NeurIPS 2026 论文列表

Tissue graph counterfactuals ask how a cell's expression would change under altered spatial contexts. Such queries are central to predicting cell behavior in tissues, but lack a unified definition, with existing methods targeting specific intervention types or treating cells as i.i.d. In this work, we first formalize tissue graph counterfactuals as a class of spatial interventions that either rewire connections between cells (edge perturbation) or modify the expression of their neighbors (node perturbation). We then introduce Cellina, a modeling framework that uses supervised disentanglement to decompose a cell's intrinsic state from its spatial context, using the latter as a conditioning input for counterfactual predictions. Across benchmarks spanning 2.5 million spatially-resolved cells in colorectal cancer and mouse brain, Cellina outperforms spatially-informed and non-spatial competitors in counterfactual predictions, disentanglement, and scalability. Additionally, we show that Cellina reveals biologically distinct cancer subdomains in an unsupervised manner and enables targeted neighbor perturbation simulations.

Reinforcement learning for long-horizon agents relies on \emph{purely retrospective} training signals: credit is assigned only after observing environmental consequences, leaving the agent's belief at action time invisible to the gradient. We introduce \textbf{Prospective Hindsight (PH)}, a self-calibrating training principle that augments any retrospective base method with a signal derived from the gap between the agent's \emph{prospective prediction} (before feedback) and the \emph{retrospective evaluation} (after feedback). This per-rollout \emph{surprise} identifies samples where the agent's self-model is most inaccurate and amplifies their gradient contribution through a stop-gradient surprise-weighted advantage. Since the prospective predictor shares parameters with the policy, the two co-evolve, progressively shifting focus to the agent's remaining blind spots. We connect this principle to a privileged-information gap and show that minimizing the surprise residual provides a descent pathway on the agent's miscalibration rate; calibration thus emerges as a byproduct of optimization rather than from an added objective. On single-turn verifiable tasks and a multi-turn personal-agent task (under GRPO, on-policy distillation, and their combination), PH improves both task performance and calibration, with consistent gains across model scales. Notably, the dominant miscalibration mode shifts structurally between regimes, overconfident failures in single-turn, underconfident successes in multi-turn, yet the same training principle addresses both successfully.

Supervised fine-tuning (SFT) is computationally efficient and broadly applicable, but often shows weaker generalization than reinforcement learning (RL). A key limitation is its off-policy objective: SFT fits fixed demonstrations token by token, including targets that may be poorly aligned with the model's pretrained distribution. Recent token-reweighted SFT methods address this issue by assigning larger training weights to tokens that better align with the model's predictive distribution, using statistics such as target-token probability or entropy. However, computing these statistics from the online model being fine-tuned makes token weights trajectory-dependent, as the model's distribution rapidly departs from the pretrained model and induces self-reinforcing reweighting dynamics. We propose PriFT, Prior-support guided Fine-Tuning, which derives token weights from a frozen pretrained reference to obtain a stable reweighting signal unaffected by online fine-tuning dynamics. This signal estimates prior support: the extent to which each target token is supported by the pretrained model before task-specific adaptation. Across multiple existing weighting and selection rules, replacing online statistics with pretrained statistics consistently improves performance. We introduce two instantiations: PriFT-prob, which uses pretrained target-token probability, and PriFT-mass, which selects tokens by relative support under the pretrained distribution. Extensive experiments on mathematical reasoning, code generation, and medical question answering show that PriFT achieves state-of-the-art SFT results and provides a better initialization for subsequent RL training.

Time-series classifiers deployed in risk-sensitive domains such as healthcare, wearable sensing, and industrial monitoring must be accurate, interpretable, and capable of abstaining when evidence is weak. No existing method delivers all three, and the obstacle is structural, rather than logistical. Meaningful temporal patterns cannot be defined without knowing segment boundaries, yet meaningful boundaries cannot be placed without knowing which patterns to expect. Existing approaches break this circularity through fixed windows or expert-annotated vocabularies, sacrificing at least one of the three properties. We introduce ConceptTime, which closes the loop through a single self-supervised signal. A frozen probabilistic forecaster predicts a distribution over the next observation at every timestep of the sequence. We call the mismatch between its prediction and the realized signal, the predictive surprise. This signal both locates segment boundaries and characterizes each resulting segment through the forecaster's own predictive statistics. Segments are thus grounded by \emph{how} they behaved relative to expectation, not by what they look like. These summaries cluster into a vocabulary of dynamical regimes that we call concepts. The vocabulary distinguishes calm-after-spike from calm-after-calm, and unifies visually distinct segments that violate expectation in the same way. A lightweight head classifies from the concept sequence, and the distance to the nearest concept yields per-input reliability for free. Across seventeen UEA, human-activity, biomedical, and fault-diagnosis benchmarks, ConceptTime matches state-of-the-art black-box accuracy, beats every interpretable baseline, and retains near 98% accuracy on Epilepsy with 1% of labels. It equals or exceeds softmax, prototype-distance, and SHAP/TimeX/TimeX++ on OOD detection and deletion-faithfulness, without a single annotation, language-model call, or domain expert.

