In this paper, we revisit multimodal few-shot 3D point cloud semantic segmentation (FS-PCS), identifying a conflict in "Fuse-then-Refine" paradigms: the "Plasticity-Stability Dilemma." In addition, Contrastive Language-Image Pre-training (CLIP)'s inter-class confusion can result in semantic blindness. To address these issues, we present the Decoupled-experts Arbitration Few-Shot SegNet (DA-FSS), a model that effectively distinguishes between semantic and geometric paths and mutually regularizes their gradients to achieve better generalization. DA-FSS employs the same backbone and pre-trained text encoder as the baseline MultiModal Few-Shot SegNet (MM-FSS) to generate text embeddings, which can increase cost-free modalities' utilization rate and better leverage each modality's information space. To achieve this, we propose a Parallel Expert Refinement module to generate each modal correlation. We also propose a Stacked Arbitration Module (SAM) to perform convolutional fusion and arbitrate correlations for each modality pathway. The Parallel Experts decouple two paths: a Geometric Expert maintains plasticity, and a Semantic Expert ensures stability. They are coordinated via a Decoupled Alignment Module (DAM) that transfers knowledge without propagating confusion. Experiments on popular datasets (S3DIS, ScanNet) demonstrate the superiority of DA-FSS over MM-FSS. Meanwhile, geometric boundaries, completeness, and texture differentiation are all superior to the baseline. The code is available at: https://github.com/MoWenQAQ/DA-FSS/.
论文检索
输入标题、作者或关键词，从 990 篇学术成果中精准定位
Predicting ligand binding sites on protein surfaces requires capturing complex local geometries and satisfying physical constraints. Existing voxel-based methods suffer from high computational costs and rotation sensitivity, while standard point-cloud GNNs often lack geometric completeness—failing to distinguish chiral structures or subtle topological variations. In this work, we propose UniPocket, a novel E(3)-equivariant surface graph neural network. Inspired by recent advances in efficient geometric completeness, UniPocket constructs a Manifold-Aware Surface Encoder that utilizes local surface normals as virtual reference frames to capture complete geometric invariants without expensive high-order tensor products. Furthermore, we introduce a Ligand-Gated Message Passing mechanism to condition the surface features on the chemical semantics of the target ligand, and a Physics-Aware Vector Rejection Module that enforces steric constraints via orthogonal vector decomposition. Experimental results on standard benchmarks (PDBbind, COACH420, Holo4k) demonstrate that UniPocket achieves state-of-the-art performance, validating that geometric completeness and physical inductive biases are key to precise binding site detection.
Cross-task generalization (CTG) enables large language models (LLMs) to handle unseen tasks proficiently, enhancing their adaptability in real-world scenarios. However, existing methods relying on per-token dynamic routing to multiple trained LoRA adapters face high computational and GPU memory costs. Recent Representation Fine-Tuning (ReFT) enhances efficiency for single-task adaptation by editing only prefix and suffix token representations. However, the semantic ambiguity of tokens and absence of a self-guided mechanism for parameter selection in unseen tasks limits their application to CTG. To this end, we propose RaMod, a Representation-Aware Modularity framework to extend the ReFT paradigm to CTG through two novel components: (i) Dual-Modular Representation & Parameter Fine-tuning, which manipulates only a strategically chosen subset of hidden representations with modular interventions to guide the model toward solving unseen tasks; and (ii) Asynchronous Orchestrator, which proactively allocates and releases GPU memory for selected interventions, thereby minimizing storage overhead. Extensive experiments demonstrate that RaMod not only achieves superior CTG performance but also substantially reduces the overhead of the latest CTG baseline, achieving 83%, 100%, and 79% reduction in its additional prefill time, generation delays, and memory consumption relative to original LLMs.
Generalized vehicle trajectory prediction across diverse junctions, including urban intersections and roundabouts, remains a fundamental task in Cooperative Vehicle–Infrastructure Systems (CVIS). This study faces two key challenges: (1) Generalize across junctions with heterogeneous map semantics and traffic behavioral patterns, where the former arises from differences in road topologies and traffic regulations, and the latter reflects diverse behavioral intentions of road users; (2) Scenario-adaptive interaction modeling, where single-modality trajectory learning captures local spatio-temporal correlation, but lacks map constraint and direction-aware interaction contexts. To overcome these challenges, we propose G-VTM, a generalized vision-trajectory model. G-VTM models fine-grained behavioral patterns and relative spatial interaction from trajectory modality. At the vision modality, G-VTM captures global map semantics while modeling scenario- and direction-aware interaction based on intuitive visual perception. Experiments on multiple real-world datasets collected by unmanned aerial vehicles (UAVs) demonstrate that our method achieves strong generalized performance under heterogeneous traffic conditions. The code is provided at https://github. com/zxyhaclyon/G-VTM.
