Searcharxiv⌕ Search

arXiv subjects

Yuchen Zhang

Publications and source records attributed to Yuchen Zhang.

At least 145 records · Page 8Linked to original sources
arXiv2025

LEO Satellite and RIS: Two Keys to Seamless Indoor and Outdoor Localization

The contemporary landscape of wireless technology underscores the critical role of precise localization services. Traditional global navigation satellite systems (GNSS)-based solutions, however, fall short when it comes to indoor environments, and existing indoor localization techniques such as electromagnetic fingerprinting methods face challenges of additional implementation costs and limited coverage. This article explores an innovative solution that blends low Earth orbit (LEO) satellites with reconfigurable intelligent surfaces (RISs), unlocking its potential for realizing seamless indoor and outdoor localization (SIOL) with global coverage. After a comprehensive review of the distinctive characteristics of LEO satellites and RISs, we showcase their potential for SIOL applications through two case studies on position error bound evaluation. Finally, we discuss system architectures and highlight open challenges in such systems.

eess.SP↗
arXiv2025

Learning Complex Heterogeneous Multimodal Fake News via Social Latent Network Inference

With the diversification of online social platforms, news dissemination has become increasingly complex, heterogeneous, and multimodal, making the fake news detection task more challenging and crucial. Previous works mainly focus on obtaining social relationships of news via retweets, limiting the accurate detection when real cascades are inaccessible. Given the proven assessment of the spreading influence of events, this paper proposes a method called HML (Complex Heterogeneous Multimodal Fake News Detection method via Latent Network Inference). Specifically, an improved social latent network inference strategy is designed to estimate the maximum likelihood of news influences under the same event. Meanwhile, a novel heterogeneous graph is built based on social attributes for multimodal news under different events. Further, to better aggregate the relationships among heterogeneous multimodal features, this paper proposes a self-supervised-based multimodal content learning strategy, to enhance, align, fuse and compare heterogeneous modal contents. Based above, a personalized heterogeneous graph representation learning is designed to classify fake news. Extensive experiments demonstrate that the proposed method outperforms the SOTA in real social media news datasets.

cs.MM↗
arXiv2025

Tarsier2: Advancing Large Vision-Language Models from Detailed Video Description to Comprehensive Video Understanding

We introduce Tarsier2, a state-of-the-art large vision-language model (LVLM) designed for generating detailed and accurate video descriptions, while also exhibiting superior general video understanding capabilities. Tarsier2 achieves significant advancements through three key upgrades: (1) Scaling pre-training data from 11M to 40M video-text pairs, enriching both volume and diversity; (2) Performing fine-grained temporal alignment during supervised fine-tuning; (3) Using model-based sampling to automatically construct preference data and applying DPO training for optimization. Extensive experiments show that Tarsier2-7B consistently outperforms leading proprietary models, including GPT-4o and Gemini 1.5 Pro, in detailed video description tasks. On the DREAM-1K benchmark, Tarsier2-7B improves F1 by 2.8% over GPT-4o and 5.8% over Gemini-1.5-Pro. In human side-by-side evaluations, Tarsier2-7B shows a +8.6% performance advantage over GPT-4o and +24.9% over Gemini-1.5-Pro. Tarsier2-7B also sets new state-of-the-art results across 15 public benchmarks, spanning tasks such as video question-answering, video grounding, hallucination test, and embodied question-answering, demonstrating its versatility as a robust generalist vision-language model.

cs.CV↗
arXiv2024

6DMA-Aided Hybrid Beamforming with Joint Antenna Position and Orientation Optimization

