NeurIPS 2026 论文列表

Multimodal large language models (MLLMs) have achieved remarkable progress on vision–language tasks, yet their reasoning processes remain sometimes unreliable. We introduce PRISM-Bench, short for Puzzle Reasoning with In-Sequence Mistakes, a benchmark of puzzle-based visual challenges designed to evaluate not only whether models can solve problems, but how their reasoning unfolds. Unlike prior evaluations that measure only final-answer accuracy, PRISM-Bench introduces a diagnostic task: given a visual puzzle and a step-by-step chain-of-thought (CoT) containing exactly one error, models must identify the first incorrect step. This setting enables fine-grained assessment of logical consistency, error detection, and visual reasoning. The puzzles in PRISM-Bench require multi-step symbolic, geometric, and analogical reasoning, resisting shortcuts based on superficial pattern matching. Evaluations across state-of-the-art MLLMs reveal a persistent gap between fluent generation and faithful reasoning: models that produce plausible CoTs often fail to locate simple logical faults. By disentangling answer generation from reasoning verification, PRISM-Bench offers a sharper lens on multimodal reasoning competence and underscores the need for diagnostic evaluation protocols in the development of trustworthy MLLMs.

Learning dynamics from sparse partial observations presents a fundamental dilemma: the pointwise mean squared error (MSE) training objective may induce local contraction and empirically lead to topological collapse, whereas matching the system's invariant measure preserves global geometry but lacks temporal ordering constraints. To resolve this, we introduce the $\textbf{P}$oincaré $\textbf{R}$eturn $\textbf{I}$nduced $\textbf{M}$easur$\textbf{e}$ $(\textbf{PRIME})$ framework. PRIME bridges this gap by adopting a novel perspective of recurrence-level temporal organization, motivated by the return map and roof time structure of suspension flow representations. Instead of relying on unstable pointwise matching, PRIME refines the learned dynamics by leveraging recurrence-level temporal information, specifically by aligning the empirical graph measure of the induced return map over recurrence blocks. We evaluate our framework on the partially observed Lorenz63 system, sensor-observed Kuramoto-Sivashinsky equation, and flow past a cylinder. PRIME effectively reduces topological collapse across our benchmarks, improving temporal consistency while maintaining or enhancing long-term geometric and spectral fidelity.

Root cause analysis (RCA) in complex systems is challenging due to error propagation across multiple variables, the need for structural causal knowledge, and the computational cost of inference at test time. We introduce PRIM (Prior-fitted Root cause Identification with Meta-learning), a causal meta-learning approach that frames RCA as a Bayesian inference task over a synthetic prior of causal models. By marginalising out structural uncertainty, PRIM implicitly identifies changes in the data-generating mechanism between baseline and anomalous periods. In doing so, PRIM infers distributional differences without explicit statistical testing, and implicitly learns causal structure without model fitting at test time. Following the simulation-based meta-learning paradigm of prior-fitted networks, PRIM uses a Model-Averaged Causal Estimation (MACE) transformer neural process that jointly attends over observational and anomalous samples and the causal structure of nodes, enabling zero-shot inference in 17\,ms for systems with up to 100 variables. Across synthetic benchmarks and two realistic benchmark datasets, PetShop and CausRCA, PRIM is competitive with methods that are aware of the system's causal graphical structure a priori while outperforming graph-unaware methods on several tasks. Lightweight fine-tuning to specific domains and data dynamics improves performance further.

Agent memory is typically constructed either offline from curated demonstrations or online from post-deployment interactions. However, regardless of how it is built, an agent faces a cold-start gap when first introduced to a new environment without any task-specific experience available. In this paper, we study pre-task memory construction: whether an agent can build procedural memory before observing any target-environment tasks, using only self-generated synthetic practice. Yet, synthetic interaction alone is insufficient, as without controlling what to practice and what to store, synthetic tasks become redundant, infeasible, and ultimately uninformative, and memory further degrades quickly due to unfiltered trajectories. To overcome this, we present Preping, a proposer-guided memory construction framework. At its core is proposer memory, a structured control state that shapes future practice. A Proposer generates synthetic tasks conditioned on this state, a Solver executes them, and a Validator determines which trajectories are eligible for memory insertion while also providing feedback to guide future proposals. Experiments on AppWorld, BFCL v3, and MCP-Universe show that Preping substantially improves over a no-memory baseline and achieves performance competitive with strong playbook-based methods built from offline or online experience, with deployment cost $2.99\times$ lower on AppWorld and $2.23\times$ lower on BFCL v3 than online memory construction. Further analyses reveal that the main benefit does not come from synthetic volume alone, but from proposer-side control over feasibility, redundancy, and coverage, combined with selective memory updates.

