NeurIPS 2026 Papers

Money laundering detection on financial transaction graphs is critical but challenging. Laundering activities often conceal illicit fund flows within dense legitimate transaction neighborhoods and disperse suspicious behaviors over extended time spans. These patterns cause weak illicit signals to be spatially diluted and temporally forgotten, limiting the effectiveness of standard graph learning methods in AML scenarios. In this paper, we propose a spatio-temporal dual denoising framework for money laundering detection on evolving graphs, named EvoDen. For spatial denoising, instead of relying on passive neighborhood aggregation, we design a risk-potential guided walk mechanism to extract denoised and suspicion-biased transaction sequences, enabling the model to isolate anomalous fund flows from noisy local neighborhoods. For temporal denoising, we propose a continual Transformer-based sequence learning method driven by a reconstruction objective, which learns denoised sequence representations while enabling latent-space replay of historical knowledge to mitigate representation drift. We conduct experiments on three transaction datasets, and the results show that EvoDen outperforms state-of-the-art baselines in accurately identifying concealed money laundering entities.

Reconstructing the motion of objects from videos is a key component for embodied AI and robot manipulation. While diverse approaches to object pose tracking have been studied, they rely heavily on strong external priors, such as depth data or 3D templates, and remain highly vulnerable to severe occlusions by hand grasps despite the use of explicit masks. In this work, we present ComPose, a 6DoF object tracking framework designed for hand-aware object pose estimation from RGB video. Rather than treating the hand purely as an occluder, our method harmonizes hand motions as a complementary cue for object tracking. In detail, we recover a variety of object motions over time by combining object- and hand-derived cues from foundation models within a unified tracking pipeline. Here, ComPose adaptively selects informative hand joints, blends object- and hand-based rotation cues, and refines translation from the visible geometric evidence using a learned correction. We further enforce the temporal consistency over both rotation and translation, yielding stable 3D object trajectories over time without any external smoothing. Extensive experiments show that our method is accurate, efficient, and robust under severe hand occlusion and geometric ambiguity. In addition, the resulting trajectories can also effectively transfer to downstream robot manipulation by enabling robots to reconstruct human actions from online videos.

The Hessian of the energy with respect to the nuclear positions is indispensable in atomistic modelling. However, constructing this matrix requires $O(N)$ Hessian vector products, traditionally limiting high-accuracy Hessians to small systems. Machine learning interatomic potentials (MLIPs) have accelerated atomistic modelling by providing highly accurate energies and forces at $O(N)$ cost, yet the resulting $O(N^2)$ cost of Hessians remains a practical bottleneck for large systems. Based on the insight that we can derive the sparsity pattern for an MLIP's Hessians in closed form, we show in this paper how to use techniques from sparse automatic differentiation to reduce the cost of a local MLIP's Hessians to a system-size-independent number of Hessian-vector products, yielding overall $O(N)$ total cost without any approximations. We benchmark our approach on a variety of systems ranging from alkane chains to water clusters to A$\beta$40 conformers. Depending on the MLIP configuration, we achieve the linear scaling regime already on relatively small systems, resulting in large runtime reductions between $2\times-15\times$ for these systems. This opens up the possibility of scaling high-accuracy MLIP Hessians to very large systems, such as proteins that were previously inaccessible.

Diffusion models achieve state-of-the-art image synthesis, with their generative trajectories fundamentally exhibit a spectral bias, resolving low-frequency global structures early and high-frequency fine details later. Conventional stochastic differential equation (SDE) solvers fail to account for this dynamic, naively injecting uniform white noise throughout the entire process and misusing the finite energy budget. In this work, we establish a mathematical framework that reconsiders SDE inference as a targeted, frequency-decoupled energy transfer. Leveraging this framework, we introduce Colored Noise Sampling (CNS), a novel, training-free stochastic solver. Rather than injecting uniform white noise, CNS utilizes a dynamic, timestep- and frequency-dependent schedule that more-efficiently allocates injected energy toward structurally unresolved frequency bands. By actively exploiting the model's inherent spectral bias, CNS systematically steers the generated distribution toward the true data manifold. Extensive experiments demonstrate that CNS significantly outperforms standard ODE and SDE baselines as a strictly plug-and-play, inference-time sampler substitution across diverse architectures (SiT, JiT, FLUX). Compared to standard sampling on ImageNet-256, CNS achieves substantial unguided FID reductions, improving from 8.26 to 6.27 on SiT-XL/2, 32.39 to 26.69 on JiT-B/16, and 11.88 to 8.31 on JiT-H/16, while yielding consistent relative FID improvements with Classifier-Free Guidance.

