NeurIPS 2026 论文列表

Autoregressive (AR) modeling has recently achieved remarkable progress in native 3D mesh generation, largely due to its natural ability to handle variable-length, discrete data structures. However, the inherent constraints of the AR paradigm severely restrict the generated meshes, leading to limited face counts, bounded vertex resolutions, and difficulties in supporting textures. To overcome these bottlenecks, we propose the Barycentric Dominance Field (BDF), a continuous representation defined on triangular mesh surfaces that elegantly encodes vertex topological connectivity. BDF bridges the fundamental gap between discrete mesh topology and continuous diffusion-based generative modeling by transforming connectivity into a continuous surface signal. As an intrinsic mesh property, BDF shares strong similarities with texture maps, enabling its seamless integration into existing 3D diffusion pipelines without requiring architectural modifications. Extensive experiments demonstrate that BDF empowers diffusion models to generate native meshes with significantly higher quality, greater scalability, and stronger robustness compared to state-of-the-art autoregressive methods.

Medical illustration generation is not merely domain-specific text-to-image (T2I) generation, but a high-constraint visual reasoning problem where visually plausible images can be invalid due to anatomical and structural errors. Existing T2I models largely rely on one-pass generation and lack an internal mechanism to inspect and correct such biomedical inconsistencies. We introduce **MedIGen**, a unified medical illustration generation model that transforms one-pass synthesis into an **interleaved introspection-aware refinement** process, coupling generation with self-reflection and re-generation through “generate–reflect–refine” cycles. MedIGen is trained with three progressive stages: (1) large-scale medical illustration pretraining on 1.21M samples, (2) mixture training over generation, reflection, and refinement sub-skills, and (3) reinforcement learning with dual-level rewards that optimize both reasoning validity and final visual correctness. We further present **IlluGenBench**, an expert-aligned, rubric-driven benchmark with 296 diverse tasks and 9,015 criteria, evaluating scientific accuracy, structural correctness, and semantic alignment beyond coarse visual plausibility. Experiments show that MedIGen substantially outperforms strong open-source unified and reasoning-based baselines, establishing a new open-source frontier. All resources will be open-sourced to facilitate future research.

Modern large language models keep the feed-forward network (FFN) intermediate width identical across every layer, a convention inherited from the original Transformer. Yet mechanistic work suggests layers at different depths do qualitatively different work, raising a natural question: are their capacity demands also non-uniform, and if so, can a fixed parameter budget be allocated more wisely than uniformly? To probe this, we apply principal component analysis (PCA) to the input of each FFN down-projection and measure, for every layer, the smallest number of principal components needed to reconstruct the activation up to a fixed cosine similarity --- the layer's intrinsic dimensionality. Scanning 58 open-weight LLMs spanning 14 families and 70M to 72B parameters, we find a recurring middle-heavy profile in which middle layers carry higher intrinsic dimensionality than edge layers; the profile is robust to the calibration corpus, even across English and Chinese, and is largely preserved through post-training fine-tuning. As a direct test that this signal is structurally meaningful, we use it to guide width pruning in a knowledge-distilled student under a matched parameter budget: the PCA-guided allocation outperforms the uniform-width convention by $+2.7$ points on Qwen2.5-3B and $+2.3$ on Qwen3-8B, while a same-scale teacher (LLaMA-3-8B) shows only $+0.9$, and a budget-matched inverted control consistently does worst. Across these three teachers, the size of the gap scales with how unevenly the teacher's intrinsic dimensionality is distributed across layers --- a single-number summary we call $\sigma_{99}$ --- and the advantage persists through downstream supervised fine-tuning.

