ICML 2026 论文列表

As humans increasingly rely on multi-round conversational AI for high-stakes decisions, principled frameworks are needed to ensure such interactions reliably improve decision quality. We adopt a human-centric view governed by two principles: counterfactual harm, ensuring the AI does not undermine human strengths, and complementarity, ensuring it adds value where the human is prone to err. We formalize these concepts via user-defined rules, allowing users to specify exactly what harm and complementarity mean for their specific task. We then introduce an online, distribution-free algorithm with finite-sample guarantees that enforces the user-specified constraints over the collaboration dynamics. We evaluate our framework across two interactive settings: LLM-simulated collaboration on a medical diagnostic task and a human crowdsourcing study on a pictorial reasoning task. We show that our online procedure maintains prescribed counterfactual-harm and complementarity violation rates even under non-stationary interaction dynamics. Moreover, tightening or loosening these constraints produces predictable shifts in downstream human accuracy, confirming that the two principles serve as practical levers for steering multi-round collaboration toward better decision quality without the need to model or constrain human behavior.

Vision–Language–Action (VLA) policies often fail under distribution shift, suggesting that decisions may depend on spurious visual correlations rather than task-relevant causes. We formulate visual–action attribution as an interventional estimation problem. Accordingly, we introduce the **Interventional Significance Score (ISS)**, an interventional masking procedure for estimating the causal influence of visual regions on action predictions, and the **Nuisance Mass Ratio (NMR)**, a scalar measure of attribution to task-irrelevant features. We analyze the statistical properties of ISS and show that it admits unbiased estimation, and we characterize conditions under which action prediction error provides a valid proxy for causal influence. Experiments across diverse manipulation tasks indicate that NMR predicts generalization behavior and that ISS yields more faithful explanations than existing interpretability methods. These results suggest that interventional attribution provides a simple diagnostic approach for identifying causal misalignment in embodied policies.

We aim to develop physics foundation models for science and engineering that provide real-time solutions to Partial Differential Equations (PDEs) which preserve structure and accuracy under adaptation to unseen geometries. To this end, we introduce General-Geometry Neural Whitney Forms (Geo-NeWF): a data-driven finite element method. We jointly learn a differential operator and compatible reduced finite element spaces defined on the underlying geometry. The resulting model is solved to generate predictions, while exactly preserving physical conservation laws through Finite Element Exterior Calculus. Geometry enters the model as a discretized mesh both through a transformer-based encoding and as the basis for the learned finite element spaces. This explicitly connects the underlying geometry and imposed boundary conditions to the solution, providing a powerful inductive bias for learning neural PDEs which we demonstrate improves generalization to unseen domains. We provide a novel parameterization of the constitutive model ensuring existence and uniqueness of the solution. Our approach demonstrates state-of-the-art performance on several steady-state PDE benchmarks and provides a significant improvement over conventional baselines on out-of-distribution geometries.

Current image editing methods excels at static attributes but fails at complex Human-Object Interactions (HOI), a critical challenge unaddressed by existing benchmarks that conflate HOI with static attributes, relying on global metrics incapable of simultaneously assessing dynamic interaction validity and entangled human-object pair preservation. Thus, we first introduce HOI-Edit, a comprehensive benchmark with three progressive cognitive levels, which features an automated metric HOI-Eval that first reliably evaluates instance-level interaction by letting VLM Q&A after thinking with images containing grounded Human-Object pair. Considering the task's essence of remodeling dynamic relationships, we benchmark Image-to-Video (I2V) models, finding them inherently suited for dynamic editing due to their temporal generation capabilities. Crucially, beyond superior performance, this capability provides a "replay of the failure process", offering unique diagnosability into why errors occur. We thus propose SCPE (Self-Correcting Process Editing), a novel, agentic self-correcting framework that constrains the generation of I2V models through iteratively refined prompts, enabling the generated videos to more accurately present the target HOI. Extracted frames from these videos are the final editing results. On HOI-Edit, SCPE achieves performance competitive with state-of-the-art (SOTA) editing models like Nano Banana on interaction.Code is available at https://github.com/oceanflowlab/HOI-Edit.

