arXiv subjects

Di Liu

Publications and source records attributed to Di Liu.

At least 73 records · Page 4Linked to original sources

arXiv2025

TherAIssist: Assisting Art Therapy Homework and Client-Practitioner Collaboration through Human-AI Interaction

Art therapy homework is essential for fostering clients' reflection on daily experiences between sessions. However, current practices present challenges: clients often lack guidance for completing tasks that combine art-making and verbal expression, while therapists find it difficult to track and tailor homework. How HCI systems might support art therapy homework remains underexplored. To address this, we present TherAIssist, comprising a client-facing application leveraging human-AI co-creative art-making and conversational agents to facilitate homework, and a therapist-facing application enabling customization of homework agents and AI-compiled homework history. A 30-day field study with 24 clients and 5 therapists showed how TherAIssist supported clients' homework and reflection in their everyday settings. Results also revealed how therapists infused their practice principles and personal touch into the agents to offer tailored homework, and how AI-compiled homework history became a meaningful resource for in-session interactions. Implications for designing human-AI systems to facilitate asynchronous client-practitioner collaboration are discussed.

cs.HC↗

arXiv2025

Accurate RNA 3D structure prediction using a language model-based deep learning approach

Accurate prediction of RNA three-dimensional (3D) structure remains an unsolved challenge. Determining RNA 3D structures is crucial for understanding their functions and informing RNA-targeting drug development and synthetic biology design. The structural flexibility of RNA, which leads to scarcity of experimentally determined data, complicates computational prediction efforts. Here, we present RhoFold+, an RNA language model-based deep learning method that accurately predicts 3D structures of single-chain RNAs from sequences. By integrating an RNA language model pre-trained on ~23.7 million RNA sequences and leveraging techniques to address data scarcity, RhoFold+ offers a fully automated end-to-end pipeline for RNA 3D structure prediction. Retrospective evaluations on RNA-Puzzles and CASP15 natural RNA targets demonstrate RhoFold+'s superiority over existing methods, including human expert groups. Its efficacy and generalizability are further validated through cross-family and cross-type assessments, as well as time-censored benchmarks. Additionally, RhoFold+ predicts RNA secondary structures and inter-helical angles, providing empirically verifiable features that broaden its applicability to RNA structure and function studies.

q-bio.QM↗

arXiv2024

RetrievalAttention: Accelerating Long-Context LLM Inference via Vector Retrieval

Transformer-based Large Language Models (LLMs) have become increasingly important. However, due to the quadratic time complexity of attention computation, scaling LLMs to longer contexts incurs extremely slow inference speed and high GPU memory consumption for caching key-value (KV) vectors. This paper proposes RetrievalAttention, a training-free approach to both accelerate attention computation and reduce GPU memory consumption. By leveraging the dynamic sparsity of attention mechanism, RetrievalAttention proposes to build approximate nearest neighbor search (ANNS) indexes for KV vectors in CPU memory and retrieve the most relevant ones through vector search during generation. Unfortunately, we observe that the off-the-shelf ANNS indexes are often ineffective for such retrieval tasks due to the out-of-distribution (OOD) between query vectors and key vectors in the attention mechanism. RetrievalAttention addresses the OOD challenge by designing an attention-aware vector search algorithm that can adapt to the distribution of query vectors. Our evaluation demonstrates that RetrievalAttention achieves near full attention accuracy while only requiring access to 1--3% of the data. This leads to a significant reduction in the inference cost of long-context LLMs, with a much lower GPU memory footprint. In particular, RetrievalAttention only needs a single NVIDIA RTX4090 (24GB) to serve 128K tokens for LLMs with 8B parameters, which is capable of generating one token in 0.188 seconds.