Large language models are increasingly deployed for open-ended question answering, yet their answers rarely come with calibrated uncertainty. We propose CAELUM, a framework that builds semantic prediction sets and separates aleatoric from epistemic uncertainty in their construction. CAELUM samples answers under prompt-ensembled clarifications, clusters them by semantic equivalence, estimates aleatoric and epistemic components via kernel Von Neumann entropy, and calibrates cluster-APS nonconformity scores with split conformal prediction. A per-instance weight $w_\lambda(x)=1+U_{\mathrm{ale}}(x)+\lambda\,U_{\mathrm{epi}}(x)$ controls how epistemic uncertainty enters the set, and a per-cell coefficient $\lambda^\star$ is fit on a held-out split to minimise prediction-set size. Our central observation is that, in open-ended generation, coverage on cluster-APS scores is silently capped by \emph{matchability}: the fraction of items whose reference answer appears in any sampled cluster. We make this dependence verifiable with a Mondrian split-conformal bound on a learned stratum, where matchability is predicted from pre-generation question features by a lightweight classifier. Across $18$ (model, dataset) cells and four split seeds on three open-weight 4--9B LLMs, the learned classifier lifts predicted-matchable coverage from $0.61$ overall to $0.71$ on non-fallback rows ($0.82$ vs $0.63$ when oracle-fallback rows are included as upper bounds), and the classifier transfers across LLMs at AUC $0.78$ (in-sample $0.80$). The cell-level $\lambda^\star$ doubles as a regime diagnostic: large values flag epistemic dominance (retrieve, abstain) and $\lambda^\star\to 0$ flags aleatoric dominance (clarify), with a per-instance log-ratio $R(x)$ extending the read-out to individual queries.

Machine unlearning (MU) aims to remove sensitive or undesired knowledge from a trained model without retraining from scratch. While MU has been widely studied for autoregressive large language models, its application to diffusion large language models (DLLMs) remains largely unexplored. In this paper, we present the first systematic study of MU in DLLMs and show that existing unlearning objectives transfer poorly to this setting due to sparse supervision and inaccurate forgetting localization. To address these challenges, we propose \textsc{DL-Eraser}, a DLLM-native unlearning framework that suppresses target recoverability under high-mask conditioning while constraining updates to a utility-preserving subspace. Extensive experiments show that \textsc{DL-Eraser} achieves stronger forgetting while better preserving model utility than existing baselines. To the best of our knowledge, this is the first work that systematically investigates MU in DLLMs.

Image generation models have rapidly advanced, with many models now supporting generation conditioned on multiple reference images and textual instructions. Such models enable a wide range of applications, including entity fusion and attribute transfer across images. However, existing benchmarks for multi-reference image generation rely on limited evaluation dimensions and fail to capture the diverse challenges of the task. To address this limitation, we propose **MDMR-Bench**, a **M**ulti-**D**imensional benchmark for **M**ulti-**R**eference image generation. MDMR-Bench is designed based on realistic usage scenarios and consists of multiple evaluation subsets spanning diverse dimensions of multi-reference image generation, including (1) common entity fusion and attribute transfer, (2) multi-element extraction from a single image, (3) infographic manipulation, and (4) visual reasoning-intensive generation. This design enables systematic analysis of model capabilities and failure modes across different challenge dimensions. Furthermore, to achieve more reliable and interpretable evaluation, we introduce a checklist-based evaluation protocol that decomposes generation quality into fine-grained evaluation aspects. Instead of relying solely on holistic scoring, our framework uses structured checklists composed of both global-level and atomic-level queries, enabling more diagnostic assessment of model performance. By benchmarking both open-source and proprietary models, we demonstrate that MDMR-Bench provides fine-grained insights into model performance across different dimensions. Our dataset is available at [Kaggle](https://www.kaggle.com/datasets/6f695be8363ee17928c25f36fa976fd10f976f9f6d4925bc0df74f38dfce268c). The code is available at [GitHub](https://anonymous.4open.science/r/Neurips2026_ED_paper3412).

