NeurIPS 2026 论文列表

Diffusion models achieve high sample quality but remain expensive at inference time because sampling requires many sequential neural function evaluations (NFEs). Existing acceleration methods either use fixed step-skipping schedules, adapt step sizes based on local numerical error, or require additional training. We introduce GeoSPRINT (Geometric Step Pruning for Inference in Trajectories), a training-free framework for constructing non-uniform sampling schedules from the geometry of denoising trajectories. GeoSPRINT detects geometrically redundant steps using a hyperplanarity test in latent space, implemented efficiently via QR factorization, and converts the resulting redundancy profile into a sampling schedule that allocates more steps to high-curvature regions of the trajectory. In addition, we introduce the trajectory projection score $\alpha_{\mathrm{traj}}$, a residual-variance metric that quantifies trajectory straightness and serves as a model-free diagnostic for rectified flow quality. Across CIFAR-10 ($32{\times}32$), LSUN Church ($256{\times}256$), and Stable Diffusion v1.5 ($512{\times}512$ latent), GeoSPRINT consistently improves over uniform DDIM (Denoising Diffusion Implicit Models) schedules at matched NFE budgets. On CIFAR-10, GeoSPRINT improves FID (Fréchet Inception Distance) by 0.7-1.1 over DDIM across 49-89 NFEs and surpasses DPM-Solver++ at NFE${\geq}30$ despite using a first-order DDIM solver. On LSUN Church, it reduces FID from 1.48 to 1.26 at 52 steps, and on Stable Diffusion v1.5 it achieves up to 1.93 FID improvement over DDIM. These results show that trajectory geometry provides a useful global signal for allocating inference steps and that schedule quality can substantially improve diffusion sampling efficiency without retraining.

Long-context DNA models are limited by token-mixing cost and by how compression allocates representational budget across the genome. Existing approaches operate close to base-pair resolution, apply fixed downsampling, or learn content-dependent chunks without an explicit genomic budget, making long-context pretraining expensive and difficult to control. We introduce GeneZip, a region-aware DNA compression framework that combines H-Net-style dynamic routing with a Region-Aware Ratio (RAR) objective and bounded routing. GeneZip uses static gene-structure annotations during compression training to specify region-wise base-pairs-per-token (BPT) targets; at inference time, it compresses raw unseen DNA without annotations. GeneZip provides three main benefits. First, it is effective: GeneZip variants achieve the best validation PPL among encoder-based compressors, with GeneZip-70M already operating at 137.6 BPT, and across four reproducible DNALongBench tasks---contact map prediction, eQTL prediction, enhancer--target gene prediction, and transcription-initiation signal prediction---GeneZip obtains the best average rank among compared sequence models. Second, it is redundancy-aware: a post-hoc RepeatMasker/TRF analysis shows that, without repeat supervision, GeneZip assigns higher local BPT to TE-derived interspersed repeats and tandem repeats, two major classes of repetitive DNA sequence redundancy. Third, it is efficient: by reducing the effective token-mixing length, GeneZip enables longer-context and larger-capacity pretraining, including 128K-context and 636M-parameter variants on a single A100 80GB GPU, and fine-tunes the eQTL task 50.4$\times$ faster than JanusDNA (50 vs. 2520 minutes). These results establish GeneZip as an effective, redundancy-aware, and efficient compression interface for long-context DNA modeling.

Conformal prediction (CP) provides a distribution-free approach to uncertainty quantification (UQ) with finite samples. However, applying CP to graph neural networks (GNNs) remains challenging. The combinatorial nature of graphs makes their encoding non-trivial, leading to insufficiently uncertain prediction logits and indiscriminative embeddings. Existing methods mostly rely on the embedding space for conformal prediction, which can be unreliable for graphs and often yields inefficient prediction sets. We propose GRAPHLCP, a structure-aware weighted conformal prediction framework that explicitly incorporates the graph topology and inter-node dependencies into localization and weighting. Based on experimental results that show a strong correlation between node homophily and sample coverage, we propose GRAPHLCP that utilizes a feature-aware densification followed by Personalized PageRank–based kernel computation to model structural proximity between nodes. Accounting for both structural and feature similarity allows GRAPHLCP to efficiently guarantee marginal coverage while attaining favorable test conditional coverage across extensive experiments on multiple datasets for both regression and classification.

