NeurIPS 2026 Papers

Variational quantum algorithms offer a promising route to practical quantum advantage on near-term hardware, yet training quantum neural networks (QNNs) remains hampered by two compounding difficulties: the exponential vanishing of gradient variance known as the barren plateau, and the $\mathcal{O}(L \cdot 2^n)$ time–memory cost of differentiating through an $n$-qubit, $L$-layer circuit. We propose RLQ-Grad, a reinforcement-learning-based optimizer in which a classical policy $\pi_\phi$ (a spectrally-normalized PPO agent) learns to propose parameter updates directly, conditioned on the QNN's current parameters, loss, accuracy, and previous update. Because the surrogate gradient is emitted by a classical network rather than obtained by differentiating through the unitary $U(\theta)$, its variance is not constrained by the barren plateau concentration bound, and its per-step cost scales independent of the Hilbert-space dimension. We prove these two properties formally and verify them empirically on a hardware-efficient ansatz across four supervised benchmarks. RLQ-Grad preserves a near-flat gradient-variance curve where backpropagation, parameter-shift, and adjoint differentiation decay by 1–2 orders of magnitude, attains $128\times$–$1841\times$ wall-clock speedups and constant $\sim0.1$ MB memory at $n=12$ qubits, and improves top-1 validation accuracy by up to $+10\%$ over the strongest gradient-based baseline at every circuit scale tested.

Due to the gigapixel-scale nature of whole-slide images (WSIs), weakly supervised WSI analysis is commonly formulated as a multiple instance learning (MIL) problem, where patch-level features are aggregated into slide-level representations. However, diagnostic and prognostic evidence often arises from spatially coherent tumor microenvironment regions and their interactions, rather than isolated patches alone. Existing patch-level or static region-based methods usually overlook how tissue regions should be adaptively formed and subsequently evolved through microenvironment interactions across heterogeneous boundaries. In this paper, we propose Concept-Guided Tumor Microenvironment Evolution (TMEvolve), a reaction-diffusion-inspired framework that models WSIs as latent tumor microenvironment fields over discrete patch graphs. TMEvolve instantiates this view as a learnable graph-discretized evolution process over patch neighborhoods. It first forms adaptive soft tissue regions as coherent microenvironment units, then performs pseudo-time evolution through two complementary local dynamics: intra-region diffusion, which stabilizes latent states within coherent tissue compartments, and concept-guided boundary flux, which propagates visual feature signals and language-derived concept signals across heterogeneous region interfaces. The evolved microenvironment regions are finally aggregated for slide-level prediction. We evaluate TMEvolve on six datasets across three weakly supervised WSI tasks: survival prediction, gene expression prediction, and histological subtype classification. TMEvolve consistently improves over representative MIL methods, pathology foundation models, and concept-guided baselines. Ablation studies and visualizations further support the effectiveness and interpretability of TMEvolve, highlighting the value of dynamic region modeling and boundary interaction.

Large language models rely on a single tokenizer that is chosen at training time and fixed thereafter. Most tokenizers are trained on English-dominant corpora, making them under-serve morphologically rich and non-Latin-script languages, where they can produce fragmented representations, longer sequence lengths, and reduced information density during training. We propose *Mixture of Tokenizers* (MoTo), a modular tokenization framework that trains dedicated per-language BPE tokenizers and composes them into a unified superset vocabulary, where tokens shared across languages are deduplicated into a common ID space. Each language tokenizer maintains its own normalization policy, pre-tokenization rules, and vocabulary budget. Despite allocating significantly fewer entries to English, MoTo retains English performance while delivering consistent gains across 21 typologically diverse languages spanning six scripts, with improvements most pronounced on morphologically complex and non-Latin-script languages that are systematically underserved by English-dominant tokenizer design. Our results suggest that modular subword tokenization is a practical and extensible alternative to monolithic tokenization.

We propose Policy-Shift-Guided Spectral Alignment (PSA), a retraining-free method for merging RLVR post-trained language-model experts by guiding spectral subspace selection with token-level expert-base policy shifts. We first show that existing SFT-oriented merging techniques under-preserve the sparse, directional changes in next-token probabilities that distinguish RLVR experts from the pretrained base. To address this challenge, PSA scores calibration tokens by expert--base probability difference under the same prefix, and converts probability-shift-weighted input activations into column weights. These weights define a weighted SVD objective that prioritizes update directions active on high-shift tokens. After low-rank truncation, PSA applies cross-expert polar alignment to the truncated task-vector bases and restores each expert's per-layer Frobenius scale before aggregation. Experiments on Qwen2.5-7B and Qwen3-1.7B across three RLVR tasks show that PSA consistently outperforms strong merging baselines while preserving expert-level capabilities in a unified model.

