NeurIPS 2026 论文列表

Decomposing surface electromyography (EMG) into the spike trains of individual motor neurons is a long-standing inverse problem and a key step toward motor-neuron-driven neural interfaces such as prosthetics and exoskeletons. The standard approach, independent component analysis (ICA) of the multichannel signal, assumes that the mixing from neurons to electrodes is stationary in time. This assumption fails during movement, when volume-conductor deformation makes the mixing time-varying, and current decomposition algorithms are correspondingly restricted to isometric contractions. We introduce a quasi-linear ICA formulation in which a static linear separator is preceded by a learned, low-rank, time-varying invertible transformation. The separator is trained with an independence loss on the uncompensated projection, and the transformation with a stationarity loss on the recovered source. Gradients are not shared between the two, so the source-extraction step reduces to classical linear ICA and inherits its identifiability guarantee, while non-stationary distortion is absorbed by the transformation. The closed-form inverse of the transformation enables per-spike subtraction with a time-varying template during sequential peel-off. On a public benchmark of dynamic high-density EMG with ground-truth spike trains, the method outperforms five adaptive ICA baselines at every recall threshold, recovering more units at a higher accuracy.

Analyzing complex data across a wide range of scientific fields often requires identifying central or typical elements, distinguishing them from atypical ones, and constructing central or "normal" regions at prespecified levels of centrality. We introduce centrality scores (C-scores) based on distance profiles for random objects taking values in general metric spaces. The proposed C-scores are defined through weighted optimal transport of distance profiles and provide a unified framework for constructing central or "normal" regions for complex data. We show that, for Euclidean data, the limiting behavior of the proposed C-scores is asymptotically equivalent to the underlying probability density function. The practical merits of the proposed method are illustrated using gene expression data, distributions of recorded temperatures, handwritten digit recognition, and taxi trip records. These examples demonstrate the effectiveness of C-scores in identifying central and peripheral elements and in yielding meaningful insights for non-Euclidean and high-dimensional data.

Demoir\'eing aims to remove moir\'e artifacts that often occur in images. While recent deep learning-based methods have achieved promising results, they typically require substantial computational resources, limiting their deployment on edge devices. Model quantization offers a compelling solution. However, directly applying existing quantization methods to demoir\'eing models introduces severe performance degradation. The main reasons are distribution outliers and weakened representations in smooth regions. To address these issues, we propose QuantDemoire, a post-training quantization framework tailored to demoir\'eing. It contains two key components. **First**, we introduce an outlier-aware quantizer to reduce errors from outliers. It uses sampling-based range estimation to reduce activation outliers and keeps a few extreme weights in FP16 with negligible cost. **Second**, we design a frequency-aware calibration strategy. It emphasizes low- and mid-frequency components during fine-tuning, which mitigates banding artifacts caused by low-bit quantization. Experiments validate that our QuantDemoire achieves large reductions in parameters and computation while maintaining quality. Meanwhile, it outperforms existing quantization methods by over **4 dB** on W4A4. We implement a CUDA kernel for the mixed-precision branch and achieve a 2.3$\times$ end-to-end speedup on an RTX 4090 GPU. Code will be made public.

While deep learning offers tremendous promise for scientific and medical imaging, any failures and hallucinations (predictions that do not coincide with reality) are hard to pinpoint and can have serious downstream consequences. Uncertainty estimation techniques, such as conformal prediction, can help by predicting statistically valid error bars for a model's prediction. However, popular conformal prediction methods were not designed for high-dimensional image-valued problems and do not take into account spatial correlations within an image during conformal calibration, resulting in larger-than-necessary uncertainty intervals. We propose a practical simultaneous quantile regression method that enables non-linear, spatially-adaptive scaling during conformal calibration. Our method, QUTCC uses a U-Net architecture with a quantile embedding to learn a full conditional quantile distribution during training, and then leverages this non-linear, learned function for spatially-adaptive conformal calibration. At test time, our method can efficiently estimate uncertainty intervals with pixel-marginal coverage guarantees. In addition, QUTCC can also predict pixel-wise conditional probability density estimates without any built-in distributional assumptions. We evaluate our method on several denoising problems, accelerated magnetic resonance imaging, and quantitative phase microscopy. Our method consistently produces tighter uncertainty intervals than prior conformal methods at the same coverage level, can predict plausible conditional distributions for different tasks, and in some cases, high-uncertainty regions can help us locate hallucinations in a model's prediction.