Reinforcement learning (RL) has become an effective way to improve prompt alignment and perceptual quality in diffusion and flow-matching generators. A critical step for applying online RL to flow matching is turning the deterministic sampling trajectory into a stochastic policy, typically by replacing the reverse-time Ordinary Differential Equation (ODE) with a Stochastic Differential Equation (SDE). The stochastic sampler, controlling the exploration behavior and denoising dynamics, is thus part of the policy, and its design can significantly affect the reward optimization performance. We break down the sampler design into two interdependent components: choosing the right amount of stochastic exploration, and discretizing the resulting SDE faithfully at the small step counts used in RL. To address the first component, we analyze the inherent tension between exploration and stability in denoising and derive an SDE schedule that balances the two. Turning to the discretization challenge, we use a toy example to show that existing samplers can deviate from the flow-matching process, either by introducing excessive discretization noise or by relying on heuristic rules that do not guarantee convergence to the data distribution. To address these issues, we propose \textsc{Precise}, a new stochastic sampler that balances effective exploration with stability. Crucially, \textsc{Precise} keeps the denoising trajectory SDE-consistent through a novel approximation that freezes the clean-latent posterior mean, resolving the excess noise issue in standard samplers. Extensive experiments demonstrate that this formulation leads to significantly faster and more stable reward optimization via reinforcement learning, achieving state-of-the-art alignment scores (e.g., PickScore, HPSv2.1) while requiring 13.1--53.2\% less wall-clock training time to match the best in-domain performance of prior samplers.

Generative AI models now produce images indistinguishable from real data, making publicly verifiable provenance essential; however, existing watermarking methods become vulnerable to forgeries and adversarial optimization attacks once their detectors are made public. We propose PP-Mark, a provenance framework that anchors lightweight statistical detection to a zero-knowledge proof of the embedding process, ensuring that forged content cannot pass full verification by construction. We establish formal unforgeability under standard cryptographic assumptions and validate PP-Mark against representative baselines across two architectures, demonstrating resistance to black-box imprint forgery, white-box optimization, and regeneration attacks while remaining practical for decentralized verification.

Multimodal large language models (MLLMs) leverage object-agnostic tokenization by default, which represents images as flat grids of patch tokens and uniformly discretizes semantically rich foreground regions and information-sparse background areas. This introduces substantial redundancy and constitutes a major source of inference cost. Existing object-level tokenizers could either discard intra-region saliency with predefined region grouping and coarse pooling or limit to a single semantic scale by employing slot attention to the final encoder feature map only. In this paper, we propose a two-stage framework named POST that decouples unsupervised object-centric grouping from language-grounded multimodal reasoning to achieve progressively semantic-aligned object-level visual tokenizers. Specifically, we develop Progressive Slot Attention (PSA) in Stage I to introduce slot attention across multiple layers of a frozen ViT encoder and propagates slot states through a cross-layer refinement chain for learning hierarchical slot--patch correspondences without segmentation supervision. Subsequently, we transfer the learned PSA to the LLaVA pipeline in Stage II for object-level visual tokenization. We design slot-weighted merging to aggregate ViT patch tokens into object-grounded visual tokens and remove low-support slots with adaptive slot pruning. Remarkably, POST eliminates the need for external segmentation models, enables progressive object-centric refinement, and adapts visual token budget to image complexity in visual tokenization. Experimental results show that PSA achieves strong unsupervised object-centric segmentation on PASCAL VOC and COCO. Furthermore, POST is comparable or superior to LLaVA-1.5 on most multimodal benchmarks using only 8.3% visual token budget and improves referring expression comprehension on RefCOCO/+/g. It also outperforms recent patch-level and object-level token compression baselines at comparable budgets.

We introduce Post-Optimization Model Edit (POME), a new algorithm that enhances the performance of fine-tuned large language models using only their pretrained and fine-tuned checkpoints, without requiring extra data or further optimization. The core idea is to apply a muon-style projection to $\Delta W$, the difference between the fine-tuned and pretrained weights. This projection uses truncated singular value decomposition (SVD) to equalize the influence of dominant update directions and prune small singular values, which often represent noise. As a simple post-processing step, POME is completely decoupled from the training pipeline. It requires zero modifications and imposes no overhead, making it universally compatible with any optimizer or distributed framework. POME delivers consistent gains, boosting average performance by +2.5\% on GSM8K and +1.0\% on code generation. Its broad applicability—from 7B foundation models to 72B RLHF-instructed models—establishes it as a practical, zero-cost enhancement for any fine-tuning pipeline.

