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

Directional Neural Collapse Explains Few-Shot Transfer in Self-Supervised Learning

Achleshwar Luthra, Yash Salunkhe, Tomer Galanti

Frozen self-supervised representations often transfer well with only a few labels across many semantic tasks. We argue that a single geometric quantity, *directional* CDNV (decision-axis variance), sits at the core of two favorable behaviors: strong few-shot transfer within a task, and low interference across many tasks. We show that both emerge when variability *along* class-separating directions is small. First, we prove sharp non-asymptotic multiclass generalization bounds for downstream classification whose leading term is the directional CDNV. The bounds include finite-shot corrections that cleanly separate intrinsic decision-axis variability from centroid-estimation error. Second, we link decision-axis collapse to multitask geometry: for independent balanced labelings, small directional CDNV across tasks forces the corresponding decision axes to be nearly orthogonal, helping a single representation support many tasks with minimal interference. Empirically, across SSL objectives, directional CDNV collapses during pretraining even when classical CDNV remains large, and our bounds closely track few-shot error at practical shot sizes. Additionally, on synthetic multitask data, we verify that SSL learns representations whose induced decision axes are nearly orthogonal.

ICML 2026

Learning to Route Languages for Multilingual Policy Optimization

Geyang Guo, Hiromi Wakaki, Yuki Mitsufuji, Alan Ritter, Wei Xu

Large language models~(LLMs) are trained on heterogeneous multilingual corpora, yet existing policy optimization methods often implicitly restrict each training question to a single response language or rely on a fixed dominant language for supervision. We propose language-routed policy optimization (LRPO), an online reinforcement learning framework that treats language as a selectable variable. LRPO elicits multilingual rollouts for each training question and integrates their relative quality into preference-based policy updates, increasing the diversity and informativeness of training signals under the fixed rollout budget. To adaptively determine which languages to explore during reinforcement learning, we introduce a trainable language router formulated as a multi-armed bandit, balancing exploration of underutilized languages with exploitation of more informative ones. Extensive experiments show that LRPO consistently improves multilingual performance, demonstrating that adaptive language routing enables effective cross-lingual knowledge exploitation for training. We release all the resources at \url{https://github.com/Guochry/LRPO}.

ICML 2026

SLQ: Bridging Modalities via Shared Latent Queries for Retrieval with Frozen MLLMs

Haoran Lou, Ziyan Liu, Chunxiao Fan, Yuexin Wu, Yue Ming, Hao Wu, Kai Zuo, Yibo Chen, Xu Tang

Multimodal Large Language Models (MLLMs) possess intrinsic reasoning and world-knowledge capabilities, yet adapting them for dense retrieval remains challenging. Existing approaches rely on invasive parameter updates, such as full fine-tuning and LoRA, which may disrupt the pre-trained semantic space and impair the structured knowledge essential for reasoning. To address this, we propose **SLQ**, a parameter-efficient tuning framework that adapts MLLMs for retrieval while keeping the backbone entirely frozen. SLQ introduces a small set of **Shared Latent Queries** that are appended to both text and image tokens, leveraging the model’s native causal attention to aggregate multimodal context into a unified embedding space. Furthermore, to better evaluate retrieval beyond superficial pattern matching, we construct **KARR-Bench**, a benchmark designed for knowledge-aware reasoning retrieval. Extensive experiments show that SLQ outperforms full fine-tuning and LoRA on COCO and Flickr30K, while achieving competitive performance on MMEB and yielding substantial gains on KARR-Bench, validating that preserving the pre-trained representations via non-invasive adaptation is an effective strategy for MLLM-based retrieval. The code is available under: https://github.com/CnFaker/SLQ.

