NeurIPS 2026 论文列表

Generative recommendation (GR) aligns with advances in generative AI by casting next-item prediction as token-level generation rather than score-based ranking. Most GR methods adopt a two-stage pipeline: (i) \textit{item tokenization}, which maps each item to a sequence of discrete, hierarchically organized tokens; and (ii) \textit{autoregressive generation}, which predicts the next item's tokens conditioned on the tokens of user's interaction history. Although hierarchical tokenization induces a prefix tree (trie) over items, standard autoregressive modeling with conventional Transformers often flattens item tokens into a linear stream and overlooks the underlying topology. To address this, we propose TrieRec, a trie-aware generative recommendation method that augments Transformers with structural inductive biases via two positional encodings. First, a \textit{trie-aware absolute positional encoding} aggregates a token's (node's) local structural context (\eg depth, ancestors, and descendants) into the token representation. Second, a \textit{topology-aware relative positional encoding} injects pairwise structural relations into self-attention to capture topology-induced semantic relatedness. TrieRec is also model-agnostic, efficient, and hyperparameter-free. In our experiments, we implement TrieRec within three representative GR backbones, achieving notably improvements of 8.83\% on average across four real-world datasets.

Predicting gene expression from H\&E-stained histology images offers a scalable alternative to costly spatial transcriptomics, yet most existing methods operate at the spot level, where signals from multiple cells are aggregated and critical cellular heterogeneity is obscured. Extending this paradigm to single-cell resolution is non-trivial. Naively applying pathology foundation models faces a scale mismatch: their patch-level representations mix multiple cells, whereas per-cell cropping or resizing distorts morphology and removes local context. Conversely, segmentation-based models without strong pretrained visual encoders often lack the morphological representation capacity needed for accurate molecular prediction and inherit errors from imperfect cell boundary masks. Here, we present CELLO, an efficient end-to-end framework that performs a single pathology foundation model forward pass per image and uses grid sampling to extract location-specific features for all cells simultaneously. We further introduce a distance-decay cross-attention module that refines each cell representation using spatially biased local morphological context. Using 52 paired Xenium--WSI samples spanning 12 organs and approximately 10M cells, CELLO achieves state-of-the-art performance in both in-distribution and out-of-distribution settings while delivering at least a 7$\times$ inference speedup over DeepSpot2Cell. Our work establishes a scalable foundation for single-cell gene expression prediction from H\&E images.

Vision-language models (VLMs) are increasingly used as automated judges for multimodal and embodied tasks, yet aggregate accuracy or consistency alone does not reveal whether a judge changes its verdict for the right reason. We propose State-Conditional Invariance (SCI), a reliability principle requiring a judge to remain stable under semantics-preserving presentation changes while responding to causal interventions that change the task outcome. We instantiate SCI in GridWM-Judge, a simulator-grounded diagnostic benchmark built from deterministic MiniGrid trajectories with aligned Full, evidence-removal, and counterfactual variants, plus presentation and representation probes. Across five diagnostic tasks, GridWM-Judge tests local perception, action-conditioned transitions, presentation stability, representation exchangeability, and Full-CF causal discrimination. Evaluating current VLM judges reveals separable failures, including presentation sensitivity, representation fragility, causal misgrounding, action-insensitive heuristics, and stability traps. These results show that reliable VLM-as-a-judge evaluation requires joint reporting of correctness, presentation invariance, and causal sensitivity rather than a single accuracy or consistency score.

LiDAR is a critical sensor for autonomous driving and robotics, yet it remains vulnerable to adverse conditions such as fog, rain, transparent objects, and low-reflectance surfaces. Full-waveform LiDAR (FWL) addresses these limitations by capturing the complete return waveform as a histogram, preserving rich reflection characteristics including multi-path echoes and weak signals. While recent Transformer-based approaches have demonstrated promise on FWL data, two fundamental bottlenecks remain: high computational cost from redundant tokens in low-intensity background regions, and limited generalization due to scarce annotated training data. We address both bottlenecks by exploiting the physical structure inherent to FWL data. First, we propose FWL-ToPM, a token pruning and merging mechanism that leverages intensity distributions to selectively reduce tokens while retaining critical waveform content. Second, we introduce FWLAug, a physically consistent data augmentation framework that preserves time-of-flight waveform structure and frustum geometry to improve generalization across diverse environments. Evaluated on the Ghost-FWL benchmark, FWL-ToPM achieves over 8$\times$ speedup at real-time throughput alongside a nearly 9-point F1 gain, establishing the first real-time FWL Transformer that simultaneously improves accuracy. FWLAug further improves generalization to both standard and out-of-distribution environments. Together, these methods push FWL-based perception toward practical deployment.