cs.LG↗

arXiv2024

Temporal Action Localization with Cross Layer Task Decoupling and Refinement

Temporal action localization (TAL) involves dual tasks to classify and localize actions within untrimmed videos. However, the two tasks often have conflicting requirements for features. Existing methods typically employ separate heads for classification and localization tasks but share the same input feature, leading to suboptimal performance. To address this issue, we propose a novel TAL method with Cross Layer Task Decoupling and Refinement (CLTDR). Based on the feature pyramid of video, CLTDR strategy integrates semantically strong features from higher pyramid layers and detailed boundary-aware boundary features from lower pyramid layers to effectively disentangle the action classification and localization tasks. Moreover, the multiple features from cross layers are also employed to refine and align the disentangled classification and regression results. At last, a lightweight Gated Multi-Granularity (GMG) module is proposed to comprehensively extract and aggregate video features at instant, local, and global temporal granularities. Benefiting from the CLTDR and GMG modules, our method achieves state-of-the-art performance on five challenging benchmarks: THUMOS14, MultiTHUMOS, EPIC-KITCHENS-100, ActivityNet-1.3, and HACS. Our code and pre-trained models are publicly available at: https://github.com/LiQiang0307/CLTDR-GMG.

cs.CV↗

arXiv2024

Aligned Yet Large Dipoles: a SMEFT Study

We study a non-universal flavor scenario at the level of the Standard Model Effective Field Theory, according to which the matrix of Wilson coefficients $c_{uW}$ of an up-type electroweak quark dipole operator is aligned with the up-type Yukawa coupling. Such an alignment usually follows from the assumption of Minimal Flavor Violation (MFV), away from which we step by allowing the entries of $c_{uW}$ to be sizable along the first quark generations. A particular example, which we refer to as ``inverse hierarchy MFV", features Wilson coefficients inversely proportional to quark masses, and arises from BSM models respecting MFV and containing heavy fields that replicate the mass hierarchy of SM quarks. We then analyze the phenomenology driven by $c_{uW}$ at colliders and at lower-energy flavor experiments. We show that precision measurements of the process $pp\rightarrow W h\rightarrow γγ\ellν$ at FCC-$hh$ could set an upper bound on $|c_{uW}|\lesssim\mathcal{O}(10^{-2})(Λ/{\rm TeV})^{2}$, with $Λ$ the cutoff of the effective field theory. This bound is an order of magnitude stronger than the existing LHC bounds. Moreover, we estimate that $W h\rightarrow b\bar b \ellν$ at HL-LHC could also give competitive bounds. In the low-energy regime, we consider bounds arising from rare kaon decays, which turn out to be loose, $|c_{uW}^{11}|<\mathcal{O}(1)(Λ/{\rm TeV})^{2}$. We finally demonstrate that our flavor and operator assumptions can be derived from a weakly-coupled UV model, which we choose to simultaneously illustrate the UV origin of inverse hierarchy MFV.

hep-ph↗

arXiv2024

Chip-to-chip quantum photonic controlled-NOT gate teleportation

Quantum networks provide a novel framework for quantum information processing, significantly enhancing system capacity through the interconnection of modular quantum nodes. Beyond the capability to distribute quantum states, the ability to remotely control quantum gates is a pivotal step for quantum networks. In this Letter, we implement high fidelity quantum controlled-NOT (CNOT) gate teleportation with state-of-the-art silicon photonic integrated circuits. Based on on-chip generation of path-entangled quantum state, CNOT gate operation and chip-to-chip quantum photonic interconnect, the CNOT gate is teleported between two remote quantum nodes connected by the single-mode optical fiber. Equip with 5 m (1 km)-long interconnecting fiber, quantum gate teleportation is verified by entangling remote qubits with 95.69% +- 1.19% (94.07% +- 1.54%) average fidelity and gate tomography with 94.81% +- 0.81% (93.04% +- 1.09%) fidelity. These results advance the realization of large-scale and practical quantum networks with photonic integrated circuits.

