arXiv:2411.12321v2 Announce Type: replace
Abstract: Principal component analysis (PCA) and its sparse variants (sPCA) are widely used as a precursor to independent component analysis (ICA) for blind source separation (BSS). However, sPCA typically relies on a deflation strategy that extracts components sequentially and imposes orthogonality between them. When the underlying sources overlap, this discards the cross component structure that ICA depends on, degrading separation. This paper proposes dissociative PCA (DPCA), which estimates components jointly rather than by deflation. DPCA introduces left and right dissociation matrices into the SVD based decomposition to explicitly model the interdependencies among principal components (PCs) and loading vectors (LVs), while sparsity constraints maintain interpretability. We develop three algorithms called DPCA1a, DPCA1b, and DPCA2, using adaptive soft thresholding with gradient and coordinate descent, together with a secondary firm thresholding step that preserves sparsity and suppresses background noise in the recovered loading vectors. The method is evaluated on four settings, namely simulated fMRI source retrieval, foreground and background separation, image reconstruction, and image inpainting, where it recovers source structure more reliably than classical sPCA based pipelines, with the largest gains under significant spatial overlap. DPCA reduces to ordinary PCA when the sparsity parameter is zero. A MATLAB implementation of the proposed algorithms is publicly available at https://github.com/usmankhalid06/DPCA.
Science Journals
Dimension Reduction via Sum-of-Squares and Improved Clustering Algorithms for Non-Spherical Mixtures
arXiv:2411.12438v2 Announce Type: replace
Abstract: We develop a new approach for clustering non-spherical (i.e., arbitrary component covariances) Gaussian mixture models via a subroutine, based on the sum-of-squares method, that finds a low-dimensional separation-preserving projection of the input data. Our method gives a non-spherical analog of the classical dimension reduction, based on singular value decomposition, that, among several other applications, forms a key component of the celebrated spherical clustering algorithm of Vempala and Wang [VW04].
As applications, we obtain an algorithm to (1) cluster an arbitrary total-variation separated mixture of $k$ centered (i.e., zero-mean) Gaussians with $n\geq \operatorname{poly}(d) f(w_{\min}^{-1})$ samples and $\operatorname{poly}(n)$ time, and (2) cluster an arbitrary total-variation separated mixture of $k$ Gaussians with identical but arbitrary unknown covariance with $n \geq d^{O(\log w_{\min}^{-1})} f(w_{\min}^{-1})$ samples and $n^{O(\log w_{\min}^{-1})}$ time. Here, $w_{\min}$ is the minimum mixing weight of the input mixture, and $f$ does not depend on the dimension $d$. Our algorithms naturally extend to tolerating a dimension-independent fraction of arbitrary outliers. Before this work, the techniques in the state-of-the-art non-spherical clustering algorithms needed $d^{O(k)} f(w_{\min}^{-1})$ samples and time for clustering such mixtures.
Our results may come as a surprise in the context of the $d^{\Omega(k)}$ statistical query and sum-of-squares lower bounds [DKS17, DKPP24] for clustering non-spherical Gaussian mixtures. While these results are usually thought to rule out $d^{o(k)}$ cost algorithms for the problem, our results show that the lower bounds can in fact be circumvented for a remarkably general class of Gaussian mixtures.
arXiv:2411.15240v5 Announce Type: replace
Abstract: Wearable movement data is collected by nearly all commercially available smartwatches and is a valuable resource for mental health research, reflecting fine-grained temporal behavioral trends. Despite its promise, the development of foundation models for health wearable modeling remains limited when compared to clinical image and text analysis. We designed transformers with patch embeddings and used self-supervised masked autoencoder pretraining on minute-level week-long actigraphy (physical activity intensity measurement) sequences to develop and evaluate the Pretrained Actigraphy Transformer (PAT). PAT is an open-source foundation model for wearable movement time series that combines week-long temporal modeling, psychiatric outcome evaluation, and reproducibility on public data. Pretrained on data from 21,538 U.S. participants in a nationally representative cohort from the National Health and Nutrition Examination Survey (NHANES), PAT consistently outperformed non-foundation-model baselines across mental health prediction tasks-including benzodiazepine and SSRI use, depression, and sleep abnormalities. During the benzodiazepine medication usage prediction task, PAT demonstrated the largest improvement over non-foundational deep learning models commonly used for time-series modeling (i.e., 55.6% improvement over the LSTM, 21.4% improvement over the 1-D CNN, 14.8% improvement over the ConvLSTM). Beyond predictive accuracy, PAT provides interpretable attention maps highlighting specific periods of daily activity most important for clinical predictions, offering model transparency and potential clinical insights. The results suggest that PAT offers an easy-to-deploy, adaptable and scalable solution to advance clinical insight from wearable sensor data for researchers and clinicians.