ICML 2026

SpecPL: Disentangling Spectral Granularity for Prompt Learning

Jingtao Zhou, Xirui Kang, feiyang huang, Lai Man Po

Existing prompt learning for VLMs exhibits a modality asymmetry, predominantly optimizing text tokens while still relying on frozen visual encoder as holistic extractor and neglecting the spectral granularity essential for fine-grained discrimination. To bridge this, we introduce Disentangling Spectral Granularity for Prompt Learning (SpecPL), which approaches prompt learning from a novel spectral perspective via Counterfactual Granule Supervision. Specifically, we leverage a frozen VAE to decompose visual signals into semantic low-frequency bands and granular high-frequency details. A frozen Visual Semantic Bank anchors text representations to universal low-frequency invariants, mitigating overfitting. Crucially, fine-grained discrimination is driven by counterfactual granule training: by permuting high-frequency signals, we compel the model to explicitly distinguish visual granularity from semantic invariance. Uniquely, SpecPL serves as a universal plug-and-play booster, revitalizing text-oriented baselines like CoOp and MaPLe via visual-side guidance. Experiments on 11 benchmarks demonstrate competitive state-of-the-art performance, achieving a new performance ceiling of 81.51\% harmonic-mean accuracy. These results validate that spectral disentanglement with counterfactual supervision effectively bridges the gap in the stability-generalization trade-off.

ICML 2026

LUCID: Attention with Preconditioned Representations

Sai Surya Duvvuri, Nirmal Patel, Nilesh Gupta, Inderjit S Dhillon

Softmax-based dot-product attention is a cornerstone of Transformer architectures, enabling remarkable capabilities such as in-context learning. However, as context lengths increase, a fundamental limitation of the softmax function emerges: it tends to diffuse probability mass to irrelevant tokens degrading performance in long-sequence scenarios. Furthermore, attempts to sharpen focus by lowering softmax temperature hinder learnability due to vanishing gradients. We introduce LUCID Attention, an architectural modification that applies a preconditioner to the attention probabilities. This preconditioner, derived from exponentiated key-key similarities, minimizes overlap between the keys in a Reproducing Kernel Hilbert Space, thus allowing the query to focus on important keys among large number of keys accurately with same computational complexity as standard attention. Additionally, LUCID's preconditioning-based approach to retrieval bypasses the need for low temperature and the learnability problems associated with it. We validate our approach by training $\sim$1 billion parameter language models evaluated on up to 128K tokens. Our results demonstrate significant gains on long-context retrieval tasks, specifically retrieval tasks from BABILong, RULER, SCROLLS and LongBench. For instance, LUCID achieves up to 18\% improvement in BABILong and 14\% improvement in RULER multi-needle performance compared to standard attention.

ICML 2026

Broadening the Backdoor Basin: Understanding LLM Backdoors Collapse and Making Backdoors Persistent

Xingyi Zhao, Tian Xie, Xiaojun Qi, Depeng Xu, Shuhan Yuan

Large Language Models (LLMs) are vulnerable to backdoor attacks, yet we observe that many LLM backdoors do not survive when end users perform supervised fine-tuning (SFT). In this work, we provide a geometric explanation: by probing the backdoor objective under controlled weight perturbations, we find that conventional poisoning often drives the backdoor loss to a narrow and sharp basin; consequently, even modest parameter drift induced by downstream SFT can push the model out of the low-loss and high-ASR region, leading to rapid backdoor forgetting. Motivated by this insight, we propose BAD-BOOM, a resilient backdoor attack via broader smoothness minimization, which explicitly broadens and smooths the backdoor basin. BAD-BOOM extends sharpness-aware minimization with a Fisher-induced ellipsoidal constraint that allocates larger perturbation budgets to backdoor-sensitive parameters, encouraging solutions whose neighborhoods also maintain low backdoor loss. Across two threat settings, three attack scenarios, three open-source LLMs, and three trigger-free downstream SFT tasks, BAD-BOOM consistently preserves high ASR while maintaining competitive utility. The code is available at https://github.com/xingyizhao/BAD-BOOM.

