NeurIPS 2026 论文列表

Continuous-time dynamic graphs model evolving systems with irregularly timed interactions, where predicting future links requires reasoning over temporal evolution, local topology, and historical relation patterns. Existing memory-based and sequence-based methods capture temporal dependencies effectively, but they often organize historical interactions as node memories or serialized neighbor sequences. As a result, they lack explicit analysis of the interaction structure around candidate nodes which prevents them from explicitly modeling local topological patterns of candidate nodes at inference time. They also lack explicit causal statistical memory for activity, recency, and repeated pairwise interactions. Motivated by these drawbacks, we propose S3Former, a temporal graph framework that jointly models sequential dynamics, shared pair-centered structure, and online statistical memory. For each candidate interaction, S3Former encodes long-term and short-term historical sequences, constructs a history-induced shared pair subgraph around the two endpoints, and computes node-level and pair-level statistics from past events only. A two-level context-aware fusion mechanism further combines these signals: NodeCCF learns reliable endpoint representations, while PairCCF performs candidate-specific relation correction using explicit pair memory. Experiments on 10 dynamic graph benchmarks show that S3Former achieves state-of-the-art performance on most datasets in both transductive and inductive link prediction. Ablation studies confirm the effectiveness of shared pair-subgraph modeling, online statistical memory, and hierarchical fusion.

Reinforcement learning from human feedback (RLHF) with preference-based reward models often exhibits unstable training dynamics. A key contributing factor is that standard RLHF relies on a single sequence-level scalar reward, which is propagated to token-level policy updates and leaves credit assignment within a response inherently ambiguous. Recent work has attempted to address this issue by refining rewards into denser token-level supervision, often relying on the implicit assumption that finer-grained credit assignment improves optimization. We argue that this assumption is incomplete: when preference signals are noisy and only defined at the response level, overly fine-grained reward refinement can amplify reward uncertainty and destabilize learning. To address this problem, we propose a granularity-aware principle for hierarchical credit assignment, emphasizing stability-oriented reward design rather than maximal allocation precision. Under this principle, sentences serve as a natural intermediate granularity, balancing semantic coherence with robustness to token-level noise. Guided by this view, we introduce S2T-RLHF. This sentence-to-token reward decomposition framework first allocates sequence-level preference rewards across sentences and then applies bounded token-level refinement within each sentence, without reward-model retraining or token-level supervision. Experiments across multiple datasets and optimization settings show that S2T-RLHF improves training stability and robustness while maintaining competitive preference alignment.

Compositional implicit surface representations model scenes as collections of objects, each encoded by a Signed Distance Field (SDF). A fundamental limitation of this approach is that multiple SDFs can produce geometries that interpenetrate, violating physical plausibility. Existing mitigation strategies rely on soft penalty terms that reduce but do not eliminate intersections, and require careful loss weighting. To truly prevent interpenetration, we propose a hard constraint on vector-valued SDFs and introduce S2MDF, a lightweight plug-and-play module that enforces the constraint on any object-compositional SDF representation without architectural modifications. It introduces \fs{negligible} computational overhead and is compatible with linearly-interpolated standard meshing algorithms such as Marching Cubes. It can be applied during training or as a post-processing step. Experiments on multiple state-of-the-art compositional methods show that S2MDF reduces intersections to numerical precision while preserving reconstruction quality, outperforming existing mitigation strategies.

In recent years, the state-of-the-art in unsupervised video instance segmentation has heavily relied on synthetic video data, generated from object-centric image datasets such as ImageNet. However, video synthesis by artificially shifting and scaling image instance masks fails to accurately model realistic instance motion in videos, such as perspective changes, movement by parts of one or multiple instances, or camera motion. To tackle this issue, we propose an unsupervised video instance segmentation model trained exclusively on real video data. We start from unsupervised instance segmentation masks on individual video frames. However, single-frame segmentations exhibit temporal noise and their quality varies through the video. Therefore, we establish temporal coherence by identifying high-quality keymasks in the video by leveraging deep motion priors. The sparse keymask pseudo-annotations are then used to train a segmentation model for implicit mask propagation, for which we propose a Sparse-To-Dense Distillation approach aided by a Temporal DropLoss. After training the final model on the resulting dense labelset, our approach outperforms the current state-of-the-art across various benchmarks.

