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

ACTIVE-o3 : Empowering MLLMs with Active Perception via Pure Reinforcement Learning

Muzhi Zhu, Hao Zhong, Canyu Zhao, Zongze Du, Mingyu Liu, Zheng Huang, Anzhou Li, Hao Chen, Cheng Zou, JingDong Chen, Ming Yang, Chunhua Shen

Active vision, also known as active perception, refers to actively selecting where and how to look in order to gather task-relevant information. It is a critical component of efficient perception and decision-making in humans and advanced embodied agents. With the rise of Multimodal Large Language Models (MLLMs) as central planners in robotic systems, the lack of methods for equipping MLLMs with active perception has become a key gap. We first provide a systematic definition of MLLM-based active perception tasks and show that GPT-o3's zoom-in strategy can be viewed as a special case, though it suffers from low efficiency and inaccurate region selection. To address these issues, we propose Active-o3, a reinforcement learning framework built on GRPO that equips MLLMs with active perception capabilities. Leveraging a modular sensing-action design and a dual-form reward, Active-o3 autonomously learns efficient and stable region selection strategies without explicit supervision. We further establish a comprehensive benchmark covering both open-world tasks (small/dense-object grounding) and domain-specific scenarios (remote sensing, autonomous driving, interactive segmentation). Experimental results demonstrate that Active-o3 significantly enhances active perception capabilities compared to Qwen2.5-VL-CoT. Moreover, we show that our RL framework not only preserves the model’s general understanding ability but can also serve as a proxy task for leveraging perception data, further improving performance on benchmarks such as RealWorldQA. We hope that our work can provide a simple codebase and unified evaluation protocol to facilitate future research on active perception with MLLMs.

ICML 2026

TokenRatio: Principled Token-Level Preference Optimization via Ratio Matching

Truong Nguyen, Tien-Phat Nguyen, Linh Ngo Van, Duy Minh Ho Nguyen, Khoa D Doan, Trung Le

Direct Preference Optimization (DPO) is a widely used RL-free method for aligning language models from pairwise preferences, but it models preferences over full sequences even though generation is driven by per-token decisions. Existing token-level extensions typically decompose a sequence-level Bradley–Terry objective across timesteps, leaving per-prefix (state-wise) optimality implicit. We study how to recover **token-level** preference optimality using only standard sequence-level pairwise comparisons. We introduce **Token-level Bregman Preference Optimization (TBPO)**, which posits a token-level Bradley--Terry preference model over next-token actions conditioned on the prefix, and derive a Bregman-divergence density-ratio matching objective that generalizes the logistic/DPO loss while preserving the optimal policy induced by the token-level model and maintaining DPO-like simplicity. We introduce two instantiations: TBPO-Q, which explicitly learns a lightweight state baseline, and TBPO-A, which removes the baseline through advantage normalization. Across instruction following, helpfulness/harmlessness, and summarization, TBPO improves alignment quality and training stability and increases output diversity relative to strong sequence-level and token-level baselines.

ICML 2026

RelayCaching: Accelerating LLM Collaboration via Decoding KV Cache Reuse

Yingsheng Geng, Yuchong Gao, Weihong Wu, Guyue Liu, Jiang Liu

The increasing complexity of AI tasks has shifted the paradigm from monolithic models toward multi-agent large language model (LLM) systems. However, these collaborative architectures introduce a critical bottleneck: redundant prefill computation for shared content generated by previous agents, which significantly increases KV cache memory usage and time-to-first-token (TTFT). While various KV cache methods have been proposed to mitigate prefill redundancy, they either fail to maintain accuracy on agent-generated outputs or exhibit low reuse rates due to rigid constraints. We present RelayCaching, a training-free inference method that directly reuses decoding phase KV caches from previous agents in subsequent prefill phases. Our key insight is that KV caches for identical content are highly consistent across phases, while prefix-induced deviations are sparse and localized within a limited range of layers and token positions. By selectively recomputing KV caches at these positions, RelayCaching preserves model accuracy with minimal overhead, yielding a superior accuracy–efficiency trade-off over existing methods. Experiments on diverse collaborative LLM tasks spanning mathematical reasoning, general knowledge, and code generation demonstrate that RelayCaching achieves over $80$\% KV cache reuse, reduces TTFT by up to $4.7\times$ compared to the standard pipeline, all with negligible accuracy degradation.

