arXiv subjects

Xin Pei

Publications and source records attributed to Xin Pei.

At least 19 recordsLinked to original sources

arXiv2026

NE-R1: Enhancing Named Entity Recognition Model via Reinforcement Learning

Named Entity Recognition (NER) has achieved substantial progress since the advent of large language models (LLMs). Nevertheless, the recognition of long-tail and domain-specific entities remains challenging due to the deficiency in parametric knowledge. Retrieval-augmented generation (RAG) offers a promising remedy by injecting external knowledge, but it also introduces noise and unnecessary cost when dealing with familiar cases. In this paper, we propose NE-R1, a novel framework for adaptive retrieval-augmented NER. We design a "retrieval-on-demand" mechanism for NER. Then we integrate it into models by a two-stage training method: (1) multi-task instruction tuning initialization; (2) end-to-end RL optimization with CoT. To achieve reasonable selection between parameterized and external knowledge, we design a multi-dimensional reward considering both accuracy and retrieval benefit. NE-R1 achieves state-of-the-art performance on various benchmarks, with an average F1 score gain of 2.52% in in-domain evaluation and 1.18% in zero-shot cross-domain evaluation.

cs.CL↗

arXiv2026

LASAR: Latent Adaptive Semantic Aligned Reasoning for Generative Recommendation

Large Language Models (LLMs) have demonstrated powerful reasoning capabilities through Chain-of-Thought (CoT) in various tasks, yet the inefficiency of token-by-token generation hinders real-world deployment in latency-sensitive recommender systems. Latent reasoning has emerged as an effective paradigm in LLMs, performing multi-step inference in a continuous hidden-state space to achieve stronger reasoning at lower cost. However, this paradigm remains underexplored in mainstream generative recommendation. Achieving this reveals three key challenges: (1) the gap between prior-less Semantic ID (SID) symbols and continuous latent reasoning, as SIDs lack pre-trained semantics, hindering joint optimization; (2) representation drift due to a lack of reasoning chain supervision; and (3) the suboptimality of applying a globally fixed reasoning depth. To address these, we propose LASAR (Latent Adaptive Semantic Aligned Reasoning), an SFT-then-RL framework. First, we bridge this gap via two-stage training: Stage 1 grounds SID semantics before Stage 2 introduces latent reasoning, ensuring efficient convergence. Second, we mitigate representation drift through explicit CoT semantic alignment. Step-wise bidirectional KL divergence constrains the latent reasoning trajectory using hidden-state anchors extracted from CoT text, while a Policy Head predicts per-sample reasoning depth. Third, during the GRPO-based RL phase, terminal-only KL alignment accommodates variable-length reasoning, and REINFORCE optimizes the Policy Head to dynamically allocate steps. This nearly halves the average latent step count while simultaneously improving recommendation quality. Experiments on three real-world datasets show that LASAR achieves the best overall performance across the evaluated settings. It adds limited inference latency and is roughly 20x faster than generating explicit CoT text.

cs.IR↗

arXiv2026

Learning User-Aware Recall: Personalized Retrieval in Long-Term Conversational Memory

Long-term conversational agents are expected to remember past interactions, but memory is useful only when the right evidence is recalled for the right user. Existing memory-augmented LLM agents have made progress in building compact memory banks, yet retrieval is still often driven by query-centered similarity or fixed ranking rules, leaving user-conditioned relevance underexplored. To address this gap, we propose Profile-guided Personalized Retrieval Optimization (PPRO), a retrieval-centric framework that makes memory retrieval both user-aware and optimizable. PPRO builds episodic and semantic memory banks from dialogue histories and derives a user profile from accumulated memories. The profile serves as an explicit personalized prior in memory ranking, allowing retrieval to account for stable user attributes, preferences, and relationships. PPRO further trains a query rewriter with Group Relative Policy Optimization, using both evidence retrieval quality and downstream answer quality as feedback while keeping the memory banks and answer model fixed. Experiments on LoCoMo and LongMemEval-S show consistent gains over training-free memory systems and training-based baselines. Ablation studies further show that both profile-guided ranking and retrieval-oriented rewriting contribute substantially to performance, highlighting retrieval optimization as a key factor in personalized long-term memory use.

cs.IR↗

arXiv2026

RepoZero: Can LLMs Generate a Code Repository from Scratch?