Prompt tuning (PT) provides a parameter-efficient way to adapt frozen large language models, but its behavior becomes less clear when task contains multiple related yet distinguishable patterns. We formalize this setting as a latent mixture target distribution, where the target behavior is modeled as a finite mixture of latent task components. We first show that static prompting can retain a non-vanishing approximation gap when one shared prompt is insufficient to capture the target distribution. Then we formalize instance-specific prompting as an input-dependent prompt mapping and show that, under ideal prompt assignment, its achievable regret can approach zero. Guided by this analysis, we propose POISE (Prompt Optimization via Instance-Specific Experts), a structured and parameter-efficient approximation to instance-specific prompting. POISE represents the prompt space with learnable expert prompts, combines them through input-dependent routing, and introduces a shared low-rank residual correction to capture common structure. Extensive experiments across multiple benchmarks show that POISE achieves strong performance while maintaining high parameter efficiency.

Real-world robot task planning must operate under both stochastic action execution and partial observability, yet constructing Partially Observable Markov Decision Process (POMDP) models for real robotics domains remains difficult and labor-intensive. We introduce PO-PDDL, a symbolic formulation of POMDPs that preserves the relational structure and LLM-friendly syntax of the Planning Domain Definition Language (PDDL), while explicitly modeling partial observability, stochasticity, and beliefs. Building on this formulation, we propose a demonstration-driven pipeline for learning PO-PDDL models. The proposed method reconstructs latent symbolic state trajectories from real-robot execution videos, identifies partial observability via inconsistencies between inferred states and visual observations, and learns stochastic transition and observation models accordingly. The resulting PO-PDDL domains are reusable across tasks and enable online belief-space planning under both perception and execution uncertainty. Experiments on real-world long-horizon manipulation tasks show that our method consistently outperforms existing PDDL and POMDP model-learning approaches, achieving robust task planning under uncertainty with significantly lower planning cost.

Precision medicine relies on integrating diverse patient data, including genetic variants, clinical phenotypes, and medical imaging, to inform personalized prevention, diagnosis, and treatment. However, learning general patient-level representations from these heterogeneous modalities remains challenging due to their high dimensionality and pervasive missingness. We propose PM1, a multimodal foundation model that learns meaningful patient-level representations across genetic, clinical, and imaging data from 337,129 individuals in the UK Biobank, with a focus on retinal imaging and ophthalmic traits. To address modality dimensionality, PM1 adopts an intermediate fusion architecture with modality-specific encoders and a shared Transformer backbone, where a novel pathway-based genotype encoder enables the incorporation of over 600,000 genetic variants by reducing dimensionality while preserving trait-relevant variation. In addition, a contrastive loss invariant to modality missingness allows PM1 to learn robust patient-level representations despite only 6\% of UK Biobank participants having complete modality coverage. By partitioning modalities into interpretable tokens, PM1 enables interpretability methods to investigate known and potentially novel associations across genetic, clinical, and imaging features, and their interactions. Evaluated across downstream tasks, including phenotype prediction, conditioned image generation, and attribution analyses, PM1 demonstrates the value of multimodal patient representations, improving predictive performance over unimodal baselines and competing methods while enabling interpretable analyses in settings with heterogeneous and incomplete patient data.

In continual learning, most parameter-efficient fine-tuning methods rely on task-specific low-rank adapters to incrementally adapt pre-trained models to new tasks. However, they overlook two critical challenges: one is the accumulation of numerous adapters that leads to linear growth in parameters and memory, and the other is the lack of an explicit mechanism to preserve previously learned knowledge during continual adaptation. In this work, we propose a simple yet scalable framework, termed Progressive Merging of Low-Rank Adapters (PM-LoRA), to address both issues simultaneously. Specifically, PM-LoRA trains a small task-specific spectral orthogonal adapter for each new task and progressively integrates it into a single evolving LoRA adapter that encodes all prior knowledge. This merging process enables continuous knowledge integration while directly mitigating catastrophic forgetting at the parameter level. Benefiting from this design, PM-LoRA achieves true scalability by maintaining constant parameter overhead throughout continual training. Extensive experiments on four benchmark datasets demonstrate that PM-LoRA achieves state-of-the-art performance with superior memory and computation efficiency.