Highlight detection in content-dense untrimmed videos, such as livestreams, is particularly challenging due to the prevalence of semantically similar moments and the application-driven demand of fitting a target duration budget. Existing methods typically rank segments independently based on semantic relevance, struggling to discriminate fine-grained quality among similar moments and allocating the budget to redundant selections. We therefore reformulate highlight detection as jointly selecting high-quality and complementary segments under a duration budget. To study this formulation, we introduce QB-Highlights, a large-scale benchmark of 50,000 e-commerce livestream videos with densely occurring query-relevant events and subtle quality variations. QB-Highlights is organized around two complementary dimensions: Segment Qualification, which assesses fine-grained per-segment quality; and Budgeted Composition, which evaluates set-level complementarity under a duration budget. It provides MLLM-assisted pseudo labels for training, dense human annotations for testing, and an evaluation protocol jointly measuring quality and diversity. We further propose a Qualification-then-Composition Reasoning (QCR) framework that performs structured deliberative reasoning to produce a highlight set matching the target duration. Extensive experiments show that QCR outperforms strong MLLM, moment retrieval, and highlight detection baselines on both segment quality and compositional diversity.

Large vision-language models (LVLMs) rely on increasingly long visual contexts, making the KV cache a major inference-time bottleneck. Existing KV cache compression methods typically use pre-decode signals such as prefill attention, visual redundancy, objectness, or layer-wise allocation, but these criteria do not directly indicate which visual tokens in the KV cache will be reused by future answer tokens. We introduce Q-ViK, a question-conditioned visual utility framework for LVLM KV cache eviction. During offline training, we run full-cache decoding and aggregate answer-to-visual attention over cached visual tokens, yielding a privileged *future-utility signal* that reflects the visual KV entries actually used during generation. We use this signal to train a lightweight question-conditioned scorer that predicts visual cache utility from prefill representations alone. At inference time, Q-ViK requires neither full-cache lookahead nor generated traces: it preserves textual KV entries and evicts low-utility visual KV entries with a single post-prefill scoring step. Experiments on seen and held-out multimodal benchmarks show that Q-ViK preserves task-relevant visual evidence in the KV cache more effectively than pre-decode saliency, especially under aggressive KV cache compression. Code will be available at [https://anonymous.4open.science/r/Q-ViK-1A75/README.md](https://anonymous.4open.science/r/Q-ViK-1A75/README.md).

Large language models (LLMs) have demonstrated remarkable performance in video question answering (VQA). To improve responsiveness and answer quality, modern LLM-based VQA services pre-extract multiple LLM-compatible modalities from videos before response generation. However, the performance impact of modality combinations (MCs) and extraction knob settings has barely been studied. Our analysis shows that both factors substantially affect answer quality and Time-to-First-Token (TTFT) latency. Furthermore, the best configuration depends on both video content and query semantics, necessitating adaptive strategies. We propose Prysma, the first modality adaptation framework for LLM-based VQA. Prysma intelligently adapts the modality configurations to optimize answer quality, subject to a Service Level Objective (SLO) on average TTFT. It combines an offline modality orchestrator and an online semantic adapter. The offline orchestrator constructs a video knowledge base to warm-start tuning, employs a latency-aware configuration pruner to reduce search space, and runs a two-stage tuner to optimize both video- and query-level configurations. The online adapter selects configurations in real time based on query semantics and tuning history. Extensive evaluations demonstrate that Prysma improves answer quality by up to 82% over SOTA methods under the same SLO setting.