Designing RNA sequences that fold into specific 3D structures is a fundamental challenge in therapeutics. Current RNA inverse folding methods typically condition on 3D backbone coordinates but the generation is limited to 1D discrete sequences. This ignores the continuous side-chain orientations, which are essential for overall structural stability. To address this issue, we explicitly introduce side-chain geometry into the RNA generative process. Unlike co-design frameworks that diffuse across separate raw spaces, we propose Geometric Optimized Latent Diffusion (\textbf{GOLD}), which project sequence and structure into a unified latent manifold. GOLD employs a novel GeoVAE to elegantly integrate discrete RNA sequences with continuous side-chain angles. By mapping these modalities into a single, smooth latent manifold, GOLD naturally facilitates a synergistic co-diffusion process. To enhance structural validity, we further introduce a training-free, gradient-guided sampling mechanism. By decoding the generated sequence probabilities and side-chain geometries into structures during the sampling process, we compute analytical gradients from physical constraints. This dynamic feedback actively guides the generated sequence to a physically stable state. Extensive experiments validate the superiority of GOLD, achieving state-of-the-art performance across sequence recovery, secondary structure validity, and 3D foldability metrics.

Scaling robot demonstrations does not guarantee better imitation: redundant trajectories dilute learning, while rare, imperfect segments may encode critical transitions. Prior curation methods overlook such dependencies by scoring samples independently at the trajectory or segment level. We reframe robot demonstration curation as a coverage-aware sequential selection problem and propose PROSE, which selects data by maximizing marginal utility under a fixed budget. PROSE unifies three signals: (i) influence on closed-loop return, (ii) kinematic reliability, and (iii) coverage gain measuring novelty with respect to the retained set, allowing full trajectories and fine-grained segments jointly participate in scoring and filtering. Across three Robomimic simulation tasks and three real Franka tasks, PROSE achieves the best success rate on every task we evaluate against three state-of-the-art curators (CUPID, SCIZOR, Demo-SCORE), with average closed-loop gains of +15\% in simulation and +35\% in real-world. Ablations attribute the gain primarily to the coverage step.

Contact-rich manipulation requires precise control and complex physical interaction with the environment, posing significant challenges for robot policy learning. Vision-only policies struggle with such tasks, as contact states and force feedback are difficult to infer from vision alone. Existing methods mitigate this issue by incorporating force or tactile sensing. However, they often treat these signals as auxiliary observations rather than using them to model future interaction dynamics, leading to inefficient modality utilization and limited generalization. To address this, we propose ForceLDM, a force-aware latent dynamics model that enables the policy to anticipate future contact and motion dynamics in latent space and use them to guide action generation. Rather than predicting future observations in pixel space, which often requires large amounts of data and risk overfitting irrelevant details, ForceLDM learns a compact task-relevant representation through knowledge distillation. Specifically, a teacher network with privileged access to future force/torque and optical flow signals extracts future dynamic features, which are then distilled into a student network trained only on current observations. This enables the student to reason about upcoming contacts and physical dynamics at deployment without relying on future sensory inputs. To improve robustness and generalization, we further introduce a curriculum-based progressive noise injection strategy to mitigate over-reliance on future features. Experiments on five real-world contact-rich manipulation tasks demonstrate that ForceLDM significantly outperforms state-of-the-art baselines, generalizes effectively to novel objects, and remains robust to environmental perturbations.