Video models absorb rich priors over how the visual world moves, interacts, and responds to contact, making them promising substrates for robotic world modeling. The central challenge is how to communicate action to such models in a form aligned with the visual space in which they learned these interaction priors, yet still grounded in physical manipulation. We introduce Masked Visual Actions, a pixel-space control interface that expresses action as a partially revealed trajectory of an arbitrary entity in a video. Revealing robot motion makes the model act as a forward dynamics model that predicts the scene's response to low-level robot actions, while revealing desired object motion makes the same model recover robot behavior consistent with that outcome. Finetuned with only 15 hours of masked examples from real videos and simulation, a single checkpoint achieves strong visual fidelity and controllability across diverse scenes and multiple embodiments. In downstream manipulation settings, the model produces imagined rollouts whose outcomes correlate with real-world execution for policy evaluation, improves decision making by ranking candidate futures in model-based planning, and supports inverse modeling by synthesizing robot motion from desired object motion.

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.

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.

Multimodal evidence can improve topic discovery, but dense auxiliary signals can make topics harder to interpret when they replace readable descriptors. This creates an evidence-role problem: symbolic signals should define what topics mean to a reader, while dense aligned signals should help infer which topics a document expresses. We introduce M3-HNTM, a hyperspherical multimodal neural topic model that separates these roles through a shared document-level latent direction. M3-HNTM utilizes a shared von Mises-Fisher (vMF) posterior for document-level topic inference and vMF-mixture symbolic decoders that represent topics as concentration-aware semantic regions. Text Bag-of-Words and speech Bag-of-Acoustic-Words provide reconstructable symbolic evidence, while aligned image-text embeddings enter posterior inference as contextual evidence and help preserve semantic structure. The model applies to image-text, speech-text, and image-speech-text corpora while keeping topics readable through symbolic descriptors. Experiments on five datasets show that M3-HNTM improves the coherence-diversity quality score over strong text-only, hyperspherical, and multimodal baselines. On SpokenCOCO-Tri, the full tri-modal model outperforms both image-text and speech-text variants, indicating that visual and acoustic signals provide complementary evidence for interpretable topic discovery.

Scaling critic capacity is a promising direction for enhancing off-policy reinforcement learning (RL). However, larger critics are prone to overfitting and unstable in replay-buffer-based bootstrap training. This paper leverages Low-Rank Adaptation (LoRA) as a structural-sparsity regularizer for off-policy critics. Our approach freezes randomly initialized base matrices and solely optimizes low-rank adapters, thereby constraining critic updates to a low-dimensional subspace. Built on top of SimbaV2, we further develop a LoRA formulation, compatible with SimbaV2, that preserves its hyperspherical normalization geometry under frozen-backbone training. We evaluate our method with SAC and FastTD3 on DeepMind Control locomotion and IsaacLab robotics benchmarks. LoRA consistently achieves lower critic loss during training and stronger policy performance. Extensive experiments demonstrate that adaptive low-rank updates provide a simple, scalable, and effective structural regularization for critic learning in off-policy RL.

Algorithmic risk predictors are increasingly being used to inform resource allocation in healthcare and other high-stakes domains. Common in many such settings, the public decision maker delegates service provision to private organizations and compensates them according to each individual's predicted cost of service. We show that this common allocation mechanism can fail when organizations engage in \emph{favorable selection}, i.e., strategically choosing individuals whose actual costs are below the payment model predictions. Motivated by health insurance payments in the Medicare Advantage (MA) program, we provide a theoretical framework to study the interaction between a decision maker and a strategically selecting service provider. Our theoretical framework predicts two empirical patterns observed in Medicare Advantage that have become central concerns: enrollment in the private program expands, while government payments rise above the counterfactual cost of direct public provision. Guided by our theoretical framework, we then propose a reformed payment policy that is implementable under the government's data-access constraints. We prove that its equilibria eliminate overpayment while preserving profits for efficient organizations. We validate the framework in synthetic and semi-synthetic experiments that illustrate the advantages of our reformed policy, over the status quo.

Multi-objective reinforcement learning (MORL) aims at optimising several, often conflicting goals to improve the flexibility and reliability of RL in practical tasks. This is typically achieved by finding a set of diverse, non-dominated policies that form a Pareto front in the performance space. However, constructing such a policy set remains computationally demanding, as it requires finding not a single optimal policy, but a set of policies to cover a wide range of trade-offs among the objectives. We introduce LLE-MORL, an approach that traces policy manifolds by utilising the local relationship between the high-dimensional policy parameter space and the performance space. This structured representation enables an efficient search within contiguous solution domains via locally linear extrapolation, allowing for the rapid generation of high-quality solutions without extensive retraining. We also provide a theoretical analysis of the policy manifold structure in order to specify the applicability of the method. Experiments across diverse continuous control domains demonstrate that LLE-MORL consistently achieves higher Pareto front quality and efficiency than state-of-the-art approaches.

