ICML 2026 论文列表

Safety-critical scenarios are central to evaluating autonomous driving systems, yet their rarity in naturalistic logs makes simulation-based stress testing indispensable. Most scenario generation methods treat surrounding agents as adversaries, but they either (i) induce failures without explicitly modeling vehicle-road physical limits, yielding visually extreme yet physically unsolvable crashes, or (ii) enforce physical feasibility or policy feasibility in isolation, which can over-focus on aggressive maneuvers or remain tied to a controller-dependent capability boundary. We propose ScenePilot, a feasibility-guided, boundary-driven framework that targets the boundary band: scenarios that are physically solvable in principle yet still cause the deployed autonomy stack to fail. We formulate generation as constrained multi-objective reinforcement learning, combining an RSS-derived physical-feasibility score $\sigma$ with an online-learned AV-risk predictor $\Phi$, and introduce step-level feasibility-aware shielding to keep exploration near the feasibility boundary while avoiding infeasible artifacts. Experiments on SafeBench with multiple planners show that ScenePilot yields substantially higher collision rates (+6.2 percentage points) while preserving physical validity, and that adversarial fine-tuning on these boundary-band scenarios consistently reduces downstream crash rates. The code is available at https://github.com/QiyuRuan/ScenePilot.

A key challenge in reconstruction-based multimodal anomaly detection is the one-to-many crossmodal mapping problem: a single 3D feature may correspond to multiple plausible RGB appearances, causing deterministic crossmodal regression to collapse valid targets into over-smoothed reconstructions and thereby weaken anomaly discrimination. In this paper, we propose Crossmodal Feature Replacer (CFR), a self-supervised framework that addresses this failure mode through selective inference-time feature replacement. CFR first learns bidirectional cyclic mappings for coarse crossmodal reconstruction, then identifies unreliable reconstructed features and selectively replaces them with high-confidence normal features to correct ambiguity-induced reconstruction failures. Extensive experiments on MVTec 3D-AD and Eyecandies under few-shot settings show that CFR consistently outperforms prior methods. In the challenging 1-shot setting, CFR achieves AUPRO scores of 92.3 and 82.7 at 30\% FPR, together with image-level AUROC scores of 74.0 and 75.9, on MVTec 3D-AD and Eyecandies, respectively. Code is available at https://github.com/Yuan-Honoka-Guo/CFR.

We analyze algorithms for solving stochastic variational inequalities (VI) without the bounded variance or bounded domain assumptions, where our main focus is min-max optimization with possibly unbounded constraint sets. We focus on two classes of problems: monotone VIs; and structured nonmonotone VIs that admit a solution to the *weak Minty VI*. The latter assumption allows us to solve structured nonconvex-nonconcave min-max problems. For both classes of VIs, to make the expected residual norm less than $\varepsilon$, we show an oracle complexity of $\widetilde{O}(\varepsilon^{-4})$, which is the best-known for constrained VIs. In our setting, this complexity had been obtained with the bounded variance assumption in the literature, which is not even satisfied for bilinear min-max problems with an unbounded domain. We obtain this complexity for stochastic oracles whose variance can grow as fast as the squared norm of the optimization variable.

Unified multimodal models (UMMs) have emerged as a promising paradigm for general-purpose multimodal intelligence. As they are deployed in real-world applications, effectively updating internal knowledge becomes critical. While knowledge editing has matured for text-only models, it remains unclear whether edits that successfully modify textual outputs also transfer to image generation in UMMs. To study this question, we introduce UniKE, the first benchmark for cross-modality knowledge editing in UMMs, comprising 2,971 edit subjects spanning attribute and relation edits. Using VQA-based visual verification, we reveal a striking modality gap: text-side efficacy can reach approximately 92\%, whereas the best overall VQA accuracy under direct image generation is only 18.5\%. We further propose Reasoning-augmented Parameter Editing, which explicitly activates edited knowledge before generation and improves overall VQA accuracy for all evaluated model-editor pairs, with gains up to 18.6 percentage points. Mechanistic analysis shows that this gap is associated with partial alignment between edited textual representations and the conditioning pathways for visual generation, where edits sufficient for text outputs may remain too weak or misaligned to steer image synthesis. These findings show that textual knowledge edits do not guarantee reliable cross-modality transfer and motivate modality-aware editing methods. Our code and data are available at https://github.com/gxx27/UniKE.

