NeurIPS 2026 Papers

Direct preference optimization (DPO) is a simple and effective alignment strategy for large language models (LLMs) based on pairwise preferences between two candidates. In recommender systems, however, user feedback is rarely pairwise. For a given context, e.g., a user, a session, or a conversation, we typically observe set-wise preferences with multiple positive items, where every positive item should outrank every unobserved or explicitly negative item, with no prescribed order among the positives or the negatives themselves. A natural generalization is to use the Plackett–Luce (PL) reward model, which extends the Bradley–Terry (BT) reward model underlying vanilla DPO from pairwise preferences to full rankings of candidates. However, adapting the PL model to set-wise preferences requires marginalizing over all consistent permutations of the positives and negatives respectively, which is intractable. To address this fundamental challenge, we propose Mult-DPO, a novel DPO objective with a tractable multinomial reward model over set-wise preferences. We show that, like the BT and PL reward models, the multinomial reward admits a closed-form DPO-style objective, enabling direct alignment of LLMs without reinforcement learning (RL). In addition, we prove that the multinomial DPO loss is a tractable upper bound on the exact marginalized PL DPO loss when optimizing against the set-wise preference data. We further characterize the tightness of this bound in terms of relative total weight (i.e., exponentiated rewards) of positives versus negatives, which provides insights into tightening the bounds with more or harder negatives. Finally, we extend the framework to a group-wise setting that accommodates multiple preference levels. Code and datasets are available at https://anonymous.4open.science/r/mult-dpo-41C7.

Tabular Foundation Models have recently established the state of the art in supervised tabular learning, by leveraging pretraining to learn generalizable representations of numerical and categorical structured data. However, they lack native support for unstructured modalities such as text and image, and rely on frozen, pretrained embeddings to process them. On established Multimodal Tabular Learning benchmarks, we show that tuning the embeddings to the task improves performance. Existing benchmarks, however, often focus on the mere co-occurrence of modalities; this leads to high variance across datasets and masks the benefits of task-specific tuning. To address this gap, we introduce MulTaBench, a benchmark of 40 datasets, split equally between image-tabular and text-tabular tasks. We focus on predictive tasks where the modalities provide complementary predictive signal, and where generic embeddings lose critical information, necessitating Target-Aware Representations that are aligned with the task. Our experimental results demonstrate that the gains from target-aware representation tuning generalize across both text and image modalities, several tabular learners, encoder scales, and embedding dimensions. MulTaBench constitutes the largest image-tabular benchmarking effort to date, spanning high-impact domains such as healthcare and e-commerce. It is designed to enable the research of novel architectures which incorporate joint modeling and target-aware representations, paving the way for the development of novel Multimodal Tabular Foundation Models.

We develop a gradient flow on the space of probability measures defined on matrix-valued parameters induced by regularized Muon, an analytically smoothed version of the idealized Muon optimizer. The key observation is that the regularized orthogonalization map is the gradient of a smooth Fenchel-dual smoothing of the nuclear norm. This identifies the (regularized) Muon update as a mirror/prox step in the update variable, with momentum acting as the dual coordinate. We use this structure to lift Muon from a single matrix parameter to finite-particle probability objectives of the form $J(\rho)=R\left(\int F d \rho\right)$, a setting motivated by mean-field descriptions of neural-network training, and derive the inertial continuous-time limit. Using this structure, we derive the finite-particle continuous-time limit under the inertial scaling of step size and momentum, and then pass to a phase-space mean-field equation over probability laws on parameter-momentum pairs. The resulting flow can be shown to be a damped Hamiltonian probability dynamics whose kinetic energy is induced by the regularized Muon mirror potential. We prove an exact Hamiltonian dissipation identity, showing that the Hamiltonian energy decreases monotonically- leading to the descent of the target objective functional. Under appropriate gradient dominance assumptions, we obtain continuous and discrete time exponential convergence rates. We also study the well-posedness of the mean field limit equation and establish propagation of chaos guarantees for the interacting particle system. Finally, we extend the formulation to Hilbert-valued feature maps on product matrix spaces, yielding a blockwise Muon probability flow applicable to smooth transformer mixture-of-experts models.

