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

SPHERE: Mitigating the Loss of Spectral Plasticity in Mixture-of-Experts for Deep Reinforcement Learning

Lirui Luo, Guoxi Zhang, Hongming Xu, Cong Fang, Qing Li

In DRL, an agent is trained from a stream of experience. In a continual learning setting, such agents can suffer from \emph{plasticity loss}: their ability to learn new skills from new experiences diminishes over training. Recently, Mixture-of-Experts (MoE) networks have been reported to enable scaling laws and facilitate the learning of diverse skills. However, in continual reinforcement learning settings, their performance can degenerate as learning proceeds, indicating a loss of plasticity. To address this, building on Neural Tangent Kernel (NTK) theory, we formalize the plasticity loss in MoE policies as a loss of \emph{spectral plasticity}. We then derive a tractable proxy for spectral plasticity, one expressible in terms of individual expert feature matrices. Leveraging this proxy, we introduce \emph{SPHERE}, a practical Parseval penalty tailored for MoE-based policies that alleviates the loss of spectral plasticity. On MetaWorld and HumanoidBench, SPHERE improves average success under continual RL by 133\% and 50\% over an unregularized MoE baseline, while maintaining higher spectral plasticity throughout training.

ICML 2026

Anytime Detection of Strategic Deviations in Multi-Agent Systems

Etienne Gauthier, Francis Bach, Michael I. Jordan

In many multi-agent systems, agents interact repeatedly and are expected to settle into stable, rational behavior over time. Yet in practice, behavior often drifts, and detecting such deviations in real time remains an open challenge. We introduce a sequential testing framework that monitors whether observed play is consistent with a benchmark of strategic behavior, without assuming a fixed sample size. Our approach builds on the e-value framework for safe anytime-valid inference: by "betting" against the benchmark, we construct a test supermartingale that accumulates evidence whenever observed payoffs systematically violate the expected conditions. For repeated normal-form games, we take equilibrium as the benchmark, yielding a statistically sound, interpretable measure of departure from equilibrium that can be monitored online; our framework unifies the treatment of Nash, correlated, and coarse correlated equilibria, offering finite-time guarantees and a detailed analysis of detection times. We also leverage Benjamini-Hochberg-type procedures to increase detection power in large games while rigorously controlling the false discovery rate. Finally, we extend our method to stochastic games, verifying online whether observed trajectories adhere to a specified target policy, such as a computed equilibrium, broadening the framework's applicability to dynamic, state-dependent settings.

ICML 2026

The Hidden Cost of Structured Generation in LLMs: Draft-Conditioned Constrained Decoding

Avinash Reddy, Thayne T. Walker, Jaime S. Ide, Amrit Singh Bedi

Large language models (LLMs) are increasingly used to generate executable outputs, JSON objects, and API calls, where a single syntax error can make the output unusable. Constrained decoding enforces validity token-by-token via masking and renormalization, but it can distort generation when the model assigns low probability mass to valid continuations, pushing decoding toward locally valid yet semantically incorrect trajectories. We propose \emph{Draft-Conditioned Constrained Decoding (DCCD)}, a simple two-step, training-free inference procedure that decouples semantic planning from structural enforcement: an unconstrained draft is generated first, and constrained decoding is then applied, conditioned on this draft, to guarantee validity. We analyze DCCD through a KL-projection view, showing that draft conditioning increases feasible mass and reduces the cumulative “projection tax” induced by hard constraints, with an optional best-of-$K$ draft selection. Across structured reasoning benchmarks, DCCD improves strict structured accuracy by up to +24 percentage points over standard constrained decoding (e.g., 15.2\% to 39.0\% on GSM8K with a 1B model), and enables smaller model pairs to match or exceed much larger constrained baselines, yielding substantial gains in parameter efficiency.

ICML 2026

Is Code Better Than Language for Algorithmic Reasoning?