Recent work shows that vision encoders capture ordinal attributes along linear axes, which can be recovered from as few as two labeled images. However, in the zero-shot setting, the text-driven rank axis for Vision-Language Models (VLMs) like CLIP remains suboptimal. In this work, we study the embeddings of Multimodal LLMs (MLLMs). We hypothesize that MLLMs can overcome this limitation due to three potential advantages: their inherent ordinal understanding, capacity for conditional embeddings, and a small cross-modal gap. We show that MLLMs are rankable using only text prompts. Experiments demonstrate that a text-driven rank axis for MLLM embeddings achieves 90\% of the performance of the supervised linear rank axis, significantly outperforming the 61\% observed in VLM embeddings. We validate that this capability stems from MLLMs' conditional embeddings and a smaller modality gap than VLMs. Furthermore, we demonstrate that this property generalizes to the audio domain. Our findings suggest that language provides a direct interface for probing latent ordinal structures in MLLMs. Code and prompts are available at https://github.com/kaist-ami/prompt-probing

Long video question answering requires locating sparse, time-scattered visual evidence within highly redundant content. Although current MLLMs perform well on short videos, long videos introduce long-horizon search and verification, which often necessitates multi-turn, agentic interaction. We show that existing LVU agents can exhibit evidence misalignment: they produce correct answers that are not supported by the retrieved or inspected evidence. To characterize this failure, we introduce two diagnostics, temporal groundedness and semantic groundedness, and use them to reveal two pressures that amplify misalignment: prompt pressure from shared-context saturation at inference time and reward pressure from outcome-only optimization during training. These findings point to a structural root cause: the coupled agent paradigm conflates long-horizon planning with answer authority. We therefore propose the decoupled planner–inspector framework, which separates planning from answer authority and gates final answering on pixel-level verification. Across four long-video benchmarks, our framework improves both answer accuracy and evidence alignment, achieving 55.1% on LVBench and 62.0% on LongVideoBench while producing interpretable search trajectories. Moreover, the decoupled architecture scales consistently with increased search budgets and supports plug-and-play upgrades of the MLLM backbone without retraining the planner. Code and models are available at https://github.com/Echochef/VideoSEAL.

In-context learning is fundamental to modern Large Language Models (LLMs); however, prevailing architectures impose a rigid and fixed contextual structure by assigning linear or constant positional indices. The rigid position information poses the full burden of organizing the input structure to attention layers, thus reducing the amount of attention that could be allocated for more critical information. To address this, we propose RePo, a novel mechanism that alleviates the burden for attention layers via context re-positioning. Unlike conventional approaches, RePo utilizes a differentiable module, $f_\phi$, to assign token positions that capture contextual dependencies, rather than replying on pre-defined order. By continually pre-training on the OLMo-2 1B \& 7B models, we demonstrate that RePo consistently enhances performance on tasks involving noisy contexts, structured data, and longer context length, while maintaining competitive performance on general short-context tasks. Analysis reveals that RePo successfully allocates more attention mass to distant but relevant information, assigns positions in a dense and non-linear space, and captures the intrinsic structure of the input context.

Segment Anything Models (SAMs) often struggle with certain specialized tasks. A common approach is to fine-tune models with specific task labels, but this often leads to overfitting, introduces model bias and significantly degrades their generalization ability. To overcome these challenges, we propose SHERPA, a novel framework that leverages a smaller SAM to guide the fine-tuning of a larger SAM via task-relevant features. Specifically, we first leverage the Fisher Ratio Separation (FRS) module to separate high task-relevant features and preserve the ability of the large SAM to perform other general tasks. Then, the Guiding Feature Extraction (GFE) module is used to extract representative guiding features from the fine-tuned small SAMs. We leverage small SAMs tailored for specific tasks (including natural image segmentation, biomedical image segmentation, and video object segmentation) as guidance and then evaluate the SHERPA scheme to fine-tune larger SAM series models. Our experiments demonstrate that SHERPA enhances the retention of generalization ability across those diverse tasks, by up to 11.1\%, and improves specific task performance by up to 2.2\%.