The quadratic computational complexity of standard attention mechanisms presents a severe scalability bottleneck for LLMs in long-context scenarios. While hybrid attention mechanisms combining Full Attention (FA) and Sparse Attention (SA) offer a potential solution, existing methods typically rely on static allocation ratios that fail to accommodate the variable retrieval demands of different tasks. Furthermore, head-level dynamic sparsity often introduces severe computational load imbalance and synchronization long-tails, which hinder hardware acceleration during autoregressive decoding. To bridge this gap, we introduce **Flux Attention**, a context-aware framework that dynamically optimizes attention computation at the layer level. By integrating a lightweight **Layer Router** into frozen pretrained LLMs, the proposed method adaptively routes each layer to FA or SA based on the input context. This layer-wise routing preserves high-fidelity information retrieval while ensuring contiguous memory access, translating theoretical computational reductions into practical wall-clock speedups. As a parameter-efficient approach, our framework requires only 12 hours of training on 8xA800 GPUs. Extensive experiments across multiple long-context and mathematical reasoning benchmarks demonstrate that Flux Attention achieves a superior trade-off between performance and inference speed compared with baseline models, with speed improvements of up to 2.8x and 2.0x in the prefill and decode stages.

Long-context training of large language and multimodal models couples expressive structured attention masks (document, prefix-LM, share-question, sliding-window, block-sparse) with multi-node context parallelism, exposing the mask as a dominant bottleneck. The column-wise sparse mask of FlashMask compresses such masks from $O(n^2)$ to $O(n)$ via four query-axis boundary vectors and covers a broad family of structured patterns. Implemented for Ampere GPUs, FlashMask does not exploit FlashAttention-3's TMA/WGMMA warp-specialized pipeline on Hopper GPUs, and offers no distributed support. We observe that the column-wise sparse mask is indexed by key positions but stores query-axis interval boundaries. Under any multi-chunk context-parallel assignment, this property reduces per-rank mask localization to a provably zero-communication \emph{clip--shift--max} on the boundary vectors, directly compatible with the single-GPU kernel. Building on this property, FlashMask-3 introduces a mask-aware Hopper kernel with a three-role warp specialization atop the FlashAttention-3 TMA/WGMMA pipeline, together with a mask-aware distributed extension: zero-communication mask localization, a sparsity-aware load balancer (HCC-IPO), and a mask-aware compute-communication overlap with mask-driven communication pruning, whose forward all-gather additionally adopts topology-aware hierarchical routing. On a single H100 GPU across 12 structured masks at context lengths from 4K to 128K, FlashMask-3 improves achieved TFLOPs over FlashMask, FlexAttention, and MagiAttention by 45\% to 141\%, 34\% to 71\%, and 2\% to 44\%, respectively. Under context-parallel degrees from 4 to 32 with 8K sequence per device, it attains 31\% to 75\% compute-communication overlap efficiency and improves throughput over Megatron-Core CP (ring), Megatron-Core CP (all-gather) and MagiAttention by $3.25\times$ to $5.11\times$, $1.97\times$ to $3.26\times$ and $1.06\times$ to $4.09\times$ respectively. The source code will be released on GitHub.

The Feed-Forward Network (FFN) dominates the activation memory of modern Transformers because the intermediate tensor of width d_ff is materialized in HBM between the two matmul stages. FlashAttention-style I/O-aware tiling avoids the analogous cost in attention, yet has not been brought to FFN. We identify the reason as a hardware-geometry constraint: under one-pass tiled accumulation a fused FFN kernel must keep an output accumulator of width d_model in on-chip SRAM, which is infeasible whenever d_model >= 2048 on currently shipping datacenter GPUs. We formalize this as an SRAM-feasibility proposition and prove a corollary: multi-head decomposition is the simplest architectural transform that brings FFN inside this SRAM-feasible regime, because it makes the per-head accumulator width d_h = d_model/H a free parameter that can be driven below the GPU's SRAM cutoff. Naive multi-head FFN, however, blows up the per-head expansion ratio d_ff/d_h as d_model grows, drifting away from the well-validated SwiGLU 8/3 optimum and degrading quality at scale; we resolve this with a dense MoE-like sub-network correction that restores the optimal ratio while preserving SRAM-feasibility. The resulting architecture, FlashFFN, is an SRAM-feasible FFN block that replaces SwiGLU under matched parameter and FLOPs budgets and derives directly from the SRAM constraint. Across 128M--1.3B parameter models trained on 60--100B tokens of The Pile, FlashFFN achieves a Pareto improvement over SwiGLU at fixed compute: up to ~4x lower peak activation memory at long sequences, inference latency that matches or improves over SwiGLU (up to ~1.32x faster on H100), and consistent quality gains (up to -0.84 in evaluation perplexity and +1.60 average accuracy across six downstream benchmarks at 1.3B)