Benchmark data contamination has become a central challenge in LLM evaluation: when evaluation examples appear in the training data of one or more audited models, reported performance can be inflated and cross-model comparisons become unreliable. A broad line of training-data detection work designs scores to quantify how strongly a model memorizes a given data point, but these score-based methods lack theoretical guarantees. Recent conformal approaches provide provable false-identification control for a single model; however, applying them separately to each model can produce model-specific benchmarks, undermining fair comparison across models. In this work, we formalize multi-model benchmark decontamination as a joint selection problem and propose Joint Envelope Conformal Selection (JECS), a conformal procedure that enables global contamination rate (GCR) control under stated assumptions. Specifically, JECS computes per-model conformal p-values, aggregates them by the per-item maximum, and reconstructs a conservative envelope of the max-p null distribution from right-tail observations above a data-driven threshold. By applying the adaptive Benjamini-Hochberg (BH) procedure to the envelope-rescaled values, we select a benchmark with provable GCR control. Extensive experiments across various models and benchmarks demonstrate that JECS achieves higher power than the max-p baseline while consistently maintaining the target GCR control.

Visible-Infrared Lifelong Person Re-Identification (VI-LReID) requires a model to sequentially acquire cross-modal person retrieval capabilities across sequentially arriving tasks while retaining performance on previously learned ones.Existing methods face two fundamental problems.First, new-task gradient updates disrupt each instance's assignment ranking over historical class prototypes, which is the direct mechanism behind past-task retrieval performance degradation. At the same time, the feature manifold inevitably undergoes global drift as a necessary byproduct of new-task adaptation. Effective anti-forgetting should target the detrimental ranking disruption while permitting this necessary drift.Second, visible RGB and thermal infrared (TIR) imaging capture fundamentally different physical cues: texture-and-color reflectance versus heat radiation contours. This causes the two modalities to form inherently inconsistent inter-class similarity structures that conventional cross-modal supervision cannot resolve, manifesting as highly asymmetric forgetting across modalities under shared-backbone continual training.We propose S-PTC (Stage-wise Prototype Topology Consistency), which preserves each instance's relative distribution over the frozen historical prototype set, protecting assignment rankings while leaving the overall feature manifold free to evolve for new-task adaptation.We further propose CM-PTC (Cross-Modal Prototype Topology Consistency), which aligns the inter-class topology matrices of RGB and IR prototypes, mitigating the structural inconsistency rooted in their imaging physics.Both modules require no stored exemplars.Extensive experiments on the VI-LReID benchmark verify the effectiveness and superiority of our approach against state-of-the-art methods.

Modern video generative models produce visually impressive results, yet frequently violate basic physical principles. We propose \textbf{Proprio}, a training-free framework that enables a frozen video generator to assess and improve the physical plausibility of its own outputs. Inspired by \textit{proprioception}, the biological sense of one’s own movement, Proprio treats the model's flow residual under controlled latent perturbations as a self-scoring signal. Samples that are better explained by the generator's learned dynamics induce smaller and more stable residuals. We aggregate this signal across timesteps and perturbations, focus it on motion-relevant regions with a dynamic spatiotemporal mask, and use it for best-of-N search, gradient-based self-refinement, or both. Across text-to-video and image-to-video benchmarks, Proprio consistently improves physical plausibility, outperforming VLM-based scoring, and external world-model baselines in several settings. On TurboWan2.2, Proprio improves Physics-IQ from 32.2 to 37.5 (+16.5%) and VideoPhy2-hard physical commonsense from 45.6 to 55.0 (+20.6%). Human evaluation further shows that raters prefer Proprio-selected or refined videos for physical plausibility in roughly two-thirds of comparisons. These results suggest that frozen video generators contain actionable internal signals for evaluating and improving the physical plausibility of their own outputs.