In this work, we introduce XSIM, a sensor simulation framework for autonomous driving. XSIM extends 3DGUT splatting with a generalized rolling-shutter modeling tailored for autonomous driving applications. Our framework provides a unified and flexible formulation for appearance and geometric sensor modeling, enabling rendering of complex sensor distortions in dynamic environments. We identify spherical cameras, such as LiDARs, as a critical edge case for existing 3DGUT splatting due to cyclic projection and time discontinuities at azimuth boundaries leading to incorrect particle projection. To address this issue, we propose a phase modeling mechanism that explicitly accounts temporal and shape discontinuities of Gaussians projected by the Unscented Transform at azimuth borders. In addition, we introduce an extended 3D Gaussian representation that incorporates two distinct opacity parameters to resolve mismatches between geometry and color distributions. As a result, our framework provides enhanced scene representations with improved geometric consistency and photorealistic appearance. We evaluate our framework extensively on multiple autonomous driving datasets, including Waymo Open Dataset, Argoverse 2, and PandaSet. Our framework consistently outperforms strong recent baselines and achieves state-of-the-art performance across all datasets.
We introduce the Visual Implicit Geometry Transformer (ViGT), an autonomous driving geometric model that estimates continuous 3D occupancy fields from surround-view camera rigs. ViGT represents a step towards foundational geometric models for autonomous driving, prioritizing scalability, architectural simplicity, and generalization across diverse sensor configurations. Our approach achieves this through a calibration-free architecture, enabling a single model to adapt to different sensor setups. Unlike general-purpose geometric foundational models that focus on pixel-aligned predictions, ViGT estimates a continuous 3D occupancy field in a bird’s-eye-view (BEV) addressing domain-specific requirements. ViGT naturally infers geometry from multiple camera views into a single metric coordinate frame, providing a common representation for multiple geometric tasks. Unlike most existing occupancy models, we adopt a self-supervised training procedure that leverages synchronized image-LiDAR pairs, eliminating the need for costly manual annotations. We validate the scalability and generalizability of our approach by training our model on a mixture of five large-scale autonomous driving datasets (NuScenes, Waymo, NuPlan, ONCE, and Argoverse) and achieving state-of-the-art performance on the pointmap estimation task, with the best average rank across all evaluated baselines. We further evaluate ViGT on the Occ3D-nuScenes benchmark, where ViGT achieves comparable performance with supervised methods.
Stochastic games have become a prevalent framework for studying long-term multi-agent interactions, especially in the context of multi-agent reinforcement learning. In this work, we comprehensively investigate the concept of constant-memory strategies in stochastic games. We first establish some results on best responses and Nash equilibria for behavioral constant-memory strategies, followed by a discussion on the computational hardness of best responding to mixed constant-memory strategies. Those theoretic insights are later verified on several sequential decision-making testbeds, including the Iterated Prisoner's Dilemma, the Iterated Traveler's Dilemma, and the Pursuit domain. This work aims to enhance the understanding of theoretical issues in single-agent planning under multi-agent systems, and uncover the connection between decision models in single-agent and multi-agent contexts. The codebase and the full version of this paper is available at github.com/Fernadoo/Const-Mem.
Hyperspectral image (HSI) clustering facilitates the unsupervised discrimination of complex surface materials but traditionally relies on the idealized assumption of centralized data availability. In real-world scenarios, however, this assumption clashes with data privacy regulations and the physical distribution of data across isolated silos. While Federated Learning offers a decentralized solution, existing frameworks in remote sensing are predominantly confined to supervised paradigms and struggle to address the heavy reliance on annotations and Non-IID distributions inherent among clients. To overcome these limitations, we propose a novel framework named Robust Federated HSI Clustering(RFHC) that enables collaborative unsupervised learning without requiring raw data exchange. Specifically, we design a dual-encoder architecture that incorporates a Federated Model Weight Augmentation strategy(FMWA), which generates consistent views through local-global network interactions to mitigate the spectral distortion introduced by traditional data augmentation. Furthermore, we develop a hybrid optimization objective that synergizes prototype relationship optimization with contrastive learning. This mechanism utilizes global prototypes to guide local training, effectively stabilizing feature learning against data heterogeneity while ensuring intra-cluster compactness. Extensive experiments on three benchmark HSI datasets demonstrate the effectiveness and superiority of the proposed method against state-of-the-art model(SOTA) federated approaches.
