Botao Peng

Yanlin Qi, Xinhang Chen, Huiqiang Jiang et al. · harvard, microsoft-research

KV-cache retrieval is essential for long-context LLM inference, yet existing methods struggle with distribution drift and high latency at scale. We introduce ParisKV, a drift-robust, GPU-native KV-cache retrieval framework based on collision-based candidate selection, followed by a quantized inner-product reranking estimator. For million-token contexts, ParisKV supports CPU-offloaded KV caches via Unified Virtual Addressing (UVA), enabling on-demand top-$k$ fetching with minimal overhead. ParisKV matches or outperforms full attention quality on long-input and long-generation benchmarks. It achieves state-of-the-art long-context decoding efficiency: it matches or exceeds full attention speed even at batch size 1 for long contexts, delivers up to 2.8$\times$ higher throughput within full attention's runnable range, and scales to million-token contexts where full attention runs out of memory. At million-token scale, ParisKV reduces decode latency by 17$\times$ and 44$\times$ compared to MagicPIG and PQCache, respectively, two state-of-the-art KV-cache Top-$k$ retrieval baselines, code is available at https://github.com/amy-77/ParisKV/tree/main.

Francesca Del Gaudio, Manos Chatzakis, Gayathiri Ravendirane et al.

Exact similarity search over large collections of data series is a fundamental operation in modern applications, yet existing solutions are often fragmented, specialized, or tailored to specific execution environments. In this paper, we present DaiSy, a unified library for exact data series similarity search that integrates multiple state-of-the-art algorithms within a single, coherent framework. DaiSy is the first library to support exact similarity search across diverse execution environments, including implementations for disk-based, in-memory, GPU-accelerated, and distributed scalable similarity search. Although designed for data series, DaiSy is also directly applicable to exact similarity search over vector data, enabling its use in a broader range of applications. The library supports interfaces in both C++ and Python, enabling users to easily integrate its functionality into a variety of tasks. DaiSy is open-sourced and available at: https://github.com/MChatzakis/DaiSy.

Jiuqi Wei, Xiaodong Lee, Botao Peng et al.

Locality-sensitive hashing (LSH) is a well-known solution for approximate nearest neighbor (ANN) search with theoretical guarantees. Traditional LSH-based methods mainly focus on improving the efficiency and accuracy of query phase by designing different query strategies, but pay little attention to improving the efficiency of the indexing phase. They typically fine-tune existing data-oriented partitioning trees to index data points and support their query strategies. However, their strategy to directly partition the multidimensional space is time-consuming, and performance degrades as the space dimensionality increases. In this paper, we design an encoding-based tree called Dynamic Encoding Tree (DE-Tree) to improve the indexing efficiency and support efficient range queries. Based on DE-Tree, we propose a novel LSH scheme called DET-LSH. DET-LSH adopts a novel query strategy, which performs range queries in multiple independent index DE-Trees to reduce the probability of missing exact NN points. Extensive experiments demonstrate that while achieving best query accuracy, DET-LSH achieves up to 6x speedup in indexing time and 2x speedup in query time over the state-of-the-art LSH-based methods. In addition, to further improve the performance of DET-LSH, we propose PDET-LSH, an in-memory method adopting the parallelization opportunities provided by multicore CPUs. PDET-LSH exhibits considerable advantages in indexing and query efficiency, especially on large-scale datasets. Extensive experiments show that, while achieving the same query accuracy as DET-LSH, PDET-LSH offers up to 40x speedup in indexing time and 62x speedup in query answering time over the state-of-the-art LSH-based methods. Our theoretical analysis demonstrates that DET-LSH and PDET-LSH offer probabilistic guarantees on query answering accuracy. This paper was published in TKDE.

Weidan Xiong, Hongqian Zhang, Botao Peng et al.

Coarse architectural models are often generated at scales ranging from individual buildings to scenes for downstream applications such as Digital Twin City, Metaverse, LODs, etc. Such piece-wise planar models can be abstracted as twins from 3D dense reconstructions. However, these models typically lack realistic texture relative to the real building or scene, making them unsuitable for vivid display or direct reference. In this paper, we present TwinTex, the first automatic texture mapping framework to generate a photo-realistic texture for a piece-wise planar proxy. Our method addresses most challenges occurring in such twin texture generation. Specifically, for each primitive plane, we first select a small set of photos with greedy heuristics considering photometric quality, perspective quality and facade texture completeness. Then, different levels of line features (LoLs) are extracted from the set of selected photos to generate guidance for later steps. With LoLs, we employ optimization algorithms to align texture with geometry from local to global. Finally, we fine-tune a diffusion model with a multi-mask initialization component and a new dataset to inpaint the missing region. Experimental results on many buildings, indoor scenes and man-made objects of varying complexity demonstrate the generalization ability of our algorithm. Our approach surpasses state-of-the-art texture mapping methods in terms of high-fidelity quality and reaches a human-expert production level with much less effort. Project page: https://vcc.tech/research/2023/TwinTex.