Recent analyses question whether reinforcement learning (RL) is responsible for strong reasoning in large language models (LLMs). At the same time, distillation and inference-time sampling, including power sampling, have emerged as effective ways to improve LLM performance. However, the relationship among RL, distillation, and sampling remains unclear. In this study, we focus on the power distribution, the target distribution of power sampling, and show that the power distribution bridges sampling, self-reward KL-regularized RL, and self-distillation. From the sampling perspective, we show that inexpensive local approximations cannot reproduce sequence-level power without information about possible suffixes. From the RL perspective, the power distribution is the closed-form optimizer of KL-regularized RL when the model's sequence-level log-probabilities are used as the reward. This identification leads to \emph{power self-distillation}, an offline distillation surrogate that shares the same target distribution and amortizes the cost of power sampling into supervised training on teacher samples. We further show that power self-distillation can achieve self-reward sharpening, while improvement in a downstream true reward is governed by the covariance between true reward and self-reward under the power distribution. Experiments on reasoning tasks support our analysis: power sampling raises self-reward, true-reward gains depend on alignment with self-reward, and power self-distillation can match or exceed the performance of power sampling at much lower inference cost.

Solubility depends on intermolecular interactions between solutes and solvents and is central to drug discovery, chemical and materials process engineering. Its prediction requires out-of-distribution (OOD) generalization to unseen solutes, solvents, and solvent mixtures, where supervised methods suffer from data scarcity, and existing self-supervised pretraining methods do not explicitly learn chemically meaningful relations. Learning chemically meaningful relational information without labels can alleviate data scarcity and improve OOD generalizations, but remains challenging. We introduce Prior Relational Information for Self-supervised Modeling (PRISM) and apply it to solubility OOD generalizations. PRISM is a label-free pretraining framework that converts expert-defined chemical priors into relational teachers. For solubility prediction, it trains four encoders to preserve the population-level relational information from priors capturing hydrophobic, electrostatic, polarizability, and substructural effects, using Kullback-Leibler (KL) divergence to match pairwise distance-based distributions during pretraining. For scaffold, solute, and solvent OOD generalizations, PRISM matches or surpasses supervised and self-supervised baselines. For mixed-solvent OOD generalizations, freezing the four PRISM encoders and training a light fusion-and-composition head outperforms the strongest supervised baselines and greatly reduces prediction variations. Ablations and control studies confirm that gains stem from chemically meaningful relational structures baked into the encoders by PRISM. We expect this strategy of turning relational priors into self-supervision signals to extend beyond solubility prediction to domains where chemically or biologically meaningful relational priors are available.

Histological whole-slide images (WSIs) are central to computational pathology but pose severe computational challenges due to their extremely high resolution, often spanning several gigabytes per slide. To enable scalable learning, existing methods apply self-supervised data condensation to reduce computational cost, but typically rely on heuristic prototype learning and do not explicitly preserve learning-relevant feature distributions for downstream tasks. In response, we introduce a principled reformulation of WSI condensation as a distribution-matching problem under a fixed representational lens, and develop NICER, a tractable approximation framework based on a nonparametric prior with slide-adaptive capacity. Experiments on five histopathology datasets, together with clinical evaluation from a board-certified pathologist, show that NICER consistently outperforms prior methods, achieving an average accuracy improvement of 7.44% while offering improved efficiency–accuracy trade-offs, highlighting the benefits of principled, distribution-aware condensation for scalable histological representation learning.

