NeurIPS 2026 论文列表

Multi-omics drug-drug interaction (DDI) prediction forecasts DDI outcomes from heterogeneous multi-omics data and complex structured rules, where multi-omics interpretability of hierarchical biological factor interactions is extremely crucial, which remains unexplored in literature. In this paper, we are the first to study the problem of Multi-Omics Interpretable DDI Prediction, which is highly non-trivial with three challenges: i) how to identify interaction-relevant biological entities from large-scale knowledge sources, which lay the foundation for interpretability; ii) how to capture multi-omics cross-modal connections that elucidate underlying mechanisms under diverse interaction contexts; and iii) how to explicitly enable mechanism-aware reasoning over structured biological rules. To tackle the challenges, we propose a Multi-omics Interpretable prediction framework with joint optimization of graph structure, Neural architecture, and symbolic rules to hanDle DDI prediction (MIND-DDI), which follows a novel interpretable learning paradigm that tightly couples biomedical graph sampling, hierarchical neural representation learning, and symbolic rule modeling under a unified optimization scheme. Specifically, we propose a curriculum-guided biological subgraph sampler for progressively constructing informative subgraphs, then introduce a hierarchical multi-omics neural architecture search module to capture multi-omics alignment as well as cross-modal interactions, and finally present a mechanism-aware pathway-based symbolic reasoner for multi-hop reasoning over a unified neural-symbolic space. Extensive experiments show the superiority of MIND-DDI in both predictive accuracy and interpretability.

Large language models (LLMs) increasingly improve their reasoning at test time via additional computation, yet most procedures treat each problem in isolation. When problems arrive sequentially, accumulating reusable experience across them can further improve performance. Existing memory-based methods either store whole-solution templates that generalize poorly to novel problems or use heuristic step-level selection that is not optimized for final-answer correctness. Learning selection policies requires large-scale training data and fixed action spaces. We propose MILES (Modular Instruction Memory with LEarnable Selection for self-improving LLM reasoning), a framework that dynamically expands step-wise memory and applies correctness-optimized memory composition under realistic test-time constraints. MILES maintains modular memory units consisting of asymmetric pairs of sub-goal embeddings and sub-instructions, each associated with a learnable selection head. This memory structure enables a coarse-to-fine retrieval mechanism: The coarse level enables memory expansion and collects supervision for training selection heads from confident samples, while the fine stage applies learned selection heads to rerank coarse-level candidates and guide reasoning for uncertain samples. MILES consistently matches or outperforms prior methods while achieving superior accuracy–efficiency tradeoffs. Extensive experiments demonstrate its effectiveness, robustness, and transferability.

Current evaluation protocols for medical image segmentation remain largely anchored in sample-wise comparisons, e.g., Dice and Hausdorff distance, which require each prediction to be paired with a ground-truth mask. Yet two limitations arise in practice: they are inapplicable when predictions are made on unlabeled data; and even when annotations are available, they cannot assess whether a collection of predictions matches the distributional structure of the ground-truth population. We introduce MID (Mask–Image Distributional Divergence), a distribution-level evaluation metric for medical image segmentation. MID builds upon the observation that segmentation quality is a property of the joint image-mask distribution: a mask may be anatomically plausible in isolation yet incorrect for the image it accompanies. MID compares the joint distribution of images and masks between a reference set and a set of predictions, without requiring sample-wise correspondence. This captures both mask realism and image-mask consistency. We evaluate MID across 13 publicly available datasets spanning CT, MRI, and MRA. Under anatomically realistic corruptions across 56 organ groups, MID tracks mean Dice and Hausdorff distance without per-sample ground-truth pairing. MID also detects distributional shifts across modalities and anatomies, identifies image-mask misalignment through controlled shuffling experiments, and produces reliable model rankings across real segmentation models.