Calibrating large language models (LLMs) in open-ended generation is uniquely challenging because many distinct token sequences can express the same underlying meaning. Prior calibration techniques target either fixed-set classification confidence or the binary correctness of individual strings, making them inherently ill-suited for the dynamic, multi-string nature of open-ended semantic outcomes. To bridge this gap, we introduce S-EDL, a novel evidential method that natively optimizes LLMs for semantic calibration. By eliciting evidence from the sequence likelihoods of the model itself, S-EDL constructs a differentiable Dirichlet prior over prompt-specific semantic classes. Optimizing the evidential loss under this prior yields a calibration-aware training signal over variable semantic classes, completely bypassing the need for fixed multiple-choice options. Evaluations across four open-ended benchmarks and three models demonstrate that S-EDL substantially reduces semantic calibration error while improving accuracy. By aligning generative likelihoods with semantic correctness, this work establishes a framework for deploying trustworthy LLMs in complex, open-ended applications.

Graph Neural Networks (GNNs) face a fundamental dichotomy between expressiveness and scalability. Recent spectral and transformer-based models approach universal approximation capabilities but rely on computationally intensive global operators that scale poorly to large graphs. Conversely, scalable approaches often compromise structural fidelity through sampling or decoupling, resulting in incomplete structural acquisition. We identify that this trade-off stems from a homogeneous treatment of graph topology, where uniform computational complexity is applied to heterogeneous structures. We propose a paradigm shift towards Hierarchical Structural Acquisition and introduce S\&P (Scalable \& Powerful), a framework grounded in Fusion Frame Theory that aligns the operator with the intrinsic hierarchy of the data. S\&P decomposes the global operator into intra-component and inter-component, and we prove that this design preserves universal spectral filtering capacity for non-degenerate inputs while remaining numerically stable and linear in complexity. Experiments on 14 datasets show that S\&P achieves state-of-the-art accuracy, bridging the gap between scalability and expressiveness. Our code is available at https://anonymous.4open.science/r/HierarchicalSP.

While dataset distillation has witnessed significant advances in image classification, its extension to dense prediction tasks such as semantic segmentation is plagued by two core bottlenecks: bi-level optimization-based approaches suffer from prohibitive computational costs stemming from pixel-wise gradient unrolling, whereas proxy-based generative methods merely infuse visual textures into fixed semantic masks derived from real data, thus failing to condense rich semantic knowledge into a compact set of informative, novel scene generations. To address both bottlenecks simultaneously, we propose a novel Sample-Set Reinforcement Learning (S$^2$-RL) framework for generative semantic segmentation dataset distillation (SSDD). Specifically, S$^2$-RL formulates SSDD as a diffusion model based text-to-image generation paradigm, enabling flexible generation of images with informative, novel semantic distributions via a concise text prompt. Furthermore, we fine-tune a diffusion policy via GRPO, leveraging a sample-set dual reward paradigm: for individual samples, it enforces semantic alignment with input text prompts and intra-class feature diversity; for sample sets, it maximizes inter-sample semantic distribution diversity by solving a contextual multi-armed bandit problem. These design choices enable S$^2$-RL to distill large-scale semantic segmentation datasets into a compact set of generated samples that encapsulate diverse, informative semantic knowledge without the need of pixel-wise gradient unrolling. Extensive experiments on the ADE20K and COCO datasets demonstrate that S$^2$-RL achieves substantial and consistent improvements over state-of-the-art baselines, establishing a new benchmark for SSDD.