We study dynamic regret minimization in non-stationary online learning, with a primary focus on follow-the-regularized-leader (FTRL) methods. FTRL is important for curved losses and for understanding adaptive optimizers such as Adam, yet existing dynamic regret analyses are less explored for FTRL. To address this, we build on the discounted-to-dynamic reduction and present a modular way to obtain dynamic regret bounds of FTRL-related problems. Specifically, we focus on two representative curved losses: linear regression and logistic regression. Our method not only simplifies existing proofs for the optimal dynamic regret of online linear regression, but also yields new dynamic regret guarantees for online logistic regression. Beyond online convex optimization, we apply the reduction to analyze the Adam optimizers, obtaining optimal convergence rates in stochastic, non-convex, and non-smooth settings. The reduction also enables a more detailed treatment of Adam with two discount parameters $(\beta_1,\beta_2)$, leading to new results for both clipped and clip-free variants of Adam optimizers.

Effective data selection is essential for pretraining large language models (LLMs), improving efficiency and generalization to downstream tasks. However, existing approaches often rely on external pretrained models, making it difficult to separate the benefits of data selection from those introduced by external models. In addition, many methods estimate data importance from a fixed model state or short-horizon update, making it hard to capture how data preference changes as the model evolves during pretraining. In this paper, we introduce BLISS (BileveL Influence Scoring method for data Selection), a lightweight data selection method that operates entirely \emph{from scratch}, without external pretrained oracle models, while modeling dynamic data preference. BLISS uses a small proxy model as a surrogate for the LLM and trains a score model to estimate sample importance through multi-step proxy updates induced by score-weighted training data. We formulate data selection as a bilevel optimization problem: the upper-level objective optimizes the score model to assign sample weights, so minimizing the lower-level weighted training loss improves validation performance. Once optimized, the score model predicts influence scores, enabling efficient selection of high-quality samples for LLM pretraining. We validate BLISS by pretraining 410M/1B/2.8B Pythia and LLaMA-0.5B models on selected C4 subsets. Under the 1B setting, BLISS achieves a $1.7\times$ speedup in reaching the same performance as the state-of-the-art method, while delivering superior performance across multiple downstream tasks.

In correctness-sensitive scenarios, it is crucial for Large Language Models (LLMs) to strictly follow the provided evidence. However, even with reference texts, models often suffer from hallucinations, especially when processing long contexts. Existing work attempts to reinforce the use of citations through Retrieval-Augmented Generation (RAG) or post-hoc methods, while citations remain a probabilistic output rather than a foundation for the generated content. To address this, we propose Guidance, which aims to correct outputs and naturally incorporate citations during the LLM decoding phase. Specifically, we first build a structured fact pool (Prefix-Tail pairs) from the documents. Then, during inference, Guidance predicts the model's intent using a lookahead strategy. When it detects a match with a context prefix, it automatically replaces the output with the verified fact and its citation. This approach is training-free and can be plugged into general-purpose or citation-fine-tuned LLMs. Experiments on LongBench-Cite demonstrate that Guidance improves the citation F1 score by 11.2\% over state-of-the-art baselines. The source code is available at: https://github.com/marlcplhra/Guidance.

Multimodal Large Language Models excel at offline audio-visual understanding, but their ability to serve as mobile assistants in continuous real-world streams remains underexplored. In daily phone use, mobile assistants must track streaming audio-visual inputs and respond at the right time, yet existing benchmarks are often restricted to multiple-choice questions or use shorter videos. In this paper, we introduce **PhoStream**, the first mobile-centric streaming benchmark that unifies on-screen and off-screen scenarios to evaluate video, audio, and temporal reasoning. PhoStream contains 5,572 open-ended QA pairs from 578 videos across 4 scenarios and 10 capabilities. We build it with an Automated Generative Pipeline backed by rigorous human verification, and evaluate models using a realistic Online Inference Pipeline and LLM-as-a-Judge evaluation for open-ended responses. Experiments reveal a temporal asymmetry in LLM-judged scores (0--100): models perform well on Instant and Backward tasks (Gemini 3 Pro exceeds 80), but drop sharply on Forward tasks (16.40), largely due to early responses before the required visual and audio cues appear. This highlights a fundamental limitation: current MLLMs struggle to decide ***when*** to speak, not just ***what*** to say. Code and datasets will be made publicly accessible at https://github.com/Lucky-Lance/PhoStream.