Large Language Models face a challenging multi-objective coupled optimization problem in constrained long-text generation, requiring the simultaneous balancing of global structure, local coherence, and constraint satisfaction. However, existing methods often rely on static pipelines or loosely coupled designs, making it difficult to achieve cross-stage collaborative optimization. To address this, we propose LoopWeaver, which models the generation process as a hierarchical, feedback-driven closed-loop optimization problem; by introducing iterative feedback between the planning and generation stages, it achieves the joint optimization of both global and local aspects. Specifically, LoopWeaver integrates constraint-aware hierarchical planning, feasibility filtering, and reward-based preference optimization, thereby allowing feedback signals to permeate both the planning and generation layers. Unlike methods that utilize feedback solely during post-processing or within a single module, LoopWeaver introduces a unified paradigm for feedback-coupled optimization, demonstrating significant improvements in text quality and constraint satisfaction capabilities across various models.

The ability to simulate the world in a spatially consistent manner is a crucial requirement for effective world models. Such a model enables high-quality visual generation, and also ensures the reliability of world models for downstream tasks such as simulation and planning. It must not only retain long-horizon observational information, but also enables the construction of explicit or implicit internal spatial representations. However, existing datasets do not explicitly enforce spatial consistency constraints, limiting both the ability to systematically evaluate this capability and to learn it through data-driven approaches. Furthermore, most existing benchmarks primarily emphasize visual coherence or generation quality, neglecting the requirement of long-range spatial consistency. To bridge this gap, we propose loopnav, a dataset and corresponding benchmark centered on loop-based navigation for evaluating spatial consistency. The dataset comprises 250 hours (20 million frames) of loop-based navigation videos with actions, collected from diverse locations in the open-world environment of Minecraft. We further introduce a Scene Graph Consistency Score to quantify spatial consistency while remaining invariant to pixel-level variations. Dataset, benchmark, and code are open-sourced to support future research.

Large software projects often depend on older versions of libraries, even as APIs continue to evolve across releases. This creates a challenge for LLMs: they must maintain knowledge of multiple API versions, not merely the latest or most common one. However, current LLMs, trained on temporally mixed corpora and lack explicit mechanisms for such version-specific reasoning, leading to anachronistic errors -- calling APIs as they exist in a different library version. To systematically evaluate this phenomenon, we introduce LibEvoBench, a multi-task benchmark spanning multiple versions of widely used Python libraries, along with a new metric, the Software Evolution Understanding Score (SEUS), to measure models' consistency when working with evolving APIs. Our results show that state-of-the-art models are largely version-oblivious: performance degrades for evolving APIs, while for stable APIs it remains the same across versions. Moreover, simply specifying the target version provides no benefit, while relevant documentation significantly boosts models' accuracy. These findings highlight a systematic limitation of current training paradigms and motivate new approaches for temporally grounded knowledge in code generation.

High-resolution 3D medical image generation remains challenging because fully volumetric models are computationally expensive, while efficient 2D slice generators often fail to preserve anatomical consistency across the third dimension. We propose LiFT, a framework for Lifted Inter-slice Feature Trajectories that factorizes 3D volume synthesis into per-slice image generation and inter-slice trajectory learning. Rather than modeling the volumetric distribution end-to-end, LiFT treats a volume as an ordered trajectory in feature space, capturing how anatomical structures appear, transform, and disappear across depth. A tri-planar drifting loss aligns the trajectory of generated slices with the trajectories of real volumes, enabling distributional learning over inter-slice progressions in unconditional generation; in paired translation, a bidirectional $z$-context mixer trained against the registered target supplies through-plane coherence while preserving per-slice fidelity. We evaluate LiFT on BraTS 2023 (unconditional and missing-modality MR) and SynthRAD2023 (MR-to-CT). Across these settings, LiFT preserves per-slice quality, approaches the reported cWDM missing-MR reconstruction quality, and improves through-plane coherence on MR-to-CT relative to a no-mapper ablation, demonstrating that lightweight inter-slice trajectory learning is a viable route to high-resolution 3D medical synthesis.

