ICML 2026 论文列表

Planning and acting in 3D environments is a fundamental capability for robotic manipulation in the real world. Although prior work has explored predictive flow planners to guide 3D manipulation, existing approaches often rely on modular pipelines stacking multiple submodels, resulting in high computational overhead and limited real-time performance. To address these challenges, we introduce RoboFlow4D, a lightweight flow world model that unifies perception and planning by estimating temporal motion in physical 3D space. As an end-to-end framework, RoboFlow4D directly predicts multi-frame 3D flows from visual observations and textual instructions, providing explicit flow-based planning to guide action generation. This design allows seamless integration with general action policies, forming an efficient observation–planning–execution closed loop. Through slow–fast collaboration between flow prediction and action control, RoboFlow4D enables real-time and resource-efficient manipulation. Extensive experiments in both simulation and real-world settings demonstrate that RoboFlow4D consistently improves manipulation success rates and computational efficiency, advancing flow-guided planning for embodied intelligence. Our project page is available at RoboFlow4D.

Lagrangian-based methodologies are one of the fundamental paradigms of safe reinforcement learning (RL) for constrained Markov decision processes, particularly when dealing with multi-constraint cases. While the specific details of the methodologies may differ, with some using a single estimator for the overall mixed penalty term of the constraints and others using separate estimators for the constraints, the fundamental question of the theoretical validity of the methodologies has remained largely unexplored. The present paper performs the first theoretical analysis of the methodologies and proves that the use of the mixed critic structure leads to the presence of a bias due to the target drift of the Lagrange multipliers. On the other hand, the use of the dedicated critic structure, where separate critics are used for the reward function and the constraint functions, does not suffer from this bias. The theoretical analysis is supported with experiments on a realistic power system environment with multiple constraints, where the dedicated critic structure succeeds in satisfying the constraints, whereas the mixed critic structure fails.

Optimal transport (OT) has emerged as a fundamental tool in modern machine learning, yet its computational cost remains a significant bottleneck for large-scale applications. While harnessing the massive parallelism of modern GPU hardware is critical for efficiency, the de facto standard Sinkhorn algorithm, despite its ease of parallelization, often suffers from slow convergence in challenging problems. More recently, the sparse-plus-low-rank quasi-Newton method offers a balance between convergence rate and per-iteration complexity; however, its efficiency on GPUs is severely hindered by the serial nature of sparse matrix symbolic analysis and irregular memory access patterns. To bridge this gap, we present cuRegOT, a high-performance GPU solver tailored for entropic-regularized OT. We introduce a suite of algorithmic and architectural optimizations, including an amortized symbolic analysis strategy to mitigate CPU bottlenecks, an asynchronous Sinkhorn iterates generation mechanism, and a fused kernel for bandwidth-efficient gradient evaluation. These strategies are backed by rigorous theoretical guarantees ensuring algorithmic convergence. Extensive numerical experiments demonstrate that cuRegOT achieves significant speedups over state-of-the-art GPU-based solvers across a variety of benchmark tasks.

Reinforcement learning (RL) refines large language models (LLMs) by directly optimizing model behavior through reward signals. While accurate state value estimation is critical for stable training in classical RL, it remains an underexplored challenge in LLM post‑training. In this work, we introduce the State Value Estimation Benchmark (SVEB) to assess state estimation within existing RL frameworks and show that critics in standard approaches like PPO collapse to a coarse group‑average baseline. To address this, we propose two techniques: \textit{Numca}, which leverages numerical spans as gradable milestones for state value estimation, and \textit{Hista}, a framework that uses LLM's hidden states as representation to weighted average disjoint rollouts and their return. Extensive experiments demonstrate that both methods yield more accurate state value estimates and enhance training performance across different RL algorithms and model sizes without incurring significant computational overhead. Code available at \url{https://github.com/VOXXXX1874/Hista}.

Selecting a pretrained large language model (LLM) to fine-tune for a task-specific dataset can be time-consuming and costly. With several candidate models available to choose from, varying in size, architecture, and pretraining data, finding the best model for a specific task often involves extensive trial and error. In addition, the "best" model may not necessarily be the one with the lowest test loss, as practical considerations such as deployment costs, inference throughput, and limited search budgets might also play crucial roles. To address this, we introduce LAMPS (LAnguage Model Pareto Selection), a novel and open-source multi-objective AutoML framework that meta-learns a resource allocation policy to efficiently identify (or approximate) the Pareto front of candidate LLMs for a task-specific dataset. It is based on two key ideas: (1) landmark fine-tuning, which generates early performance indicators of the candidate models, and (2) meta-learning via reinforcement learning, which learns an effective selection policy from historical performance data (a meta-dataset). Our results show that, on held-out datasets, LAMPS reduces search time by an average of 73% compared to exhaustive search, while still covering more than 99% of the optimal target space hypervolume.