Cross-view geo-localization (CVGL) aims to retrieve the corresponding satellite image given a street query and is critical for autonomous navigation. Although recent methods perform well on benchmarks, they often fail to generalize to unseen environments. A key limitation is the use of contrastive learning, which assigns equal labels to all negative samples and induces similarity-amplified repulsion. But should all negatives be treated equally? In CVGL, semi-positive samples that are geographically proximate to the positive often share important semantic cues. Treating them as ordinary negatives forces the model to overfit noise, leading to a collapse in generalization. To address this issue, we propose an uncertainty-aware framework grounded in Deep Evidential Regression (DER), modeling the Normal-Inverse-Gamma (NIG) distribution as a conjugate prior to quantify environmental complexity $u$ in a single forward pass. The estimated $u$ adaptively softens labels for hard negatives in Soft InfoNCE, mitigating excessive repulsion on semi-positive samples. An Uncertainty Head with cls-to-spatial cross-attention and attention statistics is designed to accurately fit the NIG distribution. Extensive experiments demonstrate state-of-the-art performance, including an average 18\% R@1 improvement in zero-shot cross-dataset transfer, filling the critical gap between laboratory benchmarks and robust real-world deployment.

Agentic systems solve complex tasks by coordinating multiple agents that iteratively reason, invoke tools, and exchange intermediate results. To improve robustness and solution quality, recent approaches deploy multiple agent teams running in parallel to explore diverse reasoning trajectories. However, parallel execution comes at a significant computational cost: when different teams independently reason about similar sub-problems or execute analogous steps, they repeatedly perform substantial overlapping computation. To address these limitations, in this paper, we propose Learning to Share (LTS), a learned shared-memory mechanism for parallel agentic frameworks that enables selective cross-team information reuse while controlling context growth. LTS introduces a global memory bank accessible to all teams and a lightweight controller that decides whether intermediate agent steps should be added to memory or not. The controller is trained using stepwise reinforcement learning with usage-aware credit assignment, allowing it to identify information that is globally useful across parallel executions. Experiments on the AssistantBench and GAIA benchmarks show that LTS significantly reduces overall runtime while matching or improving task performance compared to memory-free parallel baselines, demonstrating that learned memory admission is an effective strategy for improving the efficiency of parallel agentic systems.

Zero-shot imitation learning requires an agent to reproduce expert behavior from a single demonstration without additional environment interaction or gradient updates at test time. We introduce Contrastive Inverse Reinforcement Learning (CIRL), a self-supervised framework for pre-training zero-shot imitation agents. Our methods rests on a key observation that many useful tasks can be summarized by a single goal state. We can thus convert the multi-task inverse RL problem into a more tractable goal-inference problem, and utilize state-of-the-art goal-conditioned RL methods to recover a policy that reaches the goal. During pre-training, CIRL jointly employs three components to learn without any rewards or demonstrations: (1) a variant of contrastive RL designed to learn maximum-entropy goal-conditioned policies, (2) an automatic goal proposal mechanism (GoalKDE) that drives exploration, and (3) a mean-field variational model that performs amortized goal inference from trajectories. We prove that this procedure consistently recovers the demonstrator's intent by accounting for the relative difficulty of reaching different states and show how structurally similar prior work may otherwise fail to infer the correct reward. Experiments on goal-conditioned and standard reward-maximizing control tasks show that CIRL outperforms prior zero-shot imitation methods, supporting the expressiveness of goals as a compact summary of behavior.