This paper studies a sub-connected six-dimensional movable antenna (6DMA)-aided multi-user communication system. In this system, each sub-array is connected to a dedicated radio frequency chain and collectively moves and rotates as a unit within specific local regions. The movement and rotation capabilities of 6DMAs enhance design flexibility, facilitating the capture of spatial variations for improved communication performance. To fully characterize the effect of antenna position and orientation on wireless channels between the base station (BS) and users, we develop a field-response-based 6DMA channel model to account for the antenna radiation pattern and polarization. We then maximize the sum rate of multiple users, by jointly optimizing the digital and unit-modulus analog beamformers given the transmit power budget as well as the positions and orientations of sub-arrays within given movable and rotatable ranges at the BS. Due to the highly coupled variables, the formulated optimization problem is non-convex and thus challenging to solve. We develop a fractional programming-aided alternating optimization framework that integrates the Lagrange multiplier method, manifold optimization, and gradient descent to solve the problem. Numerical results demonstrate that the proposed 6DMA-aided sub-connected structure achieves a substantial sum-rate improvement over various benchmark schemes with less flexibility in antenna movement and can even outperform fully-digital beamforming systems that employ antenna position or orientation adjustments only. The results also highlight the necessity of considering antenna polarization for optimally adjusting antenna orientation.

eess.SP↗
arXiv2024

A path-specific effect approach to mediation analysis with time-varying mediators and time-to-event outcomes accounting for competing risks

Not accounting for competing events in survival analysis can lead to biased estimates, as individuals who die from other causes do not have the opportunity to develop the event of interest. Formal definitions and considerations for causal effects in the presence of competing risks have been published, but not for the mediation analysis setting. We propose, for the first time, an approach based on the path-specific effects framework to account for competing risks in longitudinal mediation analysis with time-to-event outcomes. We do so by considering the pathway through the competing event as another mediator, which is nested within our longitudinal mediator of interest. We provide a theoretical formulation and related definitions of the effects of interest based on the mediational g-formula, as well as a detailed description of the algorithm. We also present an application of our algorithm to data from the Strong Heart Study, a prospective cohort of American Indian adults. In this application, we evaluated the mediating role of the blood pressure trajectory (measured during three visits) on the association between arsenic and cadmium, in separate models, with time to cardiovascular disease, accounting for competing risks by death. Identifying the effects through different paths enables us to evaluate the impact of metals on the outcome of interest, as well as through competing risks, more transparently.

stat.ME↗
arXiv2024

EGP3D: Edge-guided Geometric Preserving 3D Point Cloud Super-resolution for RGB-D camera

Point clouds or depth images captured by current RGB-D cameras often suffer from low resolution, rendering them insufficient for applications such as 3D reconstruction and robots. Existing point cloud super-resolution (PCSR) methods are either constrained by geometric artifacts or lack attention to edge details. To address these issues, we propose an edge-guided geometric-preserving 3D point cloud super-resolution (EGP3D) method tailored for RGB-D cameras. Our approach innovatively optimizes the point cloud with an edge constraint on a projected 2D space, thereby ensuring high-quality edge preservation in the 3D PCSR task. To tackle geometric optimization challenges in super-resolution point clouds, particularly preserving edge shapes and smoothness, we introduce a multi-faceted loss function that simultaneously optimizes the Chamfer distance, Hausdorff distance, and gradient smoothness. Existing datasets used for point cloud upsampling are predominantly synthetic and inadequately represent real-world scenarios, neglecting noise and stray light effects. To address the scarcity of realistic RGB-D data for PCSR tasks, we built a dataset that captures real-world noise and stray-light effects, offering a more accurate representation of authentic environments. Validated through simulations and real-world experiments, the proposed method exhibited superior performance in preserving edge clarity and geometric details.

cs.CV↗
arXiv2024

AGILE: A Novel Reinforcement Learning Framework of LLM Agents

We introduce a novel reinforcement learning framework of LLM agents named AGILE (AGent that Interacts and Learns from Environments) designed to perform complex conversational tasks with users, leveraging LLMs, memory, tools, and interactions with experts. The agent possesses capabilities beyond conversation, including reflection, tool usage, and expert consultation. We formulate the construction of such an LLM agent as a reinforcement learning (RL) problem, in which the LLM serves as the policy model. We fine-tune the LLM using labeled data of actions and the PPO algorithm. We focus on question answering and release a dataset for agents called ProductQA, comprising challenging questions in online shopping. Our extensive experiments on ProductQA, MedMCQA and HotPotQA show that AGILE agents based on 7B and 13B LLMs trained with PPO can outperform GPT-4 agents. Our ablation study highlights the indispensability of memory, tools, consultation, reflection, and reinforcement learning in achieving the agent's strong performance. Datasets and code are available at https://github.com/bytarnish/AGILE.