ICML 2026

The Shape of Addition: Geometric Structures of Arithmetic in Large Language Models

Liuyuan Wen, Xun Zhu, Lihao Huang, Wenbin Li, Yang Gao

Large Language Models exhibit paradoxical fragility in fundamental arithmetic, implying a disconnect between internal computation and discrete output. By analyzing the residual stream geometry during multi-operand addition, we identify the **Iso-Raw-Sum Trajectory (IRST)**, a topological manifold where representations are anchored by semantic digits and modulated by continuous carry fibers. We propose the **Noisy Quantization Model**, which frames arithmetic errors as *topological slippages* caused by internal neural noise pushing a continuous, latent *carry potential* across quantization thresholds. This geometric framework further elucidates *probe versatility*, explaining how lightweight probes can disentangle conflicting latent signals (such as ground truth versus hallucination) from a single activation vector. Finally, we validate these insights through a geometric consistency check method that effectively detects and corrects these quantization failures during inference.

ICML 2026

From Drift to Coherence: Stabilizing Beliefs in LLMs

SongEun Kim, Seungyoo Lee, Edwin Fong, Hyungi Lee, Juho Lee

Large language models (LLMs) are often hypothesized to perform implicit Bayesian inference, yet a key coherence condition—the martingale property of predictive beliefs—has been shown to fail in controlled synthetic in-context learning settings. We revisit this question in a more typical usage regime: generic multiple-choice question answering. Exploiting the discrete answer space, we compute exact predictive distributions and study belief dynamics induced by autoregressive answer resampling. We introduce prompted predictive resampling (PPR), where an LLM generates a sequence of answers to the same question. Empirically, PPR reveals early-stage belief drift, indicating martingale violations. However, after sufficient resampling steps, the belief process self-stabilizes and converges to a coherent predictive distribution. Based on this observation, we further propose (i) a seed-answer prompting strategy to accelerate stabilization, and (ii) a self-consistency loss that amortizes early-stage drift into the model via fine-tuning. Experiments on multiple-choice QA benchmarks show that our methods substantially reduce belief drift and improve predictive coherence without sacrificing accuracy.

ICML 2026

One-shot Entropy Minimization for Language Model Reasoning

Zitian Gao, Yilong Chen, Haoming Luo, Joey Zhou, Bryan Dai

In this work, we propose One-shot Entropy Minimization (EM), a simple and fully unsupervised post-training approach that significantly improves reasoning and generation performance using only a single unlabeled data and approximately ten gradient steps. To avoid data contamination, we pretrain a 7-billion-parameter language model from scratch with strictly decontaminated data. Despite its extreme simplicity, one-shot EM yields substantial performance gains and improves reasoning abilities across a broad range of domains, including mathematical reasoning, logical reasoning, and coding. We further show that entropy minimization induces a characteristic right-skewed logit shift, amplifying high-probability tokens while suppressing low-probability tails, in contrast to reinforcement learning. Our findings suggest that entropy minimization primarily acts as a distribution shaping mechanism rather than a conventional learning process, offering an efficient and practical algorithm for post-training large language models.

ICML 2026

Safe Reinforcement Learning with Preference-based Constraint Inference

Chenglin Li, Grant Ruan, Hua Geng

Safe reinforcement learning (RL) is a standard paradigm for safety-critical decision making. However, real-world safety constraints can be complex, subjective, and even hard to explicitly specify. Existing works on constraint inference rely on restrictive assumptions or extensive expert demonstrations, which are not realistic in many real-world applications. How to cheaply and reliably learn these constraints is the major challenge we focus on in this study. While inferring constraints from human preferences offers a data-efficient alternative, we identify popular Bradley-Terry (BT) models fail to capture the asymmetric, heavy-tailed nature of safety costs, resulting in risk underestimation. It is still rare in the literature to understand the impacts of BT models on the downstream policy learning. To address the above knowledge gaps, we propose a novel approach namely Preference-based Constrained Reinforcement Learning (PbCRL). We introduce a novel dead zone mechanism into preference modeling and theoretically prove that it encourages heavy-tailed cost distributions, thereby achieving better constraint alignment. Additionally, we incorporate a Signal-to-Noise Ratio (SNR) loss to encourage exploration by cost variances, which is found to benefit policy learning. Further, two-stage training strategy is deployed to lower online labeling burdens while adaptively enhancing constraint satisfaction. Empirical results demonstrate that PbCRL achieves superior alignment with true safety requirements and outperforms state-of-the-art baselines in terms of safety and reward. Our work explores a promising and effective way for constraint inference in Safe RL, with great potential in various safety-critical applications.