Terry Tong, Yu Feng, Surbhi Goel, Dan Roth

For tool-augmented language models, comparing natural-language reasoning with code-execution pipelines is difficult because the comparison changes both the intermediate representation and the execution mechanism. We separate these factors with an intermediate intervention: the model expresses its reasoning as executable code, and the language model simulates that code in context to produce an answer. On a 40-task verifiable algorithmic benchmark, deterministic code execution outperforms natural-language reasoning by +31.6pp. We observe that the intermediate intervention is not meaningfully different from natural-language reasoning (+0.15pp). These results suggest that, in our evaluated setting, changing the intermediate representation alone does not explain the tool-use advantage, providing evidence for the performance gains requiring reliable external execution. We formalize this intuition with a simple statistical decision-theoretic model that characterizes when execution dominates end-to-end risk in our disentangled trace-generation/execution regime. We validate our theory using a reconstruction intervention that leverages a proxy language model to infer natural-language reasoning traces from code representations, recovering performance comparable to the original natural-language reasoning pipeline. All experiments are at https://github.com/TerryTong-Git/ToolProj.

ICML 2026

A Task-centric Theory for Iterative Self-Improvement with Easy-to-Hard Curricula

Chenruo Liu, Yijun Dong, Yiqiu Shen, Qi Lei

Iterative self-improvement fine-tunes an autoregressive large language model (LLM) on reward-verified outputs generated by the LLM itself. In contrast to the empirical success of self-improvement, the theoretical foundation of this generative, iterative procedure in a practical, finite-sample setting remains limited. We make progress toward this goal by modeling each round of self-improvement as maximum-likelihood fine-tuning on a reward-filtered distribution and deriving finite-sample guarantees for the expected reward. Our analysis reveals an explicit feedback loop where better models accept more data per iteration, supporting sustained self-improvement while explaining eventual saturation of such improvement. Adopting a task-centric view by considering reasoning tasks with multiple difficulty levels, we further prove quantifiable conditions on model initialization, task difficulty, and sample budget where easy-to-hard curricula provably achieve better guarantees than training on fixed mixtures of tasks. Our analyses are validated through Monte-Carlo simulations and experiments spanning a synthetic graph-based reasoning task and multiple standard mathematical reasoning benchmarks.

ICML 2026

ProSAR: Prototype-Guided Semantic Augmentation and Refinement for Time Series Contrastive Learning

Caiyi Yang, Chenglin Li, Hao Zhang, Weijia Lu, Zhifei Yang, Wenrui Dai, xiaodong Zhang, Xiaofeng Ma, Can Zhang, Junni Zou, Hongkai Xiong

Contrastive learning has advanced the representation learning across domains, yet its success relies on data augmentations that preserve semantic contents while providing the view diversities. Multivariate time series, however, are inherently noisy, non-stationary, and lack such intuitive semantic cues. Consequently, standard heuristic augmentations that ignore semantic parts may risk destroying critical temporal dependencies. Though some recent approaches attempt to isolate informative components, they typically rely on an implicit neural mechanism to infer semantics, thus limiting the interpretability and controllability. To address this, we propose ProSAR, an information-theoretic framework that leverages the explicit prototype alignment to guide semantic augmentations, and establish a feedback loop between the augmentation, contrastive learning, and prototype updates. Specifically, grounded in our proposed Prototype-Conditioned Information Bottleneck principle, we leverage the time-domain prototypes as explicit anchors to localize semantic segments, and develop a time–frequency augmentation strategy that retains prototype-consistent information while discarding noise. To promote semantically consistent prototypes for a reliable view generation, we design a dual-prototype loop where the augmented views are encoded into representations and then the learned representations are clustered to update latent prototypes, whose decoded feedback refines the time-domain prototypes for the next round of augmentation. Experiments on diverse time-series benchmarks demonstrate that ProSAR outperforms the other contrastive learning methods on downstream forecasting and classification tasks.

