NeurIPS 2026 Papers

AI-generated image detection has become an important problem in media forensics as modern generative models produce increasingly realistic images. Recent CLIP-based detectors show strong generalization ability, but CLIP image features entangle semantic content with forensic cues. Since semantic content is not an intrinsic generation trace, relying on it can introduce semantic shortcuts and unstable performance under unseen generator shifts. In this paper, we propose SAGE, a Semantic-Agnostic Image Embedding framework for generalized AI-generated image detection. SAGE constructs paired triplets of COCO images, SDXL-reconstructed images, and COCO captions so that real and fake images share the same caption-level semantics. It then suppresses semantic information by suppressing the semantic direction provided by CLIP text embeddings from CLIP image embeddings. To enable caption-free inference, SAGE learns a semantic anchor that approximates the role of paired text embeddings at test time. In addition, SAGE adopts a SoftTriple-style sub-center classifier to model intra-class variation in real and fake images, yielding a more stable authentication geometry across diverse generators. Experiments on CommunityForensics demonstrate that SAGE achieves competitive detection performance while substantially reducing generator-wise performance variation. Further analyses show that SAGE effectively reduces semantic dependence and forms a clearer real/fake feature geometry than strong baselines.

Retrieval-Augmented Generation (RAG) mitigates Large Language Model (LLM) hallucinations by grounding generation in external knowledge. Although structure-augmented RAG methods improve multi-hop reasoning, they incur high indexing costs and degrade on simple queries. We argue that this robustness gap is driven by capacity bottlenecks in fixed-dimensional inner-product scoring. As corpora grow, semantically close passages create local regions where a base scorer cannot maintain sufficient separability. Reorganizing documents into trees or graphs can expose or partially mitigate this issue, but it does not by itself provide a stronger local scoring function. We propose Semantic Ambiguity Guided Capacity Expansion (SAGE), a lightweight RAG framework that detects such regions using document-side Local Separability Deficit and expands capacity only where needed. SAGE builds a two-layer semantic index, derives atomic query views from corpus passages, and calibrates a parameter-efficient hypernetwork to generate the local Ambiguity-Conditioned Scorers for selected nodes. Extensive experiments show that SAGE improves retrieval and QA performance over dense retrievers and structure-augmented baselines, achieving a better balance between single-hop, multi-hop retrieval accuracy, and robust scalability. Anonymous Code: https://anonymous.4open.science/r/SAGE-1676.

Long-horizon reasoning remains a central challenge for large language models (LLMs) under sparse-reward regimes. We argue that this brittleness arises from two biases induced by complex reasoning spaces: an exploration bias, where models are drawn toward locally plausible but structurally unstable branches, and a compounding bias, where small local deviations accumulate across depth and suppress rare rewards. We introduce Symbolic Closure Analysis (SCA) as a theoretical lens characterizing how branching structures and sparse rewards induce these biases in long-horizon reasoning with local admissibility, and as a design principle for structural priors in less formal reasoning tasks. Motivated by this analysis, we propose \model{} (\textbf{S}tructural \textbf{A}dmissibility-\textbf{G}uided \textbf{E}xploration), a unified framework that injects structural guidance to alleviate exploration bias and compounding bias in long-horizon reasoning. \model{} combines two complementary structural dimensions: algebraic sparsification, which projects locally admissible candidates onto operator-indexed algebraic subspaces to suppress spurious branching and mitigate exploration bias, and hyperbolic structural guidance, which embeds reasoning states into a negatively curved space to provide dense depth-wise signals and mitigate compounding bias. Across 12 benchmarks and 7 model families, \model{} outperforms competitive baselines. In particular, \model{} achieves up to an 8-fold improvement on the Andrews-Curtis problem, an open real-world long-horizon task. Code is available at: \url{https://anonymous.4open.science/r/SAGE-Long-Horizon-Reasoning-AD70}.