On-policy distillation (OPD) has emerged as an efficient post-training paradigm for large language models. However, existing studies largely attribute this advantage to denser and more stable supervision, while the parameter-level mechanisms underlying OPD's efficiency remain insufficiently understood. In this work, we argue that OPD's efficiency stems from a form of ``foresight'': it establishes a direct and stable path from the initial model to the final model early in training. This foresight manifests in two aspects. First, at the \textbf{Module-Allocation Level}, OPD identifies regions with low marginal utility and concentrates updates on modules that are more critical to reasoning. Second, at the \textbf{Update-Direction Level}, OPD exhibits stronger low-rank concentration, with its dominant subspace aligning closely with the final update subspace early in training. Motivated by this theory, we propose \textbf{EffOPD}, a plug-and-play acceleration method that speeds up OPD by searching for an effective step size and extrapolating along the current update direction. EffOPD requires no additional trainable modules or complex hyperparameter tuning, and achieves up to $3.5\times$ training acceleration while maintaining comparable final performance. Overall, our findings provide a parameter-dynamics perspective for understanding the efficiency of OPD and offer practical insights for designing more efficient post-training methods for large language models. Our code is available at: https://anonymous.4open.science/r/EffOPD-7C58.

Edge-cloud collaboration between large language models (LLMs) and small language models (SLMs) offers a promising way to leverage the problem-solving capability of LLMs while keeping private data on device. Existing methods typically have the LLM generate guidance from an initial user query, which the on-device SLM combines with local private data to produce the final response. However, the LLM's general guidance often does not align with the user's personalized needs, limiting the utilization of the LLM's capabilities. It has been observed that the on-device SLM exhibits metacognitive capabilities, which allow it to recognize its limitations and adjust its reasoning process. Motivated by this, we transform the on-device SLM into a metacognitive inquirer agent that can assess its internal state and actively decide *when*, *what*, and *how* to query the LLM for personalized guidance. Specifically, we propose Active Inquiry via Metacognitive Actions (AIMA). AIMA learns an on-device policy that jointly optimizes the selection of high-level metacognitive actions and the action-conditioned query refinement. We further introduce a privacy-constrained rewriting mechanism that detects and eliminates sensitive information leakage in the refined query. Extensive experiments and theoretical analysis demonstrate that our method outperforms existing methods.

Reinforcement learning from verifiable rewards (RLVR) suffers from sparse outcome signals, creating severe exploration bottlenecks on complex reasoning tasks. Recent on-policy self-distillation methods attempt to address this by utilizing language feedback to generate dense, token-level supervision. However, these approaches rely on a fixed, passive teacher to interpret the feedback. As the student policy improves, the teacher's zero-shot assessment capabilities plateau, ultimately halting further learning. To overcome this, we propose Variational Policy Distillation (VPD), a framework that formalizes learning from language feedback as a Variational Expectation-Maximization (EM) problem. VPD co-evolves both policies: in the E-step, the teacher is actively refined on trajectory outcomes via an adaptive trust-region update, translating textual feedback into a dynamically improved target token distribution. In the M-step, the student internalizes this dense distributional guidance on its own on-policy rollouts. By continuously improving the teacher's ability to extract actionable signals from textual critique, VPD overcomes the limitations of passive distillation. Evaluated across diverse sources of diagnostic feedback on scientific reasoning and code generation tasks, VPD consistently outperforms both standard RLVR and existing self-distillation baselines. Finally, by stress-testing our framework on rigid mathematical reasoning and cold-start regimes, we illuminate the fundamental bounds of feedback-driven self-distillation compared to pure environment-driven RL.

