NeurIPS 2026 论文列表

Reinforcement Learning from Verifiable Rewards (RLVR) has driven recent progress in code large language models by leveraging execution-based feedback from unit tests, but its scalability is fundamentally constrained by the availability and reliability of high-quality test cases. We propose **CodeScaler**, a reward model designed to scale both reinforcement learning training and test-time inference for code generation. **CodeScaler** is trained on carefully curated preference data derived from verified code problems and incorporates syntax-aware code extraction and validity-preserving reward shaping to ensure stable and robust optimization. Across four coding benchmarks, **CodeScaler** consistently outperforms execution-based RL by **+1.55** points on Qwen3-8B-Base and **+4.23** points on Qwen3-14B-Base. By further scaling to 44K problems with additional synthetic data, **CodeScaler** yields **+14.64** points improvement over the base model without requiring any test cases. At inference time, **CodeScaler** serves as an effective test-time scaling method, achieving performance comparable to unit test approaches while providing a **10×** reduction in latency. Moreover, **CodeScaler** surpasses existing reward models on RM-Bench not only in the code domain (**+3.3** points), but also in general and reasoning domains (**+2.7** points on average).

Large Language Models (LLMs) struggle with temporal alignment, often producing outdated time-sensitive facts as real-world knowledge evolves. Yet the field's ability to measure this misalignment is itself fragile. Existing benchmarks are static snapshots, rely on rigid templates, are small, lack provenance, conflate willingness-to-answer with recall, and use phrasings that newer models have likely memorised. We argue that progress on temporal alignment is bottlenecked less by data scarcity than by evaluation design, and we contribute on both fronts. We present ChronosAlign, a natural language, programmatically updatable dataset and evaluation framework for temporal alignment in LLMs; generated from a Wikidata and Wikipedia corpus of ~500,000 question-answer pairs covering ~27,000 unique questions across sport, politics, and culture from 2000 to 2025. Each question carries a Wikipedia URL and a documented update procedure, so the same evaluative claim can be re-tested against future models without re-authoring the benchmark. We couple ChronosAlign with a framework focussed on three prompting modalities, explicit (year-anchored), relative ("current" anchored), and invariant (untimed control), whose disagreement isolates which component of temporal alignment a model fails. We benchmark sixteen LLMs surfacing three findings: (i) a sharp post-2022 decay in explicit recall even for models with later training cutoffs, (ii) systematic misalignment between explicit and relative recall, with some models better aligned to explicit year prompts and others to relative anchors, and (iii) a confounding effect of refusal behaviour. Our generation and update code can be found at: https://github.com/sg-sy/ChronosAlign. Our dataset can be found at: https://huggingface.co/datasets/sg-sy/ChronosAlign.

Large language models have demonstrated impressive retrieval-augmented capabilities. However, a crucial area remains underexplored: their ability to appropriately adapt responses to the certainty of the retrieved information. It is a limitation with real consequences in high-stakes domains like medicine and finance. We evaluate eight LLMs on their *context-certainty obedience*, measuring how well they adjust responses to match expressed context certainty. Our analysis reveals systematic limitations: LLMs struggle to recall prior knowledge after observing an uncertain context, misinterpret expressed certainties, and overtrust complex contexts. To address these, we propose an interaction strategy combining prior reminders, certainty recalibration, and context simplification. This approach reduces obedience errors by 25% on average, without modifying model weights, demonstrating the efficacy of interaction design in enhancing LLM reliability. Our contributions include a principled evaluation metric, empirical insights into LLMs' uncertainty handling, and a portable strategy to improve context-certainty obedience across diverse LLMs.

We present an encoding method that maps each input token to a randomized sequence of binary values (0s and 1s). By operating at the finest representational granularity and applying compression, this approach reduces the effective vocabulary to just two symbols, yielding a compact, task-agnostic representation. Across eleven main tasks spanning six modalities (human text, genetic/clinical data, programming code, system logs, biological signals, and tabular medical data), it achieves up to two orders of magnitude stronger privacy guarantees under six gradient-based attack settings compared to seven encoder baselines and four defense baselines, including up to 549× improvement on FILM and 62× on TAG. At the same time, it reduces embedding model size by up to 98%, while maintaining competitive accuracy and computational efficiency. It also improves multilingual generalization, achieving up to a 4× increase in accuracy in low-resource settings.