Linear Temporal Logic (LTL) provides a rigorous framework for specifying long-horizon robotic tasks, yet existing approaches face a trade-off: model-based synthesis relies on accurate labeled transition systems, whereas learning-based methods often require online interaction, task-specific rewards, or specification-conditioned training. We study LTL-specified robotic planning and execution in a stricter offline, model-free setting, where the agent is given only fixed, task-agnostic trajectory fragments, with no dynamics model, task demonstrations, or online data collection. To address this setting, we propose SAGAS, a framework that combines the compositionality of symbolic synthesis with the data-driven reachability structure learned from offline trajectories. SAGAS first learns a reusable latent reachability graph and a frozen goal-conditioned executor from fragmented offline data. For each new LTL formula, it performs task-time semantic graph augmentation to ground state-defined propositions on the learned graph, and applies B\"uchi product search to synthesize a cost-aware accepting prefix--suffix waypoint plan executed by the frozen executor. By shifting formula-specific reasoning from policy learning to test-time graph augmentation and symbolic search, SAGAS enables zero-shot generalization to unseen, data-supported LTL specifications without task-specific reward design, policy retraining, or online interaction. Experiments on LTL task suites constructed from OGBench locomotion domains show that this design produces executable and cost-efficient prefix--suffix behaviors for diverse unseen LTL tasks from fragmented offline data.

Circuit design for analog integrated circuits (ICs) is challenging because circuit topology, device sizing, and circuit performance are tightly coupled. Existing large language model (LLM)-based methods either rely on inference-time correction around frozen models or train on limited circuit types without directly using simulation outcomes as training signals. A key bottleneck is that existing datasets do not provide sufficient task information for training LLMs on end-to-end specification-conditioned design. To fill this gap, we first construct a large-scale simulation-grounded dataset with 8,626 design tasks across 10 different types of analog circuits, where each task includes a textual description, labeled I/O ports, loading condition, target specifications, a testbench, and a reference netlist. Using this dataset, we present SAFTAC, a simulation-augmented fine-tuning framework that trains LLMs to generate and revise analog circuit design. SAFTAC combines three-stage supervised fine-tuning, which progressively builds the capabilities required for analog circuit design and feedback-guided correction, with simulation feedback-augmented reinforcement fine-tuning, which further optimizes models using simulation-grounded rewards. We evaluate SAFTAC under single-pass generation and two-pass generation with simulation feedback, showing improvements over the strongest closed-source LLM by 15.9\% and 7.8\%, respectively.

Single-view 3D hair reconstruction has progressed rapidly, but many methods optimize for visual plausibility rather than producing strand assets that can be directly used in grooming, editing, or simulation pipelines. We propose SAFE-Hair, a framework that reconstructs explicit strand grooms from a single portrait by decoding hair from persistent follicles in a canonical scalp-UV domain. Given a fitted template head, SAFE-Hair projects self-supervised image features onto the scalp, uses a conditional Rectified Flow model to generate latent scalp fields, and decodes occupancy, segment directions, length allocation, and total length at a fixed set of scalp follicles. This representation enforces scalp-rooted strand identities by construction and enables direct export with follicle IDs and guide-family metadata. We further introduce attachment, collision, and bending priors to improve geometric validity without per-subject test-time optimization. To evaluate both reconstruction fidelity and asset usability, we introduce HairBench-3D, a benchmark built from public 3D hair assets with standardized alignment, rendering, resampling, and metrics for geometry, direction consistency, invisible-region completion, silhouette agreement, and collision. SAFE-Hair improves Chamfer distance from 3.74 mm to 3.28 mm, F-score from 77.9 to 81.7, invisible-region F-score from 66.1 to 69.8, and penetration ratio from 4.8% to 3.9% over the strongest baseline.

The difficulty of factual error correction (FEC) is not only how to repair false claims, but how to construct errors that meaningfully test repair. Existing FEC data construction methods often follow a static corruption view: they mask spans in false claims or inject errors into supported claims, but do not explicitly target the boundary of what current evidence-based correctors can repair. We introduce the notion of a \emph{repair frontier}: factual errors that are evidence-grounded, close enough to the source claim to admit a clear correction, and resistant to current correctors. We propose \textsc{SAFE-FEC}, a semantically constrained adversarial frontier-evolution framework for constructing such examples. Starting from evidence-supported claims, SAFE-FEC generates mutations from multiple factual-error perspectives, refines them through cross-perspective critique, selects or composes stronger candidates, filters semantic drift, and accepts only candidates that survive repeated corrector-in-the-loop repair attempts. This turns FEC data construction from one-shot error injection into correction-aware frontier search. Experiments on FECData, HoVer, and FEVEROUS show that SAFE-FEC consistently lowers correction performance for both LLM-based and FEC-specific correctors, especially in multi-hop and structured-evidence settings. Quality evaluation and ablations further suggest that these failures arise from plausible, semantically anchored, evidence-grounded errors rather than invalid hard negatives.

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.