Chemical reaction-condition optimization --- choosing the catalyst, ligand, solvent, reagent, temperature, time, and atmosphere that jointly maximize yield and stereoselectivity --- is a central, judgement-laden subtask of organic methodology research that large language models are increasingly expected to support. Yet existing chemistry benchmarks evaluate reaction-class labelling, retrosynthesis, or SMILES manipulation, and do not ask models to read a real condition-screening table and pick the best set. We introduce RxnOptBench, a benchmark whose every option and precedent is a real wet-lab entry mined from the optimization tables of organic-methodology papers published in 2025, graded by a continuous relative score that fuses yield with stereoselectivity (ee, dr, rr) so near-correct answers are not collapsed to zero, and equipped with a paired precedents-vs-no-precedents design that isolates in-context use of literature evidence from parametric memorization. Across nine frontier LLMs and three Chemistry LLMs, even the best models leave substantial headroom: chemistry-specialized models fall to the random-baseline floor on multi-axis selection, while open-weight models have closed most of the gap to proprietary frontier models. We release the benchmark, the human-verified extraction pipeline, and the inference and evaluation code.

Medication recommendation requires generating drug combinations that are therapeutically effective while minimizing harmful drug-drug interactions (DDIs). Both objectives are rooted in the combinatorial nature of prescriptions. Existing discriminative methods predict drugs independently, neglecting inter-drug dependencies; autoregressive methods introduce sequential dependencies but impose arbitrary generation orders and accumulate errors. Both paradigms confine DDI mitigation to training-time penalties, offering limited capacity to regulate interactions during inference for individual prescriptions. We reformulate medication recommendation as a discrete diffusion process and propose RxDiff, which leverages iterative denoising for bidirectional and revisable generation and provides a natural interface for dynamic DDI regulation at each step. A clinically grounded dual-guided forward process and an inference-time interaction-aware modulation mechanism are designed to jointly enable RxDiff to achieve consistent accuracy improvements, lower and more individually controlled DDI rates, and robustness to evolving DDI knowledge across MIMIC-III, MIMIC-IV, and a real-world inpatient dataset. Code is available at https://anonymous.4open.science/r/RxDiff-9157.

AI agents are governed by hundreds of natural language criteria---yet existing verifiers cannot efficiently evaluate an agent's output against a large set of such criteria and report which are satisfied, violated, or inapplicable. We introduce the VFM, a tree-attention verifier that encodes the shared context and target text, and scores $N$ natural language criteria in parallel, returning independent per-criterion ternary verdicts. The VFM is pretrained on CriteriaBank, an open corpus of 357K (context, target, criterion, verdict) tuples spanning over 285K distinct criterion strings. A finetuned VFM-4B reaches 88.3\% accuracy on a synthetic governance benchmark, surpassing larger generative judges, and on real insurance-compliance calls it is competitive with GPT-5.4 with synthetic finetuning alone. On the DynaBench multi-criterion benchmark, a finetuned VFM-4B reaches $0.85$ F1 on trace-level failure detection versus DynaGuard-4B's $0.72$; the VFM additionally localizes the violated rule as its top-1 prediction in $98.4\%$ of failing traces, and a top-3 cascade to a 26B Gemma 4 chain-of-thought judge reaches $0.94$ F1. CriteriaBank pretraining improves cross-domain transfer on four additional benchmarks, particularly in the low-data regime. On an H100, VFM-4B evaluates 1000 criteria against a 4K-token context in under 2s at $<$10GB VRAM, making it suitable for runtime verification. We will release CriteriaBank, trained checkpoints, and evaluation code.

Runtime monitoring of autonomous systems traditionally relies on mapping continuous sensor observations to discrete logical propositions defined over low-dimensional state variables. This abstraction breaks down in perception-driven settings, where such mappings require additional learned modules that are often computationally expensive, brittle, and semantically misaligned. In this work, we propose Embedding Temporal Logic (ETL), a temporal logic that performs monitoring directly in learned embedding spaces. ETL defines predicates through distances between observed embeddings and target embeddings derived from reference observations. This formulation allows specifications to capture high-level perceptual concepts, such as similarity to visual goals or avoidance of semantic regions, that are difficult or impossible to express using traditional predicates. By composing these predicates with temporal operators, ETL naturally expresses temporally extended and sequential perceptual behaviors. We introduce ETL monitors for evaluating specifications over bounded embedding traces, along with a conformal calibration procedure that provides reliable and safety-oriented predicate evaluation. We evaluate our approach across multiple manipulation environments to show that ETL achieves strong empirical agreement with ground-truth semantics, including accurate monitoring of temporally composed behaviors.

