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

Towards Efficient LLMs Annealing with Principled Sample Selection

Yuanjian Xu, Jianing Hao, Wanbo Zhang, Zhong Li, Guang Zhang

The annealing phase is a pivotal convergence stage in LLM pre-training that ultimately determines final model quality. However, effectively selecting training data during this phase remains a key challenge. Current strategies rely on empirical heuristics, such as domain filtering or context extension, which lack a principled grounding in optimization theory. In this work, we characterize the annealing phase through the lens of the loss landscape's spectral geometry. We argue that optimal convergence requires gradient updates to satisfy heterogeneous constraints across different eigen-directions. Building on this insight, we formulate data selection as a problem of satisfying these directional constraints. To this end, we propose **DiReCT** (**Di**rectionally-**Re**strained **C**onstrained **T**raining), a novel framework that reformulates sample selection in the annealing stage as a constrained optimization problem. By imposing explicit directional constraints on per-sample gradients based on the spectral properties of the Hessian, **DiReCT** identifies samples that align with the optimal curvature-aware descent path. Extensive experiments across various model scales demonstrate that **DiReCT** consistently achieves state-of-the-art performance. For future research, code is available at https://github.com/xuyj233/Direct.

ICML 2026

Hybrid-Gym: Training Coding Agents to Generalize Across Tasks

Yiqing Xie, Emmy Liu, Gaokai Zhang, Nachiket Kotalwar, Shubham Gandhi, Sathwik Acharya, Xingyao Wang, Carolyn Rose, Graham Neubig, Daniel Fried

When assessing the quality of coding agents, predominant benchmarks focus on solving single issues on GitHub, such as SWE-Bench. In contrast, in real use these agents solve more various and complex tasks that involve other skills such as exploring codebases, testing software, and designing architecture. In this paper, we first characterize some transferable skills that are shared across diverse tasks by decomposing trajectories into fine-grained components, and derive a set of principles for designing auxiliary training tasks to teach language models these skills. Guided by these principles, we propose a training environment, Hybrid-Gym, consisting of a set of scalable synthetic tasks, such as function localization and dependency search. Experiments show that agents trained on our synthetic tasks effectively generalize to diverse real-world tasks that are not present in training, improving a base model by 25.4% absolute gain on SWE-Bench Verified, 7.9% on SWT-Bench Verified, and 5.1% on Commit-0 Lite. Hybrid-Gym also complements datasets built for the downstream tasks (e.g., improving SWE-Play by 4.9\% on SWT-Bench Verified). We provide the code at https://github.com/Hybrid-Gym/Hybrid-Gym.

ICML 2026

Refining Context-Entangled Content Segmentation via Curriculum Selection and Anti-Curriculum Promotion

Chunming He, Rihan Zhang, Fengyang Xiao, Dingming Zhang, Zhiwen Cao, Sina Farsiu

Biological learning proceeds from easy to difficult tasks, gradually reinforcing perception and robustness. Inspired by this principle, we address Context‑Entangled Content Segmentation (CECS)—a challenging setting where objects share intrinsic visual patterns with their surroundings, as in camouflaged object detection. Conventional segmentation networks predominantly rely on architectural enhancements but often ignore the learning dynamics that govern robustness under entangled data distributions. We introduce CurriSeg, a dual‑phase learning framework that unifies curriculum and anti‑curriculum principles to improve representation reliability. In the Curriculum Selection phase, CurriSeg dynamically selects training data based on the temporal statistics of sample losses, distinguishing hard‑but‑informative samples from noisy or ambiguous ones, thus enabling stable capability enhancement. In the Anti‑Curriculum Promotion phase, we design Spectral‑Blindness Fine‑Tuning, which suppresses high‑frequency components to enforce dependence on low‑frequency structural and contextual cues. Combined with Sharpness‑Aware Minimization, this promotes convergence to flatter minima and strengthens generalization. Extensive experiments demonstrate that CurriSeg achieves consistent improvements across diverse CECS benchmarks without adding parameters or increasing total training time, offering a principled view of how progression and challenge interplay to foster robust and context‑aware segmentation. Code will be released.