GitHub: https://github.com/njacobsonlab/Pretrained-Actigraphy-Transformer/
arXiv:2606.01520v1 Announce Type: new
Abstract: A single action-conditioned latent predictive architecture can in principle be trained on the structured state of a driving scene, a robot workspace, or a financial order book. The ingredients for doing so within any one domain already exist and are individually validated: masked-latent prediction, action-conditioned latent world models, discrete action tokenization, and joint-embedding prediction on voxelized state. What is not established, and what TERRA addresses, is the transfer question: when does a representation or predictor learned in one structured-state domain carry over to a structurally analogous but otherwise unrelated domain, and by how much. We give this question a formal treatment. We model each domain as a controlled Markov process on a graded latent grid, factor any instantiation into thin domain adapters and a shared domain-invariant core, and identify a cross-domain correspondence with an approximate Markov decision process homomorphism whose quality is measured by a lax bisimulation discrepancy and, for domains lacking a shared coordinate system, by a Gromov-Wasserstein distance between their action-conditioned transition operators. Under a Lipschitz predictor we derive a transfer bound that separates source-model error from structural mismatch, grows geometrically in the prediction horizon, and is certified from below by the Gromov-Wasserstein distance; we then connect latent error to decision regret through the Lipschitz value property of bisimulation metrics. The resulting Structured-State Transfer Hypothesis is stated as a falsifiable claim with a preregistered experimental program, centered on a transfer test from driving scenes to order books, including conditions under which it is refuted. We present no empirical results: this is a research proposal that converts a widely repeated intuition into testable theory.
arXiv:2411.17790v3 Announce Type: replace
Abstract: Accurate 3D mapping in endoscopy enables quantitative, holistic lesion characterization within the gastrointestinal (GI) tract, requiring reliable depth and pose estimation. However, endoscopy systems are monocular, and existing methods relying on synthetic datasets or complex models often lack generalizability in challenging endoscopic conditions. We propose a robust self-supervised monocular depth and pose estimation framework that incorporates a Generative Latent Bank and a Variational Autoencoder (VAE). The Generative Latent Bank leverages extensive depth scenes from natural images to condition the depth network, enhancing realism and robustness of depth predictions through latent feature priors. For pose estimation, we reformulate it within a VAE framework, treating pose transitions as latent variables to regularize scale, stabilize z-axis prominence, and improve x-y sensitivity. This dual refinement pipeline enables accurate depth and pose predictions, effectively addressing the GI tract's complex textures and lighting. Extensive evaluations on SimCol and EndoSLAM datasets confirm our framework's superior performance over published self-supervised methods in endoscopic depth and pose estimation.
arXiv:2412.04177v2 Announce Type: replace
Abstract: Recently, there has been an increasing interest in performing post-hoc uncertainty estimation about the predictions of pre-trained deep neural networks (DNNs). Given a pre-trained DNN via back-propagation, these methods enhance the original network by adding output confidence measures, such as error bars, without compromising its initial accuracy. In this context, we introduce a novel family of sparse variational Gaussian processes (GPs), where the posterior mean is fixed to any continuous function when using a universal kernel. Specifically, we fix the mean of this GP to the output of the pre-trained DNN, allowing our approach to effectively fit the GP's predictive variances to estimate the DNN prediction uncertainty. Our approach leverages variational inference (VI) for efficient stochastic optimization, with training costs that remain independent of the number of training points, scaling efficiently to large datasets such as ImageNet. The proposed method, called fixed-mean GP (FMGP), is architecture-agnostic, relying solely on the pre-trained model's outputs to adjust the predictive variances. Experimental results demonstrate that FMGP improves both uncertainty estimation and computational efficiency when compared to state-of-the-art methods for DNN post-hoc Bayesian inference.