ICML 2026

Learning Cardiac Latent Representations in Vectorcardiogram Space

Bosong Huang, Panzhen Zhao, Zengxiang Li, Patricia Lee, Wei Jin, Alan Wee-Chung Liew, Ming Jin, Shirui Pan

Electrocardiography (ECG) is a cornerstone of cardiac assessment, making the learning of informative ECG representations fundamental to tasks ranging from disease diagnosis to clinical report generation. However, existing methods operate almost exclusively in the observable ECG signal space. In practice, the standard twelve-lead ECG represents multiple projections of the same underlying cardiac electrical activity from different spatial orientations. Therefore, representation learning in the ECG space inevitably introduces substantial redundancy, which may lead to spurious correlations and increased risk of overfitting. To address this and motivated by the Frank vectorcardiogram (VCG) model, we propose learning a unified latent representation of cardiac electrical activity directly in the VCG space. We introduce LVCG, the first general self-supervised representation learning framework designed to operate in this physically grounded latent space. By learning view-invariant latent VCG representations rather than lead-specific artifacts, VCG minimizes redundancy and improves generalization. LVCG generally outperforms ECG-space baselines across tasks, demonstrating enhanced robustness and generalization, especially in domain shift settings. Our code has been made available at https://github.com/BosonHwang/LVCG.

ICML 2026

Noise as a Natural Regularizer in Markov Decision Processes: Connecting Environmental Stochasticity and Policy Simplicity

Harry Chen, Yiyang Sun, Michal Moshkovitz, Zachery Boner, Lesia Semenova, Cynthia Rudin, Ronald Parr

The planning horizon in a Markov Decision Process (MDP) determines how far into the future an agent reasons. In practice, shorter horizons are commonly associated with policies that exhibit simpler or more interpretable decision-making behavior. In this paper, we establish a formal connection between environmental stochasticity and planning horizon in MDPs. We show that for broad classes of transition noise, solving a noisy MDP can be formally related to solving a noise-free MDP with a shorter effective discount factor, leading to identical optimal policies in some cases and near-optimal ones in others. We further characterize settings in which this correspondence breaks down, clarifying when horizon-based interpretations of noise are not valid. These results, which are supported by both theory and experiments, also give some insight into the common practice of using smaller discount factors for reinforcement learning than those that can be justified by standard modeling interpretations.

ICML 2026

From Absolute to Relative: Rethinking Reward Shaping in Group-Based Reinforcement Learning

Wenzhe Niu, Wei He, Zongxia Xie, Jinpeng Ou, Huichuan Fan, Yuchen Ge, Yanru Sun, Ziyin Wang, Yizhao Sun, Chengshun Shi, Jiuchong Gao, Jinghua Hao, Renqing He

Reinforcement learning has become a cornerstone for enhancing the reasoning capabilities of Large Language Models, where group-based approaches such as GRPO have emerged as efficient paradigms that optimize policies by leveraging intra-group performance differences. However, these methods typically rely on absolute numerical rewards, introducing intrinsic limitations. In verifiable tasks, identical group evaluations often result in sparse supervision, while in open-ended scenarios, the score range instability of reward models undermines advantage estimation based on group means. To address these limitations, we propose **Reinforcement Learning with Relative Rewards (RLRR)**, a framework that shifts reward shaping from absolute scoring to relative ranking. Complementing this framework, we introduce the **Ranking Reward Model**, a listwise preference model tailored for group-based optimization to directly generate relative rankings. By transforming raw evaluations into robust relative signals, RLRR effectively mitigates signal sparsity and reward instability. Experimental results demonstrate that RLRR yields consistent performance improvements over standard group-based baselines across reasoning benchmarks and open-ended generation tasks.

ICML 2026

Scene Graph Thinking: Reinforcing Structured Visual Reasoning for Multimodal Large Language Models

Zhiwei Yang, Yuanchen Wu, Nan Zhang, Yucong Meng, Ke Yan, Shouhong Ding

Multimodal Large Language Models (MLLMs) have demonstrated strong perception and reasoning capabilities. However, most existing models focus on isolated objects and neglect structured relationships for efficient target navigation, limiting their performance on visually intensive tasks. To address this challenge, we introduce Scene Graph Thinking (SaGe), a novel paradigm that enables fine-grained and structured visual reasoning through explicit scene-graph representations. Specifically, we first introduce an automated data engine that converts flat image–text corpora into structured scene graphs, where hierarchical entities constitute the nodes and diverse visual relations define the edges. Building upon this, we construct 120K high-quality training data by sampling reasoning traces from scene graphs. Then two-stage graph-aligned post-training paradigms are introduced, where supervised fine-tuning internalizes MLLMs with structured reasoning, and subsequent reinforcement fine-tuning proposes node-as-proxy graph rewards to consolidate efficient graph exploration. With curated data and graph-aligned training, our approach achieves significant improvements across eight multimodal benchmarks, demonstrating strong effectiveness on fine-grained perception and reasoning tasks.