Persuasion is a core dynamic of natural language communication, shaping how large language models (LLMs) update beliefs, resolve disagreements, and reach decisions. As LLMs increasingly debate, advise, and think collaboratively with humans and each other, resistance to harmful persuasion becomes a core requirement for reliable behavior. Yet we show that this requirement is far from met: a single targeted persuasive argument is enough to collapse model accuracy to near zero, even when the argument is factually false. We formalize this threat as adversarial persuasion and introduce an adversarial reinforcement learning framework that trains persuader agents to change a target model's answer in a single interaction. First, we show that optimizing persuasion strategies through trial and error exposes vulnerabilities that static prompting misses: RL-trained persuaders raise persuasion success from approximately 24\% to over 93\% against the training-time persuadee. Second, we find that these learned strategies transfer to unseen models, achieving 83\% attack success on Qwen-14B, 79\% on Llama-3.1-8B, and 25\% on GPT-4o-mini. Third, we demonstrate that a curriculum that bootstraps on more persuadable open-weight models before targeting harder models further increases GPT-4o-mini attack success from 25\% to 38\%. Moreover, our results reveal that optimized persuaders increasingly rely on credibility-based tactics, including fabricated citations and false authoritative evidence. Together, these findings expose a critical weakness in current LLM agents: even when they initially reason correctly, they can be steered toward false conclusions by optimized natural language influence. This positions persuasion robustness as a necessary safety criterion for multi-agent and human-AI decision-making systems.

Current text-to-image diffusion models remain unreliable for culturally grounded generation, often producing incorrect or stereotyped depictions, particularly for underrepresented cultures. While prior work has largely focused on evaluation and benchmarking, improving cultural generation remains underexplored. In this work, we study cross-cultural image generation through cultural vectors, defined as the difference between fine-tuned and pretrained model parameters. We show that cultural vectors enable fine-grained control over cultural alignment and failure modes through simple scaling at inference time. We further find that deeper U-Net layers encode stronger cultural information, while cultural vectors across countries occupy largely independent directions in parameter space. However, unlike prior work on task arithmetic, naively combining cultural vectors fails to produce meaningful multi-cultural behavior due to strong interference across cultures. Motivated by this limitation, we propose Descriptor-Guided Merging (DGM), a culturally-aware merging approach that estimates cultural vectors for unseen countries using descriptor-based similarities across cultures. Experiments on two benchmarks across 16/10 countries show that cultural vectors improve generation over pretrained models by 18.9%, while DGM improves cross-cultural generalization by 4.2% over naive merging.

Compared with residential layouts, public indoor floorplans present more substantial challenges with open corridors, complex room relations, and non-Manhattan geometries, which do not conform to conventional residential-layout assumptions. Consequently, existing methods are prone to boundary discontinuities, leading to fragmented corridors and irregular wall structures. To address the above issues, we propose \textit{LayoutBridge}, a structure-conditioned generative framework for floorplan production. By moving beyond the Manhattan-geometry assumptions commonly adopted in residential scenarios, LayoutBridge reformulates the task as a latent-space Brownian-bridge diffusion process from structural constraints to target layouts. We have constructed our PISF dataset with 3,517 representative floorplans in public indoor spaces, and LayoutBridge reduces FID by 132.35 and improves BIoU by 15.52\% over the latest image-to-image baselines. Regarding the residential benchmarks MSD and RPLAN, it also reduces FID by at least 2.53 compared with state-of-the-art. These results demonstrate its potential for scalable automated architectural design. Code implementing the proposed method is publicly available at \href{http://github.com/lalalalaxxx/LayoutBridge}{http://github.com/lalalalaxxx/LayoutBridge}.