arXiv:2412.10362v2 Announce Type: replace
Abstract: Low-rank adapters (LoRA) enable finetuning of large models with only a small number of parameters. However, they often suffer from an ill-conditioned loss landscape, leading to difficult optimization. Prior work addresses these challenges by aligning adapter updates with full finetuning gradients via custom optimizers, but these methods lack the flexibility to accommodate new adapter architectures and are computationally expensive. We instead introduce OP-LoRA, a novel method which replaces each LoRA adapter with weights predicted by an extra MLP, which is discarded after training. This temporarily allows additional parameters during training to improve optimization, yet requires less wall time than custom optimizers and zero extra cost at inference time because the MLP is discarded. Crucially, extending OP-LoRA to other adapters is as simple as modifying the size of the prediction head for each new adapter type. We show that OP-LoRA allows the optimization to adaptively increase or decrease step size, improving performance and decreasing sensitivity to learning rate. On both small and large-scale LoRA tuning tasks, we observe consistent performance gains of OP-LoRA relative to LoRA and its variants. We achieve especially notable improvements in image generation, with OP-LoRA CMMD scores improving by up to 15 points relative to LoRA. This allows OP-LoRA to achieve the performance of LoRA with half of the inference parameters.
arXiv:2412.19419v2 Announce Type: replace
Abstract: Graph neural networks are deep neural networks designed for graphs with attributes attached to nodes or edges. The number of research papers in the literature concerning these models is growing rapidly due to their impressive performance on a broad range of tasks. This survey introduces graph neural networks through the encoder-decoder framework and provides examples of decoders for a range of graph analytic tasks. It uses theory and numerous experiments on homogeneous graphs to illustrate the behavior of graph neural networks under different training sizes and degrees of graph complexity, with an emphasis on oversmoothing and oversquashing.
arXiv:2412.19444v2 Announce Type: replace
Abstract: Optimization algorithms such as AdaGrad and Adam have significantly advanced the training of deep models by dynamically adjusting the learning rate during the optimization process. However, ad-hoc tuning of learning rates poses a challenge and leads to inefficiencies in practice. To address this issue, recent research has focused on developing ``parameter-free'' algorithms that operate effectively without the need for learning rate tuning. Despite these efforts, existing parameter-free variants of AdaGrad and Adam tend to be overly complex and/or lack formal convergence guarantees. In this paper, we present AdaGrad++ and Adam++, novel and simple parameter-free variants of AdaGrad and Adam with convergence guarantees. We prove that AdaGrad++ achieves comparable convergence rates to AdaGrad in convex optimization without predefined learning rate assumptions. Similarly, Adam++ matches the convergence rate of Adam without relying on any conditions on the learning rates. Experimental results across various deep learning tasks validate the competitive performance of Adam++.
arXiv:2606.01526v1 Announce Type: new
Abstract: In multi-robot systems, maintaining persistent communication graph connectivity is often overly restrictive, especially when robots have limited communication ranges but operate in large environments. Instead, allowing robots to temporarily disconnect and later reconnect is often more desirable for efficient task execution while still ensuring timely information sharing across the team. In this paper, we propose an adaptive prescribed-time control barrier function (adaptive PT-CBF) framework that enables robots to temporarily disconnect and re-enter the communication range within an adjustable and feasible prescribed time. Moreover, we introduce a reconnection triggering mechanism that jointly considers task execution and reconnection urgency, thereby providing a principled way to decide when reconnection should occur. Theoretical analysis justifies convergence to the satisfying reconnection within a prescribed finite time. Experimental results validate the performance of our proposed adaptive PT-CBF with improved task efficiency and satisfying reconnections.