Text-to-image (T2I) models have advanced considerably in generating high-quality images from textual descriptions. However, their ability to associate colors with concepts remains largely constrained to explicit color names or codes, while their capacity to handle implicit concepts, such as emotions and visual states, remains underexplored. To address this gap, we introduce ColorConceptBench, an expert-annotated benchmark that systematically evaluates color-concept associations through probabilistic color distributions. ColorConceptBench moves beyond explicit color specifications by examining how models interpret 1,281 implicit color concepts, grounded in 6,584 human annotations. Our evaluation of nine leading T2I models reveals that performance varies substantially across semantic categories, and models exhibit a significant lack of sensitivity to abstract semantics. These limitations persist even when applying classifier-free guidance scaling at inference time, suggesting that achieving human-like color understanding demands a shift in how models learn and represent implicit semantic meaning.

Modeling biomolecular conformation and dynamics is critical for elucidating biological functions, motivating generative surrogates for molecular dynamics (MD) simulations to address two complementary tasks: time-independent conformational sampling and time-dependent trajectory generation. Fundamentally, both tasks require matching the distribution of the generated collections to the MD reference, rather than reproducing individual configurations. Yet existing deep-learning approaches predominantly optimize a per-sample regression loss (score- or flow-matching), whose gradient is computed in isolation per sample and therefore carries no direct signal about the cross-sample distributional properties that define both tasks, leading to biased ensembles and long-horizon temporal drift. We address this with Collective Supervision, a training paradigm that aligns the empirical measures of the generated and reference collections via a maximum mean discrepancy on SE(3)-invariant physical observables; a single loss handles both tasks within a unified formulation. To mitigate the exposure bias inherent in autoregressive trajectory rollout, we further introduce Collective Rolling Forcing, which couples Collective Supervision with autoregressive self-rollout during training. Our framework, CoDyna, generalizes across proteins, protein--ligand and protein--protein complexes; on four all-atom MD benchmarks (ATLAS, MISATO, DynaRepo, and DynaBench), a unified model surpasses task-specialized baselines on most thermodynamic and kinetic fidelity metrics and remains structurally stable over 2k-frame rollouts.

Generative ranking models (GRMs) have emerged as a scalable alternative to traditional recommendation pipelines by unifying items and user actions into a single token sequence and formulating recommendation as next-token prediction. Despite their promise, we identify a geometric failure mode: attention interactions with lowcardinality action tokens can induce dimensional collapse in high-rank item representations, as suggested by interaction-collapse theory. To pinpoint the origin of collapse, we view attention mechanism over item–action interleaving sequences as a mixture of directional interaction channels between token types, and find that collapse concentrates in the action-attending-item channel, where low-rank action gating drags the item value stream toward a low-dimensional subspace. To address this, we theoretically show that nonlinearity mitigates collapse, and propose Selective VAlue Nonlinearity (SVAN), a simple yet effective approach that applies nonlinear activation to the value component in the collapsed channel, protecting item representations while preserving the remaining attention geometry. SVAN consistently improves the ranking quality over strong baselines. Further analyses confirm that SVAN alleviates dimensional collapse, yielding up to a 12.58% effective-rank gain, and enhances representation discriminability.

Reasoning capabilities are critical for advancing Large Language Models, yet current approaches either require massive computational budgets or struggle to effectively distill reasoning to smaller models. Standard distillation methods rely on outcome-based rewards, failing to distinguish between sound reasoning and lucky guesses. We propose **Collaborative Reasoning Distillation (CRD)**, a framework that enhances reasoning in compact models through three innovations: (1) interactive cross-feedback where teachers iteratively critique each other's reasoning, (2) fine-grained step-wise quality assessment capturing logical validity independent of final answers, and (3) coherence-aware step stitching that synthesizes complementary strengths. Students are trained via Reasoning Quality Optimization (RQO) with budget constraints. Our model, CRD-4B, achieves 97.3\% on MATH-500 and 70.3\% on AIME'25, surpassing baselines while using only 50K training examples, up to 12 times smaller than the datasets of comparable models.