Batch selection is crucial for improving both training efficiency and predictive performance in deep multi-label classification (MLC). Existing batch selection methods typically rely on a single metric to assess instance importance and use static label weights to distinguish label significance, neglecting the dynamic evolution of metric utility and label significance during training. In addition, the method that explicitly exploits label correlations is largely affected by abundant irrelevant labels and insensitive to local label distributions. To address these issues, we propose D2ACE, a novel multi-label batch selection method guided by Dual Dynamics and Adaptive Correlation Enhancement. D2ACE explicitly captures metric and label-level training dynamics by combining stage-wise Bernoulli mixture sampling, which balances uncertainty and noise-resistant hardness, with dynamic label weighting to recalibrate label priorities at each epoch based on current metric statistics. Furthermore, D2ACE introduces a local context-aware correlation enhancement to focus on relevant labels with instance-adaptive dependencies. Extensive experiments on tabular and image benchmarks demonstrate that D2ACE outperforms existing batch selection approaches across various deep MLC models, achieving stronger predictive performance and more efficient correlation modeling.
Dynamic Graph Neural Networks (DyGNNs) are facing challenges with distribution shifts between training and test data that are similar but not identical. Existing DyGNNs for out-of-distribution scenarios primarily focus on discovering invariant patterns in the spatial domain, overlooking its impact on the structural properties in the spectral domain. In this paper, we propose a spectral-based graph augmentation framework designed to investigate and improve generalization behavior in dynamic graphs under distribution shifts. Specifically, we augment the input graph spectra into a mixture of shift components by maximizing the variance of spectral distance and propose an efficient approximation to reduce the computational cost brought by eigen-decomposition. Building on this, we develop a multi-encoder architecture in which each encoder targets a specific spectral shift component to generate referential representations. Our method adopts a new learning objective to encourage the model to rely on robust spectral properties for better generalization under distribution shifts. Extensive experiments on both real-world and synthetic datasets demonstrate that our proposed method significantly outperforms state-of-the-art approaches in node classification and link prediction tasks. Source codes are available at https://github.com/SSQiana/DSPA.
Despite decades of intensive research and optimization, modern Boolean Satisfiability (SAT) solvers have reached a plateau where significant performance gains are increasingly difficult to achieve. While Large Language Models (LLMs) have demonstrated remarkable capabilities in pattern recognition and code generation for combinatorial optimization, their direct application to highly optimized SAT solvers remains a formidable challenge due to the extreme complexity and sensitivity of solver heuristics. In this paper, we introduce AESAT (Auto-Evolving SAT solving), a novel neuro-symbolic framework designed to automatically evolve and optimize the heuristic functions of SAT solvers. AESAT employs a memetic-inspired approach, synergizing LLM-guided individual optimization with evolutionary exploration. By leveraging self-optimized prompting techniques, our framework enables LLMs to iteratively discover and refine sophisticated heuristics that bypass the limitations of human-engineered designs. The efficacy of AESAT is demonstrated by its flagship derivative, AE-Kissat-MAB, which won the main track of the 2025 International SAT Competition by a wide margin. This result represents the first time an LLM-enhanced solver has dominated the world's premier SAT competition, marking a paradigm shift in the automated design of reasoning algorithms.