Open-world semi-supervised learning aims to use limited labeled data from known classes to classify unlabeled samples that contain both known and novel classes. Most existing methods over-rely on known classes and tend to generalize incorrectly in complex open-world settings. This leads to degraded pseudo-label quality and the model is often overconfident in wrong predictions. To address this, this paper proposes a **M**itigating **C**onfidence **M**iscalibration Method in **Open**-World Semi-Supervised Learning (**OpenMCM**). By leveraging discriminative knowledge from known classes to guide learning in the novel class space, our method effectively mitigates overconfident misclassifications and improves discrimination accuracy. Furthermore, we propose an adaptive threshold calibration strategy to independently determine optimal decision boundary for each class. By integrating a high-reliable pseudo-label fusion mechanism, we enhance recognition stability for novel classes. Experiments on three benchmark datasets ($i.e.$, CIFAR-10, CIFAR-100, and ImageNet-100) show that our framework achieves performance improvements over existing state-of-the-art methods.

Long-horizon embodied intelligence requires agents to improve through interaction, not merely to execute plans generated from static goals. A central challenge is therefore to transform past executions into knowledge that can shape future decisions. Minecraft provides a representative testbed for this problem, where tasks such as crafting tools, building redstone components, and obtaining diamond equipment involve long prerequisite chains and are frequently disrupted by missing tools, blocked paths, GUI failures, or stagnant execution. To this end, we propose \textbf{MineEvolve}, a knowledge-driven self-evolution framework that converts execution feedback into actionable behavioral knowledge. MineEvolve first uses \underline{\emph{\textbf{\ding{182}Monitor}}} to convert each subgoal execution into typed feedback, including state changes, inventory changes, failure types, progress signals, and stagnation indicators. \underline{\emph{\textbf{\ding{183}Inducer}}} then derives reusable skills from successful executions and remedies from failed or stagnant executions. \underline{\emph{\textbf{\ding{184}Curator}}} validates, merges, filters, and retrieves these knowledge entries, while \underline{\emph{\textbf{\ding{185}Adaptor}}} uses them to repair the unfinished part of the plan under repeated failures or stagnation. Experiments on the Minecraft MCU long-horizon task suite show that MineEvolve consistently improves performance across multiple language-model planners, with larger gains on high-dependency task groups. Ablation and knowledge-accumulation studies further demonstrate that converting execution signals into structured behavioral knowledge is an effective path toward self-evolving embodied agents in long-horizon environments. Our code is available at \url{https://anonymous.4open.science/r/MineEvolve-1B5B}.

Self-improving LLM agents typically improve answers, not the $\textit{process}$ by which answers are improved: their search loops and mutation rules are held fixed by design. We introduce $meta^n$, a framework for $\textit{recursive}$ self-improvement in which a single universal meta-operation $\Omega$ is applied repeatedly to build a hierarchy of meta-layers whose depth is sized by convergence rather than prescribed. Each layer observes execution traces from below, diagnoses failure patterns, and emits executable code (strategic guidance via pre-processing and reusable functions via a code library) whose effects cascade downward. Inter-layer conditioning permits up to $\prod_{d=2}^{n} k_d$ effective strategy-tactic combinations across $n$ layers rather than $\sum_d k_d$. An evolutionary orchestration mode maintains a growing archive of candidate chains with fitness-weighted parent selection and cross-candidate inspiration. Across seven benchmarks (combinatorial optimization, two text classification tasks, terminal agent tasks, mathematical discovery, symbolic regression, algorithm speedup), $meta^n$ beats prior self-improving agents on all five (of seven) benchmarks where they apply, with the largest gap on CO-Bench (0.849 test vs. Gödel Agent's 0.000 and OpenEvolve's 0.816). Layers specialize without prescription and their roles emerge at depth: generic primitives at depth 2 propagate as cross-task callables, task-aware routing emerges at depth 3, and deeper layers refine via specialization. Code and data will be released publicly.

Existing VLM-based open-set semi-supervised learning (OSSL) methods primarily rely on coarse-grained class-level semantics, thereby hampering the accurate identification of in-distribution (ID) versus out-of-distribution (OOD) samples. To overcome this issue, we propose a novel memory-driven contrastive embedding enhancement approach by integrating fine-grained visual contrastive cues into class-level textual side. Concretely, we design a memory bank to construct and maintain a diverse collection of the most distinctive fine-grained visual embeddings. Guided by the memory bank, visual information is incorporated into the textual side through cross-modal contrastive learning, enabling more discriminative fine-grained separation between ID and OOD samples. Consequently, the learned OSSL model exhibits improved contrastive discriminability across known and unknown categories. Extensive experiments demonstrate that our method achieves state-of-the-art (SOTA) performance on multiple fine-grained datasets. The code is available at https://anonymous.4open.science/r/CodeForPaper.