Federated Graph Learning (FGL) on Text-Attributed Graphs often encounters the missing neighbor issue. This problem arises from structural fragmentation across dispersed clients, which restricts the effective message passing of Graph Neural Networks. Current completion methods frequently struggle in cross-domain, non-IID scenarios because they lack access to external knowledge. To address these limitations, we propose FedProG, an asymmetric framework that utilizes a frozen server-side LLM to reconstruct missing structural contexts. Furthermore, deploying Large Language Models locally to augment these graphs incurs prohibitive computational costs for edge devices. We introduce a split architecture where a lightweight client-side generator maps graph features into the LLM’s embedding space. This allows the server to produce virtual neighbors via uploaded soft prompts. To ensure system reliability and privacy, we implement a dual-guard mechanism: a server-side uncertainty filter rejects low-confidence generations through multi-path sampling, while a client-side semantic consistency projector maintains utility under differential privacy. Experiments show that FedProG improves robustness and generalization over baselines while drastically reducing client computational overhead.

Existing image watermarking methods typically entangle visual content with spatial structure, making them highly sensitive to geometric transformations and alignment discrepancies, especially in the presence of deepfake manipulations. In this paper, we propose a semantic-driven facial watermarking framework for robust identity recovery. The key idea is to decouple identity-related semantic information from spatial layout and encode it into a compact and spatially robust semantic representation. Specifically, we decompose a face into semantic components and aggregate deep features into component-wise latent representations, which are quantized via independent codebooks and converted into a compact bitstream for embedding. After decoding, the embedded semantic information is recovered and used to reconstruct identity-consistent facial content, even under slight geometric distortions and tampering. Experiments on CelebA-HQ and FFHQ demonstrate that our method significantly outperforms existing watermarking approaches in terms of reconstruction quality, identity preservation, and retrieval accuracy under both photometric and geometric attacks, validating the effectiveness of semantic component-wise encoding for reliable face recovery.

We argue that forgetting is not confined to continual learning but is a general optimization phenomenon: during standard training, dominant mini-batch gradients suppress rare but useful update directions, causing short-term forgetting at every step. When such knowledge is never revisited, these losses compound into long-term forgetting—the classical failure mode of continual learning. We introduce FOGO, a scalable optimizer that continuously detects and resolves gradient interference across both regimes. FOGO spectrally orthogonalizes momentum updates to prevent dominant directions from monopolizing optimization, then stores representative past directions in a compact codebook memory built on random projection, where pairwise distances are provably preserved in low-dimensional space. At each step, conflicts between the current update and stored directions are resolved via lightweight orthogonal correction and lifted back through a proximal step, with minimal overhead and no data storage. Across class-imbalanced classification, continual visual learning under domain and class shifts, continual fine-tuning of LLaVA-7B, and GPT-2 pretraining, FOGO consistently improves convergence and knowledge retention, outperforming Adam and Muon.

Many biological systems evolve through continuous local dynamics while switching between latent regimes defined by learning, stimulus context, internal state, or developmental stage. These processes are often observed only as unpaired longitudinal snapshots: the same cells, neurons, or animals are not tracked as matched trajectories, even though population states are sampled across successive stages. This creates two coupled challenges. First, trajectories must respect curved low-dimensional manifolds embedded in high-dimensional biological measurements. Second, the model must identify when the transport mechanism itself changes. We introduce FLUX (FLow matching for Unpaired longitudinal data with miXture-of-experts), a geometry-aware longitudinal flow-matching framework for joint transport modeling and unsupervised regime discovery. FLUX learns a data-dependent metric from pooled labeled and unlabeled observations, uses that metric to construct geometry-aware conditional paths between adjacent marginals, and decomposes the resulting velocity field into sparse expert vector fields selected by a Straight-Through Gumbel-Softmax router. Across manifold controls, a regime-switching Lorenz system, widefield cortical calcium imaging during associative learning, and embryoid body single-cell differentiation, FLUX reconstructs longitudinal transport while recovering interpretable regime structure. In neural data, the router separates early/intermediate training from late training, coinciding with the behavioral divergence of CS+ and CS- lick indices. In embryoid body differentiation, FLUX separates expression-evolution regimes associated with pluripotent and more differentiated cell populations. Ablations show that mixture-of-experts routing alone is insufficient: FLUX without geometric learning can fit local transport but fails or weakens regime discovery when regimes are encoded in local dynamics. These results suggest that geometry-aware velocity decomposition provides a general strategy for discovering latent biological state transitions from unpaired longitudinal snapshots.