In many machine learning applications, human and LLM evaluators use assessments of relevant criteria to create an overall evaluation for an item or individual. In applications like admissions, committees assess candidates on attributes such as test scores, GPA, and research experience to evaluate their overall fit for the program. In medical care, clinicians use patient reports of symptoms to consider preliminary diagnoses and assess risks. Each case involves mapping measurable criteria to an overall evaluation—a process that reflects the evaluator's underlying preferences. We focus on the fundamental issue of learning these preferences. Many applications of this problem make specific modeling assumptions on evaluator preferences that may be substantially violated in the real world. We make the minimal assumption that the preference function is coordinate-wise non-decreasing, which is reasonable in a large number of evaluation settings. We theoretically characterize the severity of model mismatch for many common assumptions and show that it can lead to catastrophic effects for learning evaluator preferences and other important downstream tasks. We then present an algorithm for learning evaluators' preferences that is robust to model mismatch. We prove theoretically that our algorithm can learn any monotonic preference function without sacrificing performance when the linearity assumption holds. Evaluations of our algorithm with synthetic simulations and real-world data confirm its ability to learn preferences robustly and illustrate key aspects of LLM and human preferences.

Offline reinforcement learning aims to learn a policy solely from fixed datasets, which often contain multimodal action distributions. Flow policies can naturally represent such multimodal behaviors, but learning an efficient one-step flow policy remains challenging: standard value guidance often leads to mode collapse or exploits overestimation bias in out-of-distribution regions. To address this, we introduce One-step Flow policy via Optimal Transport (OptiFlow), a framework for one-step flow policy learning as a structured sample-allocation problem. OptiFlow jointly trains a value-aware reference flow policy and an efficient one-step policy, coupling their action samples through state-wise entropic optimal transport. For each state, critic-estimated values define the priority of distillation target actions, while the action-distance cost ensures geometrically compatible pairings. By avoiding direct critic maximization, our transport-guided approach enables in-distribution exploitation by anchoring the one-step policy to high-value, dataset-supported modes without the risk of out-of-distribution divergence. Experimental results demonstrate that OptiFlow effectively captures optimal multimodal behaviors and achieves strong performance across diverse offline RL benchmarks.

We introduce the Lattice Deduction Transformer (LDT), a recurrent transformer that approximates logically sound deduction by projecting its latent state through a lattice between forward passes. We train on-policy in a process that mirrors deduction in a search-based constraint solver and supervise training via a domain-agnostic, abstract-interpretation-based approximation of the set of solution candidates. An $800$K-parameter LDT achieves $100\%$ accuracy on Sudoku-Extreme and Snowflake Sudoku, at a fraction of the training cost of prior small recurrent reasoners, while remaining empirically sound: the model returns a correct answer or abstains. A $1.8$M-parameter variant reaches $99.9\%$ accuracy on Maze-Hard. Frontier LLMs score $0\%$ on all three benchmarks.

Behavior policies are often formulated as continuous generative models, whose iterative denoising processes are expressive but difficult to interpret and prone to producing implausible actions. We propose the Large Discrete Policy (LDiP), a fully discrete behavior modeling framework that selects actions from a large vocabulary of physically plausible candidates. Rather than perturbing actions, LDiP improves expressivity through stochastic iterative scoring: it progressively re-scores and prunes candidates with score-space stochasticity, enabling fine-grained ranking and exploration among plausible actions while preserving an explicit decision process. Across end-to-end planning, closed-loop driving, robotic manipulation, and vision-language-action settings, LDiP consistently outperforms strong discrete and continuous baselines in autonomous driving, and exceeds or matches continuous generative policies in robotic manipulation. These results show that discrete policies, when equipped with effective scoring mechanisms, offer an expressive, plausible, and interpretable alternative for behavior modeling.

Continuous diffusion has served as a foundation for high-fidelity, controllable, and few-step generation across continuous data modalities such as images, videos, and molecular structures. However, in language modeling, prior continuous diffusion language models (DLMs) lag behind discrete counterparts. Existing categorical and simplex-based approaches operate over extremely large and sparse language spaces, while prior embedding-space approaches avoid this sparsity but lack a well-selected design space. In this work, we close this gap with **LangFlow** by connecting embedding-space DLMs to Flow Matching, alongside three key innovations: (1) we derive a novel ODE-based NLL bound for principled evaluation of continuous flow-based language models; (2) we propose an information-uniform principle for setting the noise schedule, which motivates a learnable noise scheduler based on a Gumbel distribution; and (3) we revise prior training protocols by incorporating self-conditioning, which improves both likelihood and sample quality for embedding-space DLMs and behaves differently from its use in discrete diffusion. Putting everything together, LangFlow is competitive with top discrete DLMs on both perplexity (PPL) and generative perplexity (Gen. PPL), reaching a PPL of **30.0** on LM1B and **24.6** on OpenWebText. It also exceeds autoregressive baselines in zero-shot transfer on 4 out of 7 benchmarks. As the first continuous DLM shown to rival discrete diffusion in both generative quality and perplexity, LangFlow provides clear evidence that continuous diffusion is a promising paradigm for language modeling. Code will be released upon acceptance.