arXiv:2606.01906v1 Announce Type: new
Abstract: Emotions evolve through the dynamics of conversation, and understanding their transition structure is foundational to applications ranging from mental-health screening to dialogue systems. However, existing studies typically compress multi-rater judgments into a single hard label by majority voting, discarding the uncertainty signal needed to understand turn-to-turn transitions. In this article, we propose Bayesian Spectral Emotion Transition Discovery (BSETD), a two-stage framework that discovers emotion-transition structure from multi-rater soft labels. In the first stage, a hierarchical Dirichlet-Multinomial posterior is constructed through the outer product of soft labels, equipping each cell of the K x K transition matrix with a credible interval and Benjamini-Hochberg (BH) false discovery rate (FDR)-controlled significance. In the second stage, the symmetrized graph Laplacian is spectrally decomposed to separate a low-frequency (inertia) component from a high-frequency (contagion) component. On EmotionLines, BSETD simultaneously recovers the signatures of two distinct affective spaces: the Plutchik-adjacent transitions disgust to anger (log2 lift +0.94) and anger to disgust (+0.86) are over-represented, while the Russell-valence-reversed transitions joy to anger (-0.90) and anger to joy (-0.89) are under-represented. A five-source cross-corpus validation yields pairwise Pearson correlations in 0.91-0.98 within English, 0.79-0.85 against Chinese M3ED, and 0.979 between the human hard labels and the LLM virtual soft labels on the same utterance set, demonstrating that a pipeline preserving annotator uncertainty bridges the computational study of emotion dynamics with established psychological theory.
arXiv:2501.08640v2 Announce Type: replace
Abstract: We propose a way to bound the generalisation errors of several classes of quantum reservoirs using the Rademacher complexity. We give specific, parameter-dependent bounds for two particular quantum reservoir classes. We analyse how the generalisation bounds scale with growing numbers of qubits. Applying our results to classes with polynomial readout functions, we find that the risk bounds converge in the number of training samples. The explicit dependence on the quantum reservoir and readout parameters in our bounds can be used to control the generalisation error to a certain extent. It should be noted that the bounds scale exponentially with the number of qubits n. The upper bounds on the Rademacher complexity can be applied to other reservoir classes that fulfill a few hypotheses on the quantum dynamics and the readout function.
arXiv:2501.09293v5 Announce Type: replace
Abstract: As a prominent network abstraction, coflow models efficiently capture communication patterns in data centers. Since coflow scheduling in large-scale data centers is $\mathcal{NP}$-hard, the existing literature has predominantly focused on limited environments with $m=2$ network cores, relying on flow splitting, which introduces substantial operational overhead. Crucially, no approximation algorithm with provable performance guarantees has been proposed for the more practical, non-splitting coflow scheduling problem, even for the $m=2$ case, let alone for general hybrid architectures. To bridge this critical gap, this paper investigates the non-splitting problem within a hybrid, heterogeneous parallel network featuring multiple network cores ($m \ge 2$) composed of Electronic Packet Switches (EPS), not-all-stop Optical Circuit Switches (OCS), and all-stop OCS. We propose a unified polynomial-time approximation algorithm that minimizes the makespan across this hybrid environment without incurring any splitting overhead. Let $\tau$ denote the maximum flow degree across all ports in the network, $N$ be the number of input/output ports, and $m$ be the number of network cores. In pure EPS environments, the algorithm achieves an approximation guarantee of $\min\left\{\tau, 2Nm+1\right\}$. For pure not-all-stop and pure all-stop OCS environments, the guaranteed ratios are $2\min\left\{\tau, 2Nm+1\right\}$ and $2\min\left\{2\tau-1, 2Nm+\tau\right\}$, respectively. Notably, when specialized to the $m=2$ setting, our algorithm escapes network-scale dependencies, yielding constant bounds of $2$ and $4$ for pure EPS, and pure not-all-stop OCS, respectively, and $2\tau+2$ for pure all-stop OCS. By leveraging these constituent bounds, we prove that the overall performance guarantee in the hybrid architecture is upper-bounded by the least-performing switch architecture in the network.
arXiv:2501.15168v2 Announce Type: replace
Abstract: Standard Virtual Element Method (VEM) requires stabilization terms that significantly affect the numerical computation performance. In this work, we propose a stabilization-free VEM for general order \(\mathbf{H}(\operatorname{\mathbf{curl}})\) and \(\mathbf{H}(\operatorname{div})\)-conforming spaces by constructing novel serendipity projectors and corresponding serendipity spaces with minimum number of DoFs. Our approach handles the full De Rham complex chain in \(\mathbb{R}^3\) while preserving essential properties including boundary continuity and commutativity. Since the number of DoFs are minimized, computational overhead is greatly reduced. The optimal approximation properties are rigorously proven and validated through Maxwell eigenvalue problems with numerical experiments.