Latent LiDAR pipelines suffer from flying pixels: convolutional VAEs blur sharp LiDAR contours, yielding edge depths that back-project to points floating between surfaces. We identify this as a major, directly correctable decoder bottleneck and introduce CRISP: a pixel-space diffusion decoder with a backbone-agnostic latent adapter, DiT-based denoiser, and support mask predictor. CRISP replaces convolutional decoders commonly inherited from image and video VAEs while keeping the encoder and latent generator fixed. Across KITTI-360, SemanticKITTI, and nuScenes, replacing only the decoder reduces FSVD/FPVD by 50.5% on average across frozen backbones; for generic video VAEs, the reductions reach 71%/74%. On the LiDAR-native LiDM backbone, FRID drops by 71%, with the largest gains at depth discontinuities. Inside a pretrained LiDM world model, the same zero-shot replacement improves FSVD by 15.5%, narrowing the sim-to-real gap. Code and checkpoints will be released upon acceptance.

Large Language Models (LLMs) are presently well assessed by expert–level mathematics and physics benchmarks which focus on theoretical, symbolic reasoning. However, we lack experimental benchmarks that evaluate data analysis in frontier research problems, a capability that future domain–specific foundation models must have. To this end, we present CME–SpectrumBench, an expert–designed benchmark consisting of 190 questions that measures how reliably frontier LLMs analyze research–level spectral scientific data in condensed matter experiments (CME). Using simulated CME spectral data, we prompt models to identify structures from 2D intensity arrays in the face of noise and limited instrumental resolution, a test of dense context reasoning. Models are scored by how accurately their numerical answers approach the ground truth. Under direct query, scores generally pale in comparison to handwritten code due to clear failure modes: models can find simple features but struggle to trace patterns or compute derived quantities, and performance degrades with increased data resolution and noise/convolution levels. LLM performance becomes comparable to handwritten code by allowing tool use (access to a Python interpreter) with/without ReAct prompting, in effect mapping questions onto agentic code generation problems. Our findings show that frontier models can serve as research assistants by interfacing with data through code, but still face difficulties when processing information directly from large datasets — a key barrier future foundation models must overcome.

Quantifying variability in a target population relative to a reference population is central to many scientific and clinical problems (e.g., diseased vs. healthy). Yet, without paired data and in the presence of heterogeneous target variation, existing methods struggle to separate multiple modes of target-specific variation. We propose CASL-VAE, a deep contrastive latent variable model that learns structured latent generative factors from unpaired data. CASL-VAE factorizes variation into continuous common latent factors shared across populations and hierarchical salient latent factors that model target-specific heterogeneity as discrete subtypes and continuous within-subtype variation. Using variational inference, we show how approximate joint likelihood optimization over reference and target domains can be performed using unpaired data, providing a principled basis for paired-sample generation and cross-domain analysis. We validate CASL-VAE on semi-synthetic neuroimaging data, demonstrating improved subtype recovery and paired-sample generation compared to baseline clustering and generative models. We also validate its ability to reveal biologically plausible heterogeneity in Alzheimer's disease. Code will be released upon acceptance.

Synthetic time series generation is critical for data augmentation, privacy-preserving sharing, and simulation. Autoregressive models extend to arbitrary horizons but suffer compounding errors, while diffusion models achieve high fidelity through bidirectional refinement only at fixed lengths. We propose **Horizon Diffusion**, a unified framework that resolves this tension by decomposing generation into variable-length *horizon blocks* produced autoregressively across blocks yet jointly denoised within each block. Two innovations make this hybrid practical: *Horizon-Causal Attention*, a structured mask that simultaneously preserves cross-block causality and within-block bidirectional refinement, and the *Block Size Curriculum*, a deterministic Warmup--Stable--Decay schedule that fluidly transitions training from full-sequence diffusion to block-wise autoregressive generation. Our method consistently outperforms strong baselines on fidelity, diversity, and downstream utility, and remains stable when sequence length scales by $4\times$ beyond training from a single trained model. Code is available at Supplementary Material.

