Embedding-based vector search underpins many important applications, such as recommendation and retrieval-augmented generation (RAG). It relies on vector indices to enable efficient search. However, these indices require storing high-dimensional embeddings and large index metadata, whose total size can be several times larger than the original data (e.g., text chunks). Such high storage overhead makes it difficult, or even impractical, to deploy vector search on personal devices or large-scale datasets. To tackle this problem, we propose LEANN, a storage-efficient index for vector search that recomputes embeddings on the fly instead of storing them, and compresses state-of-the-art proximity graph indices while preserving search accuracy. LEANN delivers high-quality vector search while using only a fraction of the storage (e.g., 5% of the original data) and supporting storage-efficient index construction and updates. On real-world benchmarks, LEANN reduces index size by up to 50x compared with conventional indices, while maintaining SOTA accuracy and comparable latency for RAG applications.

Deep learning models achieve state-of-the-art performance across domains but face scalability challenges in real-time or resource-constrained scenarios. To address this, we propose Correlation of Loss Differences (CLD), a simple and scalable metric for coreset selection that identifies the most impactful training samples by measuring their alignment with the loss trajectories of a held-out validation set. CLD is highly efficient, requiring only per-sample loss values computed at training checkpoints, and avoiding the costly gradient and curvature computations used in many existing subset selection methods. We develop a general theoretical framework that establishes convergence guarantees for CLD-based coresets, demonstrating that the convergence error is upper-bounded by the alignment of the selected samples and the representativeness of the validation set. On CIFAR-100 and ImageNet-1k, CLD-based coresets typically outperform or closely match state-of-the-art methods across subset sizes, and remain within 1% of more computationally expensive baselines even when not leading. CLD transfers effectively across architectures (ResNet, VGG, DenseNet), enabling proxy-to-target selection with <1% degradation. Moreover, CLD is stable when using only early checkpoints, incurring negligible accuracy loss. Finally, CLD exhibits inherent bias reduction via per-class validation alignment, obviating the need for additional stratified sampling. Together, these properties make CLD a principled, efficient, stable, and transferable tool for scalable dataset optimization.

The rapid deployment of Large Language Models (LLMs) highlights the need for efficient low-bit post-training quantization (PTQ), due to their high memory costs. A key challenge in weight quantization is the presence of outliers, which inflate quantization ranges and lead to large errors. While a number of outlier suppression techniques have been proposed, they either: fail to effectively shrink the quantization range, or incur (relatively) high bit overhead. In this paper, we present ICQuant, a novel framework that leverages outlier statistics to design an efficient index coding scheme for outlier-aware weight-only quantization. Compared to existing outlier suppression techniques requiring $\approx 1$ bit overhead to halve the quantization range, ICQuant requires only $\approx 0.3$ bits; a significant saving in extreme compression regimes (e.g., 2-3 bits per weight). ICQuant can be used on top of any existing quantizers to eliminate outliers, improving the quantization quality. Using just 2.3 bits per weight and simple scalar quantizers, ICQuant improves the zero-shot accuracy of the 2-bit Llama3-70B model by up to 130% and 150% relative to QTIP and QuIP#; and it achieves comparable performance to the best-known fine-tuned quantizer (PV-tuning) without fine-tuning.

Large Language Models (LLMs) have achieved impressive progress in natural language processing, but their limited ability to retain long-term context constrains performance on document-level or multi-turn tasks. Retrieval-Augmented Generation (RAG) mitigates this by retrieving relevant information from an external corpus. However, existing RAG systems often rely on embedding-based retrieval trained on corpus-level semantic similarity, which can lead to retrieving content that is semantically similar in form but misaligned with the question's true intent. Furthermore, recent RAG variants construct graph- or hierarchy-based structures to improve retrieval accuracy, resulting in significant computation and storage overhead. In this paper, we propose an embedding-free retrieval framework. Our method leverages the logical inferencing ability of LLMs in retrieval using iterative search space refinement guided by our novel importance measure and extend our retrieval results with logically related information without explicit graph construction. Experiments on long-context QA benchmarks, including NovelQA and Marathon, show that our approach outperforms strong baselines while reducing storage and runtime by over an order of magnitude.

Deep learning models achieve state-of-the-art performance across domains but face scalability challenges in real-time or resource-constrained scenarios. To address this, we propose Loss Trajectory Correlation (LTC), a novel metric for coreset selection that identifies critical training samples driving generalization. $LTC$ quantifies the alignment between training sample loss trajectories and validation set loss trajectories, enabling the construction of compact, representative subsets. Unlike traditional methods with computational and storage overheads that are infeasible to scale to large datasets, $LTC$ achieves superior efficiency as it can be computed as a byproduct of training. Our results on CIFAR-100 and ImageNet-1k show that $LTC$ consistently achieves accuracy on par with or surpassing state-of-the-art coreset selection methods, with any differences remaining under 1%. LTC also effectively transfers across various architectures, including ResNet, VGG, DenseNet, and Swin Transformer, with minimal performance degradation (<2%). Additionally, LTC offers insights into training dynamics, such as identifying aligned and conflicting sample behaviors, at a fraction of the computational cost of traditional methods. This framework paves the way for scalable coreset selection and efficient dataset optimization.

