducing feedback to a common intermediate representation and eliminates the need for manual loss balancing. Across discrete and continuous-control benchmarks, we show that jointly inferred reward posteriors outperform single-type baselines, exploit complementary information across feedback types, and yield policies that are more robust to environment perturbations. The inferred reward uncertainty further provides interpretable signals for analyzing model confidence and consistency across feedback types.

ICML 2026

HARD-KV: Head-Adaptive Regularization for Decoding-time KV Compression

Yuxuan Yang, Feiyang Ren, Bowen Zeng, Dalin Zhang, Jinpeng Chen, Gang Chen, Huan Li

Long-context LLM inference faces a fundamental conflict: head-adaptive compression algorithms (e.g., Top-$p$ nucleus sampling) offer superior accuracy by dynamically fluctuating memory budgets, yet modern inference engines (e.g., vLLM) demand rigid, static memory patterns to leverage CUDA Graphs and PagedAttention. We resolve this ``Static-Dynamic'' mismatch with HARD-KV, a unified framework that that bridges dynamic selection with rigid system constraints. HARD-KV introduces a Cascade Cache hierarchy, managing the token lifecycle across dense, sparse, and condensed tiers. Crucially, we propose a Logits Calibration mechanism that normalizes diverse importance metrics into a unified probability space, enabling consistent Top-$p$ budgeting across heterogeneous heads. To bridge the efficiency gap, we offer a system-level solution, which rewrites fragmented, dynamic indices into contiguous physical layouts compatible with high-performance inference engine. Extensive experiments on math-reasoning benchmarks (AIME, U-Math) verify that HARD-KV achieves up to 2$\times$ throughput improvement over static baselines while maintaining high-fidelity generation in 10k+ token scenarios. Code is available at https://github.com/SuDIS-ZJU/HARDInfer.

ICML 2026

FIRE: Multi-Fidelity Regression with Distribution-Conditioned In-Context Learning Using Tabular Foundation Models

Rosen Ting-Ying Yu, Nicholas Sung, Faez Ahmed

Multi-fidelity (MF) regression often operates in regimes of extreme data imbalance, where the commonly-used Gaussian-process surrogates struggle with cubic scaling costs and overfit to sparse high-fidelity observations, limiting efficiency and generalization in real-world applications. We introduce FIRE, a training-free MF framework that couples tabular foundation models (TFMs) to perform zero-shot in-context Bayesian inference via a high-fidelity correction model conditioned on the low-fidelity model's posterior predictive distributions. This cross-fidelity information transfer via distributional summaries captures heteroscedastic errors, enabling robust residual learning without model retraining. Across 31 benchmark problems spanning synthetic functions and real-world tasks (e.g., DrivAerNet, LCBench), FIRE delivers a stronger performance–time trade-off than seven state-of-the-art GP-based or deep learning MF regression methods, ranking highest in accuracy and uncertainty quantification with runtime advantages. Limitations include context window constraints and dependence on the quality of the pre-trained TFMs. Code & data can be found here: https://github.com/rosenyu304/FIRE.

ICML 2026

Unsupervised Process-Aware Coreset Selection for In-Context Learning

Wei Zheng, Zijie Wang, Xin Li, Bin Gong, Yuqing Sun

We address the challenge of unsupervised coreset selection for few-shot in-context learning (ICL). The goal is to select a small subset of examples under a fixed annotation budget to yield effective prompts for large language models. Existing geometry-based methods often yield coresets that suffer from a skewed distribution, due to the oversampling of peripheral examples and high local redundancy. To address these issues, we propose a process-aware framework for coreset selection. It jointly optimizes the diversity and representativeness of selected samples via an adaptive submodular objective. It ensures representativeness by selecting samples based on local density awareness, while promoting diversity by imposing a redundancy penalty relative to the evolving selected set. Thus, it performs progress-aware balancing of representativeness and diversity based on the selection context. Extensive experiments on 7 NLP datasets demonstrate that our method consistently outperforms state-of-the-art coreset selection methods in downstream ICL performance. Further analysis validates that our approach better balances diversity and representativeness in the selection process, while retaining the theoretical guarantees of adaptive submodular optimization.

ICML 2026

Envisioning Beyond the Few: Disentangled Semantics and Primitives for Few-Shot Atypical Layout-to-Image Generation

Nan Bao, Yifan Zhao, Wenzhuang Wang, Jia Li

The layout-to-image (L2I) task enables fine-grained control over image generation via object categories and spatial layouts. However, existing L2I methods yield fragmented and distorted generations under few-shot atypical settings. We term this failure as representation fragmentation, arising from a granularity mismatch that entangles semantic identity with visual details. To address this issue, we propose a representation-driven framework that disentangles semantics from primitives for robust few-shot adaptation. Specifically, Semantic Anchoring aggregates categorical semantics into anchors for stable identity, while Primitive Imbuing models recomposable primitives for robust local detail modeling. Conceptual Steering further regulates optimization with a saliency-aware objective to preserve foreground semantic consistency. Extensive experiments demonstrate consistent improvements in the 5-shot regime over state-of-the-art L2I methods in both visual fidelity and alignment across diverse atypical domains. The source code is publicly available at https://github.com/iCVTEAM/DSP.