Diffusion models have become a dominant paradigm for high-quality generative modeling, while post-training is essential for adapting them to diverse downstream applications. However, post-training of large diffusion models is still challenging due to the prohibitive memory footprints and slow training speed, which existing parameter-efficient fine-tuning methods only partially address. To overcome these limitations, we propose FourTune, an efficient post-training framework for diffusion models based on an end-to-end W4A4G4 paradigm. FourTune introduces a triple-branch hybrid pipeline that augments the standard LoRA architecture with a frozen numerical stabilizer to isolate quantization-sensitive outliers, enabling stable training under native 4-bit computation. In addition, FourTune employs hardware-efficient block-wise quantization and customized fused kernels to support efficient quantized backpropagation and reduce memory bandwidth overhead. Across customization, reinforcement learning, and distillation tasks, FourTune matches the quality of full-precision fine-tuning. On FLUX.1-dev (12B), FourTune reduces memory overhead by $2.25\times$ and increases end-to-end training throughput by $2.27\times$ compared to BF16 LoRA.

In this paper, we study the fully dynamic k-center with outliers problem, where points are inserted and deleted over time and the goal is to maintain an approximate clustering while discarding up to z outliers. Existing algorithms typically rely on radius guessing to maintain cluster representations, leading to update and query times that depend explicitly on the aspect ratio Δ. We propose a layered-sampling framework that avoids radius guessing by maintaining a hierarchy of sampled structures, which can separate most inliers from potential outliers and refine the remaining uncertain points. The resulting algorithm achieves $\tilde{O}(k^2/\epsilon^4)$ update and query time independent of Δ, while guaranteeing a constant-factor approximation with $(1+\epsilon)z$ outliers discarded. Under mild assumptions, our result is complemented by a lower bound in metric space query model.

We consider the robustness of score-based generative modeling to errors in the estimate of the score function. In particular, we show that Langevin dynamics is not robust to the $L^2$ errors (more generally $L^p$ errors) in the estimate of the score function. It is well-established that with small $L^2$ errors in the estimate of the score function, diffusion models can sample faithfully from the target distribution under fairly mild regularity assumptions in a polynomial time horizon. In contrast, our work shows that even for simple distributions in high dimensions, Langevin dynamics run for any polynomial time horizon will produce a distribution far from the target distribution in Total Variation (TV) distance, even when the $L^2$ error (more generally $L^p$) of the estimate of the score function is arbitrarily small. Considering such an error in the estimate of the score function is unavoidable in practice when learning the score function from data, our results provide further justification for diffusion models over Langevin dynamics and serve to caution against the use of Langevin dynamics with estimated scores.

Neural compression is currently dominated by Nonlinear Transform Coding (NTC), which maps data to real-valued latents via continuous transforms. Despite its success, NTC suffers from train-test mismatch due to non-differentiable quantization, a "smoothness bias" inherent in continuous transforms that precludes optimality for certain sources, and a loss of "shaping gain" due to its use of scalar quantization. We propose SoftBinary Coding (SBC), an end-to-end learning paradigm that bypasses these limitations by using a stochastic binary latent space. In the spirit of vector quantization, SBC employs discrete representations and compresses them through a novel fast binary channel simulation scheme, for which we provide a proof of rate optimality. Experimental gains on information-theoretic sources address NTC's limitations both theoretically and practically, establishing discrete binary structures as a viable path toward reaching optimal rate–distortion bounds. Surprisingly, SBC also achieves state-of-the-art performance on vector quantization of i.i.d. sources, exceeding Trellis Coded Quantization of the Gaussian source.

