Almost Asymptotically Optimal Active Clustering Through Pairwise Observations

We propose a new analysis framework for clustering $M$ items into an unknown number of $K$ distinct groups using noisy and actively collected responses. At each time step, an agent is allowed to query pairs of items and observe bandit binary feedback. If the pair of items belongs to the same (resp.\ different) cluster, the observed feedback is $1$ with probability $p>1/2$ (resp.\ $q<1/2$). Leveraging the ubiquitous change-of-measure technique, we establish a fundamental lower bound on the expected number of queries needed to achieve a desired confidence in the clustering accuracy, formulated as a sup-inf optimization problem. Building on this theoretical foundation, we design an asymptotically optimal algorithm in which the stopping criterion involves an empirical version of the inner infimum -- the Generalized Likelihood Ratio (GLR) statistic -- being compared to a threshold. We develop a computationally feasible variant of the GLR statistic and show that its performance gap to the lower bound can be accurately empirically estimated and remains within a constant multiple of the lower bound.

TADS: Task-Aware Data Selection for Multi-Task Multimodal Pre-Training

Large-scale multimodal pre-trained models like CLIP rely heavily on high-quality training data, yet raw web-crawled datasets are often noisy, misaligned, and redundant, leading to inefficient training and suboptimal generalization. Existing data selection methods are either heuristic-based, suffering from bias and limited diversity, or data-driven but task-agnostic, failing to optimize for multi-task scenarios. To address these gaps, we introduce TADS (Task-Aware Data Selection), a novel framework for multi-task multimodal pre-training that integrates Intrinsic Quality, Task Relevance, and Distributional Diversity into a learnable value function. TADS employs a comprehensive quality assessment system with unimodal and cross-modal operators, quantifies task relevance via interpretable similarity vectors, and optimizes diversity through cluster-based weighting. A feedback-driven meta-learning mechanism adaptively refines the selection strategy based on proxy model performance across multiple downstream tasks. Experiments on CC12M demonstrate that TADS achieves superior zero-shot performance on benchmarks like ImageNet, CIFAR-100, MS-COCO, and Flickr30K, using only 36% of the data while outperforming baselines by an average of 1.0%. This highlights that TADS significantly enhances data efficiency by curating a high-utility subset that yields a much higher performance ceiling within the same computational constraints.

Double-P: Hierarchical Top-P Sparse Attention for Long-Context LLMs

As long-context inference becomes central to large language models (LLMs), attention over growing key-value caches emerges as a dominant decoding bottleneck, motivating sparse attention for scalable inference. Fixed-budget top-k sparse attention cannot adapt to heterogeneous attention distributions across heads and layers, whereas top-p sparse attention directly preserves attention mass and provides stronger accuracy guarantees. Existing top-p methods, however, fail to jointly optimize top-p accuracy, selection overhead, and sparse attention cost, which limits their overall efficiency. We present Double-P, a hierarchical sparse attention framework that optimizes all three stages. Double-P first performs coarse-grained top-p estimation at the cluster level using size-weighted centroids, then adaptively refines computation through a second top-p stage that allocates token-level attention only when needed. Across long-context benchmarks, Double-P consistently achieves near-zero accuracy drop, reducing attention computation overhead by up to 1.8x and delivers up to 1.3x end-to-end decoding speedup over state-of-the-art fixed-budget sparse attention methods.

How to Achieve the Intended Aim of Deep Clustering Now, without Deep Learning

Deep clustering (DC) is often quoted to have a key advantage over $k$-means clustering. Yet, this advantage is often demonstrated using image datasets only, and it is unclear whether it addresses the fundamental limitations of $k$-means clustering. Deep Embedded Clustering (DEC) learns a latent representation via an autoencoder and performs clustering based on a $k$-means-like procedure, while the optimization is conducted in an end-to-end manner. This paper investigates whether the deep-learned representation has enabled DEC to overcome the known fundamental limitations of $k$-means clustering, i.e., its inability to discover clusters of arbitrary shapes, varied sizes and densities. Our investigations on DEC have a wider implication on deep clustering methods in general. Notably, none of these methods exploit the underlying data distribution. We uncover that a non-deep learning approach achieves the intended aim of deep clustering by making use of distributional information of clusters in a dataset to effectively address these fundamental limitations.

HyperPotter: Spell the Charm of High-Order Interactions in Audio Deepfake Detection

Advances in AIGC technologies have enabled the synthesis of highly realistic audio deepfakes capable of deceiving human auditory perception. Although numerous audio deepfake detection (ADD) methods have been developed, most rely on local temporal/spectral features or pairwise relations, overlooking high-order interactions (HOIs). HOIs capture discriminative patterns that emerge from multiple feature components beyond their individual contributions. We propose HyperPotter, a hypergraph-based framework that explicitly models these synergistic HOIs through clustering-based hyperedges with class-aware prototype initialization. Extensive experiments demonstrate that HyperPotter surpasses its baseline by an average relative gain of 22.15% across 11 datasets and outperforms state-of-the-art methods by 13.96% on 4 challenging cross-domain datasets, demonstrating superior generalization to diverse attacks and speakers.

Mapper-GIN: Lightweight Structural Graph Abstraction for Corrupted 3D Point Cloud Classification

Robust 3D point cloud classification is often pursued by scaling up backbones or relying on specialized data augmentation. We instead ask whether structural abstraction alone can improve robustness, and study a simple topology-inspired decomposition based on the Mapper algorithm. We propose Mapper-GIN, a lightweight pipeline that partitions a point cloud into overlapping regions using Mapper (PCA lens, cubical cover, and followed by density-based clustering), constructs a region graph from their overlaps, and performs graph classification with a Graph Isomorphism Network. On the corruption benchmark ModelNet40-C, Mapper-GIN achieves competitive and stable accuracy under Noise and Transformation corruptions with only 0.5M parameters. In contrast to prior approaches that require heavier architectures or additional mechanisms to gain robustness, Mapper-GIN attains strong corruption robustness through simple region-level graph abstraction and GIN message passing. Overall, our results suggest that region-graph structure offers an efficient and interpretable source of robustness for 3D visual recognition.