quant-ph↗

arXiv2024

Single V2 defect in 4H Silicon Carbide Schottky diode at low temperature

Nanoelectrical and photonic integration of quantum optical components is crucial for scalable solid-state quantum technologies. Silicon carbide stands out as a material with mature quantum defects and a wide variety of applications in semiconductor industry. Here, we study the behaviour of single silicon vacancy (V2) colour centres in a metal-semiconductor (Au/Ti/4H-SiC) epitaxial wafer device, operating in a Schottky diode configuration. We explore the depletion of free carriers in the vicinity of the defect, as well as electrical tuning of the defect optical transition lines. By detecting single charge traps, we investigate their impact on V2 optical line width. Additionally, we investigate the charge-photon-dynamics of the V2 centre and find its dominating photon-ionisation processes characteristic rate and wavelength dependence. Finally, we probe the spin coherence properties of the V2 system in the junction and demonstrate several key protocols for quantum network applications. Our work shows the first demonstration of low temperature integration of a Schottky device with optical microstructures for quantum applications and paves the way towards fundamentally scalable and reproducible optical spin defect centres in solids.

quant-ph↗

arXiv2024

A finitely convergent circumcenter method for the Convex Feasibility Problem

In this paper, we present a variant of the circumcenter method for the Convex Feasibility Problem (CFP), ensuring finite convergence under a Slater assumption. The method replaces exact projections onto the convex sets with projections onto separating halfspaces, perturbed by positive exogenous parameters that decrease to zero along the iterations. If the perturbation parameters decrease slowly enough, such as the terms of a diverging series, finite convergence is achieved. To the best of our knowledge, this is the first circumcenter method for CFP that guarantees finite convergence.

math.OC↗

arXiv2024

Large Language Models for Mathematical Reasoning: Progresses and Challenges

Mathematical reasoning serves as a cornerstone for assessing the fundamental cognitive capabilities of human intelligence. In recent times, there has been a notable surge in the development of Large Language Models (LLMs) geared towards the automated resolution of mathematical problems. However, the landscape of mathematical problem types is vast and varied, with LLM-oriented techniques undergoing evaluation across diverse datasets and settings. This diversity makes it challenging to discern the true advancements and obstacles within this burgeoning field. This survey endeavors to address four pivotal dimensions: i) a comprehensive exploration of the various mathematical problems and their corresponding datasets that have been investigated; ii) an examination of the spectrum of LLM-oriented techniques that have been proposed for mathematical problem-solving; iii) an overview of factors and concerns affecting LLMs in solving math; and iv) an elucidation of the persisting challenges within this domain. To the best of our knowledge, this survey stands as one of the first extensive examinations of the landscape of LLMs in the realm of mathematics, providing a holistic perspective on the current state, accomplishments, and future challenges in this rapidly evolving field.

cs.CL↗

arXiv2024

Layout Agnostic Scene Text Image Synthesis with Diffusion Models

While diffusion models have significantly advanced the quality of image generation their capability to accurately and coherently render text within these images remains a substantial challenge. Conventional diffusion-based methods for scene text generation are typically limited by their reliance on an intermediate layout output. This dependency often results in a constrained diversity of text styles and fonts an inherent limitation stemming from the deterministic nature of the layout generation phase. To address these challenges this paper introduces SceneTextGen a novel diffusion-based model specifically designed to circumvent the need for a predefined layout stage. By doing so SceneTextGen facilitates a more natural and varied representation of text. The novelty of SceneTextGen lies in its integration of three key components: a character-level encoder for capturing detailed typographic properties coupled with a character-level instance segmentation model and a word-level spotting model to address the issues of unwanted text generation and minor character inaccuracies. We validate the performance of our method by demonstrating improved character recognition rates on generated images across different public visual text datasets in comparison to both standard diffusion based methods and text specific methods.

cs.CV↗

arXiv2024

Resolving Inconsistent Semantics in Multi-Dataset Image Segmentation

Leveraging multiple training datasets to scale up image segmentation models is beneficial for increasing robustness and semantic understanding. Individual datasets have well-defined ground truth with non-overlapping mask layouts and mutually exclusive semantics. However, merging them for multi-dataset training disrupts this harmony and leads to semantic inconsistencies; for example, the class "person" in one dataset and class "face" in another will require multilabel handling for certain pixels. Existing methods struggle with this setting, particularly when evaluated on label spaces mixed from the individual training sets. To overcome these issues, we introduce a simple yet effective multi-dataset training approach by integrating language-based embeddings of class names and label space-specific query embeddings. Our method maintains high performance regardless of the underlying inconsistencies between training datasets. Notably, on four benchmark datasets with label space inconsistencies during inference, we outperform previous methods by 1.6% mIoU for semantic segmentation, 9.1% PQ for panoptic segmentation, 12.1% AP for instance segmentation, and 3.0% in the newly proposed PIQ metric.