ICML 2026

CONTINUUM: Restoring the Contiguous Tensor Abstraction Efficiently for Dynamic AI Workloads via Hardware Virtualization

Yangyu Zhang, Shuoming Zhang, Chunwei Xia, Shuaijiang Li, zhicheng li, Ruiyuan Xu, Zheming Yang, Lei Chen, YUAN WEN, Guangli Li, Xiaobing Feng, Huimin Cui, Jiacheng Zhao

Emerging LLM workloads demand extreme memory agility. However, state-of-the-art inference systems such as vLLM rely on software-defined paging, which sacrifices the contiguous tensor abstraction. This rigid interface exposes fragmentation complexity to developers, imposing a severe engineering burden that stifles algorithmic innovation. We introduce CONTINUUM, a tensor memory virtualization subsystem implemented as a PyTorch extension. By bypassing serialized OS bottlenecks through a lightweight GPU driver extension, CONTINUUM significantly reduces mapping costs by orders of magnitude, from milliseconds to microseconds. Built atop this low-latency API, CONTINUUM provides Elastic Tensor, a set of flexible tensor operations that natively support complex memory dynamics and zero-copy topological aliasing. Evaluations demonstrate that CONTINUUM achieves significantly higher throughput across diverse dynamic scenarios, effectively lowering the barrier to implementing next-generation LLM applications.

ICML 2026

StyleDistillation: A New Insight of Image Style Enables Personalized Aesthetic Manipulation

Yuxin Wang, Xiaoyu Geng, Yuke Li, Zheng Wang

Text-guided stylized image generation has yielded promising advances by leveraging the powerful capabilities of text-to-image diffusion models. However, the inherent coupling of style and content information within the reference image presents a significant challenge. To address this, we propose StyleDistillation, a novel approach grounded in two key observations about the CLIP embedding space from a style perspective. By leveraging a lightweight StyleDistiller module, combined with carefully designed optimization objectives based on geometric and semantic priors, we can extract fine-grained style representation from the reference image. Additionally, we introduce a Prompt Alignment Enhancement mechanism during inference, which significantly improves the control that text prompts exert over the generated images. Extensive experiments demonstrate that our method achieves outstanding performance in both style reproduction and prompt alignment. Furthermore, StyleDistillation supports various personalized operations, including style editing and style fusion, highlighting its substantial potential for diverse applications.

ICML 2026

CAOS: Conformal Aggregation of One-Shot Predictors

Maja Waldron

One-shot prediction enables rapid adaptation of pretrained foundation models to new tasks using only one labeled example, but lacks principled uncertainty quantification. While conformal prediction provides finite-sample coverage guarantees, standard split conformal methods are inefficient in the one-shot setting due to data splitting and reliance on a single predictor. We propose Conformal Aggregation of One-Shot Predictors (CAOS), a conformal framework that adaptively aggregates multiple one-shot predictors and uses a leave-one-out calibration scheme to fully exploit scarce labeled data. Despite violating classical exchangeability assumptions, we prove that CAOS achieves valid marginal coverage using a monotonicity-based argument. Experiments on one-shot facial landmarking and RAFT text classification tasks show that CAOS produces substantially smaller prediction sets than split conformal baselines while maintaining reliable coverage.

ICML 2026

From Flat Facts to Sharp Hallucinations: Detecting Stubborn Errors via Gradient Sensitivity

Liew Yee Zhing, Andrew Huey Ping Tan, Anwar P.P. Abdul Majeed

Traditional hallucination detection fails on "Stubborn Hallucinations" — errors where LLMs are confidently wrong. We propose a geometric solution: Embedding-Perturbed Gradient Sensitivity (EPGS). We hypothesize that while robust facts reside in flat minima, stubborn hallucinations sit in sharp minima, supported by brittle memorization. EPGS detects this sharpness by perturbing input embeddings with Gaussian noise and measuring the resulting spike in gradient magnitude. This acts as an efficient proxy for the Hessian spectrum, differentiating stable knowledge from unstable memorization. Our experiments show that EPGS significantly outperforms entropy-based and representation-based baselines, providing a robust signal for detecting high-confidence factual errors.