Motion instruction generation in cross-video comparison aims to produce corrective feedback that describes the differences between a query and a reference motion. However, existing models often generate instructions that exhibit motion hallucinations, failing to reflect actual kinematic differences between paired videos. To systematically investigate these hallucinations, we introduce MotionHalluc, a dedicated benchmark for evaluating motion hallucinations in paired-video comparison. MotionHalluc comprises 1540 fine-grained questions over 553 video pairs, evaluating hallucinations along three core dimensions: (1) directional hallucination, (2) attributional hallucination, and (3) temporal hallucination. Extensive evaluations of state-of-the-art large multimodal models demonstrate high susceptibility to these hallucinations. Furthermore, we provide Perceive-Parse-Verify (PPV) as a training-free measurements extraction and verification baseline that converts candidate instructions into executable measurement queries and supplies kinematic measurements at inference time. Our results show that this simple measurements injection yields an average 10.6% performance gain across models, suggesting that motion reasoning with explicit quantitative measurements is a key factor in reducing hallucinations in cross-video comparison.

Motion transfer enables controllable video generation by transferring temporal dynamics from a reference video to synthesize a new video conditioned on a target caption. However, existing Diffusion Transformer (DiT)–based methods are limited to single-object videos, restricting fine-grained control in real-world scenes with multiple objects. In this work, we introduce MotionGrounder, a DiT-based framework that $\textit{firstly}$ handles motion transfer with $\textit{multi-object controllability}$. Our Flow-based Motion Signal (FMS) in MotionGrounder provides a stable motion prior for target video generation, while our Object-Caption Alignment Loss (OCAL) grounds object captions to their corresponding spatial regions. We further propose a $\textit{new}$ Object Grounding Score (OGS), which jointly evaluates (i) spatial alignment between source video objects and their generated counterparts and (ii) semantic consistency between each generated object and its target caption. Our experiments show that MotionGrounder consistently outperforms recent baselines across quantitative, qualitative, and human evaluations.

Despite recent advancements in Text-to-Video (T2V) synthesis, generating high-fidelity and dynamic motion remains a significant challenge. Existing methods primarily rely on Classifier-Free Guidance (CFG), but standard CFG treats all semantic dimensions uniformly and provides no mechanism to selectively resolve ambiguity along the motion axis. To address this, we propose MotionCFG, a training-free approach that introduces selective guidance along the motion subspace of the condition embedding. Specifically, we construct a motion-perturbed negative condition by injecting Gaussian noise into motion-related embeddings, and steer generation away from it to selectively amplify motion intent. We show theoretically that this procedure implicitly approximates *Semantic Laplacian Sharpening*, a second-order correction that suppresses motion-ambiguous regions of the score landscape and amplifies well-resolved dynamic peaks. Combined with a piecewise guidance schedule that confines intervention to the early denoising steps, MotionCFG consistently improves motion dynamics across state-of-the-art T2V frameworks with negligible overhead. We further demonstrate that this Laplacian sharpening principle generalizes beyond motion, effectively steering complex, non-linear concepts such as precise object numerosity that are typically difficult to modulate via standard text-based guidance.

Structured video generation (e.g., autonomous driving) faces a fundamental domain gap between simple human control and dense physical reality. Text-to-Video models accept accessible inputs but struggle with precise spatial guidance, while dedicated autonomous driving world models require expensive, dense 3D annotations that are difficult for users to provide. To bridge this gap, we introduce \textbf{Motion Forcing}, a structured video generation framework that achieves precise multi-agent control using extremely sparse 2D inputs. Our key insight is to explicitly bridge human intent and visual synthesis via a hierarchical \textbf{``Point-Shape-Appearance''} paradigm. This approach decomposes generation into verifiable stages: modeling user intent as sparse geometric points, expanding them into dynamic depth maps to explicitly resolve 3D geometry and decouple ego-motion from object dynamics, and finally rendering high-fidelity textures. Furthermore, to elevate the model from passive instruction-following to active physical reasoning, we employ a \textbf{Masked Point Recovery} strategy. By forcing the reconstruction of dynamic depth from occluded trajectories, the model internalizes latent physical laws, enabling causal inference. Extensive experiments demonstrate that Motion Forcing significantly outperforms state-of-the-art baselines on large-scale autonomous driving benchmarks. Additional validation in rigid-body physics and robotic manipulation confirms the structural integrity and generalizability of our framework. \textbf{To facilitate future research, we have released our model weights and code.}