ICML 2026

BRIDGE: Predicting Human Task Completion Time From Model Performance

Fengyuan Liu, Jay Gala, Nilaksh, Dzmitry Bahdanau, Siva Reddy, Hugo Larochelle

Evaluating the real-world capabilities of AI systems requires grounding benchmark performance in human-interpretable measures of task difficulty. Existing approaches that rely on direct human task completion time annotations are costly, noisy, and difficult to scale across benchmarks. In this work, we propose BRIDGE, a unified psychometric framework that learns the latent difficulty scale from model responses and anchors it to human task completion time. Using a two-parameter logistic Item Response Theory model, we jointly estimate latent task difficulty and model capability from model performance data across multiple benchmarks. We demonstrate that latent task difficulty varies linearly with the logarithm of human completion time, allowing human task completion time to be inferred for new benchmarks from model performance alone. Leveraging this alignment, we forecast frontier model capabilities in terms of human task length and independently reproduce METR’s exponential scaling results, with the 50% solvable task horizon doubling approximately every 6 months.

ICML 2026

StructMamPose: From Sequential Perception to Structural Reasoning for 3D Human Pose Estimation

Jiahong Jiang, Miao Zhang, Jingjing Li, Leiye Liu, Yao Cui, Wei Ji, Yongri Piao, Huchuan Lu

Accurately modeling complex temporal and topological dependencies and depth information is critical for monocular 3D human pose estimation, yet existing Mamba-based approaches struggle to fulfill these demands, suffering from internal state update confusion induced by forced sequence flattening and depth modeling confusion inherent to single-view observations. To address this confusion, we propose a StructMamPose framework equipped with Identity Anchoring Mechanism (IAM) and View Transformation Hub (VTH). The IAM injects spatiotemporal identities into the parameter generation network to anchor the selectivity of state update matrices, suppressing spurious connections to enforce feature propagation along valid topological dependencies. The VTH performs internal coordinate rotation to transform implicit depth inference into observable planar features, endowing the model with explicit spatial understanding and multi-view constraints. Experimental results demonstrate that our framework achieves SOTA performance on most datasets.

ICML 2026

Break the Block: Dynamic-size Reasoning Blocks for Diffusion Large Language Models via Monotonic Entropy Descent with Reinforcement Learning

Yan Jiang, Ruihong Qiu, Zi Huang

Recent diffusion large language models (dLLMs) have demonstrated both effectiveness and efficiency in reasoning via a block-based semi-autoregressive generation paradigm. Despite their progress, the fixed-size block generations remain a critical bottleneck for effective and coherent reasoning. (I) From a global perspective, different reasoning tasks would correspond to different optimal decoding block sizes, which makes a "one-size-fits-all" assumption ineffective. (II) Even within a single reasoning task, the rigid block partitioning would break the logical flow and reduce reasoning coherence. Through empirical observations, we reveal that, for block-wise entropy, incorrect reasoning exhibits a fluctuating and unsteady trend between blocks, while the correctly generated tasks follow a consistent descending paradigm. Therefore, this paper proposes b1, a novel post-training framework that learns dynamic-size reasoning blocks via a Monotonic Entropy Descent objective with reinforcement learning to enhance reasoning coherence. b1 integrates seamlessly as a plug-and-play module with existing dLLM's post-training algorithms. Extensive experiments across various reasoning benchmarks showcase b1's consistent improvement over fixed-size block baselines. Our code has been released at https://github.com/YanJiangJerry/Block-R1.