Recent progress in multimodal, high-dimensional learning has enabled foundation models to process heterogeneous, large-scale data. However, at test time, acquiring all features or modalities can be prohibitively costly and often redundant. Sequentially selecting informative modalities is therefore critical, yet challenging when the downstream task or prediction target is unknown. To this end, we introduce ECHO-$k$, a task-agnostic and self-supervised learning principle for modality acquisition: we use a deep model’s internal pretrained representations (e.g., from a foundation model) as proxy targets that summarize cross-modal information. We provide theoretical guarantees in a linear model setting that motivate a reinforcement learning (RL) policy for sequential modality selection. Across benchmarks, the resulting acquisition strategies transfer reliably and achieve state-of-the-art performance on downstream tasks that are entirely unseen during selection. Our method provides a principled route to cost-aware test-time deployment, with implications for any multimodal system where measurements are expensive or time-constrained, and downstream tasks unknown a priori.

This paper addresses the problem of sequential decision-making under learning budget constraints. Such settings naturally arise in applications like managing a portfolio of bandit or reinforcement learning (RL) algorithms. We propose a novel UCB-type algorithm, M-LCB, designed to manage a pool of $K$ self-learning experts in a stochastic environment while accounting for a limited per-round learning budget $M$. At each round, M-LCB selects one expert to make a decision and at most $M \le K$ experts to learn. For selection, M-LCB uses confidence bounds constructed from limited prior knowledge about the experts (i.e., mild assumptions) and their observed training losses. We derive anytime regret bounds for M-LCB that scale with the individual regrets of the experts. In particular, if each expert has regret $\tilde O(T^\alpha)$ by round $T$, then M-LCB guarantees an overall regret of $\tilde O\left(\sqrt{KT/M} + (K/M)^{1-\alpha}T^\alpha\right)$ relative to the best expert in hindsight. Finally, we demonstrate the applicability of M-LCB using self-learning experts instantiated as (i) parametric models and (ii) bandit algorithms.

Transformers have achieved remarkable success across a wide range of applications, and a growing body of work suggests that part of their strength comes from their ability to learn and execute algorithmic procedures. However, our understanding of how transformers learn such algorithms remains limited, especially in the presence of layer normalization (LN). In this work, we study principal component prediction as a concrete testbed for understanding the training dynamics of transformers with LN. We prove that a looped linear transformer with LN, trained by gradient descent, converges to a solution that implements the power method, with each self-attention layer performing one power iteration. Notably, the model is trained only for principal component prediction, rather than being explicitly supervised to implement the power method. Our finding thus reveals an ``algorithmic implicit bias'' of looped transformers with LN: principal-component prediction can in principle be achieved by many mechanisms, yet gradient descent selects one that realizes the power method. We further provide a concrete comparison between transformers with and without LN: even with layerwise guidance from power iterations, a transformer without LN cannot exactly learn the power method, whereas the corresponding transformer with LN can, leading to a provable performance gap in principal component prediction. Our results provide, to our knowledge, the first theoretical analysis of the training dynamics of looped and single-layer transformers with LN, and shed light on the role of LN in transformer models.

Fine-tuned LLMs can learn complex and subtle behaviors. However, it can be difficult to ascertain what behaviors the model acquired during fine-tuning. We introduce LoRAcles: fine-tuned language models that take LoRA adapter weights as input, and answer natural language questions about them. We introduce a self-supervised pipeline for training LoRAcles: we first train LoRAs on small sets of pre-training documents, and then train LoRAcles on these LoRAs to answer questions about the documents. LoRAcles generalize far beyond their training data: they are state-of-the-art on AuditBench, a benchmark of models with sophisticated hidden behaviors; they can detect subtle changes in model organisms (fine-tunes deliberately constructed to encode a hidden behavior for auditing research), such as subliminal learning; and they are the first tool to achieve non-trivial performance at verbalizing semantic backdoor triggers. LoRAcles can also describe some learned behaviors from the weights of a full-parameter fine-tune. LoRAcles are a highly scalable method: we train LoRAcles for Qwen-3-14B and Llama-3.3-70B, and observe that performance scales smoothly with the size of our training dataset up to 100K LoRAs, though our method may need refinement in order to scale further. We note, though, that LoRAcles are prone to hallucinations and currently only elicit the most salient behavioral changes, limiting their utility beyond narrow fine-tunes.