Genetic Programming (GP) is a search paradigm inspired from natural evolution for the automated discovery of expressions, functions, and computer programs. Cartesian GP (CGP) is a flavor of GP that uses a graph-based model to encode candidate programs, as contrasted to the conventional Tree-based GP (TGP). Since its inception two decades ago, CGP has predominantly been analyzed empirically, thus little is known regarding its theoretical performance guarantees. This paper analyzes CGP for the MAX problem, which has been only rigorously studied for TGP with a proven expected runtime superlinear in the optimal program length $n$. We prove that the expected time for the (1+1) CGP employing common mutation operators to evolve an equivalent optimal of the same output is polylogarithmic in n, specifically at most $O(\log^9{n})$. This is remarkable, as it shows an exponential speedup by switching to CGP. Our results shed light on the benefit and the compactness of the graph-based representation for programs, and on how CGP can navigate its search and fitness spaces efficiently. This is a first proven performance guarantee for CGP on an established benchmark problem. Experiments complement our theoretical findings.

Game balancing is a longstanding challenge requiring repeated playtesting, expert intuition, and extensive manual tuning. We introduce RuleSmith, a framework for automated game balancing that couples multi-agent LLM self-play with Bayesian optimization over a parameterized rule space. As a proof of concept, we build CivMini, a simplified civilization-style game with two asymmetric factions governed by 12 tunable parameters. LLM agents read textual rulebooks and game states to generate legal actions, enabling fast evaluation of balance metrics such as win-rate disparity. To search the rule space efficiently, we use Bayesian optimization with acquisition-based adaptive sampling: candidates with high Expected Improvement receive more evaluation games, while exploratory candidates receive fewer. RuleSmith consistently finds near-balanced configurations and produces interpretable parameter adjustments. It provides a scalable alternative to manual playtesting. Code will be available upon acceptance.

Recent progress in large language models (LLMs) has led to impressive performance across diverse domains. However, their deployment in critical areas such as healthcare, law, and education raises serious concerns regarding the potential generation of harmful content. While reinforcement learning (RL)-based safety alignment methods have been extensively studied, they face persistent challenges, including sparse reward signals, limited interpretability, and limited transferability across domains. In this paper, we introduce Rubric‑Align, a framework that replaces static binary scalar rewards with dynamic, natural‑language evaluation rubrics. Instead of assigning a single reward to each response, Rubric‑Align provides fine‑grained and interpretable feedback, thereby alleviating reward sparsity and improving the transparency of the alignment signal. A key feature of Rubric-Align is its dynamic rubric evolution mechanism. Rather than using fixed reward templates, Rubric-Align periodically refines prompt-specific rubrics based on the current policy behavior, keeping the supervision signal informative and aligned with the model’s evolving failure modes. Experiments on safety benchmarks and vertical-domain settings show that Rubric-Align improves robustness against harmful and jailbreak prompts while largely preserving general capabilities, suggesting that natural-language rubrics provide a transferable interface for adapting safety supervision to new safety subdomains.

Convolutional architectures have emerged as powerful alternatives to Transformers for sequence modeling. The primary advantage is that they offer improved theoretical sequence length complexity by leveraging the Fast Fourier Transform (FFT). However, this theoretical improvement does not always meaningfully land in practice. One critical obstacle is that applying standard FFTs is not amenable to the large-scale training pipeline wherein data is packed from different sources into a single sequence for hardware efficiency. Indeed, standard FFT algorithms are not easily amenable to document packing. Existing workarounds suffer from severe inefficiencies, crippling the practical performance of convolutional architectures. We close this gap with RubiConv, a novel algorithm for performing hardware-efficient, boundary-respecting convolutions on packed sequences. Extensive experiments show that RubiConv achieves significant speedups over both attention and standard FFT-based baselines. This work makes the theoretical efficiency of long convolutional models a practical reality for large-scale, real-world data packing.