ICML 2026

IRPM: Intergroup Relative Preference Modeling for Pointwise Generative Reward Models

Haonan Song, Qingchen Xie, Huan Zhu, Feng Xiao, Luxi Xing, Liu Kang, Fuzhen Li, Zhiyong Zheng, Feng Jiang, Ziheng Li, Kun Yan, Qingyi Si, Yanghua Xiao, Hongcheng Guo, Fan Yang

Generative Reward Models (GRMs) have demonstrated strong performance in reward modeling, due to their interpretability and potential for refinement through reinforcement learning (RL). However, widely used pairwise GRMs create a computational bottleneck in reinforcement learning from human feedback (RLHF), when calibrating or aggregating preference signals over $n$ candidates, often incurring $\mathcal{O}(n^2)$ pairwise judgments. To address this issue, we propose **Intergroup Relative Preference Modeling (IRPM)**, an RL-based method that extends the Bradley-Terry preference-learning paradigm via intergroup comparisons to train *pointwise* GRMs from pairwise preference data. IRPM derives a pointwise reward for each response by contrasting groups of chosen vs. rejected samples, enabling pointwise scores comparable across candidate sets and $\mathcal{O}(n)$ reward evaluation for a variable number of candidates during RL training, while preserving interpretability and scalability. Experiments show that IRPM achieves state-of-the-art performance among pointwise GRMs on JudgeBench and RewardBench, and approaches the performance of leading pairwise GRMs. In addition, IRPM achieves substantial gains in post-training evaluations, demonstrating its effectiveness. Our models and code are available at https://github.com/XINGYUN-AI-LAB/IRPM.

ICML 2026

Large-capacity and Receiver Authenticable Generative Image Steganography

Jiannian Wang, Yao Lu, Guangming Lu

Diffusion-based generative image steganography converts the input single secret image into noise, and generates the stego image with it serves as the initial noise. Nevertheless, existing methods exhibit three severe limitations: (1) the fixed hiding space constrains their capacity to one secret image; (2) severe inter-secret interference arising from substantial information divergence among multiple secret images while concealing them within a shared hiding space; (3) security risks owing to the absence of the receiver-side verification mechanism. To systematically address these issues, this paper proposes a novel **Receiver Authenticable Generative Image Steganography framework** based on diffusion models. We introduce a **Dynamic Cover Selection and Optimization Engine** to adaptively allocate suitable hiding spaces for different secret images. This design permits the concealment of disparate secret images (or fragments of a single image) into separate spaces, enabling dynamic multi-image concealment while effectively preventing inter-secret interference and expanding capacity through the enlarged hiding spaces. Furthermore, a **Signature Authentication Controller** cryptographically signs the secret container after concealing and verifies it before extraction, ensuring secure receiver isolation and precise localization of the secret data container. Experiments demonstrate that the proposed framework achieves superior secure multi-receiver isolation and high-performance generative image steganography with large capacity.

ICML 2026

Instruction Decomposition and Action Alignment for Vision-Language Navigation

Zihao Xin, Wentong Li, Yixuan Jiang, Bin Wang, Piji Li, Jianke Zhu, Jie Qin, Sheng-Jun Huang

Vision-and-Language Navigation (VLN) empowered by Multimodal Large Language Models (MLLMs) is promise, yet remains challenged by long-horizon tasks with complex user instructions. Existing approaches that continuously condition on full instructions incur high latency due to abundant visual tokens and exacerbates instruction interference, where irrelevant text noise induces hallucinations. To address these limitations, we propose IDEAL-VLN ( \textbf{I}nstruction \textbf{DE}composition and \textbf{A}ction a\textbf{L}ignment ), a novel paradigm that reformulates navigation as a causal inference chain. We decompose the task into two sequential steps: Semantic Anchoring and Action Alignment. We adopt a \textit{Think-Before-Act} mechanism that first infers the immediate semantic anchor from the global context and then generates actions conditioned solely on this anchor. This design constructs an explicit information bottleneck, suppressing spurious correlations from irrelevant instruction. Moreover, to alleviate cognitive collapse and limited exploration during training, we introduce a hierarchical correction framework that combines semantic-level thought correction with a spatially-aware adaptive intervention strategy. This strategy adjusts expert intervention probability based on geodesic distance, effectively defining a semantic safety boundary. To support this paradigm, we contribute the Instruction-Aligned Navigation Dataset containing 160K image-text pairs. Extensive experiments demonstrate that IDEAL-VLN achieves state-of-the-art performance and robustness across major benchmarks while significantly reducing inference costs.