Conservative machine learning interatomic potentials (MLIPs) predict potential energy and obtain atomic forces as the negative gradient of energy with respect to atomic positions. Computing forces requires a backward pass from energy to atomic positions, and backpropagating the force loss differentiates through this pass, creating double-backward execution. This execution creates two activation classes with different lifetimes: forward activations and first-backward activations. Heterogeneous atomic graph batches make their memory footprint input dependent, while standard checkpointing mainly targets forward activations and does not directly manage first-backward activations. Therefore, we present MICA, an activation checkpointing planner for double-backward execution in conservative MLIP training. MICA combines a checkpoint primitive for double-backward phases with an input-aware dynamic programming planner that selects checkpoint modes for dynamic atomic graph batches under a specified memory budget. Across EqV3, MatRIS, PET, and UMA, MICA's full-checkpoint mode reduces peak memory by 49\% to 86\%, compared with only 10\% to 24\% from standard PyTorch checkpointing. On an 80GB GPU, training EquiformerV3 without checkpointing peaks at 75.47GB and exceeds 50GB in 76.7\% of 1000 iterations, while MICA keeps all 1000 iterations within a 50GB memory budget with 16.25\% step time overhead. Under the same GPU memory capacity, MICA increases the maximum feasible atoms per batch by $4.2\times$ to $9.2\times$. In distributed training, the reduced peak memory allows MICA to reduce reliance on heavier memory saving techniques, such as Fully Sharded Data Parallel (FSDP) and graph parallelism (GP). On a single H100 node with NVLink, MICA trains a MatRIS-MoE model with 2B parameters, achieving a $1.88\times$ to $2.03\times$ speedup over FSDP and GP baselines.

Autoregressive world models have emerged as a powerful paradigm for sample-efficient decision-making, yet their open-loop rollouts often exhibit increasing drift that leads to error accumulation even within a relatively small planning horizon. Hierarchical temporal abstraction is a natural candidate to mitigate such drift by reducing the effective prediction horizon; however, existing hierarchical designs can introduce added structural and conceptual complexity, sometimes making them difficult to control and limiting gains over flat baselines. To this end, we introduce MHWA (Multi-timescale Hierarchical World Action model), which employs a strided high-level context channel to reduce global-context update frequency, effectively curbing the propagation of compounding drift. Crucially, via context-aware routing, the gating network dynamically reconfigures a Low-Level Mixture-of-Experts by using both global context and current observations, thereby enabling flexible high--low coordination, helping alleviate interference commonly observed in static hierarchies. Empirically, MHWA (77M parameters) achieves an IQM human normalized score (HNS) of 0.867$\pm$0.047 across three training seeds on a 14-game Atari subset using 10\% subsampled offline data, matching the existing state-of-the-art 150M-parameter JOWA baseline while using nearly half the parameters and significantly reducing computational costs.

Long-horizon Large Language Model (LLM) agents need persistent memory that surfaces the right past interaction at the right time across thousands of turns. Current systems index by invoking generative LLMs to rewrite history into summaries, facts, or knowledge graphs---a step that is (a) costly (up to $\sim 50$K LLM calls and $35.83$M completion tokens per build), (b) non-deterministic (undermining reproducibility and giving inconsistent answers across runs), and (c) provenance-erasing (the reader sees synthesized text, not the original turn). We propose MGMem, an LLM-call-free framework that replaces this step with a deterministic discriminative-parser pipeline: recurring mentions across sessions are organized into an incidence graph, question mentions are resolved by a subject-conditioned three-stage resolver, and raw dialogue episodes are returned to the reader. On LoCoMo, MGMem outperforms matched-protocol generated-memory and retrieval baselines at zero generative indexing calls; on the full LongMemEval-S, it remains competitive overall and leads on single-session question types. Anonymous code: \url{https://anonymous.4open.science/r/mentiongraph}.