LiDAR scene flow estimation is essential for autonomous driving, as it provides 3D motion for each point. Self-supervised approaches use static-dynamic classification to mitigate the imbalance between static and dynamic points, deriving targeted supervision. However, existing methods rely on sparse geometric observations for this classification, making them vulnerable to data sparsity and occlusions. The resulting noisy labels provide incorrect motion guidance and degrade scene flow learning. To address this, we introduce TrackCue, a tracking-guided framework for improving dynamic object representation in LiDAR scene flow estimation. In particular, TrackCue repurposes point tracking to obtain dense image-space trajectories anchored to LiDAR points, providing motion cues beyond sparse geometric observations. Furthermore, we present a visually consistent motion compensation strategy that compares the tracked trajectories with ego-induced rigid trajectories in the image plane, effectively isolating true object motion from ego-induced apparent motion. To transfer these isolated motion cues back to the LiDAR domain, we perform visual motion cue lifting, which associates ego-compensated image trajectories with LiDAR points for static-dynamic label refinement. As a result, TrackCue produces more accurate static-dynamic classification and provides more reliable supervision for scene flow learning. Experimental results show that TrackCue significantly improves the precision and F1 score of dynamic labels, leading to performance gains in self-supervised scene flow estimation.

Efficient long-sequence modeling remains a central challenge for large language models, as self-attention scales quadratically with sequence length. Mamba offers a linear-time alternative through selective state space recurrence, but its predominantly diagonal state transitions restrict explicit interactions among state dimensions. We propose Motif-Mamba, a structured state space model that augments Mamba with a motif-constrained low-rank recurrent pathway. Inspired by the dynamics of three-node network motifs, the proposed pathway projects hidden states into a compact dynamical subspace, imposes motif-guided interactions, and maps the resulting dynamics back to the original state space. This design enhances cross-dimensional communication while preserving the linear-time recurrent structure of Mamba. Experiments on long-sequence extrapolation, language modeling benchmarks, and brain--computer interface decoding show consistent improvements over Mamba backbones, suggesting that motif-guided low-rank dynamics provide an effective structural prior for long-range sequence modeling.

Differentiable physics solvers underpin solver-in-the-loop ML training, gradient-based optimal control, and inverse problems, yet the practical cost of obtaining correct, usable gradients from a given solver on a given problem is largely undocumented. Integration effort, computational cost, gradient accuracy, and numerical conditioning vary widely across solvers and are discoverable only by trial and error. We introduce Mosaic, an extensible benchmarking framework for differentiable PDE solvers that standardizes access to solver gradients. Each solver is packaged as a containerized component (Tesseract) exposing a uniform gradient API regardless of language or automatic differentiation (AD) strategy, enabling researchers to evaluate, compare, and build on non-trivial physical solvers. Our evaluation of 14 solvers across fluid dynamics, structural mechanics, and heat transfer demonstrates that the benchmark surfaces practically relevant differences: order-of-magnitude variation in computational cost and Jacobian conditioning, alongside structural incompatibilities that eliminate solvers from realistic tasks entirely. Despite this variation, all solvers that produce gradients converge to similar optima, indicating that the practical barriers are memory limits, numerical stability, and setup compatibility rather than gradient accuracy alone. Mosaic is open-source and available at https://anonymous.4open.science/r/mosaic-bench.

Microscopy images contain rich information about how cells respond to perturbations, making them essential to applications like drug screening. To quantify images, researchers often use representation extraction methods, and recent years have seen a proliferation of deep learning methods. While measuring the quality of these representations is essential, evaluation remains fragmented, with each proposed model evaluated on different tasks and datasets, using custom pipelines and metrics, making it difficult to fairly compare models. Here, we introduce MorphoHELM, a comprehensive open benchmark for evaluating feature extraction methods for cell painting, the most widely-used morphological profiling assay. MorphoHELM consolidates evaluation standards in the field, extends and corrects them to be more robust, and evaluates on the widest range of methods to date. A defining feature of the benchmark is that each task is evaluated at different degrees of batch effects (or technical noise), directly quantifying how the ability of methods to detect biological signal degrades as noise increases. Together, these properties enable MorphoHELM to detect trade-offs between methods, and we demonstrate that models that excel at certain kinds of biological signal are weaker at others. We show that no existing model outperforms classic computer vision analytic strategies across all settings, which remain the strongest general use-case representations. All datasets, code, and evaluation tools are publicly available.