Lifelong person re-identification (LReID) requires models to continuously learn from sequentially arriving domains while retaining discriminative power for previously seen identities. A key challenge is to prevent catastrophic forgetting without access to old data, especially under exemplar-free constraints. While flat-minima optimization has shown promise in continual learning, we identify a gradient conflict that limits the effectiveness of standard Sharpness-Aware Minimization (SAM) in LReID. The ReID loss gradient dominates the perturbation direction, causing the sharpness of the distillation loss to be underestimated, which hinders the flattening of the landscape necessary for knowledge retention. To resolve this conflict, we propose a framework that unifies selective flatness-aware optimization, dual-model training, and weight-space interpolation. Specifically, we maintain two models per task: a stability model whose SAM perturbation is computed solely from the distillation loss, and a plasticity model optimized for the current domain. By decoupling the perturbation objectives, our selective SAM achieves more targeted sharpness exploration along the distillation landscape, guiding the stability model toward flatter and robust regions. After training, the two models are fused via weight-space interpolation, and we provide a theoretical bound showing that flatter stability solutions tighten the interpolation bound and reduce forgetting during fusion. Our method is lightweight, modular, and readily compatible with existing LReID frameworks. Experimental results demonstrate that the proposed method consistently improves the performance of LReID in terms of both knowledge retention and generalization to unseen domains.

Vision-language models have shown strong performance, but they often generalize poorly to specialized domains. While semi-supervised vision-language learning mitigates this limitation by leveraging a small set of labeled image-text pairs together with abundant unlabeled images, existing methods remain fundamentally pairwise and fail to model the global structure of multimodal representation manifolds. Existing topology-based alignment methods rely on persistence diagram matching, which neither guarantees geometric alignment nor utilizes the image-text pairing information central to vision-language learning. We propose Topology-Aware Multimodal Representation Alignment (ToMA), a framework that uses persistent homology to identify topologically salient edges and aligns them across modalities through available cross-modal correspondences. ToMA leverages both $H_0$-death edges and lightweight $H_1$-birth edges, allowing it to capture both connectivity and cycle structure without constructing 2-simplices. Experiments show that ToMA yields stable gains, with clear improvements on remote sensing and modest but consistent benefits on fashion retrieval. Additional analysis shows that ToMA is more stable than alternative topology-based objectives and that lightweight $H_1$-birth edges provide useful higher-order structural signals.

We propose a contextual cascading bandit model in which the click probability at each position depends on both the displayed item and the topics of previously shown items. This captures how previously displayed topics affect later click probabilities, allowing different topic orders to induce different user responses. Unlike standard cascading bandits, the optimal cascade is no longer determined only by the selected set of items, since the ordering itself affects the expected reward. To address the resulting planning challenge, we reformulate cascade construction as a Markov decision process whose state summarizes the previously selected topics. Based on this formulation, we develop an optimism-based algorithm and prove a regret upper bound of $\widetilde{\mathcal O}(\bar p^{\frac{K-1}{2}}d\sqrt{T})$, where $d$ is the number of unknown parameters, $T$ is the horizon, $K$ is the cascade length, and $\bar p<1$ upper bounds the no-click probability of an examined item. A key implication is that the regret decreases with the cascade length $K$, a phenomenon that had not been established even in order-insensitive contextual cascading bandits. We further provide a local regret lower bound showing that this decreasing dependence on $K$ is intrinsic, and validate our theory through experiments with topic-order-dependent click probabilities.

We study cost-aware cascading bandits, where a learner selects an ordered subset of options, tests them sequentially until the first success, and pays the costs of all tested options. In this problem, regret comes from both testing inefficient options and placing options in a suboptimal order, but existing analyses do not separate these effects for inefficient options and therefore yield an inverse-square dependence on the gap $c_i-\theta_i$. We develop a regret decomposition based on intermediate policies that reorder the remaining suffix and remove inefficient options one position at a time. This allows us to quantify the incremental regret incurred when each option is tested. As a consequence, we show that the regret of CC-UCB admits a problem-dependent bound of $O(\sum_{i:\theta_i/c_i<1}\log T/(c_i-\theta_i))$ up to additive terms and a problem-independent bound of order $\tilde O(L\sqrt{T})$. We further prove that the minimax regret is bounded from below by $\Omega(\sqrt{LT})$ by reducing standard multi-armed bandits to a special case of the model. Finally, we propose CC-UCBv2, which removes the need to specify a positive lower bound on costs and handles zero-cost options by separating empirically zero-cost options from the others. Numerical experiments show the effect of misspecified cost lower bounds and demonstrate that the proposed modification can reduce regret in representative instances involving zero or misspecified costs.