Joint Optimization of Latency and Accuracy for Split Federated Learning in User-Centric Cell-Free MIMO Networks

This paper proposes a user-centric split federated learning (UCSFL) framework for user-centric cell-free multiple-input multiple-output (CF-MIMO) networks to support split federated learning (SFL). In the proposed UCSFL framework, users deploy split sub-models locally, while complete models are maintained and updated at access point (AP)-side distributed processing units (DPUs), followed by a two-level aggregation procedure across DPUs and the central processing unit (CPU). Under standard machine learning (ML) assumptions, we provide a theoretical convergence analysis for UCSFL, which reveals that the AP-cluster size is a key factor influencing model training accuracy. Motivated by this result, we introduce a new performance metric, termed the latency-to-accuracy ratio, defined as the ratio of a user's per-iteration training latency to the weighted size of its AP cluster. Based on this metric, we formulate a joint optimization problem to minimize the maximum latency-to-accuracy ratio by jointly optimizing uplink power control, downlink beamforming, model splitting, and AP clustering. The resulting problem is decomposed into two sub-problems operating on different time scales, for which dedicated algorithms are developed to handle the short-term and long-term optimizations, respectively. Simulation results verify the convergence of the proposed algorithms and demonstrate that UCSFL effectively reduces the latency-to-accuracy ratio of the VGG16 model compared with baseline schemes. Moreover, the proposed framework adaptively adjusts splitting and clustering strategies in response to varying communication and computation resources. An MNIST-based handwritten digit classification example further shows that UCSFL significantly accelerates the convergence of the VGG16 model.

TIDE: Temporal Incremental Draft Engine for Self-Improving LLM Inference

Speculative decoding can substantially accelerate LLM inference, but realizing its benefits in practice is challenging due to evolving workloads and system-level constraints. We present TIDE (Temporal Incremental Draft Engine), a serving-engine-native framework that integrates online draft adaptation directly into high-performance LLM inference systems. TIDE reuses target model hidden states generated during inference as training signals, enabling zero-overhead draft adaptation without reloading the target model, and employs adaptive runtime control to activate speculation and training only when beneficial. TIDE exploits heterogeneous clusters by mapping decoupled inference and training to appropriate GPU classes. Across diverse real-world workloads, TIDE achieves up to 1.15x throughput improvement over static speculative decoding while reducing draft training time by 1.67x compared to approaches that recompute training signals.

Horizon-LM: A RAM-Centric Architecture for LLM Training

The rapid growth of large language models (LLMs) has outpaced the evolution of single-GPU hardware, making model scale increasingly constrained by memory capacity rather than computation. While modern training systems extend GPU memory through distributed parallelism and offloading across CPU and storage tiers, they fundamentally retain a GPU-centric execution paradigm in which GPUs host persistent model replicas and full autograd graphs. As a result, scaling large models remains tightly coupled to multi-GPU clusters, complex distributed runtimes, and unpredictable host memory consumption, creating substantial barriers for node-scale post-training workloads such as instruction tuning, alignment, and domain adaptation. We present Horizon-LM, a memory-centric training system that redefines the roles of CPU and GPU for large-model optimization. Horizon-LM treats host memory as the authoritative parameter store and uses GPUs solely as transient compute engines through a CPU-master, GPU-template execution model. By eliminating persistent GPU-resident modules and autograd graphs, employing explicit recomputation with manual gradient propagation, and introducing a pipelined double-buffered execution engine, Horizon-LM decouples model scale from GPU count and bounds memory usage to the theoretical parameter footprint. On a single H200 GPU with 1.5\,TB host RAM, Horizon-LM reliably trains models up to 120B parameters. On a standard single A100 machine, Horizon-LM achieves up to 12.2$\times$ higher training throughput than DeepSpeed ZeRO-3 with CPU offloading while preserving numerical correctness. Across platforms and scales, Horizon-LM sustains high device utilization and predictable memory growth, demonstrating that host memory, not GPU memory, defines the true feasibility boundary for node-scale large-model training.

Maximum-Volume Nonnegative Matrix Factorization

Nonnegative matrix factorization (NMF) is a popular data embedding technique. Given a nonnegative data matrix $X$, it aims at finding two lower dimensional matrices, $W$ and $H$, such that $X\approx WH$, where the factors $W$ and $H$ are constrained to be element-wise nonnegative. The factor $W$ serves as a basis for the columns of $X$. In order to obtain more interpretable and unique solutions, minimum-volume NMF (MinVol NMF) minimizes the volume of $W$. In this paper, we consider the dual approach, where the volume of $H$ is maximized instead; this is referred to as maximum-volume NMF (MaxVol NMF). MaxVol NMF is identifiable under the same conditions as MinVol NMF in the noiseless case, but it behaves rather differently in the presence of noise. In practice, MaxVol NMF is much more effective to extract a sparse decomposition and does not generate rank-deficient solutions. In fact, we prove that the solutions of MaxVol NMF with the largest volume correspond to clustering the columns of $X$ in disjoint clusters, while the solutions of MinVol NMF with smallest volume are rank deficient. We propose two algorithms to solve MaxVol NMF. We also present a normalized variant of MaxVol NMF that exhibits better performance than MinVol NMF and MaxVol NMF, and can be interpreted as a continuum between standard NMF and orthogonal NMF. We illustrate our results in the context of hyperspectral unmixing.