Cold-start drug-drug interaction (DDI) prediction tests whether models can identify clinically significant interactions for drugs without training-time interaction history. Existing benchmarks mostly report aggregate edge-prediction scores, leaving a key evaluation question unanswered: when models receive molecular, textual, or knowledge-graph (KG) evidence, do they actually use the evidence that pharmacologically supports the interaction? We introduce ColdDDI, a reconstructible evaluation benchmark built from the latest DrugBank 5.1.13, with 1,900 approved small-molecule drugs and 565,731 positive DDI pairs. ColdDDI evaluates three levels of drug novelty, namely test pairs whose two drugs were both seen during training, pairs with one unseen drug, and pairs with two unseen drugs. It also annotates each interaction by whether it changes drug exposure or drug effect, and by whether the biomedical knowledge graph contains shared enzymes, transporters, or targets that can plausibly mediate the interaction. These annotations allow ColdDDI to separate two factors that aggregate metrics conflate, namely whether mechanistic evidence is available, and whether a model prediction depends on that evidence. We evaluate eight conventional DDI methods and 13 LLMs; for open-weight LLMs, we test five prompt patterns and use masking, drug replacement, and channel-sensitivity metrics to probe knowledge utilization. ColdDDI exposes that, in the hardest split where both drugs are unseen, the main performance divide is mediator availability. A fine-tuned 1B LLM recovers 89-93% of interactions with a shared enzyme, transporter, or target, but only 40-62% without such a mediator. More importantly, KG-provided evidence is not always used; several KG-augmented baselines change little when the shared mediator is masked or disrupted, whereas fine-tuned LLMs respond strongly to this intervention. Thus, ColdDDI evaluates knowledge utilization rather than knowledge access alone, showing where cold-start DDI models rely on mechanistic evidence and where they fail despite receiving it. We release derivative annotations, splits, prompts, diagnostics, evaluation code, and a DrugBank reconstruction pipeline.

Stellarators are fusion energy devices that confine hot plasma using a carefully shaped magnetic field, and they are one of the most promising candidates in the race towards commercial fusion. Among the many systems that make up a stellarator, the electromagnetic coils generate the confining magnetic field. Their design is the key factor in deciding whether a stellarator can be practically engineered and cost‑effectively realized. Coilset design is an intrinsically complex problem: it does not admit either a closed or a unique solution, making it suitable for optimization. Coilset optimization is therefore at the heart of stellarator design: a coilset must accurately reproduce a target magnetic field while satisfying stringent engineering constraints on coil spacing, curvature, and length. Although recent datasets have accelerated progress on stellarator equilibria optimization, data-driven coilset design is limited by the lack of standardized datasets that pair target plasma configurations with engineering-aware coilsets. Here, we release a dataset (https://huggingface.co/datasets/proxima-fusion/coilstellaration) of 177,000 optimized stellarator coilsets targeting plasma configurations sampled from the publicly available ConStellaration dataset. For each configuration, we optimized coilsets to reproduce the magnetic field while satisfying a diverse set of engineering constraints. Alongside the dataset, we introduce a benchmark for conditional coilset generation: given a target plasma boundary and a set of engineering requirements, a model should produce a coilset that satisfies the engineering constraints while reproducing the target field. We provide reference code, evaluation scripts and baselines models trained on a subset of the provided data (https://github.com/proximafusion/coilstellaration). Beyond enabling better optimization initializations and one-shot coil design, our dataset provides a testbed for data-driven constrained optimization and for studying which plasma geometry features predict simpler, more engineerable coils. By releasing data, and code for benchmarks and baselines, we aim to lower the barrier for machine learning and optimization researchers to engage with stellarator coilset design and accelerate progress toward engineerable and cost-effective stellarators power plants.

We introduce Phase-Interference Decision Trees (PIDT), a differentiable routing model for tabular prediction in which each node propagates a bounded complex state rather than only a scalar routing probability. The main model uses two-state norm-preserving branch maps: a gate controls how much amplitude is sent to the left and right children, while learned unitary maps rotate the latent state before subsequent splits. This formulation contains ordinary soft decision trees as the phase-free scalar case, and two-state routing creates explicit score-level cross terms among latent-state trajectories. We give a self-contained PIDT definition with exact mass conservation, prove scalar phase cancellation, establish a scoped containment relation with soft trees, derive an algebraic interference decomposition, give a companion construction for shared two-state parity routing, and derive a fixed-architecture empirical Rademacher upper bound for bounded two-state PIDT scores. We evaluate PIDT on a ten-dataset OpenML suite of low-class-count tabular tasks under matched differentiable-tree controls. Across ten seeds per dataset, the main summaries track accuracy as context and report small descriptive NLL and Brier deltas relative to the scalar PIDT-1S, phase-frozen PFB, and SDT controls. The empirical study is framed as a mechanism-level study for compact differentiable trees, not as a broad tabular-performance claim.