Transcriptome-conditioned whole-slide image (WSI) synthesis aims to decode the complex mapping from molecular states to histologic phenotypes. Existing generative paradigms predominantly rely on a direct black-box transcriptome-to-image mapping, tasking a single generator with the simultaneous interpretation of transcriptome signals, inference of multicellular spatial organization, and rendering of fine-grained textures. This formulation, however, is structurally under-constrained; the underlying tissue architecture, the critical substrate linking gene expression to morphology, remains latent and only weakly supervised by pixel-level objectives. We present \textsc{TopoScape}, a topology-anchored framework for transcriptome-to-histology generation under a \emph{Layout-Before-Pixels} principle. Instead of synthesizing pixels directly from transcriptomic embeddings, \textsc{TopoScape} first resolves molecular states into explicit, multi-class cellular topologies via an RNA-guided Topological Prior Generator, reinforced by persistence-based topological regularization. These resolved topologies are further reparameterized into a suite of topology-derived controls, including structure-aware initialization, continuous density fields, and distance representations, which guide a hierarchical, frequency-decoupled flow-matching trajectory. By introducing multicellular organization as an explicit structural mediator, \textsc{TopoScape} allows molecular states to deterministically shape both the macroscopic tissue architecture and the microscopic generative process. Across five TCGA benchmarks, \textsc{TopoScape} consistently outperforms state-of-the-art methods in generative fidelity, biological realism, and downstream predictive utility. Code and pretrained models will be released.

Confidence-weighted routing, selective abstention, and ensemble weighting all assume that a model's stated confidence is informative about its capability on the question being asked. They presume functional metacognition, the capacity to assess one's own capabilities, without exercising them, relative to other frontier language models. Aggregate calibration is well studied, with mixed results, but the underlying structure of elicited confidence is less well understood. We decompose binary confidence judgements from 20 frontier Large Language Models (LLMs) across six benchmarks using tetrachoric factor analysis paired with pairwise calibration, asking whether two models that differ in confidence also differ in performance. On factual recall and information retrieval benchmarks the cross-model confidence matrix is approximately rank-one and a single dominant factor captures most of the latent variance. Models retrieving facts share an item-level difficulty axis and differ mainly in their decision thresholds along it. Across all benchmarks the relationship between confidence and performance collapses once items that all models agree on are removed. Inter-model pairwise calibration is small even where statistically significant, and what remains shrinks to nothing once base-rate differences along the shared factor are controlled for. Mathematical reasoning is the apparent exception, but this turns out to be a confound where reasoning models answer questions about their confidence by trying to solve them in their chain of thought, bypassing the sub-symbolic self-knowledge we seek to measure. We find no evidence for significant verbalised individuated metacognition in any tested domain. A trivial logistic regression on surface features of the confidence-judgement reasoning text beats the median confidence model's repeatedly sampled judgements on half the benchmarks, evidence that extracting uncertainty from the reasoning trace recovers signal the binary judgement does not.

High-performance inference for large models is critical in latency-sensitive applications. Existing inference engines suffer from sequential execution of hundreds of fine-grained kernels, causing kernel launch overheads and redundant memory accesses. A promising solution is fusing multiple kernels into a single large kernel, namely MegaKernel. However, existing MegaKernel implementations are tightly coupled to specific models and GPU architectures and require extensive manual engineering. We propose an LLM-driven framework AutoMegaKernel, which leverages an Instruction-Centric Fusion Abstraction to decompose MegaKernels into tractable fusion instructions, thereby enabling automated generation. Our framework jointly performs fusion strategy reasoning and CUDA code generation while hierarchically verifying correctness. Extensive experiments demonstrate that AutoMegaKernel consistently outperforms state-of-the-art inference engines (up to 5.04$\times$ vLLM and 2.42$\times$ SGLang) and compilers (up to 1.92$\times$ MPK), while supporting a broader range of models (dense, MoE, and VLA) and NVIDIA GPU platforms (Hopper, Ampere, and Ada).