ICML 2026

On the Fragility of Data Attribution When Learning Is Distributed

Xian Gao, Bo Hui, Min-Te Sun, Wei-Shinn Ku

Data attribution has become an important component of pricing, auditing, and governance in machine learning pipelines, yet most attribution methods implicitly assume that attribution values faithfully reflect participants' contributions. We show that this assumption can fail: a single participant in a standard distributed training workflow can substantially inflate its measured attribution value while preserving global utility. Our attribution-first attack uses latent optimization to inject small synthetic batches that preserve utility while exploiting non-IID label coverage and evaluator sensitivities. Across datasets, models, and multiple marginal-utility evaluators, the attack consistently increases the adversary’s attribution value and reshapes the relative attribution structure among benign clients without degrading accuracy or triggering geometry-based defenses. These results show that attribution itself forms a new attack surface and motivate the development of attribution-robust and incentive-compatible scoring mechanisms.

ICML 2026

SparseInfer: Accelerating Large Language Model Inference with Semantics-Inspired Adaptive Sparse Activation

Qinsi Wang, Saeed Vahidian, Hancheng Ye, Jianyang Gu, Jianyi Zhang, Yiran Chen

Large Language Models (LLMs) with billions of parameters have transformed AI applications but require immense computational and memory resources during inference. Adaptive sparse activation inference, which activates only a small number of neurons for each token, offers a novel way to accelerate model inference without degrading performance, showing great potential for resource-constrained hardware devices. Yet existing token-level MLP-based methods frequently alter activation maps, reducing efficiency gains. In this paper, we introduce \textbf{SparseInfer}, an MLP-free adaptive sparse activation inference method based on sentence-level prediction. We first propose the concept of core neurons and empirically demonstrate that, for an input sentence, LLMs only need the core neurons to maintain performance. Remarkably, we discovered that core neurons exhibit both stability and similarity in relation to the sentence's semantics—an insight overlooked by previous studies. Building on this finding, we design two semantic-based methods for predicting core neurons to fit different input scenarios, which enables core neurons to be determined during the pre-filling stage and fixed during the encoding stage. Our experiments verify SparseInfer exhibits good performance in various tasks and achieve 10.33$\times$ speed up.

ICML 2026

Advancing Analytic Class-Incremental Learning through Vision-Language Calibration

Binyu Zhao, Wei Zhang, Xingrui Yu, Zhaonian Zou, Ivor Tsang

Class-incremental learning (CIL) with pre-trained models (PTMs) faces a critical trade-off between efficient adaptation and long-term stability. While analytic learning enables rapid, recursive closed-form updates, its efficacy is often compromised by accumulated errors and feature incompatibility. In this paper, we first conduct a systematic study to dissect the failure modes of PTM-based analytic CIL, identifying representation rigidity as the primary bottleneck. Motivated by this insight, we propose **VILA**, a novel dual-branch framework that advances analytic CIL via a two-level vision-language calibration strategy. Specifically, we coherently fuse plastic, task-adapted features with a frozen, universal visual anchor at the feature level through geometric calibration, and leverage cross-modal semantic priors at the decision level to rectify prediction bias. This confluence maintains analytic-learning's extreme efficiency while overcoming its inherent brittleness. Extensive experiments across eight benchmarks demonstrate that VILA consistently yields superior performance, particularly in fine-grained and long-sequence scenarios. Our framework harmonizes high-fidelity prediction with the simplicity of analytic learning. Our code is available at https://github.com/byzhaoAI/VILA.