With the rapid emergence of personal AI agents based on Large Language Models (LLMs), implementing them on-device has become essential for privacy and responsiveness. To handle the inherently personal and context-dependent nature of real-world requests, such agents must ground their generation in device-resident personal context. However, under tight memory budgets, the core bottleneck is *what to store* so that retrieval remains aligned with the user. We propose EPIC (Efficient Preference-aligned Index Construction), which focuses on user preferences as a compact and stable form of personal context and integrates them throughout the RAG pipeline. EPIC selectively retains preference-relevant information from raw data and aligns retrieval toward preference-aligned contexts. Across four benchmarks covering conversations, debates, explanations, and recommendations, EPIC reduces indexing memory by 2,404$\times$, improves preference-following accuracy by 18.79\%p, and achieves 32.17$\times$ lower retrieval latency over the best-performing baseline. In on-device experiments, EPIC maintains under 1 MB memory and achieves 5.21 to 29.35 ms/query latency across three platforms, while supporting streaming updates under preference drift. Our code and data are available at https://github.com/UbiquitousAILab/EPIC.

Can a diffusion model trained on bedrooms recover human faces? Diffusion models are widely used as priors for inverse problems, but standard approaches usually assume a high-fidelity model trained on data that closely match the unknown signal. In practice, one often must use a mismatched or low-fidelity diffusion prior. Surprisingly, these weak priors often perform nearly as well as full-strength, in-domain baselines. We study when and why inverse solvers are robust to weak diffusion priors. Through extensive experiments, we find that weak priors succeed when measurements are highly informative (e.g., many observed pixels), and we identify regimes where they fail. To explain this behavior, we combine Bayesian-consistency theory with local-correlation analysis: the theory gives conditions under which high-dimensional measurements make the posterior concentrate near the true signal, while the correlation analysis shows that weak and stronger natural-image priors can share similar local spatial structure. These results provide a principled justification on when weak diffusion priors can be used reliably. Code is available at https://github.com/jjia131/weak-diffusion-priors-inverse-problem.

Learning to rank can be cast as a probabilistic modeling problem over permutations, where the goal is to estimate the likelihood of an observed total ordering of items. This formulation naturally involves full-order probabilities of the form $\mathbb{P}(z_1 \leq \cdots \leq z_n)$, whose exact computation and optimization are intractable due to the factorial growth of the permutation space with respect to the list size. In this work, we introduce the *Full-Order Bound* (FOB), a tractable lower bound on the probability of an observed ordering, constructed from a subset of ordering constraints that factorizes across items while preserving full-order structure and order-reversal invariance. Under log-concave latent densities, the bound induces a convex inner tightening problem over latent cut points, which we solve efficiently during training using a *safe-region gradient ascent* (SRGA) procedure. Experiments on synthetic ranking tasks and large-scale learning-to-rank benchmarks show that FOB improves full-list ordering metrics and remains competitive on NDCG, while an optional metric-aligned variant recovers NDCG gains. Our code is available at https://github.com/tyxaaron/FOB.

Reinforcement learning (RL) in real-world tasks often suffers from the performance degradation due to the distribution shift between training and deployment environments. Distributionally Robust RL (DR-RL) addresses this issue by optimizing the worst-case performance over an uncertainty set of transition dynamics, providing an optimized baseline performance upon deployment. However, existing methods typically require strong data access assumptions (e.g., a generative model or comprehensive offline datasets) and mostly focus on tabular settings. In this paper, we introduce a purely online DR-RL algorithm with general function approximation that learns a robust policy directly from interaction, without any prior knowledge or pre-collected data. Our method uses a dual-based fitted robust Bellman update to jointly learn the value function and the robust backup operator. We establish the first regret guarantee for online DR-RL in terms of an intrinsic complexity measure—the robust Bellman–Eluder (BE) dimension, for general $\phi$-divergence uncertainty sets. Our regret bound is sublinear and independent of $|\mathcal{S}|$ and $|\mathcal{A}|$, and recovers sharp rates in structured regimes, providing a scalable method for practical DR-RL.

We study the error rate of LLMs on tasks like arithmetic that require a deterministic output, and repetitive processing of tokens drawn from a small set of alternatives. We argue that incorrect predictions arise when small errors in the attention mechanism accumulate to cross a threshold, and use this insight to derive a quantitative two-parameter relationship between the accuracy and the complexity of the task. The two parameters vary with the prompt and the model; they can be interpreted in terms of an elementary noise rate, and the number of plausible erroneous tokens that can be predicted. Our analysis is inspired by an "effective field theory'' perspective: the LLM's many raw parameters can be reorganized into just two parameters that govern the error rate. We perform extensive empirical tests, using Gemini 2.5 Flash, Gemini 2.5 Pro and DeepSeek R1, and find excellent agreement between the predicted and observed accuracy for a variety of tasks, although we also identify deviations in some cases. Our model provides an alternative to suggestions that errors made by LLMs on long repetitive tasks indicate the "collapse of reasoning'', or an inability to express "compositional'' functions. Finally, we show how to construct prompts to reduce the error rate.