Large Language Models (LLMs) increasingly ship with “thinking modes”, yet their counterpart, the “no-thinking” has received far less exploration. In this work, we revisit language model “no-thinking” behavior along the following efforts: **(a) Explore the definition of no-thinking.** Rather than relying on proxies like thinking-mode control, we split each response into pre-answer text and a final answer, scoring both answer-only compliance and the question–pre-answer relevance. **(b) Broad experimental coverage.** We evaluate multiple no-think controls (thinking-mode toggles, prompt instructions, *etc.*) across boolean, multiple-choice, and open-ended tasks, on open-source models with scaled variants, and proprietary models. With extensive experiments, we found that **(i)** Explicit no-think controls do not reliably eliminate visible reasoning-like content. Instead, models exhibit **(ii)** *“thinking inertia”*: residual content is systematically organized by the task's answer space, with boolean verification compressing most easily, multiple-choice tasks forming an intermediate regime, and open-ended tasks remaining the most resistant. **(iii)** We further identify what we call a no-thinking and performance trade-off in open-ended: stronger answer-only constraints on complex tasks either fail to suppress the intermediate payload or succeed by removing computation needed for accuracy. **(iv)** Finally, we show that compressibility depends strongly on the structural support provided by the question itself. Thus, no-think controls are not direct guarantees of no-thinking; they must be evaluated jointly through answer-only success, visible payload, and task accuracy. We hope our work moves LLMs closer to a human-like ability to stop thinking on demand.

Despite the remarkable progress of evolutionary LLM frameworks like AlphaEvolve in program and algorithm discovery, they consistently struggle with tasks requiring deep algorithmic reasoning and long-horizon planning, such as the Abstraction and Reasoning Corpus (ARC-AGI). A fundamental limitation of current evolutionary code generation is its reliance on unguided stochasticity to derive child programs from parents, lacking a systematic mechanism for knowledge accumulation, whereas human problem-solving thrives on the continuous consolidation and reuse of high-level conceptual abstractions. To bridge this gap, we propose the \textbf{Library-driven Evolutionary Abstraction Paradigm (LEAP)}, a cognitive-inspired framework that enables LLMs to autonomously construct and evolve a globally shared library of reusable algorithmic primitives. The evolution of this library is governed by two rigorous theoretical principles: First, the generation of new primitives is driven by a Minimum Description Length (MDL) objective, ensuring the system only assimilates concepts that genuinely compress the problem space. Second, the evolutionary survival and selection of these primitives are governed by a principled exploration-exploitation mechanism, dynamically regulating the library's life-cycle to strike an optimal balance between exploiting proven cognitive operators and exploring novel hypotheses while strictly bounding context entropy. Extensive experiments demonstrate that LEAP significantly outperforms existing LLM evolutionary baselines on the ARC-AGI benchmark and math optimizations problems, exhibiting robust cross-task generalization, highly efficient context utilization, and autonomous concept discovery capabilities.

Reinforcement learning (RL) has become central to post-training large language models, but its rollout generation stage is often the dominant system bottleneck. The inefficiency comes from two sources. First, autoregressive decoding makes latency grow with response length. Second, response lengths vary widely within a batch: short sequences finish early, but the batch remains blocked by the longest sequence, leaving GPU capacity underutilized. This effect is amplified in multi-sample rollouts, where long responses can also concentrate on a few decoding workers and delay synchronization. We propose LADDERS (Length-Aware Data Distribution and Existing-Response Speculation), a lightweight framework for accelerating RL rollout generation. LADDERS first uses hidden-state-based length prediction to group prompts with similar expected response lengths, and then applies an S-shaped allocation rule to balance multi-sample requests across workers. It further reuses responses already generated by the policy as draft continuations through prompt-specific suffix trees, enabling speculative decoding without an auxiliary draft model. Experiments on Qwen3-1.7B and Qwen3-8B show that LADDERS reduces rollout generation time by up to 56% while preserving final task performance, and can be integrated into existing RL systems with minimal engineering effort.