cs.CV↗

arXiv2024

FlowGPT: Exploring Domains, Output Modalities, and Goals of Community-Generated AI Chatbots

The advent of Generative AI and Large Language Models has not only enhanced the intelligence of interactive applications but also catalyzed the formation of communities passionate about customizing these AI capabilities. FlowGPT, an emerging platform for sharing AI prompts and use cases, exemplifies this trend, attracting many creators who develop and share chatbots with a broader community. Despite its growing popularity, there remains a significant gap in understanding the types and purposes of the AI tools created and shared by community members. In this study, we delve into FlowGPT and present our preliminary findings on the domain, output modality, and goals of chatbots. We aim to highlight common types of AI applications and identify future directions for research in AI-sharing communities.

cs.HC↗

arXiv2024

Euler Product Sieve

We study a class of approximations to the Riemann zeta function introduced earlier by the second author on the basis of Euler product. This allows us to justify Euler Product Sieve for generation of prime numbers. Also we show that Bounded Riemann Hypothesis (stated in a paper by the fourth author) is equivalent to conjunction the Riemann Hypothesis + the simplicity of zeros. 16 pages.

math.NT↗

arXiv2024

Make Safe Decisions in Power System: Safe Reinforcement Learning Based Pre-decision Making for Voltage Stability Emergency Control

The high penetration of renewable energy and power electronic equipment bring significant challenges to the efficient construction of adaptive emergency control strategies against various presumed contingencies in today's power systems. Traditional model-based emergency control methods have difficulty in adapt well to various complicated operating conditions in practice. Fr emerging artificial intelligence-based approaches, i.e., reinforcement learning-enabled solutions, they are yet to provide solid safety assurances under strict constraints in practical power systems. To address these research gaps, this paper develops a safe reinforcement learning (SRL)-based pre-decision making framework against short-term voltage collapse. Our proposed framework employs neural networks for pre-decision formulation, security margin estimation, and corrective action implementation, without reliance on precise system parameters. Leveraging the gradient projection, we propose a security projecting correction algorithm that offers theoretical security assurances to amend risky actions. The applicability of the algorithm is further enhanced through the incorporation of active learning, which expedites the training process and improves security estimation accuracy. Extensive numerical tests on the New England 39-bus system and the realistic Guangdong Provincal Power Grid demonstrate the effectiveness of the proposed framework.

eess.SY↗

arXiv2024

Instantaneous Perception of Moving Objects in 3D

The perception of 3D motion of surrounding traffic participants is crucial for driving safety. While existing works primarily focus on general large motions, we contend that the instantaneous detection and quantification of subtle motions is equally important as they indicate the nuances in driving behavior that may be safety critical, such as behaviors near a stop sign of parking positions. We delve into this under-explored task, examining its unique challenges and developing our solution, accompanied by a carefully designed benchmark. Specifically, due to the lack of correspondences between consecutive frames of sparse Lidar point clouds, static objects might appear to be moving - the so-called swimming effect. This intertwines with the true object motion, thereby posing ambiguity in accurate estimation, especially for subtle motions. To address this, we propose to leverage local occupancy completion of object point clouds to densify the shape cue, and mitigate the impact of swimming artifacts. The occupancy completion is learned in an end-to-end fashion together with the detection of moving objects and the estimation of their motion, instantaneously as soon as objects start to move. Extensive experiments demonstrate superior performance compared to standard 3D motion estimation approaches, particularly highlighting our method's specialized treatment of subtle motions.

cs.CV↗

arXiv2024

Evaluating the Application of ChatGPT in Outpatient Triage Guidance: A Comparative Study