ICML 2026

Kuramoto Oscillatory Phase Encoding: Neuro-inspired Synchronization for Improved Learning Efficiency

Mingqing Xiao, Yansen Wang, Dongqi Han, Caihua Shan, Dongsheng Li

Spatiotemporal neural dynamics and oscillatory synchronization are widely implicated in biological information processing and have been hypothesized to support flexible coordination such as feature binding. By contrast, most deep learning architectures represent and propagate information through activation values, neglecting the joint dynamics of rate and phase. In this work, we introduce Kuramoto oscillatory Phase Encoding (KoPE) as an additional, evolving phase state to Vision Transformers, incorporating a neuro-inspired synchronization mechanism to advance learning efficiency. We show that KoPE can improve training, parameter, and data efficiency of vision models through synchronization-enhanced structure learning. Moreover, KoPE benefits tasks requiring structured understanding, including semantic and panoptic segmentation, representation alignment with language, and few-shot abstract visual reasoning (ARC-AGI). Theoretical analysis and empirical verification further suggest that KoPE can accelerate attention concentration for learning efficiency. These results indicate that synchronization can serve as a scalable, neuro-inspired mechanism for advancing state-of-the-art neural network models.

ICML 2026

LEGO-FL: Learning Heterogeneous Federated Models as a LEGO Assembly Games

Zeqi Leng, Chunxu Zhang, Guodong Long, Bo Yang

Just as LEGO pieces can be assembled into an unlimited variety of structures, heterogeneous federated learning (HFL) can be viewed as the assembly of diverse model components. Inspired by this analogy, we reformulate HFL as a LEGO-like assembly game. The central challenge in HFL lies in learning across heterogeneous model architectures, which hinders direct parameter sharing. To address this challenge, we propose to decompose models into a set of modular components—analogous to LEGO pieces and collaboratively learn these components across clients under predefined composition rules. Based on this perspective, we develop a novel federated learning framework, termed LEGO-FL, which enables flexible model construction while preserving collaborative learning. Extensive experiments validate the effectiveness of LEGO-FL under different heterogeneous settings and system scales.

ICML 2026

Correctness-Optimized Residual Activation Lens (CORAL): Transferrable and Calibration-Aware Inference-Time Steering

Miranda Muqing Miao, Young Min Cho, Lyle Ungar

Large language models (LLMs) exhibit persistent miscalibration, especially after instruction tuning and preference alignment. Modified training objectives can improve calibration, but retraining is expensive. Inference-time steering offers a lightweight alternative, yet most existing methods optimize proxies for correctness rather than correctness itself. We introduce CORAL (Correctness-Optimized Residual Activation Lens), a regularized inference-time steering method that captures distributed correctness signals from model internal activations using weight-decay MLP probes. We evaluate CORAL across three 7B-parameter models and find that it consistently improves accuracy by 10\% and expected calibration error (ECE) by 50\% on average. We additionally demonstrate that these gains transfer without retraining to the complete published test sets of four held-out benchmarks (ARC-Challenge, HellaSwag, Math-MC, OpenBookQA), averaging 14\% accuracy improvements and 49\% ECE improvements. Our results support the hypothesis that distributed information in model internals can be extracted using regularized probes when individual neurons are insufficient. CORAL thus provides a compute-efficient, transferable, and calibration-aware approach to improve MCQA performance during inference.

ICML 2026

EngiAgent: Fully Connected Coordination of LLM Agents for Solving Open-ended Engineering Problems with Feasible Solutions

Xiyuan Zhou, Ruixi Zou, Xinlei Wang, Yuheng Cheng, Yan Xu, Junhua Zhao, Jinjin Gu

Engineering problem solving is central to real-world decision-making, requiring mathematical formulations that not only represent complex problems but also produce feasible solutions under data and physical constraints. Unlike mathematical problem solving, which operates on predefined formulations, engineering tasks demand open-ended analysis, feasibility-driven modeling, and iterative refinement. Although large language models (LLMs) have shown strong capabilities in reasoning and code generation, they often fail to ensure feasibility, which limits their applicability to engineering problem solving. To address this challenge, we propose EngiAgent, a multi-agent system with a fully connected coordinator that simulates expert workflows through specialized agents for problem analysis, modeling, verification, solving, and solution evaluation. The fully connected coordinator enables flexible feedback routing, overcoming the rigidity of prior pipeline-based reflection methods and ensuring feasibility at every stage of the process. This design not only improves robustness to diverse failure cases such as data extraction errors, constraint inconsistencies, and solver failures, but also enhances the overall quality of problem solving. Empirical results across four representative domains demonstrate that EngiAgent achieves substantial improvements in feasibility compared to prior approaches, establishing a new paradigm for feasibility-oriented engineering problem solving with LLMs. Our source code and data are available at https://github.com/AI4Engi/EngiAgent.