ICML 2026

POLCA: Stochastic Generative Optimization with LLM

Xuanfei Ren, Allen Nie, Tengyang Xie, Ching-An Cheng

Optimizing complex systems, ranging from LLM prompts to multi-turn agents, traditionally requires labor-intensive manual iteration. We formalize this as a stochastic generative optimization problem where a language model acts as the optimizer, guided by numerical and text feedback to discover the best system. We introduce **P**rioritized **O**ptimization with **L**ocal **C**ontextual **A**ggregation (POLCA), a scalable framework designed to handle stochasticity in optimization—such as noisy feedback, sampled minibatches, and stochastic system behaviors—while effectively managing the unconstrained expansion of the solution space. POLCA maintains a priority queue to enable exploration–exploitation, tracking candidate solutions and their evaluation histories. To enhance efficiency, we integrate an $\varepsilon$-Net mechanism to maintain parameter diversity and an LLM Summarizer to perform meta-learning across historical trials. We theoretically prove that POLCA converges to near-optimal candidate solutions under stochasticity. We evaluate our framework on diverse benchmarks, including $\tau$-bench, HotpotQA, VeriBench, and KernelBench. Experimental results demonstrate that POLCA achieves robust, sample- and time-efficient performance, consistently outperforming state-of-the-art algorithms in both deterministic and stochastic problems. The codebase for this work is publicly available at https://github.com/rlx-lab/POLCA.

ICML 2026

Rare Event Analysis of Large Language Models

Jake McAllister Dorman, Edward Gillman, Dominic C Rose, Jamie F. Mair, Juan P. Garrahan

Being probabilistic models, during inference large language models (LLMs) display *rare events*: behaviour that is far from typical but highly significant. By definition all rare events are hard to see, but the enormous scale of LLM usage means that events completely unobserved during development are likely to become prominent in deployment. Here we present an end-to-end framework for the systematic analysis of rare events in LLMs. We provide a practical implementation spanning theory, efficient generation strategies, probability estimation and error analysis, which we illustrate with concrete examples. We outline extensions and applications to other models and contexts, highlighting the generality of the concepts and techniques presented here.

ICML 2026

Asymptotic Universal Alignment: A New Alignment Framework via Test-Time Scaling

Yang Cai, Weiqiang Zheng

Aligning large language models (LLMs) to serve users with heterogeneous and potentially conflicting preferences is a central challenge for personalized and trustworthy AI. We formalize an ideal notion of *universal alignment* through *test-time scaling*: for each prompt, the model produces $k\ge 1$ candidate responses and a user selects their preferred one. We introduce *$(k,f(k))$-robust alignment*, which requires the $k$-output model to have win rate $f(k)$ against any other single-output model, and *asymptotic universal alignment (U-alignment)*, which requires $f(k)\to 1$ as $k\to\infty$. Our main result characterizes the optimal convergence rate: there exists a family of *single-output* policies whose $k$-sample product policies achieve U-alignment at rate $f(k)=\frac{k}{k+1}$, and no method can achieve a faster rate in general. We show that popular post-training methods, including Nash learning from human feedback (NLHF), can fundamentally underutilize the benefits of test-time scaling. Even though NLHF is optimal for $k=1$, sampling from the resulting (often deterministic) policy cannot guarantee win rates above $\tfrac{1}{2}$ except for an arbitrarily small slack. This stems from a lack of output diversity: existing alignment methods can collapse to a single majority-preferred response, making additional samples redundant. In contrast, our approach preserves output diversity and achieves the optimal test-time scaling rate. In particular, we propose a family of symmetric *multi-player alignment games* and prove that any symmetric Nash equilibrium policy of the $(k+1)$-player alignment game achieves the optimal $(k,\frac{k}{k+1})$-robust alignment. Finally, we provide theoretical convergence guarantees for self-play learning dynamics in these games and extend the framework to opponents that also generate multiple responses.

ICML 2026

Hyper-LLaVA: Hyperbolic Uncertainty-aware Modality-Balanced Routing for Multimodal Continual Instruction Tuning