Learning to Defer (L2D) enables a model to predict autonomously or defer to an expert, but prior work largely assumes flat label spaces. We study the first L2D setting with hierarchical multi-label decisions, motivated by medical-imaging workflows in which findings are organised by clinical taxonomies. In this setting, deferral is a delegation action rather than a label assignment, so treating it as an independent per-label decision can produce \emph{deferral incoherence}, including taxonomic contradictions, delegation violations, and deferrals of labels already implied by the model's own assertions. We formalise coherent hierarchical deferral under a Selective-Exclusion handoff contract, characterise the Bayes-optimal coherent deferral rule, and show that even nodewise Bayes L2D can be action-incoherent. We then propose two remedies: exact coherent projection, a dynamic-programming decoder over the coherent action set, and Taxonomic Belief Propagation (TBP) with Recursive Policy Optimisation (RPO), a contract-aware joint action model trained through the same recursion used at inference. Across real-reader and controlled-expert medical-imaging benchmarks, naïve binary-relevance L2D exhibits non-trivial incoherence. Projection removes it exactly, and fast TBP+RPO drives incoherence near zero while retaining strong utility.

Robots operating in semantic environments often need to satisfy linear temporal logic (LTL) tasks before the semantic map is fully known. Many practical semantic-LTL planners maintain semantic beliefs but execute a single task policy induced by a point semantic interpretation, such as a maximum-a-posteriori (MAP) semantic map, possibly supported by risk checks or active perception. This premature commitment can be brittle when distant semantic observations are weak or correlated. We propose Coherence-Aware Transition-Intent Fusion, an online planner that preserves automaton-relevant semantic uncertainty using a finite top-$K$ intent abstraction. Given a conservative current automaton estimate, the planner propagates plausible semantic assignments through the automaton, converts feasible successor transitions into weighted reach-avoid intents, and fuses their risk-gated Dijkstra progress scores. When competing intents create incoherent motion, a KL-regularized calibration step shifts weight toward intents consistent with recent physical progress. Experiments on random-obstacle and room-like semantic maps show improved satisfaction over single-intent and raw-fusion variants, and over a TOAPP* MAP-plus-active-perception baseline under the same static-view sensor. Ablations attribute the gain primarily to intent-level calibration.

Self-improvement is a critical capability for large language models and other intelligent systems, enabling them to refine their behavior and internal consistency without external supervision. Despite its importance, prior approaches largely rely on empirical heuristics and lack formal guarantees. In this paper, we propose a principled framework for self-improvement based on the concept of coherence, which requires that a model's outputs remain consistent under task-preserving transformations of the input. We formalize this concept using projection-based mechanisms that update a baseline model to be coherent while remaining as close as possible to its original behavior. We provide rigorous theoretical guarantees that these mechanisms achieve monotonic improvement, measured by a reduction in expected Bregman divergence. Our analysis is comprehensive, covering both \emph{direct} and \emph{two-step} projection methods, and robustly extends these guarantees to non-realizable settings, empirical (finite-sample) distributions, and relaxed coherence constraints.

Recent studies suggest that large language models (LLMs) exhibit a range of cognitive biases familiar from human cognition. This paper argues that $\textbf{cognitive bias benchmarks should incorporate insights from ecological rationality}$, a leading paradigm in the study of cognitive bias. Three strategies for resisting some existing allegations of cognitive bias are extracted from the ecological rationality paradigm. Each strategy is used to generate a concrete recommendation for improving cognitive bias benchmarks.

The reasoning capabilities of large language models are reported to drop sharply when they are forced to think in heavily regulated target languages such as Chinese — a phenomenon the literature attributes to data imbalance, multilingual transfer failures, or, more recently, RL-induced cross-lingual collapse. We propose and test an alternative mechanistic account: that the gap reflects RL-induced selection between conditional policies sharing the same parameters, rather than a loss of underlying capability. We construct a model organism for this account. Two policies — identified solely by the language of an unsupervised chain of thought — are installed via SFT on disjoint splits of ARC-Challenge, with one policy trained to answer and the other to refuse on each split. Reinforcement learning with a final-answer reward, restricted to one split, drives the language of reasoning to collapse onto the rewarded policy across both splits, producing a 67% → 10% accuracy collapse on the held-out split despite no reward signal ever observing it. General capability is unaffected: MMLU accuracy is 71.2% before and after RL. A depth-wise activation steering intervention then recovers held-out accuracy from 0% to 85% on the worst-case slice (Chinese-CoT completions) while preserving Chinese as the surface chain-of-thought language and leaving the rewarded policy intact (83% vs. 94% unsteered). The capability was never lost; it was gated. To the extent deployed regulated-language models contain analogous structure, surface evaluations of such models will systematically understate capability hidden behind learned policy gates.