arXiv:2606.01527v1 Announce Type: new
Abstract: Machine unlearning is motivated by legal and user-facing requirements to remove the influence of individuals' data from trained models, such as the right to be forgotten. Prior work has developed algorithms and error bounds for unlearning in smooth strongly convex stochastic optimization, but the fundamental statistical cost of unlearning has remained unclear. We nearly resolve this problem by proving upper and lower bounds on the excess population risk of approximate $\varepsilon$-unlearning; our bounds are tight up to a condition-number factor. For mean estimation over the unit ball, our upper and lower bounds match. The optimal rate is the usual statistical error plus an unlearning penalty that interpolates between the retraining-from-scratch rate and an exponentially smaller term as $\varepsilon/d$ grows, where $d$ is the dimension of the model. In particular, when $\varepsilon \gg d$, our $\varepsilon$-unlearning algorithm offers an exponential accuracy improvement over retraining the model from scratch and differentially private baselines. On the other hand, when $\varepsilon \le d$, retraining from scratch is optimal.
arXiv:2502.04512v4 Announce Type: replace
Abstract: AI advancements have been significantly driven by a combination of foundation models and curiosity-driven learning aimed at increasing capability and adaptability. Within this landscape, open-endedness, where AI agents autonomously and indefinitely generate novel behaviors, representations, or solutions, has gained increasing interest. This has become relevant in the context of self-evolving agents and long-horizon discovery. This position paper argues that the defining properties of open-ended AI systems introduce a distinct and underexplored class of safety challenges, including loss of predictability, emergent misalignment, and difficulties in maintaining effective control as systems evolve beyond their initial design assumptions, that must be addressed preemptively. These challenges differ qualitatively from those associated with task-bounded or static models and are unlikely to be addressed by existing safety frameworks alone, which is why these risks must be examined proactively, before large-scale deployment. The paper proposes a taxonomy for key challenges, discusses research opportunities, and calls for coordinated action to support the safe and responsible development of open-ended AI.
arXiv:2502.04646v2 Announce Type: replace
Abstract: Weighted sampling -- sampling from a probability density function (PDF) proportional to the product of a base PDF and a weight function -- is a fundamental technique with wide-ranging applications in variance reduction, biased sampling, data augmentation, and more. Leveraging the increasing availability of pretrained score-based generative models (SGMs), we propose a training-free weighted sampling framework that approximates the backward diffusion process of the target distribution by augmenting the pretrained base score function with an auxiliary guidance term, in a principled and computationally efficient manner. Our approach builds on two key components: a lightweight approximation of the guidance that avoids costly higher-order derivatives of both the score and weight functions, and an uncertainty-aware scheduler that dynamically adjusts the guidance strength based on a temporal analysis of approximation error. Together, these components enable accurate and stable sampling without relying on particle-based resampling or Hessian evaluations commonly required by existing methods. We validate the effectiveness of our method from synthetic to large-scale settings such as Stable Diffusion XL, where our framework achieves $1.2\times$ to $4.7\times$ speedups while consistently matching or outperforming state-of-the-art baselines in task performance. These results position our method as a scalable and inference-efficient solution for task-adaptive, time-sensitive sampling in generative applications.