Open agent systems (OASYS) are increasingly prevalent in real-world domains where the sets of agents and tasks change unpredictably over time. Such openness, including agent openness (AO) and task openness (TO), poses a fundamental challenge to multi-agent reinforcement learning (MARL), which typically assumes fixed state and action spaces. Existing methods address openness only partially: padding and masking approaches introduce artificial bounds, while recent graph-based or hypergraph methods handle one dimension of openness but still depend on restrictive assumptions. In this paper, we introduce Pointer Learner for Agent and Task Openness (PLATO), a pointer-network-based actor combined with a centralized graph neural network (GNN) critic, trained with multi-agent proximal policy optimization under a centralized training and decentralized execution paradigm. Our pointer-based actor outputs distributions directly over the current task set. This directly supports changing action spaces without masking or retraining. Our GNN critic encodes agent–task interactions as a graph that changes shape with task and agent composition. Together, these components consider AO and TO without the boundedness of existing approaches. We formalize PLATO in a Task-and-Agent-Open Markov Game (TaAgO-MG), extending prior task-open formulations, and prove it is well-defined over the resulting unbounded state and action spaces. We evaluate PLATO with the Methods for Open Agent Systems Evaluation Initiative (MOASEI) wildfire suppression domain, an environment designed for open multi-agent system evaluation, and we demonstrate strong performance and more consistent zero-shot generalization than state-of-the-art baselines in OASYS.

Streaming reconstruction from monocular image sequences remains challenging, as existing methods typically favor either high-quality rendering or accurate geometry, but rarely both. We present PLANING, an efficient on-the-fly reconstruction framework built on a hybrid representation that loosely couples explicit geometric primitives with neural Gaussians, enabling geometry and appearance to be modeled in a decoupled manner. This decoupling supports an online initialization and optimization strategy that separates geometry and appearance updates, yielding stable streaming reconstruction with substantially reduced structural redundancy. Despite operating online, PLANING improves dense mesh Chamfer-L2 by 18.52% over the offline baseline PGSR, surpasses the streaming baseline ARTDECO by 1.31 dB in PSNR, and reconstructs ScanNetV2 scenes in under 100 seconds, over 5x faster than offline 2D Gaussian Splatting while matching per-scene optimization quality. Beyond reconstruction quality, the structural clarity and computational efficiency of PLANING make it well suited for a broad range of downstream applications, such as enabling large-scale scene modeling and simulation-ready environments for embodied AI.

While While Vision Foundation Models (VFMs) are increasingly used in several computer vision tasks, their internal representations remain substantially opaque. This mostly stems from polysemanticity, i.e., individual neurons encode mixtures of unrelated visual patterns. In stark contrast, human reasoning is inherently monosemantic, i.e., it naturally relies on distinct, isolated features to process information. Therefore, monosemanticity needs to be implemented within the model's activation space to obtain representations that are human-understandable concepts. Existing methods mostly operate on convolutional networks, so when applied to VFMs their "crop-and-resize" approach distorts the model's representations by disrupting global self-attention mechanisms and discarding spatial geometry. Furthermore, prior work requires downstream classification labels and is based on KL-divergence, which requires to propagate the gradients back from the classifier head. Ultimately incurring in excessive concept extraction time, and making it hardly applicable to extract task-agnostic concepts. To overcome these issues, we propose PLACE, a fully unsupervised concept extraction framework that operates directly on the native patch-token activations of a VFM. By introducing a geometric Gram-matrix alignment loss, PLACE mechanistically controls downstream KL divergence, thus enforcing faithfulness -- i.e., the notion that extracted concepts, although obtained in an unsupervised fashion, are relevant to downstream classification tasks. Evaluations on image classification tasks (ImageNet and COCO) on DINOv2, ViT-MAE and ViT-B/16 show that PLACE (i) using Gram-alignment it extracts concepts about $20\times$ faster compared to KL-supervised extraction and $11\times$ faster than Sparse Autoencoders (SAEs). Moreover, PLACE yields highly sparse concepts that (ii) achieve up to 40 percentage points sparser compared to the state of the art (i.e., max 0.933 Gini sparsity score), and (iii) are up to 92.3% similar to those obtained under classifier supervision (i.e., 0.923 cosine similarity).

