arXiv subjects

Tianhao Zhu

Publications and source records attributed to Tianhao Zhu.

5 recordsLinked to original sources

arXiv2026

The Knot Invariant Associated to Two-Parameter Quantum Algebras II

Fan, Ma, and Xing constructed oriented-tangle invariants from finite-type two-parameter quantum algebras. In this paper, we construct an explicit parameter-transport comparison between two-parameter modules and their corresponding one-parameter modules, and we verify this comparison on every elementary oriented-tangle operator. After extending scalars to a common coefficient field, we prove that if $M_1$ is any finite-dimensional integrable type-1 simple highest-weight $U_{v,1}$-module whose weights lie in an admissible lattice and $M_t=Φ_t(M_1)$ is its transported module, then for every oriented link $L$, the corresponding normalized invariants satisfy $I_{v,t}^{M_t}(L)=I_{v,1}^{M_1}(L)$. Consequently, the two invariants assign equal values to exactly the same pairs of oriented links and therefore have the same distinguishing power; this includes the vector representations of the finite classical types A, B, C, and D. Sean Clark's comparison of ordinary and super quantum knot invariants is obtained as a specialization of the same transport principle in which explicit scalar factors are allowed.

math.QA↗

arXiv2025

From Principles to Practice: A Systematic Study of LLM Serving on Multi-core NPUs

With the widespread adoption of Large Language Models (LLMs), the demand for high-performance LLM inference services continues to grow. To meet this demand, a growing number of AI accelerators have been proposed, such as Google TPU, Huawei NPU, Graphcore IPU, and Cerebras WSE, etc. Most of these accelerators adopt multi-core architectures to achieve enhanced scalability, but lack the flexibility of SIMT architectures. Therefore, without careful configuration of the hardware architecture, as well as deliberate design of tensor parallelism and core placement strategies, computational resources may be underutilized, resulting in suboptimal inference performance. To address these challenges, we first present a multi-level simulation framework with both transaction-level and performance-model-based simulation for multi-core NPUs. Using this simulator, we conduct a systematic analysis and further propose the optimal solutions for tensor parallelism strategies, core placement policies, memory management methods, as well as the selection between PD-disaggregation and PD-fusion on multi-core NPUs. We conduct comprehensive experiments on representative LLMs and various NPU configurations. The evaluation results demonstrate that, our solution can achieve 1.32x-6.03x speedup compared to SOTA designs for multi-core NPUs across different hardware configurations. As for LLM serving, our work offers guidance on designing optimal hardware architectures and serving strategies for multi-core NPUs across various LLM workloads.

cs.AR↗

arXiv2021

Cross-Modal Object Tracking: Modality-Aware Representations and A Unified Benchmark

In many visual systems, visual tracking often bases on RGB image sequences, in which some targets are invalid in low-light conditions, and tracking performance is thus affected significantly. Introducing other modalities such as depth and infrared data is an effective way to handle imaging limitations of individual sources, but multi-modal imaging platforms usually require elaborate designs and cannot be applied in many real-world applications at present. Near-infrared (NIR) imaging becomes an essential part of many surveillance cameras, whose imaging is switchable between RGB and NIR based on the light intensity. These two modalities are heterogeneous with very different visual properties and thus bring big challenges for visual tracking. However, existing works have not studied this challenging problem. In this work, we address the cross-modal object tracking problem and contribute a new video dataset, including 654 cross-modal image sequences with over 481K frames in total, and the average video length is more than 735 frames. To promote the research and development of cross-modal object tracking, we propose a new algorithm, which learns the modality-aware target representation to mitigate the appearance gap between RGB and NIR modalities in the tracking process. It is plug-and-play and could thus be flexibly embedded into different tracking frameworks. Extensive experiments on the dataset are conducted, and we demonstrate the effectiveness of the proposed algorithm in two representative tracking frameworks against 17 state-of-the-art tracking methods. We will release the dataset for free academic usage, dataset download link and code will be released soon.

cs.CV↗

arXiv2019

Dynamic Local Regret for Non-convex Online Forecasting

We consider online forecasting problems for non-convex machine learning models. Forecasting introduces several challenges such as (i) frequent updates are necessary to deal with concept drift issues since the dynamics of the environment change over time, and (ii) the state of the art models are non-convex models. We address these challenges with a novel regret framework. Standard regret measures commonly do not consider both dynamic environment and non-convex models. We introduce a local regret for non-convex models in a dynamic environment. We present an update rule incurring a cost, according to our proposed local regret, which is sublinear in time T. Our update uses time-smoothed gradients. Using a real-world dataset we show that our time-smoothed approach yields several benefits when compared with state-of-the-art competitors: results are more stable against new data; training is more robust to hyperparameter selection; and our approach is more computationally efficient than the alternatives.

cs.LG↗

arXiv2019

Time-Smoothed Gradients for Online Forecasting

Here, we study different update rules in stochastic gradient descent (SGD) for online forecasting problems. The selection of the learning rate parameter is critical in SGD. However, it may not be feasible to tune this parameter in online learning. Therefore, it is necessary to have an update rule that is not sensitive to the selection of the learning parameter. Inspired by the local regret metric that we introduced previously, we propose to use time-smoothed gradients within SGD update. Using the public data set-- GEFCom2014, we validate that our approach yields more stable results than the other existing approaches. Furthermore, we show that such a simple approach is computationally efficient compared to the alternatives.

cs.LG↗