Pruning reduces the inference cost of large language models, but existing criteria primarily preserve large activations or reconstruct layer outputs. We argue that this overlooks a key computation performed by particularly sparsity-sensitive neurons in the MLP up and gate projections: separating similar inputs into dissimilar outputs. This suggests that effective pruning should preserve not only activations, but also pairwise output differences. We introduce a family of difference-informed pruning methods built upon this principle. Wisp is a first-order, update-free method that scores weights using input-difference norms, and Wisp+ refines this score neuronwise using the input pairs each neuron separates most strongly. Finally, Whisper is a second-order method that uses a lightly regularized difference Hessian as its reconstruction objective. Across the Llama 2 and 3.1 families, our second-order variant consistently improves language modeling performance over strong reconstruction-based baselines, while our update-free variants improve over activation-aware update-free baselines, with gains stronger in more constrained settings. The improvements over Wanda and SparseGPT extend to structured sparsity, downstream evaluations, and other model families, suggesting that preserving input differentiation is a broadly useful signal for post-training LLM sparsification.

Recent text-to-image diffusion models (T2I DMs) depend on vast, uncurated datasets that often include copyrighted artworks and personal images, risking the generation of unwanted content. While concept erasure methods have emerged to suppress such outputs, they predominantly rely on text prompts, limiting their effectiveness for visually nuanced or ineffable styles that are difficult to articulate verbally. To bridge this gap, we propose Quiet Prompt (QuP), a reference-based concept erasure method that identifies complex concepts using fewer than ten reference images. QuP operates in two stages: (1) Concept Embedding Generation (CEG), which captures the intricate visual morphology of an unwanted concept into a single latent embedding; and (2) Concept leakage-aware Negative Guidance (CNG), which utilizes this embedding as a negative semantic condition to steer the diffusion process. In addition, to overcome the limitations of conventional fixed-scale negative guidance (negative prompting)—which often suffers from structural distortion and unintended content loss—we introduce concept leakage-aware negative guidance scale $n_g(t)$. This mechanism adaptively modulates the guidance strength at each denoising step based on a semantic measurement of concept leakage between the intermediate generated image and the target concept in a joint embedding space. Extensive evaluations on idiosyncratic art styles and object erasure tasks demonstrate that QuP achieves superior concept suppression and content preservation, outperforming state-of-the-art text-based baselines in both image fidelity and erasure precision. The source code will be publicly provided to ensure reproducibility of our work.

Large-scale transformer training and deployment are increasingly constrained by the transfer of activations, gradients, and optimizer states across accelerators. Low-bit quantization offers a natural remedy, but transformer activations are often heavy-tailed and outlier-dominated, making simple quantization highly lossy. We show that this difficulty is not only a property of the quantizer, but also of the architecture. Specifically, residual connections can drive transformer activations away from Gaussianity during training. Using controlled comparisons between residual and residual-free transformers, we demonstrate that this effect leads to substantially higher quantization error and accuracy degradation at low precision in residual models. We explain the phenomenon through an excess kurtosis analysis, showing that residual mixing can amplify non-Gaussianity, whereas dense mixing in residual-free contracts non-Gaussianity. We then show that residual-free transformers can be made trainable using orthogonal initialization, spectral or second-order optimization, and depth-aware scaling of attention temperature. In language tasks, while there is a small drop in full precision performance, these models retain near-Gaussian activations and exhibit significantly improved robustness to low-bit quantization. Our results identify an accuracy-compressibility trade-off in transformer design and motivate architecture-level approaches to quantization-friendly foundation models.