arXiv:2502.08884v3 Announce Type: replace
Abstract: We present ShapeLib, the first method that uses the priors of Large Language Models (LLMs) to design libraries of programmatic 3D shape abstractions. Our system accepts two forms of user-provided design intent: high-level text descriptions of functions to include in the output library and a small seed set of exemplar shapes. We discover a library of abstractions that matches this design intent with a guided LLM workflow that first proposes different ways of applying and implementing functions, and then validates these functions are helpful in representing seed set shapes. To extend beyond the seed set, we develop library-specific recognition networks that map shapes (represented as primitives, voxels, or point clouds) to programs that use these newly discovered abstractions. Across multiple modeling domains (split by shape category), we find that LLMs, when thoughtfully combined with geometric reasoning, can be guided to author libraries of abstraction functions that generalize across shape distributions. Our framework takes a step towards realizing the long-standing shape analysis aspiration of discovering reusable, programmatic shape abstractions while exposing interpretable, semantically aligned interfaces. Our extensive evaluation demonstrates that ShapeLib provides distinct advantages over prior alternative abstraction discovery works in terms of generalization, usability, and maintaining plausibility under manipulation. Finally, we demonstrate that ShapeLib's abstraction functions unlock a number of downstream applications, combining LLM reasoning over shape programs with geometry processing tools to support shape editing and generation workflows.
arXiv:2606.01540v1 Announce Type: new
Abstract: Shapley values are a widely used tool for attributing importance and interactions among input variables in black-box models, but their computation involves a function defined over an exponentially large space of subsets. We propose TN-SHAP-G, a framework that exploits structure in graph-structured inputs to compute Shapley values and higher-order interaction indices efficiently. Given a predictor and a fixed masking scheme, TN-SHAP-G learns a compact, graph-aligned multilinear surrogate that approximates the masked-input behavior, represented as a tensor network whose topology mirrors the input graph. Once trained from a small number of oracle queries, the surrogate enables deterministic recovery of first- and higher-order Shapley indices via the multilinear extension, without additional model queries or Monte Carlo variance. Experiments on molecular benchmarks show that the learned factorization closely matches exact Shapley values on small graphs and scales efficiently to larger graphs where sampling-based methods become infeasible.
arXiv:2502.20016v2 Announce Type: replace
Abstract: Sustainability encompasses three key facets: economic, environmental, and social. However, the nascent discourse on sustainable artificial intelligence (AI) predominantly focuses on the environmental sustainability of AI, neglecting the economic and social aspects. Achieving truly sustainable AI necessitates addressing the tension between its environmental sustainability, which emphasises mitigating AI's climate impact, and its social sustainability, hinging on equitable access to AI development resources. This push for increased accessibility, however, often overlooks the environmental costs of expanding such resource usage. This position paper argues that reconciling climate awareness and resource awareness is essential to realising truly sustainable AI, and neglecting these factors fuels a global AI arms race. Applying Karl Marx's base-superstructure framework from historical materialism, we analyse how the material conditions are shaping the current AI progress and the discourse surrounding it. Further, we introduce the Climate and Resource Aware Machine Learning (CARAML) framework with actionable recommendations spanning individual, community, industry, government, and global levels to achieve sustainable AI.
arXiv:2503.00424v2 Announce Type: replace
Abstract: In this study, we develop a hybrid operational typhoon forecasting model that integrates the FuXi machine-learning (ML) model with the physics-based Shanghai Typhoon Model (SHTM) into a dual physics-data-driven framework. By employing spectral nudging, the hybrid model named FuXi-SHTM leverages FuXi's robust large-scale forecasting capabilities alongside SHTM's mesoscale strengths, significantly enhancing track, intensity, and precipitation predictions for super typhoons Yagi (2024) and Krathon (2024). Besides, this study aims to identify the sensitive regions for the hybrid model by using Conditional Nonlinear Optimal Perturbation (CNOP) method. Despite being constrained by FuXi's large-scale forecast fields, the dense assimilation of satellite observations within these sensitive regions can further enhance typhoon forecasts. Besides, this study offers key insights into the emerging paradigms that are set to shape the future development of both machine learning and physics-based modeling approaches.
arXiv:2606.01317v1 Announce Type: new
Abstract: Large language models are increasingly deployed as coding agents, shifting safety from individual responses to action sequences. Existing benchmarks, however, primarily assess whether models refuse unsafe prompts, leaving impacts on stateful workspaces largely unexamined. We present SABER, a benchmark for environment-aware operational safety that places models in realistic agent-style projects and evaluates safety from the final environment state after a sequence of actions. Beyond binary safety-violation reports, SABER categorizes violations by cause, enabling analysis of model-specific safety profiles. Our evaluations show that even the best-performing model has more than a 54% harmful safety-violation rate (HSR), suggesting that current alignment remains insufficient for realistic project environments. SABER further reveals distinct safety profiles across models. Our benchmark is publicly available at https://github.com/sssr-lab/saber.