Learning visual representations that generalize across domains remains challenging when source-domain supervision is entangled with spurious dataset-specific cues. This issue is particularly pronounced in face attack detection (FAD), where attack artifacts vary substantially across capture devices, manipulation pipelines, and image quality. In this paper, we propose Prompt-Conditioned Semantic Bottleneck, an information-bottleneck-inspired representation learning framework for cross-domain FAD. Unlike prior methods that use prompts as image-text matching anchors for multi-modal feature learning, our method uses label- and attack-type-conditioned prompts to elicit attack-aware semantic targets from a frozen VLM. These prompt-conditioned semantics provide offline supervision for a lightweight visual detector, encouraging its representation to preserve attack-relevant cues while reducing reliance on source-domain nuisance factors. Extensive experiments on face anti-spoofing and face forgery detection benchmarks demonstrate consistent improvements under cross-dataset evaluation. Ablation studies further show that the gains are not simply due to stronger visual or multi-modal models, but arise from attack-aware prompt-conditioned semantic supervision. Importantly, the VLM and prompts are removed during inference, enabling efficient vision-only deployment. Overall, our results suggest that prompt-conditioned VLM semantics provide an effective way to improve the trade-off among detection accuracy, cross-domain generalization, and inference efficiency in FAD.

Training-signal imbalance in medical image segmentation is commonly diagnosed as a data-distribution problem, such as class frequency imbalance, foreground sparsity, or domain shift, and addressed through reweighting, sampling, or domain adaptation. We argue that this diagnosis is incomplete: a more fundamental source is structural misalignment between supervision targets and segmentation objectives. Weidentify two operative mechanisms underlying this phenomenon: gradient-mass dilution, where dominant classes consume gradient capacity needed for foreground discrimination, and inter-class supervision noise, where weak subtype boundaries generate unreliable optimization signals. On a private renal pathology dataset, four standard segmentation architectures trained under conventional four-class supervision underperform a foreground-focused supervision regime (a one-line modification of the loss) by 7.87–16.05 fg-mIoU points. The same effect replicates on three public datasets, suggesting foreground-focused supervision as a low-cost, general-purpose recipe for any pixel-imbalanced segmentation task. Building on this observation, we propose Progressive Signal Calibration (PSC), a framework that calibrates training signals at three abstraction levels. At the annotation level, PSC adaptively selects the supervision granularity that maximizes signal qual ity. At the architectural level, PSC introduces a boundary-aware feature gating mechanism for structure-sensitive feature aggregation. At the regularization level, PSC employs uncertainty- and ratio-aware constraints to stabilize optimization and prevent late-stage class-proportion drift. Importantly, PSC satisfies a con ditional gain monotonicity property: when structural misalignment is weak or absent, its regularization terms naturally attenuate, avoiding systematic degradation. Across 18 public histopathology benchmarks, PSC achieves statistically significant improvement on six datasets with no statistically significant regression on any benchmark. On the private renal pathology dataset, PSC reaches 96.0 fg-mIoU, ex ceeding the strongest matched-backbone baseline by +2.56 points under identical FG3 supervision—a substantial gain in a regime where the FG3 baseline is already above 93 fg-mIoU

Enhancing Vision-Language Models (VLMs) on downstream tasks with unlabeled data has attracted increasing attention. Constructing a pseudo-labeled dataset by pseudo-labeling is a common method. Nonetheless, owing to the inherent class-wise prediction bias in VLMs, they tend to generate long-tailed pseudo-labels that are inconsistent with the true label distribution. Motivated by this, we first divide all classes into pseudo-head, pseudo-middle, and pseudo-tail classes based on the pseudo-label quantity. Accordingly, we propose a **P**rogressive **P**seudo-label **S**elf-**B**alancing (PPSB) framework, which measures the class-wise prediction bias and calculates quantity upper bounds for certain classes to construct relatively balanced pseudo-labeled dataset, while introducing fewer incorrect pseudo-tail labels. In this way, the class-wise prediction bias is progressively corrected and the pseudo-label dataset scale increases autonomously during training. Furthermore, the confidence scores generated by VLMs are not entirely reliable. Therefore, we design a neighborhood consistency filtering mechanism and a visual classifier to improve the pseudo-label accuracy. We theoretically prove that our method can significantly reduce the generalization error under certain conditions. Extensive experiments across six benchmarks under three learning paradigms demonstrate that our method outperforms state-of-the-art methods by average **3.84**% in accuracy. **Code is available in the supplementary materials.**