We consider the conversion of musical recordings into human-readable sheet music annotated with timestamps. Such output lets a listener clearly visualize *rubato* (temporally expressive playing), a learner diagnose ensemble precision and timing choices against the written music, and a musicology scholar compare performance styles across recordings of the same work. We introduce (1) a prompt-conditioned encoder--decoder model, named Rubato, trained to output (2) a new textual representation for polyphonic music, named InterMo, which we designed for compatibility with sequence-to-sequence training. Our experiments demonstrate that Rubato produces timestamped piano sheet music from audio with higher notational accuracy than the best existing approaches, which are based on cascades. We find that even if the cascade is given ground-truth MIDI instead of audio, Rubato performs better, suggesting that the ceiling of existing approaches is primarily representational, not acoustic. Further, because Rubato is trained on several related tasks (with prompts), it competes with or outperforms the best single-task systems on related but simpler tasks like MIDI note grounding and beat/downbeat detection. We will release the model and code on publication, and an anonymized demo is available at https://rubato-transcription.github.io.

Irregular multivariate time series (IMTS) are sampled at non-uniform timestamps and asynchronous across channels, their dependencies are shaped by time gaps, local ordering, and channel-specific sampling patterns. Building a faithful attention mechanism for IMTS exposes two limitations of existing work. First, current irregular-time attention methods typically regularize raw inputs into interpolated, aligned, or continuous-time-embedded forms before applying attention, which blurs exactly these irregular cues that determine how two observations relate. Second, beyond representation, standard dot-product attention scores pairs through learned token projections with no intrinsic tie to the shape of the underlying series, and an attention that does reflect this shape becomes costly to compute in high-channel IMTS. We propose Rubato, which reads two views directly from the raw irregular input: per-channel local dynamics, and a path signature that summarizes the joint multi-channel series. Attention in Rubato then scores pairs by a signature-kernel measure of series similarity rather than by a generic dot product, and a structured random projection (SORF) keeps this comparison affordable when the channel count is large. We prove that the structured projection introduces only a controlled bias that vanishes as the number of channels grows, and experiments on multiple IMTS benchmarks show that Rubato consistently outperforms strong baselines.

A two-branch routed regressor realizes exactly the function class of ordinary quadratic regression. Because routing does not enlarge the observable function class here, the routed model differs from quadratic regression only through the prior induced by routed coordinates. We compute this induced prior in closed form and show that fiber integration along the routing map creates a logarithmically singular density on the linear submodel. The induced posterior over quadratic coefficients then coincides exactly with the quadratic-regression posterior under the pushed-forward prior, isolating the role of prior geometry in this proxy model. For compactly supported priors on linear truth ($q_2=0$), the support-relative global real log canonical threshold (RLCT) is $(3/2,2)$ when the support reaches the collapsed stratum and $(3/2,1)$ when it avoids it; under the full-support Gaussian-coordinate prior, the global RLCT is $(3/2,2)$. Against smooth coefficient-space baselines with the same known noise variance on linear truth, this singular-versus-smooth prior comparison yields a rigorous $\log\log n$ Bayes-factor advantage. The same multiplicity-$2$ product singularity transfers locally to sigmoid gates on linear truth and extends locally to $d$-dimensional inputs.

LLM routing aims to choose, for each prompt, which model in a portfolio is most likely to answer correctly. This only makes sense when the benchmark contains enough prompt-specific variation for different models to be best on different inputs. On coarse-scored LLM benchmarks, however, many models often tie for the best score, and the single best model may already leave little room for improvement. We therefore propose a routeability-first audit, instantiated as RAP and RouteabilityBench, a reviewer-runnable evaluation package. Across four benchmarks and 66 LLMs, generic routing enhancements such as larger embedding sets, dimensionality reduction, selective abstention, clustering, and stronger regressors do not consistently outperform the single best model. The clearest positive evidence is concentrated in portfolio-dependent Omni-MATH settings, while GPQA, MMLU-Pro, and IFEval show different ways in which routing can remain hard or predictor-sensitive. Our practical recommendation is that routing gains should be reported together with routeability diagnostics, tied-best analysis, portfolio construction details, and family-corrected statistical tests.