cs.LG↗
arXiv2024

Rethinking Human Evaluation Protocol for Text-to-Video Models: Enhancing Reliability,Reproducibility, and Practicality

Recent text-to-video (T2V) technology advancements, as demonstrated by models such as Gen2, Pika, and Sora, have significantly broadened its applicability and popularity. Despite these strides, evaluating these models poses substantial challenges. Primarily, due to the limitations inherent in automatic metrics, manual evaluation is often considered a superior method for assessing T2V generation. However, existing manual evaluation protocols face reproducibility, reliability, and practicality issues. To address these challenges, this paper introduces the Text-to-Video Human Evaluation (T2VHE) protocol, a comprehensive and standardized protocol for T2V models. The T2VHE protocol includes well-defined metrics, thorough annotator training, and an effective dynamic evaluation module. Experimental results demonstrate that this protocol not only ensures high-quality annotations but can also reduce evaluation costs by nearly 50\%. We will open-source the entire setup of the T2VHE protocol, including the complete protocol workflow, the dynamic evaluation component details, and the annotation interface code. This will help communities establish more sophisticated human assessment protocols.

cs.CV↗
arXiv2024

Deep Learning for Weather Forecasting: A CNN-LSTM Hybrid Model for Predicting Historical Temperature Data

As global climate change intensifies, accurate weather forecasting has become increasingly important, affecting agriculture, energy management, environmental protection, and daily life. This study introduces a hybrid model combining Convolutional Neural Networks (CNNs) and Long Short-Term Memory (LSTM) networks to predict historical temperature data. CNNs are utilized for spatial feature extraction, while LSTMs handle temporal dependencies, resulting in significantly improved prediction accuracy and stability. By using Mean Absolute Error (MAE) as the loss function, the model demonstrates excellent performance in processing complex meteorological data, addressing challenges such as missing data and high-dimensionality. The results show a strong alignment between the prediction curve and test data, validating the model's potential in climate prediction. This study offers valuable insights for fields such as agriculture, energy management, and urban planning, and lays the groundwork for future applications in weather forecasting under the context of global climate change.

cs.LG↗
arXiv2024

GDeR: Safeguarding Efficiency, Balancing, and Robustness via Prototypical Graph Pruning

Training high-quality deep models necessitates vast amounts of data, resulting in overwhelming computational and memory demands. Recently, data pruning, distillation, and coreset selection have been developed to streamline data volume by retaining, synthesizing, or selecting a small yet informative subset from the full set. Among these methods, data pruning incurs the least additional training cost and offers the most practical acceleration benefits. However, it is the most vulnerable, often suffering significant performance degradation with imbalanced or biased data schema, thus raising concerns about its accuracy and reliability in on-device deployment. Therefore, there is a looming need for a new data pruning paradigm that maintains the efficiency of previous practices while ensuring balance and robustness. Unlike the fields of computer vision and natural language processing, where mature solutions have been developed to address these issues, graph neural networks (GNNs) continue to struggle with increasingly large-scale, imbalanced, and noisy datasets, lacking a unified dataset pruning solution. To achieve this, we introduce a novel dynamic soft-pruning method, GDeR, designed to update the training ``basket'' during the process using trainable prototypes. GDeR first constructs a well-modeled graph embedding hypersphere and then samples \textit{representative, balanced, and unbiased subsets} from this embedding space, which achieves the goal we called Graph Training Debugging. Extensive experiments on five datasets across three GNN backbones, demonstrate that GDeR (I) achieves or surpasses the performance of the full dataset with 30%~50% fewer training samples, (II) attains up to a 2.81x lossless training speedup, and (III) outperforms state-of-the-art pruning methods in imbalanced training and noisy training scenarios by 0.3%~4.3% and 3.6%~7.8%, respectively.

cs.LG↗
arXiv2024

Self-Control of LLM Behaviors by Compressing Suffix Gradient into Prefix Controller