Many everyday programming tasks resist clean rule-based implementation, such as alerting on important log lines, repairing malformed JSON, or ranking search results by intent, and are increasingly outsourced to large language model APIs at the cost of locality, reproducibility, and price. We propose *fuzzy-function programming*: compiling such a function from a natural-language specification into a compact, locally-executable neural artifact. We instantiate this paradigm with Program-as-Weights (PAW), in which a 4B compiler trained on FuzzyBench, a 10M-example dataset we release, emits parameter-efficient adapters for a frozen, lightweight interpreter. A 0.6B Qwen3 interpreter executing PAW programs matches the performance of direct prompting of Qwen3-32B, while using roughly one fiftieth of the inference memory and running at 30 tokens/s on a MacBook M3. PAW reframes the foundation model from a per-input *problem solver* into a *tool builder*: invoked once per function definition, it produces a small reusable artifact whose subsequent calls per function application are cheap and offline.

Multi-modal large language models (MLLMs) with impressive perception and understanding capabilities will enable a range of downstream applications. However, their substantial computational and memory requirements hinder the real-world implementation, particularly for resources-constrained edge devices. Quantization has emerged as an effective solution for deploying large models. While post-training quantization (PTQ) successfully retrains the performance at moderate bit-width (\textit{e.g.}, W8A8), it suffers from severe performance degradation under low-bit quantization (\textit{e.g.}, W4A8/W8A8), especially for small-scale models that are more suitable for edge deployment. In this paper, we propose \texttt{ProQuant}, a novel weight-activation quantization-aware training (QAT) framework tailored for low-bit MLLMs. First, to align the limited finetuning dataset distribution with the pretrained dataset distribution, we propose a self-relabeling (SRL) scheme to resample the responses of the open-source multimodal dataset. Second, we are the \textit{first} to take a decoupled view of multi-modal (MM) understanding and language modeling abilities. We propose a progressive block activation (PBA) mechanism to prioritize the MM understanding recovery. We also introduce a vision-sensitive factor $\vec{\tau}$ that effectively identifies the MM-critical layers. Extensive experiments across various benchmarks, covering models with 2B$\sim$8B parameters, show that \texttt{ProQuant} significantly outperforms existing methods. For example, our W4A8 \texttt{Qwen3-VL-2B-Instruct} improves average accuracy by impressively 6.6\% and achieves performance comparable to full precision counterparts with only $\sim$1\% performance drop. Code will be released upon acceptance.

Feed-forward 3D foundation models have recently reshaped multi-view reconstruction, yet dynamic 4D understanding still often relies on large-scale motion supervision or hand-crafted, architecture-specific heuristics. We ask whether frozen 3D foundation model tokens already encode motion-relevant information that can be exposed by lightweight readout functions, rather than re-learning motion-specific features with high-capacity decoders. Through probing on three representative backbones, we find that static--dynamic separation is decodable from frozen token representations. Our rank-restricted and spectral analyses on $\pi^3$X reveal that the recovered motion cues are concentrated in a low-dimensional subspace. Building on this, we propose Probing-based Motion Distillation (PMD), which converts pairwise motion-state compatibility scores against a fixed anchor token into dense motion masks. Trained on only 160 YouTube-VOS videos using a single 16 GB GPU, PMD transfers zero-shot to DAVIS, SegTrackv2, and FBMS-59 without target-benchmark fine-tuning. With multi-view pretrained geometric backbones, PMD outperforms training-free heuristics and approaches substantially heavier supervised and self-supervised methods, suggesting that motion decoding from frozen 3D foundation models can be lightweight and data-efficient.