Accurate trajectory prediction of multiple road users at urban intersections--including motorized and nonmotorized vehicles and pedestrians--is critical for cooperative vehicle-infrastructure systems and intelligent transportation systems. This study focuses on multiple road users' trajectory prediction in urban intersections. Such predictions face two key challenges: modeling interactions among multiple road users in complex scenarios and achieving accurate long-term prediction. Existing solutions inadequately incorporate these interactions and suffer from error accumulation or overall bias when performing long-term prediction. To overcome these challenges, we propose a long-term Trajectory prediction multi-scale AutoRegressive framework (TrajAR), which follows an encoder-decoder structure. The encoder dynamically perceives road users' motion trends, types, signals, and implicit interactions for effective handling of complex scenarios. The decoder employs a multi-scale prediction strategy that progressively refines the predicted trajectory from coarse to fine scales, where coarse-scale predictions establish long-term path backbones and finer scales enhance precision. These designs allow TrajAR to achieve accurate long-term prediction in real-world scenarios, demonstrated through experiments on four real-world urban datasets from different intersections. Our results show an average improvement of 23.8%. We provide the code of TrajAR at https://github.com/LetianGong/TrajAR.
We investigate the interaction between quantization and pruning in the compression of open-weight small language models (SLMs), as these techniques are frequently combined in practice without a clear understanding of whether their effects are antagonistic, synergistic or additive. Prior work has reported ordering effects and studied pruning or quantization in isolation, but rarely quantifies their interaction across models and evaluation metrics. We introduce an interaction coefficient that isolates non-additive effects and apply it to Falcon3-1B-Base and LLaMA-3.2-1B, with a limited study on Qwen2.5-1.5B. Our experiments cover four hybrid application orders, multiple pruning sparsities and 4/8-bit quantization. We find non-monotonic interactions: memory savings are dominated by 4-bit quantization, while pruning alone provides limited benefits. Hybrids exhibit the greatest effects at global unstructured pruning sparsity s ∈ {0.2, 0.3} while getting close to additivity at s=0.5. At low sparsity, truthfulness improves, while reasoning losses diminish at higher sparsity. Future work will extend interaction analysis to hardware-aware sparse kernels and larger models.
Gradient boosting remains a strong and widely used method for tabular data learning, but its performance often degrades when training labels are noisy. This behavior is largely related to the way boosting algorithms emphasize samples with large gradients, without explicitly accounting for whether such errors originate from informative hard cases or from unreliable labels. We address this issue by reconsidering how sample reliability is evaluated during boosting. Instead of relying on instantaneous error, we examine the evolution of each sample’s residuals across iterations. Based on this insight, we propose Information-Theoretic Trust Boosting (ITBoost), which uses the Minimum Description Length principle to measure the complexity of residual trajectories. Samples whose residual patterns fluctuate in an irregular manner are treated as less trustworthy and are down-weighted during learning. Theoretically, we derive a tighter generalization bound for ITBoost under label noise. Empirical results on various tabular benchmarks indicate that ITBoost provides improved robustness in noisy environments over leading boosting and deep tabular models, while retaining best average performance on clean data.
Deterministic auctions are attractive in practice due to their transparency, simplicity, and ease of implementation, motivating a sharper understanding of when they can attain the same outcomes as randomized mechanisms. We study deterministic implementation in single-item auctions under two notions of outcomes: (revenue, welfare) pairs and interim allocations. For (revenue, welfare) pairs, we show a separation in discrete settings: there exists a pair implementable by a deterministic Bayesian incentive-compatible (BIC) auction but not by any deterministic dominant-strategy incentive-compatible (DSIC) auction. For continuous atomless priors, we identify conditions under which deterministic DSIC auctions are equivalent to randomized BIC auctions in terms of achievable outcomes. For interim allocations, under a strict monotonicity condition, we establish a deterministic analogue of Border's theorem for two bidders, providing a necessary and sufficient condition for deterministic DSIC implementability. Using this characterization, we exhibit an interim allocation implementable by a randomized BIC auction but not by any deterministic DSIC auction.
Recent efforts have successfully scaled plain Vision Transformers (ViTs) to unprecedented sizes, ranging from 6B to 22B parameters. However, hierarchical ViTs, which are inherently better suited for multi-scale representation and dense prediction tasks, have largely remained constrained to under 2B parameters. This scaling gap prevents the community from leveraging high-capacity, multi-scale foundation models for complex visual scenes. To bridge this gap, we propose EHV, an Efficient Hierarchical ViT architecture designed for massive scaling. Our dense models scale from 200M to 5B parameters, and we further introduce a Sparse Mixture-of-Experts (SMoE) variant, pushing the scale to an industry-leading 30B parameters. The training pipeline follows a two-stage pretraining strategy: (1) MAE Stage: self-supervised pretraining on ImageNet-21K using a Masked Autoencoder (MAE); and (2) Distillation Stage: distilling knowledge from multiple state-of-the-art foundation models on a 27M-image dataset. With only 6.7B active parameters, EHV-5B-MoE achieves an exceptional 89.0% linear accuracy on ImageNet-1K, outperforming much larger models like EVA-CLIP-18B and DINOv3-7B. These results demonstrate that EHV effectively learns high-quality, generalizable, and linearly separable features across image classification, video analysis, and dense prediction tasks.