Recent advancements in audio generation have been largely driven by Transformer-based diffusion models. However, these models suffer from quadratic complexity of self-attention, severely bottlenecking the long-form audio synthesis. To overcome this limitation, we propose MFlowAudio, a novel latent audio generation framework that synergizes the continuous-time dynamics of Flow Matching with a custom-designed TFMamba backbone. TFMamba uses an innovative dual-scan mechanism: a TimeMamba module to capture long-range causal dependencies with linear complexity, and a FrequencyMamba module to model spectral correlations such as harmonic structures. Exploiting this structural foundation, we formulate the Stateful Flow Matching (SFM) paradigm. This framework inherently enables chunk-wise training and streaming generation, maintaining an $\mathcal{O}(1)$ caching complexity without incurring extra computational overhead. To enable fine-grained controllable synthesis, we devise a novel guidance mechanism that neutralizes vector field collisions precipitated by on-the-fly semantic transitions of prompts. Comprehensive empirical evaluations confirm that MFlowAudio yields generative fidelity on par with state-of-the-art baselines while establishing significant computational efficiency, achieving an $81.8$% acceleration in generation and facilitating perceptually seamless streaming synthesis with a constant, ultra-low latency of $1.8$ seconds. Demo:https://huggingface.co/spaces/mflowaudio/MFlowAudio

Current datasets for text-to-video generation are largely limited to short clips depicting a single event or coarse-grained captions. As a result, they provide limited supervision for modeling long-take temporal dependencies, often leading to temporally inconsistent generations when describing multiple events. In this paper, we introduce MEV, a multi-event video dataset designed for long-take video generation. MEV provides high-quality real-world videos where subjects can perform a sequence of distinct, non-overlapping events, featuring precise temporal boundaries and fine-grained procedural annotations. This event-centric discretization reduces confounding factors and enables models to support temporally localized conditioning and build long-take videos from atomic event units. Furthermore, we introduce a comprehensive annotation pipeline that segments videos into temporally grounded events, and generates structured captions at both the global level and the event level. In addition, under an event-centric evaluation protocol, we conduct multi-event generation experiments by fine-tuning on MEV with temporally grounded event conditioning, leading to improved long-take event transitions and more coherent content. We believe this work removes a key barrier to training video foundation models for multi-event scenarios and provides practical insights into learning from temporally-structured video-text data.

Deployed language models are increasingly expected to remove private, copyrighted, or hazardous content without full retraining. Existing unlearning methods remain brittle because they usually optimize a fixed forgetting objective with a global update schedule: weak updates leave paraphrased knowledge intact, while stronger updates can damage retained capabilities or nearby facts. We identify this failure mode as update homogeneity. To address it, we introduce METAFORGET, a meta-optimization framework that treats unlearning as learning an audit-driven update policy rather than designing another standalone forgetting loss. A lightweight controller maps memorization, paraphrase-sensitivity, and signed forget-retain conflict signals to span weights, layer gates, step sizes, and retain-gradient projection strengths. The controller is trained with a bilevel objective that differentiates through short LoRA unlearning trajectories and evaluates the resulting model on held-out forget, retain, locality, and leakage audits. This policy can instantiate NPO- or RMU-style losses while changing where and how strongly they act. Across TOFU, WMDP, and MUSE-style sequential deletion settings, METAFORGET improves the forget-retain-robustness frontier over strong baselines, moves loss-based membership-inference diagnostics closer to chance, and better preserves utility under repeated requests. The results support a view of practical LLM unlearning as audit-driven policy learning: the central object is not only the forget loss, but the localized update that must pass the deletion audit.