KV-cache compression for long-horizon LLM agents is often guided by accumulated attention, yet attention frequency can retain repetitive error traces while discarding decisive instructions. We propose TaskKV, a streaming step-level retention policy with three contributions: (1) a signed directional utility label from the first-order change in action likelihood, distinguishing helpful steps from confusing distractors unlike unsigned saliency; (2) a structured residual scorer that treats attention mass and intent alignment as fixed priors and learns only a denoising correction, converging with 500 trajectories; and (3) an entropy-based regime classifier that falls back to contiguous retention when the scorer cannot confidently rank steps. With a 20% KV budget on AgentBench and AlfWorld, TaskKV preserves $\sim$87--89% of full-cache success rate, improving over SnapKV by 5.0--7.9 SR points and over a strong heuristic by 2.9--7.3 points; on dense tasks, gains come from detecting when utility pruning should be disabled. Code is available at https://anonymous.4open.science/r/taskkv-F0D5.

Object detectors are expected to recognize objects independently of intrinsic object-level attributes, such as scale and local visibility. Yet, natural detection datasets contain systematic intrinsic attribute biases, and modern detectors inevitably entangle these biases within their learned representation geometry, leading to non-uniform performance across the continuous attribute spectrum. This observation exposes a central limitation of conventional data augmentation: while attribute-blind transformations enlarge the training distribution, they fail to explicitly correct the dataset-inherent nuisance structure. To address this, we propose Target-Aware Nuisance Shaping} (TANS, a unified framework that re-purposes data augmentation as an object-conditioned vicinal distribution design. TANS processes training samples through a serial pipeline of two fundamental operators: first, Scale Prior Shaping (SPS) geometrically transports object scales toward low-density regions of the natural scale distribution via class-conditional log-area priors; subsequently, Local Visibility Shaping (LVS) photometrically modulates local foreground-background contrast by constructing smooth, box-conditioned Gaussian fields, strictly preserving the newly established geometry and labels. Furthermore, a feature-state controller monitors the evolving representation geometry to adaptively adjust the shaping strength during training. Extensive experiments on MS COCO and Pascal VOC demonstrate that TANS significantly improves detection performance over strong augmentation baselines across modern architectures. Specifically, on COCO with YOLOv11, TANS achieves a 3.6 mAP gain over the Mosaic baseline. Beyond aggregate accuracy, our attribute-regime analyses, feature-state dynamics, schedule comparisons, and logit-space probes consistently indicate that TANS effectively decouples the detector from intrinsic dataset biases, establishing target-aware shaping as a rigorous paradigm for learning attribute-invariant representations.

Concept erasure aims to remove a target attribute from a representation while preserving the other information encoded in it. This is difficult beyond the linear setting: a target signal hidden from one probe may remain recoverable by a fresh nonlinear probe, while unconstrained nonlinear updates may remove the target by pushing representations off the manifold of natural hidden states. We propose the *Manifold Representation Hypothesis* (MRH): natural hidden states concentrate near a structured, lower-dimensional manifold, so surgical erasure should act along local manifold degrees of freedom rather than arbitrary ambient directions. We operationalize this hypothesis with the TanGCE family of erasure methods. The core method estimates each representation's local tangent space from nearest-neighbor secants, projects a nonlinear concept-scorer gradient onto that tangent, and applies a per-sample trust-region step; TanGCE+ and TanGCE++ prepend closed-form first- and second-moment erasers before the same manifold-constrained loop. Across 119 settings spanning 13 language models, three NLP concepts, and 40 CelebA-CLIP attributes under two control regimes, TanGCE++ removes more target signal than the strongest published baseline at matched control-damage budgets under one fixed hyperparameter recipe. Applying the same manifold-constrained loop after prior erasers also consistently reduces residual nonlinear leakage without leaving the control budget, empirically supporting MRH's operational prediction that manifold-constrained edits are a useful inductive bias for surgical concept erasure.

We study Stackelberg learning in which followers use lower-tail CVaR as a reward utility. In cooperative bandits, where both agents share the CVaR objective, we prove a spectral-risk lower bound that gives $\Omega(\sqrt{K(AB-1)/\tau})$ for CVaR and give a Stackelberg-factorized CVaR-UCB algorithm with matching $\widetilde O\sqrt{ABK/\tau})$ regret up to logarithmic factors. Thus CVaR learning admits a minimax-optimal realizable response certificate in bandits. In Markov games, a risk-neutral leader faces a CVaR-sensitive follower. We introduce a certified follower-response oracle based on shortfall planning and decompose true Stackelberg regret into certified oracle regret and benchmark response certification error. The first term is sublinear without coverage, while true regret requires comparison coverage and response compatibility.