ICML 2026

M-Star: Markovian Projection of Star-Shaped Diffusion for Exponential Family Distributions

François Bertholom, Khalid Oublal

Diffusion models achieve state-of-the-art performance in generative modeling but are limited by their reliance on Gaussian noise and the high computational cost of iterative sampling. Star-shaped diffusion addresses the former by introducing a non-Markovian forward process, yet this comes at the expense of temporal coherence in the reverse process. We propose a novel framework that resolves this trade-off by learning a Markovian projection of a star-shaped forward process, and its reversal. This design enables learning over a broad class of exponential models and recovers DDPM as a special case. It is particularly well-suited for knowledge distillation, allowing few-step or even single-step generation. Experiments demonstrate the effectiveness and flexibility of our approach across multiple generative tasks. Code and demo are available at: https://oublalkhalid.github.io/MStar-Diffusion/.

ICML 2026

Unsupervised Partner Design Enables Robust Ad-hoc Teamwork

Constantin Ruhdorfer, Matteo Bortoletto, Victor Oei, Anna Penzkofer, Andreas Bulling

We introduce Unsupervised Partner Design (UPD), a population-free multi-agent reinforcement learning method for robust ad-hoc teamwork. UPD generates training partners on-the-fly and selects them adaptively based on a learnability criterion, removing the need for pre-trained partner populations or manual parameter tuning. We show that this simple mechanism enables effective partner diversity and can be extended to joint partner-environment selection when a procedural level generator is available. Across Level-Based Foraging, Overcooked-AI, and the Overcooked Generalisation Challenge, UPD consistently achieves strong performance compared to both population-based and population-free baselines. In a human-AI user study, agents trained with UPD achieve higher returns and are rated as more adaptive, more human-like, and less frustrating than all evaluated baseline methods.

ICML 2026

Disentangling Consensus and Value-Specific Representations for Controllable Pluralistic Value Alignment of LLMs

JianKui Zhou, Jing Yao, Xiaoyuan Yi, Peng Zhang, Ning Gu, Zhan Hu, Xing Xie, Tun Lu

With the widespread deployment of large language models (LLMs), aligning model outputs with pluralistic human values has become an important research problem. Recent approaches that train task-specific experts and merge them through parameter aggregation have shown promise for pluralistic alignment. However, these methods often overlook the intrinsic complexity of real-world value data, where multiple correlated value dimensions coexist, resulting in highly similar and entangled expert representations. Consequently, modifying the contribution of one value expert may unintentionally influence other values, limiting fine-grained controllability. To address this issue, we propose DisAlign, a model-merging framework that explicitly decomposes value representations into consensus and value-specific components using an information-geometric perspective. DisAlign first extracts a consensus anchor and subspace to capture shared structure across values, and then applies spectral decomposition to the residual representations to construct disentangled value subspaces. This design enables more precise and independent modulation of multiple values. Experiments on three datasets covering different value frameworks demonstrate that DisAlign consistently improves value disentanglement and achieves more accurate pluralistic value control compared to existing baselines. Our code is available at \url{https://anonymous.4open.science/r/DisAlign-7F35}

ICML 2026

Computational Arbitrage in AI Model Markets

Ricardo Olmedo, Bernhard Schölkopf, Moritz Hardt

Consider a market of competing model providers selling query access to models with varying costs and capabilities. Customers submit problem instances and are willing to pay up to a budget for a verifiable solution. An arbitrageur efficiently allocates inference budget across providers to undercut the market, thus creating a competitive offering with no model-development risk. In this work, we initiate the study of arbitrage in AI model markets, empirically demonstrating the viability of arbitrage and illustrating its economic consequences. We conduct an in-depth case study of SWE-bench GitHub issue resolution using two representative models, GPT-5 mini and DeepSeek v3.2. In this verifiable domain, simple arbitrage strategies generate net profit margins of up to 40\%. Robust arbitrage strategies that generalize across different domains remain profitable. Distillation further creates strong arbitrage opportunities, potentially at the expense of the teacher model’s revenue. Multiple competing arbitrageurs drive down consumer prices, reducing the marginal revenue of model providers. At the same time, arbitrage reduces market segmentation and facilitates market entry for smaller model providers by enabling earlier revenue capture. Our results suggest that arbitrage can be a powerful force in AI model markets with implications for model development, distillation, and deployment.