We present complementary branching, a new branching approach for model counting based on the complement counting paradigm. Instead of branching on individual variables, complementary branching decomposes the counting problem for arbitrary CNF formulas into several subformulas, which naturally augments the classic DPLL branching. We show two novel results in which the main tool is complementary branching. First, we design new #SAT algorithms for sparse CNF formulas running in time O*(2^(alpha n)), for some constant alpha < 1. As a second application, we improve the best known deterministic upper bound for #3-SAT to O*(1.637^n) by using a version of clause learning based on complementary branching. These results demonstrate that complementary branching is a powerful tool for designing faster exact algorithms for propositional model counting.
4D Gaussian Splatting (4DGS) enables high-quality, real-time rendering of dynamic scenes and is becoming a popular format for sharing 4D assets. This trend calls for robust copyright watermarking that can be verified from rendered videos without access to the original scene or model parameters. However, watermarking 4DGS is challenging: verification relies on short multi-view clips whose frames vary with motion, viewpoint changes, and post-processing. More importantly, decoding from rendered frames is easily dominated by scene content (objects, textures, illumination) rather than subtle watermark traces, leading to unstable evidence across frames and poor generalization across scenes. We propose Guard4D, a decoupled watermarking framework for 4DGS. Guard4D pre-trains a general-purpose message decoder under text supervision and embeds a binary message by optimizing compact spherical-harmonic offsets while keeping geometry and opacity fixed. To improve extraction from short clips and suppress semantic interference, we introduce a temporal modeling and semantic decoupling (TMSD) module that temporally aggregates watermark information and uses clean and noise-perturbed control clips generated from the non-watermarked model to reduce the influence of semantics on watermark decoding. Extensive experiments on dynamic 4DGS scenes demonstrate the effectiveness of Guard4D. Code is available at https://github.com/shisyy/Guard4D.
Few-shot learning aims to recognize novel categories from limited labeled samples, where prototypes estimated from 1--5 supports per class are often unreliable. Semantic-based approaches alleviate this by introducing class-level priors, but they often ignore instance-level cues and rarely optimize queries under the inductive protocol. We propose PMCE, a Probabilistic framework that leverages Multi-granularity semantics with Caption-guided Enhancement for few-shot classification. On base classes, we build a knowledge bank with class-wise visual statistics and class-name embeddings. At test time, the semantic embedding of a novel class retrieves a few similar base classes whose visual priors are aggregated into a class-specific prior and combined with the support-based prototype via MAP estimation. Simultaneously, we train a lightweight enhancer on base classes that fuses frozen BLIP captions with visual features, and apply it to both supports and queries without using query-set statistics or novel labels. A simple caption-consistency regularizer further improves robustness to noisy captions. Experiments on four standard benchmarks with ResNet-12 and Swin-T backbones show that PMCE outperforms state-of-the-art few-shot baselines, achieving up to 7.71% gains over the strongest competitor on MiniImageNet in the challenging 1-shot setting. Our code is available at https://github.com/channa419/PMCE.
Learning to Defer operates by deferring AI-uncertain samples to humans, enabling the system to outperform either alone. Some works extend it by introducing human-AI combination to deferral. However, they remain limited to binary choices. Given that AI, humans, and human-AI combination are each indispensable, we extend the binary deferral paradigm to a ternary one. There are two challenges: i) how to effectively select among the three modes, especially distinguishing humans from combination? ii) how to design an enhanced combination without being degraded by unreliable model predictions? To address the challenges, we propose TriHAI, a tri-mode deferral method that routes samples to suitable modes based on normalized confidence scores obtained through a discriminative gating network, and enhances combination mode by fusing model predictions refined by human-guided Conformal Prediction and human predictions via Bayesian theory. Experiments on three datasets show that TriHAI surpasses other human-AI baselines by up to 9.57% in accuracy.