Direct Preference Optimization (DPO) has become a popular route for aligning large language models with human preferences, but existing pipelines treat all preference pairs uniformly and ignore prompt-level heterogeneity. We show that the optimal pair-selection strategy varies systematically with prompt characteristics: prompts with concentrated reward distributions benefit from large reward-gap pairs that provide unambiguous signal, while prompts with diverse responses benefit from moderate-gap pairs because extreme positions are dominated by outliers. No fixed strategy is optimal across this heterogeneity. We propose META-PAP (Meta-learning for Prompt-aware Preference Pairing), a framework that turns this observation into a learned algorithm. META-PAP generates multiple diverse pairs per prompt via a structured grid over the response reward distribution, extracts a compact prompt-aware feature vector, and trains a lightweight meta-network through bilevel optimization to predict per-pair weights. The inner loop is a weighted DPO update; the outer loop evaluates a virtual policy on a small clean meta-set. Across Llama-3-8B, Mistral-7B-v0.3, and Llama-2-7B, META-PAP consistently outperforms vanilla DPO, fixed-position pairing, reward-gap weighting, top-$k$ filtering, curriculum, and statistical rejection sampling, with average gains of $+3.9$ points on AlpacaEval~2.0 and $+3.2$ points on Arena-Hard, and approaches an oracle that exhaustively searches per prompt. The learned weighting policy is interpretable: it favors large-gap pairs on low-diversity prompts and softly rejects extreme pairs on high-diversity prompts. We additionally find that the meta-network requires only $M\!=\!150$ pairs to saturate, transfers across domains, tolerates label noise on the meta-set, and remains effective with as few as $n\!=\!32$ on-policy samples per prompt.

Scene flow can capture low-level 3D motion displacements in dynamic scenarios. Early pairwise estimators relying on instantaneous two-frame motion lack long-term temporal correlation and also struggle with poor extrapolation ability in future prediction. Although some recent methods attempt to explore multi-frame scene flow estimation in a sequence-to-sequence manner, they typically suffer from heavy computational overhead with increasing input frames and long-horizon prediction degradation due to ineffective motion propagation. To address these problems, we propose a novel memory-enhanced sequential scene flow pipeline, called MESSENGER. To sufficiently mine long-term temporal dependencies naturally within consecutive sequences, a memory buffer is designed by explicitly storing multiple history flow estimates and latent states. For each input frame, the temporally stored flows and states are correlated and retrieved to predict the current initialized flow in a next-frame forecasting manner. Furthermore, we develop an uncertainty-aware reweighting module to filter unreliable retrievals and mitigate accumulated errors. Extensive experiments on nuscenes and Argoverse 2 demonstrate state-of-the-art performance of our MESSENGER, reducing EPE3D by 71.6% on nuScenes and 67.7% on Argoverse 2 in long-horizon future extrapolation. This superiority can be attributed to our designed autoregressive forecasting paradigm, which naturally forces the network to progressively learn the next-frame distribution based on history observations. Code will be released upon publication.

Foundation models for electroencephalography (EEG) have shown promise in learning transferable representations, but existing approaches treat EEG as a generic time series, ignoring the Riemannian geometry of spatial covariance structure that is fundamental to neural signal analysis. We propose MENDR (Manifold-Embedded Neural Data Representations), the first EEG foundation model that builds this geometry directly into its architecture (via the matrix logarithm and Log-Euclidean tangent space) rather than learning it from data. MENDR embeds windowed covariance matrices into the Log-Euclidean tangent space via differentiable matrix logarithm, where standard transformer operations become geometrically equivalent to Riemannian operations. A channel-agnostic spatial projection based on Perceiver-style cross-attention enables seamless transfer across electrode configurations ranging from 6 to 64 channels. Pretrained on the Temple University Hospital EEG Corpus (4,000+ hours, 14,987 subjects) using a masked autoencoder objective in the tangent space, MENDR achieves state-of-the-art results on 3 of 6 downstream benchmarks (TUAB abnormality, TUEV event, CHB-MIT seizure) with only 1.2M parameters, up to $42\times$ fewer than competing foundation models.