ICML 2026

BALLAST: Bayesian Active Learning with Look-ahead Amendment for Sea-drifter Trajectories under Spatio-Temporal Vector Fields

Rui-Yang Zhang, Lachlan Astfalck, Edward Cripps, David S. Leslie, Henry Moss

We introduce a formal active learning methodology for guiding the placement of Lagrangian observers to infer time-dependent vector fields -- a key task in oceanography, marine science, and ocean engineering -- using a physics-informed spatio-temporal Gaussian process surrogate model. The majority of existing placement campaigns either follow standard `space-filling' designs or relatively ad-hoc expert opinions. A key challenge to applying principled active learning in this setting is that Lagrangian observers are continuously advected through the vector field, so they make measurements at different locations and times. It is, therefore, important to consider the likely future trajectories of placed observers to account for the utility of candidate placement locations. To this end, we present BALLAST: Bayesian Active Learning with Look-ahead Amendment for Sea-drifter Trajectories. We observe noticeable benefits of BALLAST-aided sequential observer placement strategies on both synthetic and high-fidelity ocean current models. In addition, we developed a novel GP inference method -- the Vanilla SPDE Exchange (VaSE) -- to boost the GP posterior sampling efficiency, which is also of independent interest.

ICML 2026

Explicitly Modeling Censoring Produces Superior Survival Predictors

Shi-ang Qi, Yakun Yu, Russell Greiner

Likelihood-based training is the dominant paradigm in survival prediction. Under independent censoring, we can factorize the likelihood and optimize only the terms related to event modeling, effectively treating the censoring mechanism as incidental. This is justified when censoring is *non-informative*, i.e., when the censoring process shares no parameters with the event-time model. However, this may not hold in practice, and ignoring censoring contributions may discard useful signals for learning representations that can help to effectively estimate event distributions. Motivated by this, we argue that explicitly modeling censoring can improve representation learning and time-to-event estimation, particularly when event and censoring processes are coupled. We introduce a latent decomposition view in which observed covariates are mapped to latent components corresponding to event-specific, censoring-specific, confounding, and irrelevant information. We then learn decomposed representations for the first three categories to guide a better estimation of the event distribution. We instantiate our method on 4 popular deep-learning survival models and evaluate on 10 datasets (2 semi-synthetic and 8 real-world), showing consistent gains over strong baselines and multiple SOTA methods.

ICML 2026

Pull Requests as a Training Signal for Repo-Level Code Editing

Qinglin Zhu, Tianyu Chen, Shuai Lu, Lei Ji, Runcong Zhao, Murong Ma, Xiangxiang Dai, Yulan He, Lin Gui, Peng Cheng, Yeyun Gong

Repository-level code editing requires models to understand complex dependencies and execute precise multi-file modifications across a large codebase. While recent gains on SWE-bench rely heavily on complex agent scaffolding, it remains unclear how much of this capability can be internalised via high-quality training signals. To address this, we propose Clean Pull Request (Clean-PR), a mid-training paradigm that leverages real-world GitHub pull requests as a training signal for repository-level editing. We introduce a scalable pipeline that converts noisy pull request diffs into Search/Replace edit blocks through reconstruction and validation, resulting in the largest publicly available corpus of 2 million pull requests spanning 12 programming languages. Using this training signal, we perform a mid-training stage followed by an agentless-aligned supervised fine-tuning process with error-driven data augmentation. On SWE-bench, our model significantly outperforms the instruction-tuned baseline, achieving absolute improvements of 13.6% on SWE-bench Lite and 12.3% on SWE-bench Verified. These results demonstrate that repository-level code understanding and editing capabilities can be effectively internalised into model weights under a simplified, agentless protocol, without relying on heavy inference-time scaffolding.