ICML 2026

PointDiT: Pixel-Space Diffusion for Monocular Geometry Estimation

Haofei Xu, Rundi Wu, Philipp Henzler, Nikolai Kalischek, Michael Oechsle, Fabian Manhardt, Marc Pollefeys, Andreas Geiger, Federico Tombari, Michael Niemeyer

State-of-the-art single-image 3D reconstruction methods often rely on complex hybrid architectures and loss functions (e.g., MoGe), or necessitate compressing geometry into latent spaces (e.g., GeometryCrafter) to leverage pre-trained latent diffusion models. In this work, we demonstrate that such architectural overhead and intricate loss formulations are unnecessary. We introduce a minimalist pixel-space Diffusion Transformer built on a plain ViT, which operates directly on raw 3D point map patches and is conditioned on image tokens from a pre-trained DINOv3. Unlike existing latent diffusion-based approaches, we train our diffusion backbone entirely from scratch, eliminating the need for point map tokenizers. We show that this streamlined approach yields results superior to complex latent-based diffusion models while remaining significantly simpler than hybrid alternatives. Notably, our model produces sharper geometric structures and achieves significantly better results on highly ambiguous regions, such as transparent objects.

ICML 2026

Temporal-aware Flow Matching for Video Generation with Temporally Coherent Motion

Zirui Pan, Xin Wang, Yipeng Zhang, Yuwei Zhou, Wenwu Zhu

Despite rapid advances in text-to-video generation, state-of-the-art generative models still suffer from producing temporally incoherent and unrealistic motion for videos. The key weakness of existing works is that they commonly treat videos as frame sequences and directly adopt Flow Matching (FM) objectives, which are originally designed for images. This practice fails to explicitly model motion priors or temporal dependencies, resulting in suboptimal dynamics that may appear incoherent and unrealistic. To solve this problem, we propose Temporal-aware Flow Matching (TFM), a novel training paradigm that embeds inter-frame constraints into the flow objective, leading to temporally coherent motion modeling in video generation. More specifically, the proposed TFM enforces temporal correlations across frames while retaining the desirable properties of FM, and further introduces a residual-type loss that aligns naturally with this new flow. We theoretically prove that models trained with TFM are able to exhibit remarkably enhanced temporal perception ability. Notably, TFM imposes no additional cost during inference and is applicable to any model using FM. Extensive experiments demonstrate that our TFM can significantly improve motion realism across diverse motion types. Generated videos are presented at https://pzrain.github.io/tfm.

ICML 2026

AIR: Improving Agent Safety through Incident Response

Zibo Xiao, Jun Sun, Junjie Chen

Large Language Model (LLM) agents are increasingly deployed in practice across a wide range of autonomous applications. Yet current safety mechanisms for LLM agents focus almost exclusively on preventing failures in advance, providing limited capabilities for responding to, containing, or recovering from incidents after they inevitably arise. In this work, we introduce AIR, the first incident response framework for LLM agent systems. AIR defines a domain-specific language for managing the incident response lifecycle autonomously in LLM agent systems, and integrates it into the agent's execution loop to (1) detect incidents via semantic checks grounded in the current environment state and recent context, (2) guide the agent to execute containment and recovery actions via its tools, and (3) synthesize guardrail rules during eradication to block similar incidents in future executions. We evaluate AIR on three representative agent types. Results show that AIR achieves detection, remediation, and eradication success rates all exceeding 90%. Extensive experiments further confirm the necessity of AIR's key design components, show the timeliness and moderate overhead of AIR, and demonstrate that LLM-generated rules can approach the effectiveness of developer-authored rules across domains. These results show that incident response is both feasible and essential as a first-class mechanism for improving agent safety.