Kunlun Xu, YanQin Zhang, Wenwen Qiang, Jiahuan Zhou

Multimodal Continual Instruction Tuning (MCIT) aims to exploit the incrementally accumulated knowledge to process multimodal inputs of diverse tasks, where parameter routing plays an important role. State-of-the-art methods rely on sample-to-task center similarity and cross-modal fusion with equal weight during routing. However, such solutions face two fundamental flaws: (1) Within each modality, the sample-to-task center distance is sub-optimal for routing since the abundant intra-task diversity information is underleveraged. (2) Different modalities exhibit varying reliability across tasks, where the modality with inter-task ambiguity can easily misguide the routing result. To address these problems, we propose Hyperbolic Uncertainty-aware Modality-Balanced Routing (Hyper-LLaVA) to improve parameter routing capacity based on cross-modality task feature uncertainty modeling. Specifically, to improve intra-modality task matching, Hyper-LLaVA accesses the sample to task distribution similarity in the Hyperbolic space. Besides, to alleviate the degradation brought by unreliable modality, Hyper-LLaVA quantifies the task matching ambiguity within each modality to achieve adaptive balancing between task matching across modalities. Based on the complementary intra- and inter-modality task matching enhancement, our Hyper-LLaVA outperforms state-of-the-art approaches by large margins. Our source code is available at https://github.com/zhoujiahuan1991/ICML2026-Hyper-LLaVA

ICML 2026

TINNs: Time-Induced Neural Networks for Solving Time-Dependent PDEs

Chen-Yang Dai, Che-Chia Chang, Te-Sheng Lin, Ming-Chih Lai, Chieh-Hsin Lai

Physics-informed neural networks (PINNs) solve time-dependent partial differential equations (PDEs) by learning a mesh-free, differentiable solution that can be evaluated anywhere in space and time. However, standard space-time PINNs take time as an input but reuse a single network with shared weights across all times, forcing the same features to represent markedly different dynamics. This coupling degrades accuracy and can destabilize training when enforcing PDE, boundary, and initial constraints jointly. We propose *Time-Induced Neural Networks (TINNs)*, a novel architecture that parameterizes the network weights as a learned function of time, allowing the effective spatial representation to evolve over time while maintaining shared structure. The resulting formulation naturally yields a nonlinear least-squares problem, which we optimize efficiently using a Levenberg-Marquardt method. Experiments on various time-dependent PDEs show up to $4\times$ improved relative $L^2$ error and $10\times$ faster convergence compared to PINNs and strong baselines. Code is available at https://github.com/CYDai-ml/TINN.

ICML 2026

Target-Driven Policy Optimization for Sequential Counterfactual Outcome Control

Xin Wang, Xiangyu Zhang, Shengfei Lyu, Huanhuan Chen

Identifying optimal intervention sequences from offline data to guide temporal systems toward target outcomes is a critical challenge with profound implications for fields like personalized medicine. While existing methods are mostly evaluated in offline settings, practical applications demand online, adaptive strategies that can respond in real-time. To address this, we propose \textbf{G}oal-conditioned \textbf{I}ntervention via \textbf{F}actual-\textbf{T}argeted Training (\textbf{GIFT}), a novel framework for learning sequential intervention policies from observational data. GIFT learns a goal-conditioned policy by rescaling rewards with clipped importance weights, stabilizing learning and steering toward the target. Under standard assumptions, the induced operator has a unique fixed point and our procedure converges to it. We also bound the bias from clipping and approximation via the gap to the policy’s true value. Experiments show GIFT significantly outperforms existing methods in creating goal-conditioned policies for online deployment.

ICML 2026

Two-Parameter Flows for Learning Population Dynamics of Physical Systems

Paul Schwerdtner, Tobias Blickhan, Benjamin Peherstorfer

This work addresses the problem of learning the dynamics of high-dimensional probability densities over time using unlabeled samples, without assuming access to trajectory information. We introduce two-parameter flows that learn only sampling-time transports from a base distribution to each marginal and then extract a physics-time velocity by regressing on coupled synthetic trajectories. We prove that the resulting physics-time dynamics are unique and inherit regularity from the sampling-time transports. Because we can build on standard, well-developed conditional flow matching techniques for learning the base-to-marginal transports, our approach scales to high dimensions and avoids per-step optimal-transport couplings, while allowing admissible non-gradient dynamics that can naturally explain rotational or circulating physics phenomena.