ICML 2026

Continuous-Time Piecewise-Linear Recurrent Neural Networks

Alena Brändle, Lukas Eisenmann, Florian Götz, Daniel Durstewitz

In dynamical systems reconstruction (DSR) we aim to recover the dynamical system (DS) underlying observed time series. Specifically, we aim to learn a generative surrogate model which approximates the underlying, data-generating DS, and recreates its long-term properties (`climate statistics'). In scientific and medical areas, in particular, these models need to be mechanistically tractable -- through their mathematical analysis we would like to obtain insight into the recovered system's workings. Piecewise-linear (PL), ReLU-based RNNs (PLRNNs) have a strong track-record in this regard, representing SOTA DSR models while allowing mathematical insight by virtue of their PL design. However, all current PLRNN variants are *discrete-time maps*. This is in disaccord with the assumed continuous-time nature of most physical and biological processes, and makes it hard to accommodate data arriving at *irregular* temporal intervals. Neural ODEs are one solution, but they do not reach the DSR performance of PLRNNs and often lack their tractability. Here we develop theory for *continuous-time* PLRNNs (cPLRNNs): We present a novel algorithm for training and simulating such models, bypassing numerical integration by efficiently exploiting their PL structure. We further demonstrate how important topological objects like equilibria or limit cycles can be determined semi-analytically in trained models. We compare cPLRNNs to both their discrete-time cousins as well as Neural ODEs on DSR benchmarks, including systems with discontinuities which come with hard thresholds.

ICML 2026

The Invisible Lottery: How Subtle Cues Steer Algorithm Choice in LLM Code Generation

Akanksha Narula, Mofasshara Binte Rafique, Laurent Bindschaedler

Large language models (LLMs) now generate substantial production code, often for tasks with multiple valid algorithmic solutions. Incidental prompt cues—contextual words or metadata outside the task specification—can steer which algorithm the model selects, even when all outputs pass the same tests. Prompt sensitivity is well studied as a mechanism for improving output quality; here, we instead study *output policy*: algorithm choice under fixed correctness. We define *algorithm steering* as cue-induced shifts in algorithm-family distributions and run 46,535 controlled experiments across 11 tasks, 19 cue types (18 channels plus a memoization semantic-vs-surface ablation that preserves meaning while changing typography and punctuation), and 15 model configurations. We find large, systematic shifts in algorithm-family distributions (up to 100 percentage points, pp), largely consistent with cue semantics, including in applied tasks such as rate limiting. Direct algorithm naming is the most reliable mitigation we tested. These results reveal an “invisible lottery” in which accidental context alters downstream properties such as performance, security, and maintainability.

ICML 2026

SONAR: Spectral‑Contrastive Audio Residuals for Generalizable Deepfake Detection

Ido Nitzan Hidekel, Gal lifshitz, Khen Cohen, Dan Raviv

Deepfake audio detectors often fail to generalize to unseen attacks, in part due to \emph{spectral bias}: neural networks prioritize low-frequency structure while under-exploiting subtle high-frequency (HF) artifacts left by generative models. We introduce \textbf{SONAR} (Spectral-cONtrastive Audio Residuals), a frequency-guided framework that \emph{explicitly enforces representation-level consistency} between semantic content and HF residuals. Unlike prior frequency-aware or dual-stream detectors that treat HF cues as auxiliary features, SONAR encourages structured interaction between content and noise representations in latent space. The model employs a dual-path architecture in which an XLSR encoder captures low-frequency content, while a parallel branch with learnable, value-constrained 1D SRM (Spatial Rich Model) high-pass filters distills HF residuals. The two representations are fused via frequency cross-attention and trained with a \emph{Jensen--Shannon alignment loss} that promotes LF–HF consistency for genuine audio and amplifies inconsistency for deepfakes. Evaluated on ASVspoof~2021 and in-the-wild benchmarks, SONAR achieves state-of-the-art performance in a \textbf{single run} setting and converges faster than strong baselines. By mitigating the effects of spectral bias through frequency-guided alignment, SONAR provides a fully data-driven and architecture-agnostic approach to generalizable audio deepfake detection.

ICML 2026

Self-Distilled Reasoner: On-Policy Self-Distillation for Large Language Models

Siyan Zhao, Zhihui Xie, mengchen liu, Jing Huang, Guan Pang, Feiyu Chen, Aditya Grover

Knowledge distillation improves large language model (LLM) reasoning by compressing the knowledge of a teacher LLM to train smaller LLMs. On-policy distillation advances this approach by having the student sample its own trajectories while a teacher LLM provides dense token-level supervision, addressing the distribution mismatch between training and inference in off-policy distillation methods. However, on-policy distillation typically requires a separate, often larger, teacher LLM and does not explicitly leverage ground-truth solutions available in reasoning datasets. Inspired by the intuition that a sufficiently capable LLM can rationalize external privileged reasoning traces and teach its weaker self, we introduce On-Policy Self-Distillation (OPSD), a learning algorithm where a single LLM acts as both teacher and student with different contexts. The teacher policy conditions on privileged information while the student policy sees only the question; training minimizes the per-token divergence between these distributions over the student's own rollouts. We demonstrate the efficacy of our method on multiple mathematical reasoning benchmarks, achieving superior token efficiency compared to reinforcement learning methods and better performance over off-policy distillation methods.

Keep browsing

More papers from top AI conferences

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