We propose SelfControl, an inference-time model control method utilizing gradients to control the behavior of large language models (LLMs) without explicit human annotations. Given a desired behavior expressed in a natural language suffix string concatenated to the input prompt, SelfControl computes gradients of the LLM's self-evaluation of the suffix with respect to its latent representations. The gradients are used to directly control the auto-regressive generation process towards desired behaviors, which eliminates human supervision, achieves precise and transparent control, and offers on-the-fly adaptability. To further enhance efficiency, we introduce SelfControl_{Prefix}, a compact module that encapsulates the learned representations from gradients into a SelfControl_{Prefix}, facilitating efficient inference-time control with no latency compared to the original model and allowing control for multiple behaviors simultaneously. Our experiments demonstrate SelfControl's efficacy across multiple domains, where it improves over SOTA for 8.3% in detoxification, 3.1% in truthfulness enhancement, 4%~10% in controlling on emotion tones, and 48.2% in privacy protection, i.e., completely remove privacy leakage issue. Additionally, we demonstrate that SelfControl can be used for data synthesis and to improve reasoning abilities.

cs.CL↗
arXiv2024

Two Trades is not Baffled: Condensing Graph via Crafting Rational Gradient Matching

Training on large-scale graphs has achieved remarkable results in graph representation learning, but its cost and storage have raised growing concerns. As one of the most promising directions, graph condensation methods address these issues by employing gradient matching, aiming to condense the full graph into a more concise yet information-rich synthetic set. Though encouraging, these strategies primarily emphasize matching directions of the gradients, which leads to deviations in the training trajectories. Such deviations are further magnified by the differences between the condensation and evaluation phases, culminating in accumulated errors, which detrimentally affect the performance of the condensed graphs. In light of this, we propose a novel graph condensation method named \textbf{C}raf\textbf{T}ing \textbf{R}ationa\textbf{L} trajectory (\textbf{CTRL}), which offers an optimized starting point closer to the original dataset's feature distribution and a more refined strategy for gradient matching. Theoretically, CTRL can effectively neutralize the impact of accumulated errors on the performance of condensed graphs. We provide extensive experiments on various graph datasets and downstream tasks to support the effectiveness of CTRL. Code is released at https://github.com/NUS-HPC-AI-Lab/CTRL.

cs.LG↗
arXiv2024

Tarsier: Recipes for Training and Evaluating Large Video Description Models

Generating fine-grained video descriptions is a fundamental challenge in video understanding. In this work, we introduce Tarsier, a family of large-scale video-language models designed to generate high-quality video descriptions. Tarsier employs CLIP-ViT to encode frames separately and then uses an LLM to model temporal relationships. Despite its simple architecture, we demonstrate that with a meticulously designed two-stage training procedure, the Tarsier models exhibit substantially stronger video description capabilities than any existing open-source model, showing a $+51.4\%$ advantage in human side-by-side evaluation over the strongest model. Additionally, they are comparable to state-of-the-art proprietary models, with a $+12.3\%$ advantage against GPT-4V and a $-6.7\%$ disadvantage against Gemini 1.5 Pro. When upgraded to Tarsier2 by building upon SigLIP and Qwen2-7B, it further improves significantly with a $+4.8\%$ advantage against GPT-4o. Besides video description, Tarsier proves to be a versatile generalist model, achieving new state-of-the-art results across nine public benchmarks, including multi-choice VQA, open-ended VQA, and zero-shot video captioning. Our second contribution is the introduction of a new benchmark -- DREAM-1K (https://tarsier-vlm.github.io/) for evaluating video description models, consisting of a new challenging dataset featuring videos from diverse sources and varying complexity, along with an automatic method specifically designed to assess the quality of fine-grained video descriptions. We make our models and evaluation benchmark publicly available at https://github.com/bytedance/tarsier.

cs.CV↗
arXiv2024

The LDBC Social Network Benchmark

The Linked Data Benchmark Council's Social Network Benchmark (LDBC SNB) is an effort intended to test various functionalities of systems used for graph-like data management. For this, LDBC SNB uses the recognizable scenario of operating a social network, characterized by its graph-shaped data. LDBC SNB consists of two workloads that focus on different functionalities: the Interactive workload (interactive transactional queries) and the Business Intelligence workload (analytical queries). This document contains the definition of both workloads. This includes a detailed explanation of the data used in the LDBC SNB, a detailed description for all queries, and instructions on how to generate the data and run the benchmark with the provided software.

cs.DB↗
arXiv2024

Privacy Preservation in Delay-Based Localization Systems: Artificial Noise or Artificial Multipath?