ICML 2026

Boosting World Models Learning via Latent-Space Value Alignment

Xingyu Jiang, Yuheng Pan, Mukang You, Xiuhui Zhang, Ning Gao, Guanwei Yan, Hao Li, Yue Deng

Model-based reinforcement learning aims to construct world models for efficient sampling. Current mainstream algorithms can be broadly categorized into two paradigms: maximum likelihood and value-aware world models. The former employs structured Recurrent/Transformer State-Space Models to capture environmental dynamics but overlooks task-relevant features. The latter prioritizes decision-critical states but suffers from sub-optimal performance. While recent efforts have sought to integrate these approaches, they typically rely on auxiliary modules or heavy external priors that significantly increase computational complexity. In this work, we propose a Value-Aligned World Model, a minimalist framework designed to synergize these two paradigms with negligible overhead. Specifically, We introduce an intrinsic latent-space value-alignment regularization that compels the world model to prioritize task-relevant features while maintaining the structural integrity of stochastic dynamics. To ensure stable optimization, we develop an adaptive weighting mechanism that acts as a self-regulating curriculum, balancing reconstruction fidelity with decision-making utility. Extensive experiments on Atari 100k and DeepMind Control benchmarks demonstrate that our algorithm consistently boosts existing methods with minimal added code and computational overhead. Code is available at supplementary material.

ICML 2026

$\tau$-Voice: Benchmarking Full-Duplex Voice Agents on Real-World Domains

Soham Ray, Keshav Dhandhania, Victor Barres, Karthik R Narasimhan

Full-duplex voice agents—systems that listen and speak simultaneously—are rapidly moving from research to production. However, existing evaluations address conversational dynamics and task completion in isolation. We introduce τ-Voice, a benchmark for evaluating voice agents on grounded tasks with real-world complexity: agents must navigate complex multi-turn conversations, adhere to domain policies, and interact with the environment. The framework extends τ²-bench into a novel voice agent benchmark combining verifiable completion of complex grounded tasks, full-duplex interaction, and realistic audio—enabling direct comparison between voice and text performance. A controllable and realistic voice user simulator provides diverse accents, realistic audio environments, and rich turn-taking dynamics; by decoupling simulation from wall-clock time, the user simulator can use the most capable LLM without real-time constraints. We evaluate task completion (pass@1) and voice interaction quality across 278 tasks: while GPT-5 (reasoning) achieves 85%, voice agents reach only 31–51% under clean conditions and 26–38% under realistic conditions with noise and diverse accents—retaining only 30–45% of text capability; qualitative analysis confirms 79–90% of failures stem from agent behavior, suggesting that observed failures primarily reflect agent behavior under our evaluation setup. τ-Voice provides a reproducible testbed for measuring progress toward voice agents that are natural, conversational, and reliable.

ICML 2026

Trust It or Not: Evidential Uncertainty for Feed-Forward 3D Reconstruction with Trust3R

Zihao Zhu, Wenyuan Zhao, Nuo Chen, Chao Tian, Zhiwen Fan

Geometric foundation models hold promise for unconstrained dense geometry prediction from uncalibrated images. However, current feed-forward designs often produce heuristic confidence scores that lack probabilistic interpretation and fail to indicate where and how much the predicted geometry can be trusted. To address this gap, we present ***Trust3R***, a lightweight evidential uncertainty framework for feed-forward 3D reconstruction. Trust3R combines gated residual mean refinement with a Normal-Inverse-Wishart evidential head, yielding a closed-form multivariate Student-t distribution for per-point geometric uncertainty. This provides probabilistically grounded pointmap uncertainty estimates with moderate inference overhead. We evaluate on diverse indoor and outdoor benchmarks and compare against MASt3R's built-in confidence map, single-pass heteroscedastic regression, MC dropout, and deep ensembles. Experimental results show that Trust3R consistently improves risk--coverage and sparsification, generally improves geometric accuracy, and strengthens uncertainty ranking across benchmarks. On ScanNet++, Trust3R achieves 25% lower AURC and 41% lower AUSE, providing a practical reliability signal for uncertainty-aware weighting in downstream geometry pipelines. Our project page and code are available at https://trust3r-z.github.io.