Low-Rank Adaptation (LoRA) achieves parameter-efficient fine-tuning by constraining model updates to a low-rank subspace and has been widely used in practice. However, LoRA typically employs a shared low-rank update across tokens, which limits its ability to fully exploit the adaptation subspace for tokens from different sequences. To address this issue, we propose an adaptive utilization of Low-Rank Adaptation (U-LoRA), which employs conditioned gating to explicitly learn effective token-level utilization of the limited low-rank adaptation subspace. Specifically, U-LoRA generates utilization coefficients along low-rank directions for each token and jointly coordinates and constrains them using sequence-level contextual information, thereby inducing more consistent adaptive patterns within a sentence. To further enhance training stability, we introduce a bias-corrected exponential moving average (EMA) historical prior that calibrates utilization signals across optimization steps, suppressing noise caused by batch-to-batch fluctuations. The effectiveness of our method arises from a better utilization of the existing low-rank subspace via input-conditioned strategies, rather than from expanding the subspace. Experiments on mathematical reasoning and natural language understanding benchmarks demonstrate that U-LoRA achieves competitive performance under comparable parameter budgets when with strong LoRA baselines and recent variants.

We propose a modular, data-driven framework for jointly learning unknown functional mappings and discovering the underlying one-parameter symmetry subgroup governing the data. Unlike conventional geometric deep learning methods that assume known symmetries, our approach identifies the relevant continuous subgroup directly from data. Our framework focuses on three primary geometric components of one-parameter subgroup actions: elliptic, hyperbolic, and parabolic regimes. For the given regime, our framework instantiates a corresponding symmetry discovery architecture with invariant and equivariant representation layers structured according to the Lie algebra of the subgroup, and learns the exact generator parameters end-to-end from data. This yields models whose invariance or equivariance is guaranteed by construction and admits formal proofs, enabling symmetry to be explicitly traced to identifiable components of the architecture. The approach is applicable to one-parameter subgroups of a wide range of matrix Lie groups, including $SO(n)$, $SL(n)$, and the Lorentz group. Experiments on synthetic and real-world systems, including moment of inertia prediction, double-pendulum dynamics, and high-energy \textit{Top Quark Tagging}, demonstrate accurate subgroup recovery and strong predictive performance across both compact and non-compact regimes.

Many learning tasks in science and engineering are characterized by sparse datasets, which limits the effectiveness of purely data-driven approaches. At the same time, these problems are often accompanied by rich domain knowledge derived from physical laws, operational requirements, and expert heuristics. Such knowledge is frequently expressed as rules involving logical propositions and linear inequalities. Existing neuro-symbolic methods typically enforce these rules approximately through soft penalties, assume input-independent rules when designing specialized architectures, or rely on non-differentiable post-processing at inference time to achieve hard constraint satisfaction. While recent advances in differentiable optimization layers enable end-to-end feasibility enforcement within neural networks, extending these approaches to logical or mixed-integer rules remains challenging due to inherent nonconvexity. In this work, we propose a unified end-to-end framework for enforcing hard, input-dependent mixed integer linear constraints within neural networks. Our approach represents rules as disjunctive constraints and applies hierarchical convex relaxations to obtain convex hull formulations. These relaxations yield tractable linear constraints that can be embedded as differentiable optimization layers while enabling exact rule satisfaction. We demonstrate the effectiveness of the proposed framework on real-world datasets, achieving perfect rule satisfaction and strong predictive performance.

We present HOI-PAGE, a new approach that prioritizes part-level affordance reasoning to generate high-fidelity 4D human-object interactions (HOIs) from text prompts in a zero-shot fashion. In contrast to prior works that focus on global, whole body-object motion synthesis, our approach explicitly reasons about the underlying part-level mechanics of interactions using large language models (LLMs). We capture this reasoning in a structured part affordance graph (PAG) representation, serving as a high-level interaction scaffolding to guide a three-stage synthesis: first, decomposing input 3D objects into semantic parts; then, generating reference HOI videos from text prompts to extract part-based motion constraints; and finally, optimizing for 4D HOI motion sequences that mimic the reference dynamics while satisfying part-level contact constraints. Extensive experiments show that our approach is flexible and capable of generating complex multi-object or multi-person interaction sequences, with significantly improved realism and text alignment for zero-shot 4D HOI generation.