Localization plays an increasingly pivotal role in 5G/6G systems, enabling various applications. This paper focuses on the privacy concerns associated with delay-based localization, where unauthorized base stations attempt to infer the location of the end user. We propose a method to disrupt localization at unauthorized nodes by injecting artificial components into the pilot signal, exploiting model mismatches inherent in these nodes. Specifically, we investigate the effectiveness of two techniques, namely artificial multipath (AM) and artificial noise (AN), in mitigating location leakage. By leveraging the misspecified Cramér-Rao bound framework, we evaluate the impact of these techniques on unauthorized localization performance. Our results demonstrate that pilot manipulation significantly degrades the accuracy of unauthorized localization while minimally affecting legitimate localization. Moreover, we find that the superiority of AM over AN varies depending on the specific scenario.

eess.SP↗
arXiv2024

A Benchmark Dataset for Multimodal Prediction of Enzymatic Function Coupling DNA Sequences and Natural Language

Predicting gene function from its DNA sequence is a fundamental challenge in biology. Many deep learning models have been proposed to embed DNA sequences and predict their enzymatic function, leveraging information in public databases linking DNA sequences to an enzymatic function label. However, much of the scientific community's knowledge of biological function is not represented in these categorical labels, and is instead captured in unstructured text descriptions of mechanisms, reactions, and enzyme behavior. These descriptions are often captured alongside DNA sequences in biological databases, albeit in an unstructured manner. Deep learning of models predicting enzymatic function are likely to benefit from incorporating this multi-modal data encoding scientific knowledge of biological function. There is, however, no dataset designed for machine learning algorithms to leverage this multi-modal information. Here we propose a novel dataset and benchmark suite that enables the exploration and development of large multi-modal neural network models on gene DNA sequences and natural language descriptions of gene function. We present baseline performance on benchmarks for both unsupervised and supervised tasks that demonstrate the difficulty of this modeling objective, while demonstrating the potential benefit of incorporating multi-modal data types in function prediction compared to DNA sequences alone. Our dataset is at: https://hoarfrost-lab.github.io/BioTalk/.

q-bio.GN↗
arXiv2024

AutoEval-Video: An Automatic Benchmark for Assessing Large Vision Language Models in Open-Ended Video Question Answering

We propose a novel and challenging benchmark, AutoEval-Video, to comprehensively evaluate large vision-language models in open-ended video question answering. The comprehensiveness of AutoEval-Video is demonstrated in two aspects: 1) AutoEval-Video constructs open-ended video-questions across 9 skill dimensions, addressing capabilities of perception, comprehension, and generation. 2) AutoEval-Video contains newly collected videos that cover over 40 distinct themes. To efficiently evaluate responses to the open-ended questions, we employ an LLM-based evaluation approach, but instead of merely providing a reference answer, we annotate unique evaluation rules for every single instance (video-question pair). To maximize the robustness of these rules, we develop a novel adversarial annotation mechanism. By using instance-specific rules as prompt, GPT-4, as an automatic evaluator, can achieve a stable evaluation accuracy of around 97.0%, comparable to the 94.9% - 97.5% accuracy of a human evaluator. Furthermore, we assess the performance of eight large vision-language models on AutoEval-Video. Among them, GPT-4V(ision) significantly outperforms other models, achieving an accuracy of 32.2%. However, there is still substantial room for improvement compared to human accuracy of 72.8%. By conducting an extensive case study, we uncover several drawbacks of GPT-4V, such as limited temporal and dynamic comprehension, and overly general responses. Code is available at https://github.com/Xiuyuan-Chen/AutoEval-Video.

cs.CV↗