ICML 2026

Large Scale Manifold Balanced Clustering

FangFang Li, Quanxue Gao, Xingyu Xue

Manifold clustering has demonstrated strong capability in capturing complex data structures and has been widely studied in cluster analysis. However, many existing methods mainly focus on combining K-means with manifold learning, while overlooking the consistency between data structures and clustering labels, and often suffer from high computational cost when handling large scale data. To address these issues, we propose a manifold balanced clustering method based on anchor induced distance(LMBC), grounded in the relationship between K-means clustering and manifold learning. Specifically, the LMBC uses label information to guide the construction of the manifold structure, thereby ensuring consistency between data structures and clustering labels. To enable large scale clustering, we introduce an anchor induced distance representation that models manifold structure in a compact anchor space, significantly reducing computational complexity while preserving essential structural information. Furthermore, to naturally maintain class balance during clustering, we maximize the Schatten-p norm of the label representation and provide theoretical analysis to support its effectiveness. Experimental results on several benchmark datasets demonstrate the effectiveness and scalability of the proposed method.

ICML 2026

LEMUR: Learned Multi-Vector Retrieval

Elias Jääsaari, Ville Hyvönen, Teemu Roos

Multi-vector representations generated by late interaction models, such as ColBERT, enable superior retrieval quality compared to single-vector representations in information retrieval applications. In multi-vector retrieval systems, both queries and documents are encoded using one embedding per token, and similarity between queries and documents is measured by the MaxSim similarity measure. However, the improved quality of multi-vector retrieval comes at the expense of significantly increased search latency. In this work, we introduce LEMUR, a simple yet efficient framework for multi-vector similarity search. LEMUR consists of two consecutive problem reductions: First, we formulate multi-vector similarity search as a supervised learning problem that can be solved using a one-hidden-layer neural network. Second, we reduce inference under this model to single-vector similarity search in its latent space, enabling the use of existing single-vector search indexes to accelerate retrieval. LEMUR is an order of magnitude faster than prior multi-vector similarity search methods. Our code is available at https://github.com/ejaasaari/lemur

ICML 2026

Reasoning Theater: Disentangling Model Beliefs from Chain-of-Thought

Siddharth Boppana, Annabel Ma, Max Loeffler, Raphaël Sarfati, Eric Bigelow, Atticus Geiger, Owen Lewis, Jack Merullo

We provide evidence of \textit{performative} chain-of-thought (CoT) in reasoning models, where a model becomes strongly confident in its final answer, but continues generating tokens without revealing its internal belief. Our analysis compares activation probing, early forced answering, and a CoT monitor across two large models (DeepSeek-R1 671B \& GPT-OSS 120B) and find task difficulty-specific differences: The model's final answer is decodable from activations far earlier in CoT than a monitor is able to say, especially for easy recall-based MMLU questions. We contrast this with genuine reasoning in difficult multihop GPQA-Diamond questions. Despite this, \textit{inflection points} (e.g., backtracking, `aha' moments) occur almost exclusively in responses where probes show large belief shifts, suggesting these behaviors track genuine uncertainty rather than learned ``reasoning theater." Finally, probe-guided early exit reduces tokens by up to 80\% on MMLU and 30\% on GPQA-Diamond with similar accuracy, positioning attention probing as an efficient tool for detecting performative reasoning and enabling adaptive computation.

ICML 2026

A Minimax Approach for Optimal Intervention Policy Learning with Two-Stage Outcomes

Chenyang Li, hao mei, Yue Liu

When designing interventions to promote desired actions, two-stage agent heterogeneity -- encompassing both engagement with the intervention and completion of the desired action -- creates significant challenges in identifying optimal intervention policies. While this two-dimensional heterogeneity creates distinct agent response types with varying marginal policy returns, existing literature typically falls short in full identification of all agent types, leading to inefficient intervention allocations. To address the challenge of learning optimal policies that account for two-stage outcomes, we propose a minimax approach within a counterfactual principal strata framework. A value function, accommodating varying policy returns across six potentially non-identifiable principal strata, is designed and partially identified to minimize the worst-case value loss relative to three benchmark policies: never-treat, always-treat, and oracle. We introduce three estimators for optimal policy learning: Principal Outcome Regression (P-OR), Principal Inverse Propensity Scoring (P-IPS), and Principal Doubly Robust (P-DR), providing theoretical guarantees for their unbiasedness, robustness, and regret upper bounds. Extensive numerical experiments demonstrate the effectiveness and superiority of the proposed approach.