During evolution, biological neurons scale computation by expanding dendritic branches. However, this expansion creates a biophysical dilemma: increased membrane area typically imposes a capacitive load that slows somatic dynamics and narrows temporal bandwidth. Here, we investigate how primate cortical neurons resolve this tradeoff. While primary basal dendrite number is relatively conserved across mouse cortical areas, it increases systematically along the primate cortical hierarchy. Using biophysically constrained multicompartment modeling, we identify a key dimensionless control parameter---the dendritic-to-somato-apical specific membrane resistance ratio, $\rho \equiv R_{m,\mathrm{dend}}/R_{m,\mathrm{sa}}$, that governs the coupling between dendritic morphology and the effective somatic time constant $\tau$. In mouse-like neurons ($\rho>1$), adding basal dendrites progressively increases $\tau$ and promotes reliable low-pass integration. Conversely, human-like neurons operate near a balanced-resistance regime ($\rho \approx 1$), where resistive reweighting counterbalances morphology-driven capacitive loading. This allows $\tau$ to remain nearly invariant despite expanded dendritic topology, shifting the structure-function tradeoff toward faster, more flexible coding with improved high-frequency tracking. Our results reveal a biophysical scaling principle linking evolutionary dendritic architecture to hierarchy-dependent coding, offering potential design rules for preserving temporal bandwidth in dendrite-inspired neuromorphic architectures.

Simulating in silico cellular responses to interventions is a promising direction to accelerate high-content image-based assays, critical for advancing drug discovery and gene editing. To support this, we introduce MorphGen, a state-of-the-art diffusion-based generative model for fluorescent microscopy that enables controllable generation across multiple cell types and perturbations. MorphGen is trained with an alignment loss that matches its representations to phenotypic embeddings from a biology foundation model, encouraging meaningful morphological patterns consistent with real cell images. Unlike prior approaches that compress multichannel stains into RGB images, sacrificing organelle-specific detail and focusing on a single cell type, MorphGen generates the complete set of fluorescent channels jointly, preserving per-organelle structure and enabling post-generation interpretation. We demonstrate biological consistency with real images via CellProfiler features, and MorphGen attains an FID score over 35% lower than the prior state-of-the-art MorphoDiff. Finally, in a compositional generalization test that holds out cell type--perturbation combinations during training, MorphGen achieves in-distribution quality on 55% of unseen pairs under a seen-calibrated criterion.

Autoregressive generation in Large Language Models (LLMs) is constrained by the memory and computational demands of attention mechanisms. Sparse attention methods mitigate this cost by selecting only high-probability entries of the attention matrix. We observe that in many such methods, this renders the probability-value multiplication negligible, shifting the bottleneck to the query-key step. Key heads can therefore be reduced to accelerate inference, while value heads preserve capacity at no additional cost. We introduce Sparse Asymmetric Group-Query Attention (SAGA), which decouples key and value head counts to exploit this principle, and pair it with approximate top-N (Atop-N) attention, a simple GPU-agnostic sparse attention method designed to isolate sparsity's effect on decoding-optimized architectures. We formalize the benefits of this asymmetry theoretically and validate it empirically, achieving end-to-end decoding speedups exceeding $2\times$ at long contexts across multiple model scales and benchmarks. Models trained from scratch with SAGA nearly match the quality of comparable GQA variants while delivering substantial efficiency gains. To facilitate adoption, we introduce an efficient fine-tuning method that converts pretrained models to the SAGA architecture at a small to negligible cost to quality, enabling practitioners to benefit from our approach without costly retraining.

Vision-Language Model (VLM) driving agents promise explainable end-to-end autonomy by first producing natural-language reasoning and then predicting trajectory planning. However, whether planning is **causally** driven by this reasoning remains a critical but unverified assumption. To investigate this, we build DriveMind, a large-scale driving Visual Question Answering corpus with plan-aligned Chain-of-Thought (CoT), automatically generated from nuPlan. Our data generation process converts sensors and annotations into structured inputs and, crucially, separates priors from to-be-reasoned signals, enabling clean information ablations. Using DriveMind, we train representative VLM agents with Supervised Fine-Tuning and Group Relative Policy Optimization and evaluate them with nuPlan’s metrics. Our results, unfortunately, indicate a consistent **causal disconnect** in reasoning-planning: removing ego/navigation priors causes large drops in planning scores, whereas removing CoT produces only minor changes. Attention analysis further shows that planning primarily focuses on priors rather than the CoT. Based on this evidence, we propose the Reasoning-Planning Decoupling Hypothesis, positing that the training-yielded reasoning is an ancillary byproduct rather than a causal mediator. To enable efficient diagnosis, we introduce a novel, training-free probe that measures an agent's reliance on priors by evaluating its planning robustness against minor input perturbations. In summary, we provide the community with a new dataset and a diagnostic tool to evaluate the **causal fidelity** of future models.