Educational LLM systems generate assessment questions on demand and depend on the assumption that a model can be controlled to a specified cognitive level. We test the assumption. CogBench is a benchmark for cognitive-level control in LLM question generation, grounded in the Revised Bloom's Taxonomy. Its central design choice is a two-mode protocol that separates cognition from imitation: in standard mode the model is asked to generate at level L_t; in adversarial mode it must do so while restricted to verbs from a different level L_v, demonstrating the requested level structurally rather than lexically. CogBench spans 8 subjects, 6 Bloom levels, and 120 CC-BY OpenStax passages, with ~17,000 graded generations across 13 models (six frontier closed APIs and seven open-source local models), each scored by a deliberately dual evaluator: a 28-rule constraint checker, and the Cognitive Complexity Score (CCS), a fine-tuned BERT classifier at 82.0% exact accuracy that outperforms a four-model LLM-as-judge panel by 7.8 points. We find that (1) adversarial vocabulary collapses strict adherence by 24-56 pp across the 12 models above floor, with the strongest standard performer suffering the largest collapse; (2) Remember-level adherence under adversarial vocabulary is essentially 0% in all 13 models, suggesting Remember lives almost entirely in its surface verbs; (3) the two evaluators rank models differently, including on the leader, a divergence we argue benchmarks should report rather than hide; and (4) the most adversarially robust models on CCS are not frontier flagships but gpt-4o-mini (46.8%) and llama3.1-8b (45.6%). What current LLMs offer educational systems looks like cognitive control and is largely verb-level imitation that resembles it. We release the dataset (CC-BY 4.0; Croissant 1.0 with Responsible-AI fields), the evaluation harness, and a 13-model leaderboard at https://huggingface.co/spaces/cogbench-anonymous/cogbench-leaderboard.

As LLM agents advance beyond short-horizon tasks, evaluating their ability to perform long-horizon strategic decision-making in realistic multi-agent settings remains a key challenge. Existing agent benchmarks typically focus on isolated task completion or interactions with rule-based or fixed-policy counterparts, limiting their ability to capture strategic adaptation and emergent behaviors arising from sustained multi-agent interactions. We introduce \textbf{CoffeeBench}, a benchmark for evaluating LLM agents in a dynamic multi-agent economic environment consisting of farmers, roasters, and retailers forming a multi-stage supply chain. The environment consists of autonomous firms interacting over a multi-month horizon with evolving supply, demand, and pricing, creating sustained competition and supply-chain dynamics. In each evaluation, the evaluated model controls one firm and must make sequential decisions on procurement, production, pricing, and negotiation to maximize cumulative net income. CoffeeBench enables the study of emergent behaviors arising from repeated strategic interactions, including negotiation dynamics, pricing discipline, and coordination failures. We evaluate several frontier and pareto-frontier LLMs on CoffeeBench to analyze their economic performance and strategic behavior. Most evaluated models achieve positive net income, with GPT-5.5 achieving the highest mean net income. In contrast, Claude~Haiku~4.5 frequently yields negative net income, exhibiting an idle-drift failure mode in which agents collapse into inactivity despite coherent plans. We further find that stronger models proactively negotiate with counterparties through frequent messaging, whereas weaker models trade reactively with limited communication. CoffeeBench provides a controllable testbed for studying strategic interaction, coordination, and long-horizon behavior in multi-agent economies.

Vision-Language-Action (VLA) models have driven significant progress in robotic manipulation, yet they fundamentally struggle with the ``vision-override'' phenomenon. Driven by the severe modality imbalance between dense visual streams and sparse linguistic instructions, VLAs frequently fall prey to causal confusion. Instead of treating language as the primary causal driver, the policy entirely bypasses the original instruction by overfitting to spurious visual confounders, such as prominent objects or familiar layouts. To systematically alleviate this bias, we formalize the process of action generation as a Dual-path Deconfounding Graph (DDG) and propose CofactVLA, a novel causal intervention framework. By dynamically constructing a language-masked counterfactual branch within a single forward pass, CofactVLA isolates and neutralizes visual confounders through two synergistic mechanisms. First, Action-Level Orthogonal Projection Guidance (OPG) geometrically projects the factual velocity field away from the counterfactual visual bias during continuous flow matching, extracting the pure semantic intent. Second, Feature-Level Counterfactual Covariance Reduction (CCR) mathematically deconfounds latent representations by penalizing the positive eigenspace of the covariance difference, explicitly suppressing dominant visual shortcuts while preserving the causal language intent. Extensive experiments demonstrate that CofactVLA establishes a new state-of-the-art across diverse simulation benchmarks. Beyond simulation, real-world robot experiments demonstrate the causal efficacy of our method in bridging the generalization gap, yielding a 52.3\% absolute success rate gain under out-of-distribution scenarios.