We study mixed-variable optimization in scientific discovery, where the key challenge is to efficiently explore the search space under expensive experimental evaluations. Traditional Bayesian optimization (BO) methods typically rely on structural descriptors (e.g., molecular fingerprints) to measure similarity among categorical variables. However, such task-agnostic similarity often fails to reflect task-specific objectives, leading to biased generalization. To address this limitation, we propose \textbf{TagBO} (\textbf{T}ask-\textbf{a}ware \textbf{G}raph \textbf{B}ayesian \textbf{O}ptimization), a method that integrates LLM-derived relational priors with descriptor-based structural information for mixed-variable Bayesian optimization. Rather than directly using LLM outputs as predictive scores, TagBO treats LLM outputs as a potentially noisy source of task-aware relational priors and extracts coarse ordinal relational signals from LLM reasoning to construct task-aware similarity structures for scientific optimization. TagBO then performs constrained Gaussian process Bayesian optimization over the resulting joint discrete-continuous representation space. Experiments on diverse chemistry and materials formulation tasks demonstrate that TagBO consistently improves sample efficiency under fixed evaluation budgets across LLMs of varying capabilities.

Video understanding models often rely on motion, but faithful explanations must reveal not only whether motion matters, but also which source of motion supports a prediction. We identify motion-source under-specification as a key limitation of existing video XAI: region-centric explanations are source-ambiguous, while concept-based explanations are source-incomplete when their motion vocabulary is restricted to single-person pose sequences. To bridge this gap, we propose TraCE-Trajectory-Aware Concepts for Explainable Video Understanding-a concept-based framework that elevates visual trajectories to first-class explanatory concepts. By clustering optical-flow trajectories, TraCE discovers source-flexible motion concepts that capture dynamic evidence from people, objects, and interactions, while object and scene concepts account for static context. TraCE applies the same typed trajectory/object/scene concept interface to both action recognition and video question answering (VQA), enabling concept-level explanations beyond a single task. We evaluate TraCE across six benchmarks: NTU RGB+D Mutual, Chiral SSv2, UCF-101, KTH, TOMATO, and STAR. Experiments show that TraCE provides trajectory-aware explanations of dynamic evidence with minimal performance trade-off, trailing non-interpretable baselines by only 0.9 points on action recognition and 0.1 points on VQA on average. User studies, faithfulness analyses, temporal sensitivity tests, and concept-intervention results further show that TraCE produces interpretable, faithful, and practically useful explanations.

We propose TRACE, a structure-aware framework leveraging diffusion models for localized character encoding to embed data. Unlike existing methods that rely on edge features or pre-defined codebooks, TRACE exploits character structures that provide inherent resistance to noise interference due to their stability and unified representation across diverse characters. Our framework comprises three key components: **(1)** adaptive diffusion initialization that automatically identifies handle points, target points, and editing regions through specialized algorithms including movement probability estimator (MPE), target point estimation (TPE) and mask drawing model (MDM), **(2)** guided diffusion encoding for precise movement of selected point, and **(3)** masked region replacement with a specialized loss function to minimize feature alterations after the diffusion process. Comprehensive experiments demonstrate TRACE's superior performance over state-of-the-art methods, achieving more than 5 dB improvement in PSNR and 5% higher extraction accuracy following cross-media transmission. TRACE achieves broad generalizability across multiple languages and fonts, making it particularly suitable for practical document security applications.

Watermarking text-to-image diffusion models provides a practical mechanism for provenance tracking and responsible deployment. Post-processing methods are easy to deploy but vulnerable to image-space transformations. In-processing methods improve robustness by embedding the watermark within the denoising trajectory. Yet most existing methods inject the signal into the initial noise or a fixed intermediate latent, without controlling how it evolves during the remaining denoising steps. This can entangle watermark preservation with text-guided generation, risking weaker verification or degraded content fidelity. We propose TIDE, a trajectory-aware watermarking method for text-to-image diffusion models. TIDE injects a learnable watermark into an intermediate latent and jointly optimizes it with an auxiliary watermark condition, using preservation and detection objectives to limit deviation from the unwatermarked reference while maintaining separable watermark evidence. During sampling, TIDE estimates recent text-guidance directions and redirects watermark guidance toward the residual component less aligned with this local text subspace, reducing avoidable interference with semantic generation. Verification uses null-prompt partial inversion to recover the injection latent and match its masked coefficients to the target watermark. Experiments show that TIDE achieves reliable verification on unattacked images, improves robustness under common attacks, and better preserves semantic and visual fidelity.