ICML 2026

When Diffusion Language Models Hesitate: Detecting and Correcting Visual Hallucinations via Confidence Fluctuation

Wenzheng Song, Pei Chen, Yichen Tan, Zejian Li, Lingyun Sun

Multi-modal Diffusion Language Models (MDLMs) have emerged as a powerful alternative to autoregressive models in vision understanding, offering advantages in bidirectional context modeling and parallel decoding. However, existing MDLMs suffer from visual hallucinations due to the static nature of visual perception. Unlike autoregressive models, MDLMs lack the sequential dependency to dynamically interact with visual content. Therefore, MDLMs rely on fixed visual features encoded at initialization, causing the denoising process to drift toward language priors and lose its anchor to visual evidence. In this paper, we propose VGR (Visual-Guided Refinement), a framework that enables MDLMs to revisit visual details by exploiting diffusion dynamics. Our key insight is that the temporal trajectory of confidence during denoising reveals intrinsic uncertainty: while grounded tokens converge smoothly, hallucinated ones exhibit pronounced confidence fluctuation. VGR utilizes this fluctuation signal to detect uncertain spans and corrects them through targeted visual evidence extraction and in-place remasking. Extensive experiments on image captioning and hallucination evaluation benchmarks demonstrate that our method reduces hallucinations and recalls more details. We release our code at https://github.com/SongWZ3214/VGR.

ICML 2026

Shared Lexical Task Representations Explain Behavioral Variability In LLMs

Zhuonan Yang, Xiaochen Li, Francisco Piedrahita Velez, Eric Todd, David Bau, Michael Littman, Stephen Bach, Ellie Pavlick

One of the most common complaints about large language models (LLMs) is their prompt sensitivity---that is, the fact that their ability to perform a task or provide a correct answer to a question can depend unpredictably on the way the question is posed. We investigate this variation by comparing two very different but commonly-used styles of prompting: *instruction-based* prompts, which describe the task in natural language, and *example-based* prompts, which provide in-context few-shot demonstration pairs to illustrate the task. We find that, despite large variation in performance as a function of the prompt, the model engages some common underlying mechanisms across different prompts of a task. Specifically, we identify task-specific attention heads whose outputs literally describe the task --- which we dub *lexical task heads*---and show that these heads are shared across prompting styles and trigger subsequent answer production. We further find that behavioral variation between prompts can be explained by the degree to which these heads are activated, and that failures are at least sometimes due to competing task representations that dilute the signal of the target task. Our results together present an increasingly clear picture of how LLMs' internal representations can explain behavior that otherwise seems idiosyncratic to users and developers.

ICML 2026

OPTION: Optimal Transport–Guided Flow Matching for Incomplete and Unaligned Multi-View Clustering

Siyuan Zhou, Zhibin Gu

Multi-view clustering effectively exploits rich information from multiple views, yet real-world applications are frequently challenged by missing views and cross-view sample misalignment, hindering cross-view modeling and resulting in inferior clustering performance. To address these challenges, this paper presents a novel method, **OP**timal **T**ransport–Gu**I**ded fl**O**w Matchi**N**g for incomplete and unaligned multi-view clustering (**OPTION**). Specifically, OPTION employs conditional flow matching to learn deterministic transport paths for missing-view imputation, enabling stable manifold-preserving recovery and more discriminative representations. To support alignment-free fusion, we introduce a Gromov-Wasserstein-inspired structural regularization that aligns intra-view geometric structures in the latent space without solving hard correspondences. Furthermore, an optional contrastive regularization is incorporated to enhance cross-view consistency specifically for aligned settings. Extensive experiments demonstrate that OPTION outperforms state-of-the-art methods across ideal, incomplete, and unaligned scenarios evaluated separately. Code: https://github.com/TimoZhou1024/OPTION.