LLM-based agents increasingly operate in persistent environments where they must store, update, and reason over information across many sessions. While prior benchmarks evaluate only single-entity updates, MEME defines six tasks spanning the full space defined by the multi-entity and evolving axes, including three not scored by prior work: Cascade and Absence (dependency reasoning) and Deletion (post-removal state). Evaluating six memory systems spanning three memory paradigms on 100 controlled episodes, we find that all systems collapse on dependency reasoning under the default configuration (Cascade: 3\%, Absence: 1\% in average accuracy) despite adequate static retrieval performance. Prompt optimization, deeper retrieval, reduced filler noise, and most stronger LLMs fail to close this gap. Only a file-based agent paired with Claude Opus 4.7 partially closes the gap, but at $\sim$70$\times$ the baseline cost, indicating closure currently depends on configurations that are not practical at scale. Code is available at https://anonymous.4open.science/r/MEME-0612 and the dataset at https://huggingface.co/datasets/meme-benchmark/MEME.

Multimodal sentiment analysis (MSA) and emotion recognition (ER) are closely related affective understanding tasks, yet they are usually studied separately due to differences in label space, task formulation, dataset distribution, and modality dependence. In this paper, we propose MEME ($\textbf{M}$ixture-of-$\textbf{E}$xperts for $\textbf{M}$ultimodal sentiment analysis and $\textbf{E}$motion recognition), a lightweight hierarchical MoE framework for unified multimodal affective computing across MSA, conversational emotion recognition, and dynamic facial expression recognition. MEME operates on frozen text, visual, and audio features, compresses variable-length modality sequences with learned-query attention pooling, and processes them with a shared hierarchical MoE backbone. Each block first applies hard modality experts for modality-specific refinement and then task-conditioned cross experts for task-aware multimodal interaction. A $\texttt{[TASK]}$ token provides an explicit task anchor for routing, while modality dropping regularizes unified training. We jointly train MEME on nine affective benchmarks and evaluate all datasets using a single composite-best checkpoint without dataset-wise adaptation. Extensive experiments show that MEME outperforms strong task-specific baselines and recent large-model-based unified methods on most benchmarks, while maintaining favorable efficiency, robustness and generalization.

Long-term LLM agents must decide what to write into persistent memory before future queries are known, yet existing evaluations measure only final QA accuracy, entangling memory writing with retrieval and reasoning. We introduce MEMAUDIT, a package-oracle evaluation protocol that turns memory writing into a finite, auditable optimization problem with a certified ground-truth optimum under a fixed storage budget. Each evaluation package specifies an experience stream, candidate memory representations, and future-query requirements, enabling exact measurement of how well a memory writer preserves task-relevant information. We instantiate MEMAUDIT with a semantic coverage objective under storage and exclusivity constraints and compute exact optima via certified optimization. Across controlled and naturalistic settings, MEMAUDIT disentangles representation quality, validity preservation, and budget-aware selection effects that end-to-end QA cannot isolate. This enables, for the first time, principled and reproducible evaluation of memory-writing policies independent of downstream retrieval and reasoning.

We introduce Multilingual Document Parsing Benchmark, the first benchmark for multilingual digital and photographed document parsing. Document parsing has made remarkable strides, yet almost exclusively on clean, digital, well-formatted pages in a handful of dominant languages. No systematic benchmark exists to evaluate how models perform on digital and photographed documents across diverse scripts and low-resource languages. MDPBench comprises 3,400 document images spanning 17 languages, diverse scripts, and varied photographic conditions, with high-quality annotations produced through a rigorous pipeline of expert model labeling, manual correction, and human verification. To ensure fair comparison and prevent data leakage, we maintain separate public and private evaluation splits. Our comprehensive evaluation of both open-source and closed-source models uncovers a striking finding: while closed-source models (notably Gemini3-Pro) prove relatively robust, open-source alternatives suffer dramatic performance collapse, particularly on non-Latin scripts and real-world photographed documents, with an average drop of 17.8% on photographed documents and 14.0% on non-Latin scripts. These results reveal significant performance imbalances across languages and conditions, and point to concrete directions for building more inclusive, deployment-ready parsing systems.