Recent development of large language models (LLMs) has empowered multi-agent systems (MAS) through external skills and inter-agent discussion to solve complex tasks. Although such a paradigm improves the capability of LLM systems, it also introduces substantial efficiency overhead. Existing approaches mainly reduce this overhead through software-level optimization. However, these methods overlook how to exploit the graph-level structure of MAS discussion and its suitability for hardware-aware acceleration, thus causing latency, especially when the number of agents, discussion rounds, or concurrent sessions increases. In this paper, we propose FASD, an FPGA-algorithm co-design framework for acceleration towards graph dynamic system agent discussion. We argue that MAS discussion can be formed as a graph-coupled dynamical system and thus agent activation pruning can be optimized through phase-coupled dynamics method. Based on these insights, we designed the FPGA-aware optimization for the problem. FASD mainly consists of the following parts. Firstly, we profile representative MAS workflows and construct a phase profile for dynamic system modeling. Secondly, the hardware-friendly optimization progress, given the profile, is implemented on FPGA. Through extensive experiments on multi-agent discussion workloads, we demonstrate that FASD improves discussion efficiency while preserving task performance, with stronger benefits as the agent graph becomes larger and more complex.

This paper studies category-level RGB-D object pose estimation, which recovers an object's 3D rotation and translation without instance-specific CAD models or reference views. This task is highly ambiguous due to intra-class variations, symmetries, and partial observations. Current solutions struggle to balance reliability and efficiency: deterministic methods are prone to error propagation from intermediate structures, while diffusion models suffer from high inference latency and complex post-hoc candidate extraction. To address this, we present F2G-Pose, a real-time direct, single-pass framework that predicts category-level pose, metric size, and camera-frame completed shape from a single RGB-D observation in one feed-forward pass. F2G-Pose lifts dense visual foundation features to partial point clouds, encodes local geometry with DGCNN tokenization, and integrates object-level structure with a Mixture-of-Experts Transformer. Joint size prediction and camera-frame shape completion encourage metric consistency through dense geometric supervision. Trained only on synthetic SOPE data, F2G-Pose achieves state-of-the-art accuracy on SOPE and ROPE while running at 28 FPS, and further demonstrates strong camera-frame geometry on HouseCat6D and real-object transfer on HANDAL. Analyses of latency, robustness, stability, shape completion, and GenPose++ candidate behavior further demonstrate the efficiency and reliability of F2G-Pose, with real-world manipulation experiments demonstrating deployment potential under segmented RGB-D inputs.

Extremely sparse-view computed tomography (xSV-CT) is critical when scanning time, motion, or radiation tolerance limits each scan to only a few projections. In many such scenarios, the same acquisition limits also constrain dataset construction, making pre-reconstructed 3D volumes from dense scans unavailable. This exposes a gap in current sparse-view approaches: Optimization-based methods, which use the sparse measurements directly but lack data-driven priors to suppress artifacts, and learning-based methods, which use strong priors but usually require densely scanned training volumes acquired outside the xSV-CT regime. We study this train-sparse / infer-sparse setting by learning a pose-aware diffusion prior from one 2D projection per training sample, then guiding diffusion sampling with measured-view fidelity, shared-volume reprojection, and projection-physics consistency for tomographic reconstruction. On two public CT datasets across 1-, 4-, and 8-view settings, the proposed method achieves the best novel-view synthesis scores and best or competitive reconstruction quality compared with baselines that use dense-volume supervision.