Modern large language models (LLMs) increasingly depend on efficient long-context processing and generation mechanisms, including sparse attention, retrieval-augmented generation (RAG), and compressed contextual memory, to solve complex tasks. We show that these optimizations can be unified into a four-stage memory processing pipeline: *Prepare Memory*, *Compute Relevancy*, *Retrieval*, and *Apply to Inference*. Through systematic profiling, we identify a 22\%-97\% memory processing overhead in LLM inference and strong computational heterogeneity across stages in memory processing. Motivated by this insight, we argue that **heterogeneous systems** are well-suited to accelerate memory processing and thus end-to-end inference. We demonstrate this approach on a GPU-FPGA system by offloading sparse, irregular, and memory-bounded operations to FPGAs while retaining compute-intensive operations on GPUs. Evaluated on an AMD MI210 GPU and an Alveo U55C FPGA, our system is up to $2.2\times$ faster and $4.7\times$ energy reduction across multiple LLM optimizations than the GPU baseline (with similar results on NVIDIA A100), establishing heterogeneous systems as a practical direction for efficient LLM inference and informing future heterogeneous hardware design.

This paper proposes a suite of rationality measures and associated theory for reinforcement learning agents, a property increasingly critical yet rarely explored. We define an action in deployment to be perfectly rational if it maximises the hidden true value function in the steepest direction. The expected value discrepancy of a policy's actions against their rational counterparts, culminating over the trajectory in deployment, is defined to be expected rational risk; an empirical average version in training is also defined. Their difference, termed as rational risk gap, is decomposed into (1) an extrinsic component caused by environment shifts between training and deployment, and (2) an intrinsic one due to the algorithm's generalisability in a dynamic environment. They are upper bounded by, respectively, (1) the $1$-Wasserstein distance between transition kernels and initial state distributions in training and deployment, and (2) the empirical Rademacher complexity of the value function class. Our theory suggests hypotheses on the benefits from regularisers (including layer normalisation, $\ell_2$ regularisation, and weight normalisation) and domain randomisation, as well as the harm from environment shifts. Experiments are in full agreement with these hypotheses. The code is available at \href{https://github.com/EVIEHub/Rationality}{https://github.com/EVIEHub/Rationality}.

Training large language models (LLMs) on heterogeneous data requires selecting minibatches that balance convergence speed with coverage across domains. Existing methods either select samples independently within each domain or rely on computationally expensive proxy models to learn continuous domain weights. We propose PartitionSel, a cross-domain minibatch selection approach that maximizes a validation-guided gradient-matching utility under per-domain budgets encoded as a partition-matroid constraint. By coupling the per-domain budgets through a single utility, PartitionSel is designed to reduce redundancy in selections across domains. The proposed objective is weakly submodular and admits an orthogonal matching pursuit algorithm with provable approximation guarantees. Empirically, we evaluate PartitionSel for minibatch selection during the fine-tuning of Qwen2.5 and Llama-3 on MetaMathQA and Mol-Instructions. PartitionSel achieves robust gains over per-domain and domain-agnostic baselines on both benchmarks. It also reduces the number of conflicting gradient pairs within each batch, indicating that the cross-domain coupling translates into more compatible training updates.

Speculative Decoding (SD) has emerged as a critical technique for accelerating Large Language Model (LLM) inference. Unlike deterministic system optimizations, SD performance is inherently data-dependent, meaning that diverse and representative workloads are essential for accurately measuring its effectiveness. Existing benchmarks suffer from limited task diversity, inadequate support for throughput-oriented evaluation, and a reliance on high-level implementations that fail to reflect production environments. To address this, we introduce **SPEED-Bench**, a comprehensive suite designed to standardize SD evaluation across diverse semantic domains and realistic serving regimes. SPEED-Bench offers a carefully curated *Qualitative* data split, selected by prioritizing semantic diversity across the data samples. Additionally, it includes a *Throughput* data split, allowing speedup evaluation across a range of concurrencies, from latency-sensitive low-batch settings to throughput-oriented high-load scenarios. By integrating with production engines like vLLM and TensorRT-LLM, SPEED-Bench allows practitioners to analyze system behaviors often masked by other benchmarks. We highlight this by quantifying how synthetic inputs overestimate real-world throughput, identifying batch-size dependent optimal draft lengths and biases in low-diversity data, and analyzing the caveats of vocabulary pruning in state-of-the-art drafters. We release SPEED-Bench to establish a unified evaluation standard for practical comparisons of SD algorithms.