With the widespread use of virtual reality applications, 3D scene generation has become a new challenging research frontier. 3D scenes have highly complex structures and need to ensure that the output is dense, coherent, and contains all necessary structures. Many current 3D scene generation methods rely on pre-trained text-to-image diffusion models and monocular depth estimators. However, the generated scenes occupy large amounts of storage space and often lack effective regularisation methods, leading to geometric distortions. To this end, we propose BloomScene, a lightweight structured 3D Gaussian splatting for crossmodal scene generation, which creates diverse and high-quality 3D scenes from text or image inputs. Specifically, a crossmodal progressive scene generation framework is proposed to generate coherent scenes utilizing incremental point cloud reconstruction and 3D Gaussian splatting. Additionally, we propose a hierarchical depth prior-based regularization mechanism that utilizes multi-level constraints on depth accuracy and smoothness to enhance the realism and continuity of the generated scenes. Ultimately, we propose a structured context-guided compression mechanism that exploits structured hash grids to model the context of unorganized anchor attributes, which significantly eliminates structural redundancy and reduces storage overhead. Comprehensive experiments across multiple scenes demonstrate the significant potential and advantages of our framework compared with several baselines.

Federated unlearning has emerged as a promising paradigm to erase the client-level data effect without affecting the performance of collaborative learning models. However, the federated unlearning process often introduces extensive storage overhead and consumes substantial computational resources, thus hindering its implementation in practice. To address this issue, this paper proposes a scalable federated unlearning framework based on isolated sharding and coded computing. We first divide distributed clients into multiple isolated shards across stages to reduce the number of clients being affected. Then, to reduce the storage overhead of the central server, we develop a coded computing mechanism by compressing the model parameters across different shards. In addition, we provide the theoretical analysis of time efficiency and storage effectiveness for the isolated and coded sharding. Finally, extensive experiments on two typical learning tasks, i.e., classification and generation, demonstrate that our proposed framework can achieve better performance than three state-of-the-art frameworks in terms of accuracy, retraining time, storage overhead, and F1 scores for resisting membership inference attacks.

Resistive Random Access Memory (ReRAM) has emerged as a promising platform for deep neural networks (DNNs) due to its support for parallel in-situ matrix-vector multiplication. However, hardware failures, such as stuck-at-fault defects, can result in significant prediction errors during model inference. While additional crossbars can be used to address these failures, they come with storage overhead and are not efficient in terms of space, energy, and cost. In this paper, we propose a fault protection mechanism that incurs zero space cost. Our approach includes: 1) differentiable structure pruning of rows and columns to reduce model redundancy, 2) weight duplication and voting for robust output, and 3) embedding duplicated most significant bits (MSBs) into the model weight. We evaluate our method on nine tasks of the GLUE benchmark with the BERT model, and experimental results prove its effectiveness.

A widely used interpretation by example We design, implement, and evaluate DeepEverest, a system for the query is, "find the top-inputs that produce the highest activation efficient execution of interpretation by example queries over the values for an individual neuron or a group of neurons" [12, 14, 21, activation values of a deep neural network. DeepEverest consists 33, 50, 57, 58, 61]. Another common query is, "for any input, find of an efficient indexing technique and a query execution algorithm the k-nearest neighbors in the dataset using the activation values of a with various optimizations. We prove that the proposed query group of neurons based on the proximity in the latent space defined execution algorithm is instance optimal.

Despite being conceptually attractive, kNN-MT is burdened with massive storage requirements and high computational complexity since it conducts nearest neighbor searches over the entire reference corpus. In this paper, we propose a simple and scalable nearest neighbor machine translation framework to drastically promote the decoding and storage efficiency of kNN-based models while maintaining the translation performance. To this end, we dynamically construct an extremely small datastore for each input via sentence-level retrieval to avoid searching the entire datastore in vanilla kNN-MT, based on which we further introduce a distance-aware adapter to adaptively incorporate the kNN retrieval results into the pre-trained NMT models. Experiments on machine translation in two general settings, static domain adaptation, and online learning, demonstrate that our proposed approach not only achieves almost 90% speed as the NMT model without performance degradation, but also significantly reduces the storage requirements of kNN-MT. Domain adaptation is one of the fundamental challenges in machine learning which aspires to cope with the discrepancy across domain distributions and improve the generality of the trained models. It has attracted wide attention in the neural machine translation (NMT) area (Britz et al., 2017; Chen et al., 2017; Chu & Wang, 2018; Bapna & Firat, 2019; Bapna et al., 2019; Wei et al., 2020). Recently, kNN-MT and its variants (Khandelwal et al., 2021; Zheng et al., 2021a;b; Wang et al., 2022a) provide a new paradigm and have achieved remarkable performance for fast domain adaptation by retrieval pipelines. These approaches combine traditional NMT models (Bahdanau et al., 2015; Vaswani et al., 2017) with a token-level k-nearest-neighbour (kNN) retrieval mechanism, allowing it to directly access the domain-specific datastore to improve translation accuracy without fine-tuning the entire model.