Image generation models have rapidly advanced, with many models now supporting generation conditioned on multiple reference images and textual instructions. Such models enable a wide range of applications, including entity fusion and attribute transfer across images. However, existing benchmarks for multi-reference image generation rely on limited evaluation dimensions and fail to capture the diverse challenges of the task. To address this limitation, we propose **MDMR-Bench**, a **M**ulti-**D**imensional benchmark for **M**ulti-**R**eference image generation. MDMR-Bench is designed based on realistic usage scenarios and consists of multiple evaluation subsets spanning diverse dimensions of multi-reference image generation, including (1) common entity fusion and attribute transfer, (2) multi-element extraction from a single image, (3) infographic manipulation, and (4) visual reasoning-intensive generation. This design enables systematic analysis of model capabilities and failure modes across different challenge dimensions. Furthermore, to achieve more reliable and interpretable evaluation, we introduce a checklist-based evaluation protocol that decomposes generation quality into fine-grained evaluation aspects. Instead of relying solely on holistic scoring, our framework uses structured checklists composed of both global-level and atomic-level queries, enabling more diagnostic assessment of model performance. By benchmarking both open-source and proprietary models, we demonstrate that MDMR-Bench provides fine-grained insights into model performance across different dimensions. Our dataset is available at [Kaggle](https://www.kaggle.com/datasets/6f695be8363ee17928c25f36fa976fd10f976f9f6d4925bc0df74f38dfce268c). The code is available at [GitHub](https://anonymous.4open.science/r/Neurips2026_ED_paper3412).

Non-stationary time series forecasting (NTSF) requires modeling evolving trends and seasonal patterns. Although linear decomposition operators (e.g., FFT) help isolate these patterns, they often introduce operator-dependent biases and idiosyncratic noise. To address this issue, we propose a novel Multi-view Decomposed Kalman Mixture of Experts (MDK-MoE) framework, which \textit{improves forecasting by strategically integrating multiple complementary, yet biased, linear decompositions}. Specifically, a Multi-view Decomposition (MVD) extracts frequency components from three complementary views. To mitigate view-specific noise, a Maximizing Mutual Information (MMI) enhances cross-view consistency, maximizes task-relevant information across diverse views, and suppresses view-dependent task-irrelevant information. To address the conflicts inherent in multi-source observations, the efficient Kalman MoE adaptively fuses distinct multi-view features. Instead of adopting traditional $O(d^3)$ covariance inversion, our learnable Kalman gain design enhances numerical stability and enables reliable state estimation under non-stationary scenarios. Extensive experiments on 13 real-world datasets demonstrate that MDK-MoE consistently achieves state-of-the-art performance.

Partial differential equation (PDE) solvers underpin scientific computing, but real-world deployment is bounded by compute. Classical Monte Carlo solvers such as Walk-on-Spheres (WoS) are unbiased and geometry-agnostic but are slow. Learned solvers are fast but biased and brittle under distribution shift. We present \textbf{MC$^2$}, a hybrid WoS-Neural Network (WoS-NN) PDE solver that treats a low-budget Monte Carlo solution as a structured estimator of the true field and learns a single-pass neural correction to recover a high-fidelity solution. MC$^2$ matches the accuracy of solutions using over $1000\times$ more Monte Carlo compute, outperforming all evaluated classical, denoising, and neural-operator baselines. To enable reproducible study of finite-compute PDE solving, we additionally release \textbf{PDEZoo}, the largest standardized elliptic PDE benchmark to date: 2M PDEs spanning five elliptic families and unlimited geometric compositions, with analytic ground truth and multi-budget Monte Carlo trajectories. Together \textbf{MC$^2$} and \textbf{PDEZoo} (1) empirically establish that finite-sample Monte Carlo error is structured, learnable, and correctable in a single forward pass, (2) show that we can solve PDEs $\sim$\textbf{1000x} faster than with just WoS, and (3) provide the evaluation infrastructure the field has so far lacked.