Graph structure learning is a core problem in graph-based machine learning, essential for uncovering latent relationships and ensuring model interpretability. However, most existing approaches are ill-suited for large-scale and dynamically evolving graphs, as they often require complete re-learning of the structure upon the arrival of new nodes and incur substantial computational and memory costs. In this work, we propose GraphFLEx—a unified and scalable framework for Graph Structure Learning in Large and Expanding Graphs. GraphFLEx mitigates the scalability bottlenecks by restricting edge formation to structurally relevant subsets of nodes identified through a combination of clustering and coarsening techniques. This dramatically reduces the search space and enables efficient, incremental graph updates. The framework supports 48 flexible configurations by integrating diverse choices of learning paradigms, coarsening strategies, and clustering methods, making it adaptable to a wide range of graph settings and learning objectives. Extensive experiments across 26 diverse datasets and graph neural network architectures demonstrate that GraphFLEx achieves state-of-the-art performance with significantly improved scalability. Our implementation is publicly available here: https://anonymous.4open.science/r/Scaling_Graph_Learning-CB67/README.md.

While recent advancements in Vector Quantization (VQ) models have successfully achieved complete codebook utilization, a critical bottleneck remains largely unexplored: the effective dimensionality of the codebook embedding space. We observe that discrete codebook representations tend to degenerate into low-dimensional subspaces, characterized by significantly lower effective rank than continuous representations during quantization. Through comprehensive spectral analysis, we identify that this dimensional collapse stems from the suppression of low-variance components inherent to the vector quantization process, thereby severely limiting the expressive capacity of VQ models. To mitigate this fundamental issue, we propose a simple yet effective codebook regularization strategy designed to restore low-variance components, effectively bridging the spectral gap between discrete codebook spaces and continuous representations. Extensive experiments demonstrate that this regularization objective is compatible with diverse VQ training paradigms, yielding significant improvements in reconstruction fidelity and downstream performance in autoregressive image generative models.

Bagging-based ensembles, most notably Adaptive Random Forests, are among the strongest performers for learning from data streams. A common denominator across these methods is their reliance on Hoeffding Trees as base learners, which grow decision trees incrementally by testing whether a candidate split is significantly better than its alternatives using concentration inequalities. Despite their empirical success, existing Hoeffding Trees variants lack valid statistical guarantees. Current analyses rely on fixed-sample concentration bounds, while split decisions are made using data-dependent stopping rules, which invalidates their guarantees and can drive the probabilty of incorrect splits to one. We introduce a principled alternative based on \emph{anytime-valid inference}. Our method provides: (i) anytime-valid control of false splits under arbitrary data streams, including non-stationary settings; (ii) finite commitment time under a predictive advantage; and (iii) under stationary i.i.d.\ data, risk is monotone decreasing and strictly improves at every split. Empirically, we evaluate both standalone trees and their use within Adaptive Random Forests on non-stationary streams. Our method improves performance while producing substantially smaller trees.

Automatic Heuristic Design (AHD) has emerged as a transformative approach for solving combinatorial optimization problems. While recent Large Language Model (LLM)-based methods have shown promise, they predominantly rely on fixed evolutionary operators and struggle to effectively accumulate and reuse historical search experience. This paper proposes RefineEvo, a novel evolutionary framework that transforms AHD from a static trial-and-error process into a planning-guided, experience-driven system. RefineEvo introduces a Planner to dynamically schedule evolutionary operators and trigger refinement based on the current search state, and a Reflector to distill valuable lessons into a Bidirectional Experience Pool containing both positive insights and negative pitfalls. This synergistic framework enables the system to adapt its search tools to the evolving complexity of the problem and leverage trajectory-aware, situation-conditioned insights to guide generation. Experiments on several classic combinatorial optimization benchmarks demonstrate that RefineEvo consistently outperforms strong baselines. In particular, RefineEvo delivers superior solution quality while improving token efficiency, enabling more efficient and autonomous heuristic design.