Leveraging event-driven computation mechanism, Spiking Neural Networks (SNNs) have emerged as a representative paradigm for energy-efficient edge intelligence. However, extending SNNs to modern deep language models still faces two fundamental challenges. First, dead neurons in deep SNNs lead to degraded gradients, limiting the training effectiveness of spiking language models. Second, removing Softmax for energy efficiency weakens token-wise competition, reducing the model’s ability to select salient tokens. To address these challenges, we propose Spiking Language Model (SpikingLM) to bridge the efficiency of SNNs and the capability of modern language models through two key innovations. First, we propose Distribution-aware Scaling method, which rescales linear outputs into an activation-friendly range to alleviate dead neurons and stabilize gradient propagation. Notably, its scaling parameters can be fused into the preceding linear layers, incurring no additional inference overhead. Second, we introduce Spike2Max to restore winner-takes-all mechanism via base-2 exponentiation and max-subtraction. Compared with Softmax, Spike2Max reduces energy consumption by over 95\% using hardware-efficient bit-shift operations. Experiments show that SpikingLM reduces energy consumption by 57.9\% and achieves state-of-the-art performance on GLUE, laying a promising foundation for energy-efficient language modeling. Code is available at~\url{https://github.com/hamings1/SpikingLM.git}.

Automated ``LLM-as-a-Judge" frameworks have become the de facto standard for scalable evaluation across natural language processing. For instance, in safety evaluation, these judges are relied upon to evaluate harmfulness in order to benchmark the robustness of safety against adversarial attacks. However, we show that existing validation protocols fail to account for substantial distribution shifts inherent to red-teaming: diverse victim models exhibit distinct generation styles, attacks distort output patterns, and semantic ambiguity varies significantly across jailbreak scenarios. Through a comprehensive audit using 6642 human-verified labels, we reveal that the unpredictable interaction of these shifts often causes judge performance to degrade to near random chance. This stands in stark contrast to the high human agreement reported in prior work. Crucially, we find that many attacks inflate their success rates by exploiting judge insufficiencies rather than eliciting genuinely harmful content. To enable more reliable evaluation, we propose ReliableBench, a benchmark of behaviors that remain more consistently judgeable, and JudgeStressTest, a dataset designed to expose judge failures.

Large Language Models are rapidly becoming core components of modern software development workflows, yet ensuring code security remains challenging. Existing vulnerability detection pipelines either rely on static analyzers or use LLM/GNN-based detectors trained with coarse program-level supervision. Both families often require complete context, provide sparse end-of-completion feedback, and can degrade as code length grows, making them ill-suited for real-time, prefix-level assessment during interactive coding and streaming generation. We propose \textbf{SecCodePRM}, a security-oriented process reward model that assigns a \textbf{context-aware}, \textbf{step-level} security score along a code trajectory. To train the model, we derive step-level supervision labels from static analyzers and expert annotations, allowing the model to attend more precisely to fine-grained regions associated with inter-procedural vulnerabilities. SecCodePRM has three applications: full-code vulnerability detection (VD), partial-code VD, and secure code generation (CG). For VD, SecCodePRM uses risk-sensitive aggregation that emphasizes high-risk steps; for CG, SecCodePRM supports inference-time scaling by ranking candidate continuations and favoring higher cumulative reward. This design yields dense, real-time feedback that scales to long-horizon generation. Empirically, SecCodePRM outperforms prior approaches in all three settings, while preserving code functional correctness, suggesting improved security without a safety–utility tradeoff.