ICML 2026

Reason with Thumbnails, Answer with Focus: An Efficient and Effective Paradigm for Multimodal Grounded Visual Reasoning

An-Lan Wang, Guozhi Tang, Lei Liao, Hanshen Zhu, Kai Huang, Jingqun Tang, Jiaming Zhou, Kun-Yu Lin

To enhance the interpretability of multimodal large language models' outputs, recent efforts explored Grounded Visual Reasoning (GVR), in which the model is trained to select relevant image regions before answering the question. However, the multi-round ``ground-then-answer'' and reasoning nature of these methods imposes much more computational costs compared to non-GVR methods. To attain efficient and effective GVR, in this paper, we propose a novel paradigm called Reason with Thumbnails, Answer with Focus (RTAF), which feeds the model with low-resolution images to reason the relevant regions and high-resolution crops to answer the final answer. Our motivation arises from the observation that, in many cases, the key area required to answer questions can be inferred from the low-resolution thumbnails, without the need for a full-resolution image. Additionally, for extreme cases where thumbnails lack sufficient information (leading to undirected region guessing and increased computation), we equip the model with a tool to access higher-resolution images. For training efficiency, we adopt pure reinforcement learning (i.e., GRPO) and design a suite of reward functions to supervise the model's behavior, alongside a resolution-aware training data selection strategy. Finally, our model, based on Qwen2.5-VL, achieves significant improvements across a range of benchmarks with reduced computation, demonstrating the effectiveness and efficiency of our proposed RTAF, e.g., compared to the non-GVR model Qwen2.5-VL, our model achieves a performance gain of 5.8 while using comparable visual tokens (471 vs. 391). Against state-of-the-art GVR methods, RTAF reduces visual token usage by half while delivering superior performance.

ICML 2026

Modelling Attention with Aitchison Geometry: Token Distinguishability and Temperature Scaling

Sam Hilton-Jones, Timothy J. Norman, Zhanxing Zhu

The attention mechanism with softmax normalisation is a foundational component of Transformer-based large language models. However, with very long contexts, attention scores are known to diminish, raising fundamental questions about token distinguishability and how it can be preserved. In this work, we provide a formal characterisation of token distinguishability in attention as a function of context length and embedding dimension. We introduce Aitchison distance to quantify relative differences among attention probabilities, and show that, with Gaussian queries and keys, even in the long-context regime, token distinguishability converges to a finite, non-zero limit rather than vanishing. Leveraging the linear relationship between inverse-temperature scaling and Aitchison distance, we derive a theoretical lower bound of $\Omega(\sqrt{\log L})$ on the logit scaling required to produce a sharp attention distribution. Finally, we demonstrate that Aitchison distance provides a principled and practical alternative to entropy for monitoring training and inference, as it captures the full compositional structure, including the smaller components of the attention probabilities.

ICML 2026

MUSA-PINN: Multi-scale Weak-form Physics-Informed Neural Networks for Fluid Flow in Complex Geometries

Weizheng Zhang, Xunjie Xie, Hao Pan, Xiaowei Duan, Bingteng Sun, Qiang Du, Lin Lu

While Physics-Informed Neural Networks (PINNs) offer a mesh-free approach to solving fluid-flow PDEs, standard point-wise residual minimization suffers from convergence pathologies in topologically complex domains like Triply Periodic Minimal Surfaces (TPMS). The locality bias of point-wise constraints fails to propagate global information through tortuous channels, causing unstable gradients and conservation violations. To address this, we propose the Multi-scale Weak-form PINN (MUSA-PINN), which reformulates Navier-Stokes equation constraints as integral conservation laws over hierarchical spherical control volumes. We enforce continuity and momentum conservation via flux-balance residuals on control surfaces. Our method utilizes a three-scale subdomain strategy-comprising large volumes for long-range coupling, skeleton-aware meso-scale volumes aligned with transport pathways, and small volumes for local refinement-alongside a two-stage training schedule prioritizing continuity. Experiments on steady incompressible flow in TPMS geometries show MUSA-PINN outperforms state-of-the-art baselines, reducing relative errors by up to 93\% and preserving mass conservation.

Keep browsing

More papers from top AI conferences

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