Contrastive Language-Image Pre-training (CLIP) is fundamentally limited by its 77-token restriction, lack of multilingual capabilities, and coarse-grained semantic representations. While replacing CLIP’s native text encoder with a Large Language Model (LLM)-based embedder offers a promising solution, direct, from-scratch alignment can disrupt the semantic structures learned during pre-training. This often leads to degradation of cross-modal knowledge and particularly impairs recognition capabilities in zero-shot scenarios. In this paper, we propose ProCLIP, a curriculum-learning-inspired progressive alignment framework designed to systematically bridge the LLM embedder and CLIP's visual space, unlocking CLIP's potential for long-text, multilingual, and fine-grained understanding. Our framework operates in two stages: (1) Representation Inheritance, which distills CLIP's original text-space knowledge into an LLM adapter to establish a robust initial vision-language prior, and (2) Contrastive Tuning, which refines the cross-modal alignment with self-distillation regularization on the image encoder to further prevent catastrophic forgetting. To maintain semantic and geometric consistency, we introduce instance-level semantic and global structural alignment constraints throughout both stages. Extensive experiments demonstrate that ProCLIP improves zero-shot classification accuracy by 6.8%--13.5% over existing LLM-augmented baselines and achieves state-of-the-art performance in diverse long-text, multilingual, and fine-grained cross-modal retrieval tasks under comparable settings.

Aerial-Ground Person Re-Identification (AG-ReID) aims to match pedestrian images captured by unmanned aerial vehicles (UAVs) and ground-based surveillance cameras. The task remains highly challenging due to severe viewpoint discrepancies, frequent occlusions, and substantial domain gaps between aerial and ground imagery. Beyond these observable factors, existing methods often overlook two fundamental structural issues: cumulative positional drift during hierarchical feature extraction and semantic inconsistency across cross-view feature distributions. To address these challenges, we propose ProAlign, a Progressive Positional and Prototype-Guided Alignment Network for AG-ReID. ProAlign comprises two key components: a Layer-wise Progressive Positional Embedding (LPPE) module and a View-Aware Prototype Contrastive Learning (PCL) module. LPPE performs adaptive positional calibration throughout transformer layers by employing conditional positional encoding in shallow layers to mitigate local spatial distortions, while introducing learnable static positional embeddings in deeper layers to reinforce global semantic priors. Meanwhile, PCL maintains view-specific aerial and ground prototypes for each identity and enforces cross-view semantic consistency via a dual-prototype contrastive objective. Extensive experiments on the challenging CARGO benchmark demonstrate the effectiveness of ProAlign. In the aerial-ground setting, ProAlign surpasses previous state-of-the-art methods by 13.89% mAP and 9.39% Rank-1 accuracy.

Long-context decoding in large language models (LLMs) is increasingly bottlenecked by the memory and computation required to attend over an ever-growing Key-Value (KV) cache at each autoregressive step. Although token-level sparse attention reduces this burden by restricting computation to a small subset of relevant past tokens, its practical gains are often offset by repeatedly recomputing layer-wise sparse indices as the context grows. A common remedy is to share sparse indices across layers by computing them only at designated anchor layers, but such static reuse ignores the layer-wise evolution of attention patterns, causing the reused indices to progressively deviate from the layer-specific optima and incur substantial attention loss. By revisiting cross-layer sparsity from the perspective of attention dynamics, we find that inter-layer salient token shift is highly localized: although the exact top-$\kappa$ indices differ across layers, the core high-attention tokens remain stable, with changes concentrated near the expanded boundary of previously selected regions. Motivated by this, we propose Prism Attention, a proposal-refined sparse attention framework. It replaces rigid cross-layer index reuse with a coarse-to-fine strategy, preserving layer-wise adaptability while retaining the efficiency benefits of cross-layer sharing. Extensive experiments show that Prism Attention achieves state-of-the-art performance among mainstream sparse attention methods on both reasoning and long-context benchmarks, while achieving $2.6\times\sim7.5\times$ kernel speedup over FlashAttention at 128K context length.