Streaming long-video understanding is a realistic setting for always-on video assistants, where visual input arrives continuously and users may ask questions at arbitrary times. We study streaming long-video question understanding (QA) under a unified temporal formulation in which multiple questions are revealed over time and may concern the past, present, or future relative to their query times. The model receives no task-type labels and must operate under strict sequential access and bounded shared memory, deciding whether each active question is already answerable or should remain open for future evidence. This differs from prior streaming settings that often focus on short streams, prefix-answerable queries, separated temporal categories, or response timing without long-horizon shared memory. To evaluate this formulation, we propose Ref2Stream (Reference-to-Stream), a general benchmark-conversion protocol that turns temporally grounded offline video QA benchmarks into streaming QA benchmarks. Instantiated on LVBench, Ref2Stream yields LVBench-Ref2Stream, which mixes past, present, and future questions under strict sequential access and evaluates both answer accuracy and answer latency. Existing streaming video methods typically improve efficiency or response timing through predefined compression, retrieval, or response policies, while offline video agents perform adaptive evidence gathering but assume access to the full video and target question. We introduce PIVOT (Planning over Incremental Video Observations for Timely Answering), a unified agentic framework that incrementally updates bounded memory from the observed stream and uses a planner-controlled action loop to retrieve relevant memory, analyze current evidence, reflect on candidate answers, and decide whether to answer or defer. Our work suggests that agentic reasoning is a promising direction for building streaming long-video systems that can adaptively gather evidence and answer only when sufficient information has been observed.

Multi-modal cloud removal exploits complementary optical and synthetic aperture radar (SAR) images to restore cloud-degraded remote sensing images. Most existing methods rely on black-box, data-driven architectures with limited interpretability of cross-modal interactions. Although some attempts introduce physical priors into networks, their oversimplified formulations fail to faithfully characterize the underlying physical imaging process and the networks remain loosely coupled with optimization variables. To address these issues, we propose a physics-informed deep unfolding network for cloud removal via optical-SAR image fusion, termed as PIU-CR. We first formulate cloud removal as a physics-informed optimization problem. Specifically, we fundamentally ground the optimization in the physical imaging mechanism of cloud degradation by embedding the atmospheric scattering model into data fidelity term. Then, the regularization terms establish an explicit cross-modal interaction mechanism, overcoming the single-modal information scarcity and the obscure, uninterpretable interactions in black-box models. They are dedicated to SAR-guided structure and spectral regularization, jointly introducing cross-modal structural feature alignment and coordinated spectral consistency constraints. The resulting optimization problem is then unfolded into a multi-stage neural network with dedicated structure and spectral branches. Each stage corresponds to explict optimization iteration step, enabling interpretable and effective reconstruction process. Experiments demonstrate that the proposed method outperforms state-of-the-art methods.

Diffusion-based solvers have become a prominent approach to neural combinatorial optimization. At inference time, they assign each decision variable a prediction score. A greedy decoder ranks candidates by these scores and checks hard constraints to ensure feasibility. Top-ranked candidates should be both promising and jointly feasible, making prediction--constraint alignment critical. When this alignment is weak, greedy decoding skips constraint-violating candidates and falls back to lower-ranked alternatives, degrading solution quality. Existing test-time methods improve search, sampling, or decoding, but do not directly strengthen this alignment before decoding. We observe that trained denoisers already carry constraint-aligned structural signals. Building on this observation, we propose Perturbed Instance-Structure Guidance (PISG), a training-free method that amplifies these signals at test time. At each denoising step, PISG constructs a structure-degraded prediction and extrapolates the unperturbed prediction away from it. The resulting guided prediction improves candidate rankings before constrained decoding. Signal analysis shows that this guidance concentrates on constraint-critical variables rather than uniformly rescaling scores. Under greedy decoding and without downstream refinement, PISG improves all 16 TSP solver-scale pairs across DIFUSCO, T2T, FastT2T, and StruDiCO, and all four MIS-ER solvers, with gains up to +8.4\%. These results identify prediction-constraint alignment as an effective test-time enhancement direction for diffusion-based combinatorial optimization.

AI video generation is moving beyond general generation, which relies on exhaustive prompt-engineering and "cherry-picking", towards fine-grained, controllable generation and high-fidelity post-processing. In professional AI-assisted filmmaking, the core requirement is the ability to perform precise, targeted modifications. A key task is video instance insertion, which requires precise spatial-temporal placement, physically consistent scene interaction (e.g., shadows and reflections), and the faithful preservation of original dynamics - all achieved under minimal user effort. In this paper, we propose PISCO, a video diffusion model for precise video instance insertion with arbitrary sparse keyframe control. PISCO allows users to specify a single keyframe, start-and-end keyframes, or sparse keyframes at arbitrary timestamps, and automatically propagates object appearance, motion, and interaction. To stabilize generation under sparse conditioning, we introduce Variable-Information Guidance and Distribution-Preserving Temporal Masking, complemented by geometry-aware conditioning. We further construct PISCO-Bench, a benchmark with verified instance annotations and paired clean background videos, and evaluate performance using both reference-based and reference-free perceptual metrics. Experiments demonstrate that PISCO consistently outperforms existing baselines and scales effectively as additional control signals are provided.