Localizing AI-edited regions is essential for interpretable forensic analysis, but remains challenging due to subtle and spatially distributed artifacts that are misaligned with semantic or object boundaries. Existing approaches rely on pixel-level supervision from controlled editing pipelines, which is difficult to scale and can introduce misleading signals: artifacts frequently extend beyond annotated regions, while out-of-mask pixels are treated as authentic. This limits models' ability to capture transferable evidence and generalize across generators and datasets. To address these issues, we propose \textbf{ReGFLoW}, a \textbf{Re}construction-\textbf{G}uided \textbf{F}ake \textbf{Lo}calization framework under \textbf{W}eak supervision, which is the first weakly supervised approach for diffusion-edited fake region localization. ReGFLoW requires only real/fake labels at the image-level and uses diffusion reconstruction errors as dense spatial guidance to inject them into both feature and score spaces. Furthermore, by artifact-centric multiple instance learning, ReGFLoW utilizes localized diffusion evidence without relying on semantic-affinity or boundary-based pseudo-mask priors. Extensive experiments demonstrate that ReGFLoW achieves stronger out-of-domain generalization than fully supervised learning baselines.

Many real-world applications require highly interpretable machine learning systems, particularly in high-stakes domains such as healthcare. A promising recent direction is the paradigm of Maximal Coding Rate Reduction (MCR$^2$), which seeks to characterize and preserve the low-dimensional structure underlying each class. However, we find that exhaustively preserving structural information is often unnecessary and can even be detrimental in supervised learning, especially under noisy and uncertain real-world conditions, as it may overly constrain the fitting flexibility of the model. In contrast, we propose a simple yet effective framework, termed SimCoding, which captures only minimal structural information for each class. Despite relying on substantially less structural information, SimCoding significantly improves the generalization ability and robustness of deep models. Extensive experiments across diverse benchmark datasets demonstrate the effectiveness of SimCoding. We further validate SimCoding on a challenging real-world application, Parkinson’s disease severity assessment from free-living human activity signals, where it consistently achieves strong robustness and outperforms competing methods. Moreover, SimCoding can be naturally extended to incremental learning scenarios, where it substantially alleviates catastrophic forgetting and consistently surpasses strong baselines.

Reinforcement learning (RL) post-training has become an important paradigm for improving multimodal large language models (MLLMs), especially with automatically verifiable rewards. For vision-centric MLLMs, self-supervised visual pretext tasks provide such rewards without human annotations. However, existing self-supervised RL methods mostly exploit within-instance structure, such as spatial or temporal ordering within a single image or video, offering limited supervision for cross-instance discrimination and fine-grained comparison. We introduce Group-and-Order Self-Supervised Reinforcement Learning (GO-SSL), a cross-instance jigsaw framework for vision-centric MLLM post-training. Given two visual instances, GO-SSL mixes their local elements and trains the model to group them by instance of origin while recovering the order within each group, coupling instance-level comparison with spatial, temporal, or geometric structure recovery. This paired formulation turns the same unlabeled data into richer verifiable supervision through diverse pairings, shuffles, and hard-pair curricula. We instantiate GO-SSL mainly on cross-image jigsaw tasks and further extend it to 3D depth and video temporal ordering. Across diverse benchmarks, GO-SSL consistently improves over the base MLLM and prior baseline methods, with clear gains in fine-grained perception and spatial understanding. These results suggest a data-efficient direction for self-supervised RL in MLLMs: constructing comparative cross-instance contexts can provide richer transferable supervision than merely scaling data volume or adding isolated pretext tasks. Code will be released later.

In-context watermarking (ICW) prepends an instruction to a query asking the model to embed a statistically detectable signal in its response. It thus equips LLMs with a watermarking interface that third parties can invoke without access to model internals. Its reliability hinges on the LLM following the instruction without degrading answer quality, yet how well current LLMs do so has not been measured. We introduce ICWBench, a benchmark of three verifiable ICW instruction families, each scored on both detectability and answer quality. Evaluating 14 frontier proprietary and open-source LLMs, we find that none of the evaluated LLMs achieves both objectives across all three families. To address this, we propose a self-contained two-stage training method, requiring no distillation from a stronger model, no manual annotation, and no pre-existing ICW IF ability. The first stage, self-distillation with logits perturbation (SDLP), uses the same base LLM as both teacher and student: an instruction-equivalent decoding-time logits perturbation makes the teacher follow the ICW instruction, and the student is trained to match the teacher's output distribution. The second stage applies reinforcement learning with the automatic verifier as the reward. Applied to Qwen3-14B, the weakest of the 14 evaluated LLMs in ICW IF, our method raises average TPR@$1\%$FPR across three ICW instructions from $0.100$ to $0.974$, achieving a more favorable trade-off than the frontier proprietary LLMs we evaluate.