Large language models can resist task-misaligned activation steering during inference, sometimes recovering mid-generation to produce improved responses even when steering remains active. We term this Endogenous Steering Resistance (ESR). Using sparse autoencoder (SAE) latents to steer model activations, we find that Llama-3.3-70B shows substantial ESR, while smaller models from the Llama-3 and Gemma-2 families exhibit the phenomenon less frequently. We identify 26 ``off-topic detector'' latents that predict ESR episodes in Llama-3.3-70B. Zero-ablating these latents reduces the multi-attempt rate by 25\%, providing causal evidence for dedicated internal consistency-checking circuits. We demonstrate that ESR can be deliberately enhanced through both prompting and training: meta-prompts instructing the model to self-monitor increase the multi-attempt rate by 5$\times$ for Llama-3.3-70B, and fine-tuning on self-correction examples successfully induces ESR-like behavior in smaller models. These findings have dual implications: ESR could protect against adversarial manipulation but might also interfere with beneficial safety interventions that rely on activation steering. Understanding and controlling these resistance mechanisms is important for developing transparent and controllable AI systems.

Nowcasting forms the first line of defense against rapidly evolving weather hazards, where even minutes of delay can lead to severe societal impacts. However, existing systems predominantly extrapolate 2D radar reflectivity, which struggles under rapid intensification regimes. We introduce StormInsight, a multi-scale modeling framework that enables coherent reconstruction of the three-dimensional evolution of convective systems while explicitly conditioning on the ambient environment. StormInsight integrates multi-source observations—including radar, satellite, and station—with reanalysis fields through two components: (i) Storm Evolution Encoder that explicitly disentangles convective system state form vertical thermodynamic coupling and large-scale environmental forcing; (ii) Convective System Decoder that predicts future echos by adaptively aggregating cross-layer interactions conditioned on evolving environmental conditions. To support comprehensive evaluation, we build a new benchmark StormBench that integrates observational and reanalysis data across regions. On this benchmark, StormInsight consistently achieves the best performance, reducing MAE by 12.4% and improving the mCSI by 34.0%.

Despite their dominance in vision and language, deep neural networks often underperform relative to tree-based models on tabular data. To bridge this gap, we incorporate five key inductive biases into deep tabular learning: robustness to irrelevant features, axis alignment, localized irregularities, feature heterogeneity, and training stability. We propose *LassoFlexNet*, an architecture that evaluates the linear and nonlinear marginal contribution of each input via Per-Feature Embeddings, and sparsely selects relevant variables using a Tied Group Lasso mechanism. Because these components introduce optimization challenges that destabilize standard proximal methods, we analyze stochastic hierarchical proximal dynamics and develop a *Sequential Hierarchical Proximal Adaptive Gradient optimizer with exponential moving averages (EMA)* designed to stabilize training in practice. Across 52 datasets from three benchmarks, LassoFlexNet matches or outperforms leading tree-based models, achieving up to a $10$\% relative gain, while maintaining Lasso-like interpretability. We substantiate these empirical results with ablation studies and theoretical proofs confirming the architecture's enhanced expressivity and structural breaking of undesired rotational invariance.

Large language models (LLMs) demand substantial computational and memory resources, creating deployment challenges. Quantization-aware training (QAT) addresses these challenges by reducing model precision while maintaining performance. However, the scaling behavior of QAT, especially at 4-bit precision (W4A4), is not well understood. Existing QAT scaling laws often ignore key factors such as the number of training tokens and quantization granularity, which limits their applicability. This paper proposes a unified scaling law for QAT that models quantization error as a function of model size, training data volume, and quantization group size. Through 268 QAT experiments, we show that quantization error decreases as model size increases, but rises with more training tokens and coarser quantization granularity. To identify the sources of W4A4 quantization error, we decompose it into weight and activation components. Both components follow the overall trend of W4A4 quantization error, but with different sensitivities. Specifically, weight quantization error increases more rapidly with more training tokens. Further analysis shows that the activation quantization error in the FC2 layer, caused by outliers, is the primary bottleneck of W4A4 QAT quantization error. By applying mixed-precision quantization to address this bottleneck, we demonstrate that weight and activation quantization errors can converge to similar levels. Additionally, with more training data, weight quantization error eventually exceeds activation quantization error, suggesting that reducing weight quantization error is also important in such scenarios. These findings offer key insights for improving QAT research and development.

Explanations of model behavior are commonly evaluated via proxy properties weakly tied to the purposes explanations serve in practice. We contribute a decision theoretic framework that treats explanations as information signals valued by the expected improvement they enable on a specified decision task. This approach yields three distinct estimands: (i) a theoretical benchmark that upper-bounds achievable performance by any agent with the explanation, (ii) a human-complementary value that quantifies the theoretically attainable value that is not already captured by a baseline human decision policy, and (iii) a behavioral value representing the causal effect of providing the explanation to human decision-makers. We instantiate these definitions in a practical validation workflow, and apply them to assess explanation potential and interpret behavioral effects in human–AI decision support and mechanistic interpretability.