ICML 2026

Causal discovery for time series with endogenous context variables

Oana-Iuliana Popescu, Wiebke Günther, Martin Rabel, Jakob Runge

Many real-world systems exhibit both context- and time-dependent causal dynamics, where the dynamical system state also influences its context. For instance, soil moisture is driven by precipitation, yet also provides the context for heat-flux realization. We capture such dynamics in Structural Causal Models (SCMs) by introducing endogenous and time-dependent discrete context variables, also allowing for possibly lagged dependencies with the system variables. While context variables are discrete, they may also be proxies of continuous variables. The enabling assumptions for causal discovery of our model are either persistence of the context or sparsity of the context–system dependencies. We design two new PCMCI-based algorithms for causal discovery with endogenous context variables for time series and prove their soundness. A systematic evaluation on synthetic benchmarks and an application to a real-world land-atmosphere feedback problem demonstrate their effectiveness and applicability.

ICML 2026

COPF: An Online Framework for Deployment-Stable Counterfactual Fairness in Evolving Graphs

Sheng'en Li, Dongmian Zou

Online link recommendation on evolving graphs is performative: by choosing which candidate links to show users, the system changes which links form and what feedback it later observes. Consequently, fairness estimates from logged outcomes can be misleading and may drift after deployment when the recommendation policy is updated. We introduce COPF (Counterfactual Online Performative Fairness), a decision-layer framework for deployment-stable fairness monitoring and control in online link recommendation. COPF (i) defines group-level opportunity gaps over exposure (shown vs. not shown) counterfactuals, (ii) makes them estimable by explicit exploration and by logging the probability (propensity) that each candidate is shown, and (iii) audits and controls fairness using residual outcome indistinguishability (OI) over a configurable auditor family with graph-aware doubly robust (GA-DR) estimators. We provide a noisy transfer theorem showing that Residual-OI on estimated GA-DR residuals implies bounds on exposure-counterfactual group gaps under temporal mixing and bounded local interference, and we instantiate an online multicalibration auditor together with a primal-dual controller. Experiments on two TGB streams and a controlled synthetic bipartite stream show that COPF reduces worst-case spikes in exposure-counterfactual group disparities with modest impact on ranking utility. Our code is available at https://github.com/lsnnnnnnnn/COPF.

ICML 2026

CRAG: Can 3D Generative Models Help 3D Assembly?

Zeyu Jiang, Sihang Li, Siqi Tan, Chenyang Xu, Juexiao Zhang, Julia Galway-Witham, Xue Wang, Scott A. Williams, Radu Iovita, Chen Feng, Jing Zhang

Most existing 3D assembly methods treat the problem as pure pose estimation, rearranging observed parts via rigid transformations. In contrast, human assembly naturally couples structural reasoning with holistic shape inference. Inspired by this intuition, we reformulate 3D assembly as a joint problem of assembly and generation. We show that these two processes are mutually reinforcing: assembly provides part-level structural priors for generation, while generation injects holistic shape context that resolves ambiguities in assembly. Unlike prior methods that cannot synthesize missing geometry, we propose CRAG, which simultaneously generates plausible complete shapes and predicts poses for input parts. Extensive experiments demonstrate state-of-the-art performance across in-the-wild objects with diverse geometries, varying part counts, and missing pieces. Our code and models will be released.

ICML 2026

Information Geometry Loss for Time Series Forecasting

Jiayu Fang, Xuande Liu, Sangsha Fang, Ernie Tian, Hongwei Ma, Zhiqi Shao, Junbin Gao

Time series forecasting fundamentally involves learning probability distributions over future observations. However, existing loss functions rely on point-wise Euclidean metrics, neglecting the intrinsic geometric structure of probability distributions. This leads to suboptimal alignment between predicted and true distributions, particularly for uncertainty quantification. We propose InfoGeo Loss, a principled loss function grounded in information geometry that measures distributional discrepancies on statistical manifolds. Our approach comprises three key components: (1) a distribution parameterization module that models predictions with learnable sufficient statistics, (2) a Fisher information metric that quantifies intrinsic distributional distance, and (3) a Bregman divergence component that captures asymmetric prediction errors. We further introduce a natural gradient weighting strategy for efficient optimization on statistical manifolds. Theoretically, we prove statistical consistency and establish convergence guarantees. Extensive experiments on seven datasets with five architectures show that InfoGeo Loss consistently outperforms existing losses, achieving average improvements of 6.8% in MSE and 5.3% in MAE.

Keep browsing

More papers from top AI conferences

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