Generating physically buildable brick structures from 3D shapes requires more than geometric reconstruction: the output must also satisfy discrete part constraints and structural stability. Existing brick generation methods either rely on heuristic optimization, which can break down when the target 3D shape does not admit a feasible structure under predefined constraints, or generate brick sequences without explicitly modeling the underlying 3D geometry and assembly relations. In this work, we present BrickAnything, a geometry-conditioned autoregressive framework for generating buildable brick structures from diverse 3D representations. BrickAnything uses point clouds as a unified geometric interface and predicts brick sequences that reconstruct the target shape under assembly constraints. To model structural dependencies among bricks, we introduce a structure-aware tree tokenization, which represents brick structures through local attachment relations. This formulation makes sequence generation more consistent with the physical construction process, and reduces invalid intermediate states. We further introduce preference-based alignment post-training, validity-constrained decoding and adaptive rollback to improve buildability objectives such as stability and geometric fidelity. Extensive experiments demonstrate that BrickAnything produces geometrically faithful and physically realizable brick structures, and that the proposed tokenization effectively reduces rollback and regeneration compared with conventional ordering strategies.

Tabular data synthesis aims to generate high-quality data while preserving privacy. However, we find that existing tabular generative models exhibit a clear tradeoff in the small-data regime: improving data quality typically comes at the cost of increased memorization of training samples, thereby weakening privacy protection. This tradeoff arises because small training sets make it difficult for dataset-specific generative models to distinguish generalizable structure from sample-specific patterns. To address this, we propose DiffICL, which formulates tabular data generation as an in-context learning problem. Instead of fitting each dataset from scratch, DiffICL leverages pretrained structural priors learned from a large collection of datasets, enabling it to infer data distributions from limited context rather than memorizing individual samples. We evaluate DiffICL on 14 real-world datasets. Results show that DiffICL improves both data quality and privacy, and generates synthetic data that provides effective data augmentation. Our findings suggest that the quality–privacy tradeoff can be improved through better training paradigms.

Reinforcement learning (RL) has emerged as a paradigm for fine-tuning large-scale generative models, such as diffusion and flow models, to align with complex human preferences and user-specified tasks. A fundamental limitation remains *the curse of diversity collapse*, where the objective formulation and optimization landscape inherently collapse the policy to a Dirac delta distribution. To address this challenge, we propose **DRIFT** (**D**ive**R**sity-**I**ncentivized Reinforcement **F**ine-**T**uning for Versatile Image Generation), an innovative framework that systematically incentivizes output diversity throughout the on-policy fine-tuning process, reconciling strong task alignment with high generation diversity to enhance versatility essential for applications that demand diverse candidate generations. We approach the problem across three representative perspectives: i) **sampling** a reward-concentrated subset that filters out reward outliers to prevent premature collapse; ii) **prompting** with stochastic variations to expand the conditioning space, and iii) **optimization** of the intra-group diversity with a potential-based reward shaping mechanism. Experimental results show that DRIFT exhibits clear Pareto dominance in task alignment and generation diversity, achieving 7.19\%$\sim$93.40\% higher diversity at matched alignment and 13.23\%$\sim$60.13\% higher alignment at matched diversity.

Recent advancements in generative models have increasingly leveraged self-supervised visual representations to guide the synthesis process, significantly improving generation quality and semantic consistency. However, the reverse paradigm of harnessing the generative process to enhance visual representations remains largely underexplored. In this paper, we investigate the semantic properties of class tokens synthesized by generative models. We observe that generative models equipped with representation entanglement can generate class tokens that exhibit stronger discriminative capabilities than those extracted from the original pretrained visual models. Motivated by this observation, we propose a completely new Generation-to-Perception Knowledge Distillation (GPKD) framework, where our method generates class tokens as teacher signals to instill global semantics into the student model. To prevent the degradation of local details, we further incorporate a new masked patch-level distillation objective. This dual distillation strategy enhances global representations while mitigating the forgetting of local details, thereby producing more robust representations. Extensive experiments demonstrate that GPKD obtains consistent improvements across various downstream tasks compared with the base visual encoder, achieving a gain of more than 2\% in $k$-NN accuracy on ImageNet-1K.