ICML 2026

Shift-Dependent Asymmetry: Orthogonal Inverse Low-Rank Adaptation for Federated Medical Segmentation

Xingyue Zhao, Wenke Huang, Linghao Zhuang, Haoran Wu, Anwen Jiang, Zhifeng Wang, Wenwen He, Ming Feng, Mang Ye, bo xu

Low-Rank Adaptation (LoRA) enables efficient federated fine-tuning of segmentation foundation models for medical imaging. However, most federated LoRA methods adopt a uniform aggregation rule, which breaks under the encoder–decoder asymmetry in medical segmentation: the encoder is dominated by appearance shifts, while the decoder is dominated by supervision variations. This mismatch entangles shared anatomy with site-specific biases and harms generalization. To address this, we propose Inverse Asymmetric Tuning (IAT). IAT aligns adaptation with heterogeneity sources by personalizing module-specific components in the encoder to absorb appearance shifts and in the decoder to accommodate site-dependent supervision, while retaining a shared pathway for transferable consensus. However, structural separation alone is insufficient under LoRA’s bilinear parameterization, where multiplicative coupling can still cause site-specific updates to leak into the shared direction. We therefore introduce a Subspace Orthogonality Regularizer that penalizes shared–local collinearity in the effective update space, mitigating leakage without extra communication. Experiments show consistent improvements over strong federated LoRA and parameter-efficient FL baselines.

ICML 2026

MetaOthello: A Controlled Study of Multiple World Models in Transformers

Aviral Chawla, Galen Hall, Juniper L Lovato

Foundation models must handle multiple generative processes, yet mechanistic interpretability largely studies capabilities in isolation; it remains unclear how a single transformer organizes multiple, potentially conflicting "world models". Previous experiments on Othello-playing neural networks test world-model learning, but focus on a single game with a single set of rules. We introduce *MetaOthello*, a controlled suite of Othello-like games with shared syntax but different rules or tokenizations, and train small GPTs on mixed-variant data. We show that transformers trained on multiple Othello variants learn **shared world-state representations**: linear probes trained on one game intervene on another's board state nearly as well as matched probes. When the games conflict, the model resolves the resulting *ambiguity* through a localized mechanism we identify and steer. For isomorphic games with token remapping, representations are equivalent up to a single orthogonal rotation that generalizes across layers, showing the shared structure is abstract rather than tied to surface form. Together, these results show that transformers reconcile conflicting world models by sharing structure and localizing conflict. *MetaOthello* thus offers a path toward understanding how transformers organize many world models at once.

ICML 2026

CausalProfiler: Generating Synthetic Benchmarks for Rigorous and Transparent Evaluation of Causal Machine Learning

Panayiotis Panayiotou, Audrey Poinsot, Alessandro Leite, Nicolas CHESNEAU, Marc Schoenauer, Özgür Şimşek

Causal machine learning aims to answer "what if" questions using machine learning algorithms, making it a promising tool for high-stakes decision-making. Yet, empirical evaluation practices remain limited. Existing benchmarks often rely on a handful of hand-crafted or semi-synthetic datasets, leading to brittle, non-generalizable conclusions. To bridge this gap, we introduce CausalProfiler, a synthetic benchmark generator for causal machine learning methods. Based on a set of explicit design choices about the class of causal models, queries, and data considered, CausalProfiler randomly samples causal models, data, queries, and ground truths constituting the synthetic causal benchmarks. In this way, causal machine learning can be rigorously and transparently evaluated under a variety of conditions. This work offers the first random generator of synthetic causal benchmarks with coverage guarantees and transparent assumptions operating on the three levels of causal reasoning: observation, intervention, and counterfactual. We demonstrate its utility by evaluating several state-of-the-art methods under diverse conditions and assumptions, both in and out of the identification regime, illustrating the types of analyses and insights CausalProfiler enables.

Keep browsing

More papers from top AI conferences

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