arXiv:2606.01544v1 Announce Type: new
Abstract: Deploying Large Language Models (LLMs) in practice incurs substantial memory and computational costs. Post-training pruning (PTP) is an effective approach to reducing these costs by removing weights without additional training. Among existing methods, RIA introduces relative importance scores normalized by row and column sums, achieving state-of-the-art accuracy. However, RIA considers only 1D cross-shaped (row/column) directional information and assigns equal weight to row and column contributions. In this paper, we propose \textbf{CRePE}, which incorporates 2D local neighborhood context and adaptive coefficients into Relative Importance scoring. CRePE consistently outperforms existing PTP methods across diverse models and sparsity settings. However, identifying optimal adaptive coefficients via perplexity (PPL)-based hill climbing requires numerous PPL evaluations and approximately 11 hours of search time. To address this, we propose \textbf{PHO} (Proxy-based Hyperparameter Optimization), which eliminates the need for repeated PPL measurements and reduces the search time to approximately 20 minutes. Furthermore, the optimal hyperparameter configuration found by PHO on one model transfers well to other models, demonstrating strong generalization. Finally, we verify that CRePE can be orthogonally combined with existing techniques including Channel Permutation, non-uniform sparsity allocation, and re-pruning methods.
arXiv:2503.05641v4 Announce Type: replace
Abstract: Combining existing pre-trained LLMs is a promising approach for diverse reasoning tasks. However, task-level expert selection is often too coarse-grained, since different instances may require different expertise. To address this, we propose Skill-MoE, a symbolic, skill-based, and gradient-free Mixture-of-Experts framework for instance-level expert selection. Skill-MoE infers skills (e.g., algebra in mathematics) from each query, selects experts based on skill relevance, and lets each expert generate its own reasoning. The resulting k outputs are then synthesized by an aggregator chosen for its ability to integrate diverse responses. While instance-level selection substantially improves performance, naively implementing it incurs heavy overhead from repeated model loading and offloading. We address this with a batch inference strategy that groups instances by assigned experts, allowing each model to be loaded only once. As a result, Skill-MoE integrates 16 expert models on a single GPU with runtime comparable to prior multi-agent baselines using 4 GPUs. Across diverse benchmarks (MMLU-Pro, GPQA, AIME, and MedMCQA), Skill-MoE achieves an average absolute improvement of 8.15% over the best baseline. It also generalizes well to unseen tasks and outperforms discussion-based methods without requiring expensive multi-round interactions.
arXiv:2606.01549v1 Announce Type: new
Abstract: AI-based semantic and instance segmentation of terrestrial and drone LiDAR point clouds is emerging as a transformative approach for converting the complex 3D structure of forests into actionable information for forest monitoring and biodiversity assessment. However, forest LiDAR scenes remain highly challenging due to their large data volumes, irregular sampling density, overlapping and complex canopy structure, and geographic variability. Existing methods based on sparse convolutions or Transformers achieve promising results, but suffer from two key limitations: Quadratic complexity of attention scales poorly to large forest scenes, and Generic context modeling does not exploit forest structural priors, limiting tree separation in complex regions. To address these challenges, we propose ForestMamba, a structure-aware method that incorporates forest-specific priors into feature encoding, query generation, and query refinement, while replacing quadratic attention with linear-time state-space modeling. First, we introduce a sparse encoder with vertical-priority slab serialization that organizes sparse voxels into vertically coherent sequences for efficient long-range context modeling. Second, we propose a geometry-guided query initialization strategy based on an on-the-fly multi-scale Canopy Height Model (CHM), where canopy maxima provide ecologically meaningful query seeds, supplemented by Farthest Point Sampling (FPS) to cover understory trees. Third, we design a Mamba-based query decoder that combines local kNN voxel aggregation with a spatial dual-path Mamba for query refinement with linear computational complexity. Extensive experiments across seven forest regions demonstrate that ForestMamba consistently outperforms existing baselines in both segmentation tasks, while achieving 3 times faster inference and 2.3 times lower GPU memory than Transformer-based methods.