Dataset pruning remains underexplored for 3D modalities, where inherent class imbalance persists across ***both*** training and test sets. This creates a divergence in evaluation: overall accuracy favors natural frequency, reflecting practical usage; while mean accuracy demands balanced generalization. Instead of forcing a premature trade-off, we advocate for base principles that remain universally robust and beneficial across diverse priors. We cast pruning as a quadrature approximation on population risk and decompose the error bound into *representation error* (fidelity to the underlying manifold) and *prior-mismatch bias* (distribution shift), clarifying what can be improved jointly across priors. To address prior-mismatch bias, we decouple likelihood from prior in the posterior and transfer the structural likelihood via distillation with a calibrated teacher and geometry-preserving constraints. Simultaneously, to reduce representation error, we audit common pruning signals and choose geometric embedding, which exhibits greater robustness given the high inductive bias of 3D models. We also prioritize a safety floor before selection, capturing high-reward regions beneficial across priors. Finally, acknowledging that no single subset optimally satisfies divergent evaluation priors, we augment these principles with a steering wrapper that interpolates between stratified seeding and global selection. Empirical results demonstrate that our framework elevates the performance floor while offering flexibility for different prior preferences.

Monocular-to-stereo conversion synthesizes stereoscopic content from 2D videos for immersive 3D experiences. In modern Depth-Image-Based Rendering (DIBR) approaches, stereo inpainting of disocclusions is the critical bottleneck. Training-based methods achieve superior quality but rely on scarce stereo pairs or synthetic data with domain gaps. We address this through the first self-supervised framework learning from monocular videos via cycle consistency. Our key contribution is the **Geometric Reciprocity Theorem (GRT)**: under the nearest-neighbor DIBR formulation, the disocclusion mask when synthesizing a target view equals the mask of pixels lost when warping back from target to source, enabling analytical computation of test-time disocclusion masks directly from monocular images. This yields train-test consistency for the stated warping formulation, supporting self-supervised learning from unlimited monocular videos and substantial improvements over training-free and supervised state-of-the-art methods. Project page: https://visual-ai.github.io/grt/

Multimodal Retrieval-Augmented Generation (MRAG) has emerged as a key paradigm for grounding MLLMs with external knowledge. While query pre-processing (e.g., rewriting) is standard in text-based RAG, existing MRAG pipelines predominantly treat visual inputs as static and immutable, implicitly assuming they are noise-free. However, real-world visual queries are often ``imperfect''---suffering from geometric distortions, quality degradation, or semantic ambiguity---leading to catastrophic retrieval failures. To address this gap, we propose V-QPP-Bench, the first comprehensive benchmark dedicated to Visual Query Pre-processing (V-QPP). We formulate V-QPP as an agentic decision-making task where MLLMs must autonomously diagnose imperfections and deploy perceptual tools to refine queries. Our extensive evaluation across 46,700 imperfect queries and diverse MRAG paradigms reveals three critical insights: (1) Vulnerability---visual imperfections severely degrade both retrieval recall and end-to-end MRAG performance; (2) Restoration Potential \& Bottleneck---while oracle preprocessing recovers near-perfect performance, off-the-shelf MLLMs struggle with tool selection and parameter prediction without specialized training; and (3) Training Enhancement---supervised fine-tuning enables compact models to achieve comparable or superior performance to larger proprietary models, demonstrating the benchmark's value for developing robust MRAG systems The code is available at https://github.com/phycholosogy/VQQP_Bench

Diffusion language models (DLMs) can match or surpass similarly sized autoregressive language models on language understanding and reasoning. However, their mask-and-denoise pretraining relies on heuristic random masking, which fails to target the most informative tokens. Consequently, the model spends significant computational effort on redundant or trivial tokens. To address this, we propose InfoDLM, an adaptive DLM pretraining framework that reformulates mask selection as an active, feedback-driven process. InfoDLM targets tokens that offer the highest measurable information gain during mask selection. Specifically, we: (1) introduce a Trainable Information-Gain (TIG) signal to quantify information gain of each masking configuration; (2) develop a feedback mechanism that adapts the masking policy to the model’s evolving state with a maturity indicator; and (3) jointly optimize the DLM and masking policy through an interleaved training flow with minimal computational overhead. Across reasoning-oriented benchmarks, InfoDLM achieves up to 13\% improvement in reasoning accuracy over a small variant of LLaDA under comparable pretraining budgets.