ICML 2026

Adalina: Adaptive Linear Approximation for the Shapley Value and Beyond

Weida Li, Yaoliang Yu, Bryan Kian Hsiang Low

The Shapley value, and its broader family of semi-values, has received much attention in various attribution problems. A fundamental and long-standing challenge is their efficient approximation, since exact computation generally requires an exponential number of utility queries in the number of players $n$. To meet the challenges of large-scale applications, we explore the limits of efficiently approximating semi-values under a $\Theta(n)$ space constraint. Building upon a vector concentration inequality, we establish a theoretical framework that enables sharper query complexities for existing unbiased randomized algorithms. Within this framework, we systematically develop a linear-space algorithm that requires $O(\frac{n}{\epsilon^{2}}\log\frac{1}{\delta})$ utility queries to ensure $P(\\|\hat{\boldsymbol\phi}-\boldsymbol\phi\\|\geq\epsilon)\leq \delta$ for all commonly used semi-values. In particular, our framework naturally bridges OFA, unbiased kernelSHAP, SHAP-IQ and the regression-adjusted approach, and definitively characterizes when paired sampling is beneficial. Moreover, our algorithm allows explicit minimization of the mean squared error $\mathbb{E}[\\|\hat{\boldsymbol\phi}-\boldsymbol\phi\\|^{2}]$ for each specific utility function. Accordingly, we introduce the first adaptive, linear-time, linear-space randomized algorithm, Adalina, that theoretically achieves improved mean squared error. All of our theoretical findings are experimentally validated. Our code is available at https://github.com/watml/adalina.

ICML 2026

DiffuMamba: High-Throughput Diffusion LMs with Mamba Backbone

Vaibhav Singh, Oleksiy Ostapenko, Pierre-Andre Noel, Eugene Belilovsky, Torsten Scholak

Diffusion language models (DLMs) have emerged as a promising alternative to autoregressive (AR) generation, yet their reliance on Transformer backbones limits inference efficiency due to quadratic attention or KV-cache overhead. We introduce DiffuMamba, a masked diffusion language model built on a bidirectional Mamba backbone that combines the diffusion objective with linear-time sequence modeling, and DiffuMamba-H, a hybrid variant with interleaved attention. Across scales up to 1.3B parameters, our models match Transformer-based diffusion in downstream performance while achieving up to 8.2× and 4.3× higher inference throughput, respectively, on long sequences. We further present a systematic analysis of inference efficiency across modern DLM variants, combining asymptotic complexity with empirical measurements. Notably, cache-efficient block diffusion with Mamba mixers emerges as the only strategy that scales linearly with sequence length and achieves the strongest performance across all baselines, suggesting a promising direction for future diffusion-based generation systems.

ICML 2026

RedVisor: Reasoning-Aware Prompt Injection Defense via Zero-Copy KV Cache Reuse

Mingrui Liu, Sixiao Zhang, Cheng Long, Kwok-Yan Lam

Large Language Models (LLMs) are increasingly vulnerable to *Prompt Injection (PI)* attacks, where adversarial instructions hidden within retrieved contexts hijack the model's execution flow. Current defenses typically face a critical trade-off: *prevention-based* fine-tuning often degrades general utility via the "alignment tax", while *detection-based* filtering incurs prohibitive latency and memory costs. To bridge this gap, we propose **RedVisor**, a unified framework that synthesizes the explainability of detection systems with the seamless integration of prevention strategies. To the best of our knowledge, RedVisor is the first approach to leverage fine-grained reasoning paths to simultaneously *detect* attacks and *guide* the model's safe response. We implement this via a lightweight, removable adapter positioned atop the frozen backbone. This adapter serves a dual function: it first generates an explainable analysis that precisely localizes the injection and articulates the threat, which then explicitly conditions the model to reject the malicious command. Uniquely, the adapter is active only during this reasoning phase and is effectively muted during the subsequent response generation. This architecture yields two distinct advantages: (1) it mathematically preserves the backbone's original utility on benign inputs; and (2) it enables a novel **KV Cache Reuse** strategy, eliminating the redundant prefill computation inherent to decoupled pipelines. We further pioneer the integration of this defense into the vLLM serving engine with custom kernels. Experiments demonstrate that RedVisor outperforms state-of-the-art defenses in detection accuracy and throughput while incurring negligible utility loss.

Keep browsing

More papers from top AI conferences

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