Autoregressive graph generation is commonly formulated by linearizing a graph into a sequence via a flat walk over its nodes and edges. While effective for small molecular graphs, such representations do not scale gracefully to large, structurally complex biological graphs, where higher-order organization is both dense and functionally important. To address this limitation, we introduce a hierarchical graph abstraction together with a coarse-to-fine autoregressive pipeline that separates coarsening, tokenization, and decoding, and we study sequence constructions that expose hierarchy in the tokenization. Concretely, we compare a flat representation with two hierarchical alternatives: one that explicitly factorizes communities and their interactions, and another that induces hierarchy through a depth-first traversal. Across eight benchmarks, differences are modest on simpler domains but become pronounced on larger, more structurally complex settings such as cyclic peptides, proteins, and hard conditional-generation tasks. In these regimes, flat representations degrade in validity or distributional fidelity, while the traversal-based hierarchical representation is consistently more reliable; the explicitly factorized variant is generally weaker, suggesting that how hierarchy is exposed in the sequence matters. Finally, the same coarse-to-fine representation naturally enables motif-conditioned generation without architectural changes: on larger and more structurally complex graphs, conditioning on higher-level prefixes yields strong motif retention together with high validity, uniqueness, and novelty, whereas flat representations can exhibit severe mode collapse under comparable constraints.

Outliers are essential for evaluating and improving the robustness of machine learning systems, especially when future distributions may differ significantly from historical training data. In high-stakes applications, robustness often depends on rare cases that finite datasets fail to capture, making simple resampling or perturbation insufficient for stress scenario generation. Existing outlier synthesis methods typically rely on sparse neighborhoods, low support latent regions, or classifier boundary crossings, which can be heuristic, unstable, and tied to specific modalities or architectures. We therefore propose Sinkhorn Boundary Outlier Generation (SBOG), a structured framework for latent-space outlier generation that couples Sinkhorn optimal transport geometry with distributionally robust boundary modeling. The resulting Sinkhorn-induced support cost guides the sampler toward weakly supported boundary regions, while semantic constraints prevent uncontrolled drift from the intended context, yielding controlled deviations from the in-distribution reference measure rather than arbitrary sparse-region samples. Experiments on time series anomaly generation and image outlier synthesis show that our framework produces informative, semantically controlled outliers and improves downstream robustness evaluation across modalities, providing a foundation for stress scenario generation beyond empirical support.

Structured generation remains a critical bottleneck for Multimodal Large Language Models (MLLMs). Current post-training paradigms struggle to resolve this: Supervised Fine-Tuning (SFT) hits a rigid ceiling, while scalar-reward Reinforcement Learning (e.g., DPO, GRPO, SimPO) suffers from a policy-level signal gap. Compressing long routing trajectories into sparse signals induces a short-completion bias and traps RL near the SFT baseline, whereas vanilla self-distillation actively regresses. To systematically quantify this joint visual-structural-relational reasoning, we introduce OracleGraph, a 10,000-page 2.5D historical document benchmark featuring a 12-dimensional diagnostic VQA suite and a structured-hallucination taxonomy. To overcome these optimization pathologies, we propose PRISM, a Policy-Reward Integrated Self-distillation framework. PRISM leverages multimodal information asymmetry via a Hindsight Teacher guided by a Diagnostic Graph Report (DGR). By synergizing Softmax Reward-Weighted Aggregation (preserving Graph-F1 rankings) with a Length-Normalized Auxiliary Preference Loss, PRISM explicitly neutralizes catastrophic truncation, yielding a $+3.81$pp Graph Reward gain and a $+2.3$pp schema-parsing improvement over SDPO ($p < 0.001$). While PRISM's nominal $+1.02$pp mean gain over SFT is not statistically significant ($p = 0.12$), it drastically stabilizes optimization, achieving $2.4\times$ lower cross-seed variance. Crucially, on a cross-book out-of-distribution (OOD) probe, PRISM's stability advantage amplifies to a $14\times$ variance reduction over SFT, confirming robust structural stabilization. Code and datasets are available at https://anonymous.4open.science/r/PRISM2026.