The integration of Artificial Intelligence (AI) in healthcare presents a transformative potential for enhancing operational efficiency and health outcomes. Large Language Models (LLMs), such as ChatGPT, have shown their capabilities in supporting medical decision-making. Embedding LLMs in medical systems is becoming a promising trend in healthcare development. The potential of ChatGPT to address the triage problem in emergency departments has been examined, while few studies have explored its application in outpatient departments. With a focus on streamlining workflows and enhancing efficiency for outpatient triage, this study specifically aims to evaluate the consistency of responses provided by ChatGPT in outpatient guidance, including both within-version response analysis and between-version comparisons. For within-version, the results indicate that the internal response consistency for ChatGPT-4.0 is significantly higher than ChatGPT-3.5 (p=0.03) and both have a moderate consistency (71.2% for 4.0 and 59.6% for 3.5) in their top recommendation. However, the between-version consistency is relatively low (mean consistency score=1.43/3, median=1), indicating few recommendations match between the two versions. Also, only 50% top recommendations match perfectly in the comparisons. Interestingly, ChatGPT-3.5 responses are more likely to be complete than those from ChatGPT-4.0 (p=0.02), suggesting possible differences in information processing and response generation between the two versions. The findings offer insights into AI-assisted outpatient operations, while also facilitating the exploration of potentials and limitations of LLMs in healthcare utilization. Future research may focus on carefully optimizing LLMs and AI integration in healthcare systems based on ergonomic and human factors principles, precisely aligning with the specific needs of effective outpatient triage.

cs.CL↗

arXiv2024

Training Like a Medical Resident: Context-Prior Learning Toward Universal Medical Image Segmentation

A major focus of clinical imaging workflow is disease diagnosis and management, leading to medical imaging datasets strongly tied to specific clinical objectives. This scenario has led to the prevailing practice of developing task-specific segmentation models, without gaining insights from widespread imaging cohorts. Inspired by the training program of medical radiology residents, we propose a shift towards universal medical image segmentation, a paradigm aiming to build medical image understanding foundation models by leveraging the diversity and commonality across clinical targets, body regions, and imaging modalities. Towards this goal, we develop Hermes, a novel context-prior learning approach to address the challenges of data heterogeneity and annotation differences in medical image segmentation. In a large collection of eleven diverse datasets (2,438 3D images) across five modalities (CT, PET, T1, T2 and cine MRI) and multiple body regions, we demonstrate the merit of the universal paradigm over the traditional paradigm on addressing multiple tasks within a single model. By exploiting the synergy across tasks, Hermes achieves state-of-the-art performance on all testing datasets and shows superior model scalability. Results on two additional datasets reveals Hermes' strong performance for transfer learning, incremental learning, and generalization to downstream tasks. Hermes's learned priors demonstrate an appealing trait to reflect the intricate relations among tasks and modalities, which aligns with the established anatomical and imaging principles in radiology. The code is available: https://github.com/yhygao/universal-medical-image-segmentation.

cs.CV↗

arXiv2024

AC-EVAL: Evaluating Ancient Chinese Language Understanding in Large Language Models

Given the importance of ancient Chinese in capturing the essence of rich historical and cultural heritage, the rapid advancements in Large Language Models (LLMs) necessitate benchmarks that can effectively evaluate their understanding of ancient contexts. To meet this need, we present AC-EVAL, an innovative benchmark designed to assess the advanced knowledge and reasoning capabilities of LLMs within the context of ancient Chinese. AC-EVAL is structured across three levels of difficulty reflecting different facets of language comprehension: general historical knowledge, short text understanding, and long text comprehension. The benchmark comprises 13 tasks, spanning historical facts, geography, social customs, art, philosophy, classical poetry and prose, providing a comprehensive assessment framework. Our extensive evaluation of top-performing LLMs, tailored for both English and Chinese, reveals a substantial potential for enhancing ancient text comprehension. By highlighting the strengths and weaknesses of LLMs, AC-EVAL aims to promote their development and application forward in the realms of ancient Chinese language education and scholarly research. The AC-EVAL data and evaluation code are available at https://github.com/yuting-wei/AC-EVAL.

cs.CL↗