Bioassay activity prediction is often data-limited because drug-discovery datasets rely on time-consuming and expensive wet-lab experiments for data generation and evaluation. This challenge has inspired recent research into molecular foundation models (MFMs), which aim to encode general-purpose chemical knowledge into molecular representations that generalize well in data-constrained scenarios. This paper presents Monroe, a new MFM with several innovations over the existing state of the art: increased scale allowing pre-training on over 80 million molecules from the PM6 quantum chemistry dataset; improved graph representation of stereochemistry; improved training losses including conformer denoising and embedding decorrelation; improved multi-task learning; and the use of a prior-data-fitted model (TabPFN) for downstream in-context prediction. Our evaluations use a principled pairwise comparison framework that measures statistically significant performance differences. Across established Polaris benchmarks, Monroe matches or exceeds existing MFMs, while on activity cliff benchmarks, designed to assess utility for molecular discovery, it achieves significant improvements over prior methods. Finally, ablation and transfer experiments show that PFN-based downstream predictors also substantially improve two leading existing models, MiniMol and CheMeleon, yielding new state-of-the-art variants we call MiniMol_PFN and Chemeleon_PFN, suggesting that our downstream adaptation strategy generalizes beyond Monroe. Full source code is at https://anonymous.4open.science/r/monroe-0E0D, and will be openly released.

We revisit the problem of computing mean-field equilibria (MFEs) in discrete-time, monotone, finite-horizon mean-field games (MFGs). We show that, when the transition kernel is independent of the state-measure term and the reward function satisfies the usual weak monotonicity condition and is Lipschitz continuous, anchored proximal gradient descent methods can be used to compute a monotone MFE. We also establish last-iterate convergence results for these methods. Our approach relies on formulating the computation problem as an optimization problem over the space of occupation measures. Using this formulation, we show that the problem is equivalent to a class of constrained Lipschitz monotone inclusion problems. We then apply iterative methods for this monotone inclusion formulation to derive a tractable algorithm. The resulting algorithm achieves a convergence rate of $O(1/\sqrt{T})$ after $T$ iterations, without requiring any regularization. This rate holds even in the absence of a uniqueness assumption for the corresponding MFE.

We introduce a notion of monoculture robustness in Probably Approximately Correct (PAC) learning, as a way to mitigate the problem of *algorithmic monoculture* (Kleinberg & Raghavan, 2021): the tendency of models sharing the same components (e.g., training data) to fail on the same inputs. Specifically, we ask whether a learner with access to a single dataset can output $k$ individually accurate hypotheses whose joint failure probability is comparable to training on $k$ independent datasets. We say that such a learning procedure achieves *monoculture robustness*, and we quantify this by bounding the *conjunctive error* that all $k$ hypotheses misclassify points in an individual sense. We design methods for achieving this type of guarantee by drawing a surprising connection between replicability (Impagliazzo et al., 2022) and monoculture robustness. Specifically, we show that if the base learner is $\rho$-replicable, then running it independently $k$ times on the same sample yields individual monoculture error that shrinks exponentially with $k$, controlled by the single-run error of the base learner at the point and $\rho$. We complement these positive results with a lower bound: for individual monoculture robustness, we prove a worst-case lower bound showing that, for learners, driving the individual conjunctive error down to $\gamma$ can require a sample-size multiplier of $t = \Omega(\log(1/\gamma))$.

Existing inverse physics methods recover physical parameters from multi-view videos, where geometric constraints across views resolve scale and 3D structure. In monocular settings, however, such constraints are absent, leading to severe scale ambiguity, inaccurate geometry, and weak coupling between appearance optimization and physical simulation. We propose MonoPhysics, a framework for monocular inverse physics estimation of deformable objects using differentiable MPM simulation and 3D Gaussian Splatting, which jointly optimizes geometry, appearance, and physical parameters from a single camera view. We address these challenges through three visual-physical bridges: global scale alignment, physics-aware geometry refinement, and a differentiable position map, which together enable accurate optimization from image-space losses alone. We evaluate on Vid2Sim and our new dataset of elastic and plastic objects, showing that MonoPhysics outperforms existing baselines in monocular settings and achieves performance comparable to multi-view baselines using only a single camera.