As AI systems are deployed in open-ended, high-stakes domains, a critical behavioral dimension remains unmeasured: whether models differ systematically in how they translate perceived risk into action. We introduce a cross-domain evaluation framework that isolates and quantifies \emph{risk attitude} in large language models (LLMs) by decoupling contextual belief ($B_C$, a model's perceived danger level given situational context) from categorical risk decision ($R_D$, the action chosen in response to that belief). Unlike existing capability benchmarks, which assess factual accuracy but do not probe the belief-to-decision mapping, this framework directly targets the disposition governing whether an agent acts cautiously or aggressively under identical levels of perceived danger. We applied the framework to six frontier LLMs and 100 human participants across spatial navigation, clinical triage, and financial allocation tasks, and identified two qualitatively distinct behavioral profiles. Five models satisfied both reliability criteria (Contextual Belief Consistency and Risk Decision Consistency) across all conditions and tasks. These models showed strong measurement reliability with stable belief formation and belief-to-decision mappings, and exhibited stable, trait-level cross-domain risk attitudes that were preserved across all three tasks (Kendall's $W=1.00$, $p=0.017$). One model, Grok~4, failed both criteria: its belief formation was unstable in Drone Navigation Control task and its decision mapping was inconsistent in Clinical Triage Decision task, yielding task-specific rather than trait-level risk behavior. Across all six LLMs, risk profiles converged toward a restricted region of the broader human risk-attitude distribution, suggesting that alignment training constrains models toward a narrow behavioral consensus. These results demonstrate that the framework reliably measures risk attitude as a stable, model-specific behavioral dimension and can serve as a diagnostic tool for pre-deployment assessment by distinguishing models with coherent risk personalities from those with domain-contingent risk postures.

Conditional generators provide a natural tool for controllable generation, including settings where the desired condition is a new composition of observed attributes or experimental factors. In many applications, especially in scientific domains, such models are attractive to explore conditions for which real samples are rare, expensive, or not yet observed. However, this creates a circularity for evaluation: standard conditional quality metrics require a reference target distribution, but in the extrapolative regime that distribution is unavailable by definition. We address this problem with a post-hoc, per-sample trust score for assessing conditional samples using only the training distribution. The score combines two estimable quantities: global realism, measuring compatibility with the real data manifold, and attribute-wise faithfulness, measuring whether a sample is closer to the requested attributes than to plausible alternatives. We show that the score can recover meaningful comparisons across extrapolated generations, under a mild coverage condition on the observed attributes. These comparisons enable effective filtering, ranking, and abstention of generations and can be used directly on off-the-shelf pretrained models. In biological imaging, selected samples preserve real morphological structure better and improve downstream predictive performance, while similar gains are observed on controlled vision benchmarks. Finally, we show how the score can be applied during generation, enabling abstention before full decoding.

Today, we improve models by training and evaluating them on problems at the frontier of their abilities. Creating such problems is itself a demanding task, requiring the ability to probe model limits and generalize beyond existing question distributions. It also means placing problems at a precise difficulty level, which requires understanding what it takes to solve them. In short, generating problems calibrated to a model's current frontier demands capability beyond it, an increasingly burdensome constraint as models improve. Our key insight is that we can leverage this constraint to our advantage: a model that can generate problems consistently calibrated to a given frontier must possess capability beyond it. Accordingly, we present Ask-E, an environment that benchmarks and trains models on their ability to write questions at a given skill level, rather than answer them. Concretely, we define target skill levels as ranges bounded by the capabilities of two existing language models. A generated question is successfully calibrated if exactly one of the two models can solve it, placing it precisely within the target range and differentiating the capabilities of these models. Ask-E serves both as a benchmark and a training environment, where models generate problems calibrated to a variety of skill levels. We find that even frontier models achieve below 50\% calibration on the benchmark, leaving significant headroom to measure future progress. We also show that training on this environment leads to improvements across a number of downstream math benchmarks even with no new math data, no interaction with stronger models, and no correctness-based reward.

A bottleneck in learning to understand articulated 3D objects is the lack of large and diverse datasets. In this paper, we propose to leverage large language models (LLMs) to close this gap and generate articulated assets at scale. We reduce the problem of generating an articulated 3D asset to that of writing a program that builds it. We then introduce a new agentic system, Articraft, that writes such programs automatically. We design a programmatic interface and harness to help the LLM do so effectively. The LLM writes code against a domain-specific SDK for defining parts, composing geometry, specifying joints, and writing tests to validate the resulting assets. The harness exposes a restricted workspace and interface to the LLM, validates the resulting assets, and returns structured feedback. In this way, the LLM is not distracted by details such as authoring a URDF file or managing a complex software environment. We show that this produces higher-quality assets than both state-of-the-art articulated-asset generators and general-purpose coding agents. Using Articraft, we build Articraft-10K, a curated dataset of over 10K articulated assets spanning 245 categories, and show its utility both for training models of articulated assets and in downstream applications such as robotics simulation and virtual reality.