Visual Autoregressive (VAR) models have emerged as a strong alternative to diffusion for image synthesis, yet their fixed training resolution prevents direct generation at higher resolutions. Naively transferring training-free extrapolation methods from LLMs or diffusion models to VAR yields three characteristic failure modes: global repetition, local repetition, and detail degradation. We trace them to a unified band-stage mismatch: VAR generates images in a coarse-to-fine, scale-wise process where each stage is driven by a distinct dominant RoPE frequency band, and each failure mode emerges when the dominant band of a particular stage is disrupted. Building on this insight, we propose Stage-Aware RoPE Remapping, a training-free strategy that assigns each frequency band a stage-specific remapping rule, jointly suppressing all three failure modes. We further observe that attention becomes systematically dispersed as the image resolution increases. Existing methods typically depend on predefined attention scaling factors, which are neither adaptive to the target resolution nor capable of faithfully capturing the actual extent of attention dispersion. We therefore propose Entropy-Driven Adaptive Attention Calibration, which quantifies dispersion via a resolution-invariant normalized entropy and yields a closed-form per-head scaling factor that realigns the extrapolated-resolution attention entropy with its training-resolution counterpart. Extensive experiments show that our method consistently outperforms prior resolution-extrapolation methods in both structural coherence and fine-detail fidelity. Our codes have been released in supplementary materials and will be released on Github.

In high-stakes risk prediction, interval-valued predictions provide a natural way to represent predictive uncertainty. However, standard evaluation tools such as the receiver operating characteristic (ROC) curve and the area under the curve (AUC) are designed for point-valued predictions and do not capture how uncertainty affects discrimination performance. To address this gap, we develop an uncertainty-aware ROC framework and corresponding interval-based AUC (iAUC) metrics for evaluating the performance of interval-valued risk predictions. The framework constructs two ROC-style curves with associated areas $\mathrm{AUC}_L$ and $\mathrm{AUC}_U$, and shows that these quantities induce a three-region decomposition of positive-negative rankings into confidently correct, ambiguous, and confidently incorrect orderings. Under valid class-conditional coverage, $\mathrm{AUC}_L$ and $\mathrm{AUC}_U$, together with the pairwise miscoverage rate, provide theoretical bounds on the optimal AUC, linking interval coverage to achievable discrimination. The framework is compatible with a range of methods for quantifying epistemic uncertainty in risk prediction, including Bayesian, bootstrap, and ensemble-based procedures, and provides a practical way to compare predictive models and interval-generation methods. Experiments on clinical benchmark data and MIMIC-IV mortality prediction show that models with similar point AUC can have different uncertainty-aware ranking profiles, and that the proposed decomposition can support risk-aware model selection and threshold-based abstention.

Human experts can accumulate experience from open-ended and complex inspection tasks, thereby continually improving their inspection capabilities. Actually, industrial hardware inspection faces challenges including open-set defect categories, complex defects (tiny, high-gloss, low-light, or blurred), high inference cost, and difficulty in accumulating experience post-deployment. Existing end-to-end inspection methods typically couple image restoration with defect recognition in a single forward pass, limiting generalization to unseen components or composite defects; cascade “restore-then-detect” approaches often rely on static preprocessing, hindering adaptive adjustment based on scenario, defect morphology, and historical failures. To address this, we propose EvoInspect, the first memory-enhanced multi-modal multi-agent framework for industrial defect object detection. It leverages a multi-modal agentic memory mechanism to distill self-evolving scenario-specific Defect Detail Restoration decisions and dynamically grounded trajectories, enabling “accumulating experience like human experts.” Specifically, (1) we introduce a dynamic Defect Detail Restoration strategy, including adaptive slicing for tiny defects, highlight suppression, low-light enhancement, super-resolution, and binarization, combined with a coarse-to-fine token-efficient grounding mechanism for efficient defect capture; (2) we design a dual-channel distillation mechanism unifying restoration and detection (perception and execution) experience, incorporating both successful and failed validation trajectories to support system self-evolution. Experiments on bearing surfaces, PCBs, solar electroluminescence (solar EL), and magnetic tile datasets show that EvoInspect consistently outperforms strong baselines in defect localization recall, inference accuracy, while demonstrating cross-scenario adaptability and offline continual improvement.