Large Language Models (LLMs) have recently shown remarkable progress in code generation, yet their ability to construct complete software repositories from scratch remains poorly understood. A fundamental bottleneck is the lack of verifiable and scalable evaluation: existing benchmarks either focus on patch-based editing or rely on human or LLM-based judgments, which introduce bias and limit reproducibility. In this work, we present RepoZero, the first benchmark that enables fully automated, execution-based verification of repository-level generation from scratch. Our key idea is to reformulate generation as repository reproduction: given only API specifications, an agent must re-implement an entire repository such that its behavior matches the original implementation. This design allows for strict black-box validation via output equivalence, while naturally supporting large-scale construction by reusing existing open-source repositories. To further mitigate data leakage and shortcut solutions, we introduce cross-language constraints and a sandboxed evaluation protocol. Building on this benchmark, we propose an Agentic Code-Test Evolution (ACE) framework that performs iterative test generation and error-driven refinement, enabling effective test-time scaling for repository-level synthesis. Extensive experiments across multiple state-of-the-art LLMs and agent frameworks reveal that even the strongest LLM agents achieve only limited pass rates (30\% - 55\%), exposing a substantial gap between current capabilities and real-world software development requirements. Our results establish RepoZero as a challenging, scalable, and reliable testbed for end-to-end code generation, and highlight self-verification via test generation as a critical direction for advancing LLM-based coding agents.

cs.SE↗

arXiv2026

It Takes 8 Tokens: Weak-to-Strong Off-Policy RL via Auxiliary Branches

Reinforcement learning with verifiable rewards has emerged as a standard approach for enhancing reasoning in large language models, which typically optimizes the policy by contrasting multiple self generated rollouts. However, we identify a critical support limited bottleneck in this paradigm: on challenging reasoning tasks, the target model's samples often exhibit semantic redundancy, converging into the same erroneous "reasoning basins" that offer negligible reward contrast for policy updates. In this paper, we propose to overcome this limitation through a weak to strong learning paradigm, where a policy's exploration is informed by a weaker but computationally efficient auxiliary model. We introduce W2SPO, an off policy RL method that injects short auxiliary segments often as brief as 8 tokens into intermediate target model trajectories and the target model then completes the reasoning path from these diverted states. Policy updates are restricted to these short inserted segments based on final verifiable rewards. Empirically, W2SPO achieves superior performance among evaluated 4B scale models on mathematical reasoning benchmarks, outperforming evaluated post trained baselines. Compared with vanilla GRPO under the same sampling budget, W2SPO improves Pass@1 from 62.3% to 64.2% while achieving a 3.55 times training speedup. These results suggest that weak auxiliary branches can induce stronger target reasoning policies by expanding local exploration support.

cs.AI↗

arXiv2025

Which2comm: An Efficient Collaborative Perception Framework for 3D Object Detection

Collaborative perception allows real-time inter-agent information exchange and thus offers invaluable opportunities to enhance the perception capabilities of individual agents. However, limited communication bandwidth in practical scenarios restricts the inter-agent data transmission volume, consequently resulting in performance declines in collaborative perception systems. This implies a trade-off between perception performance and communication cost. To address this issue, we propose Which2comm, a novel multi-agent 3D object detection framework leveraging object-level sparse features. By integrating semantic information of objects into 3D object detection boxes, we introduce semantic detection boxes (SemDBs). Innovatively transmitting these information-rich object-level sparse features among agents not only significantly reduces the demanding communication volume, but also improves 3D object detection performance. Specifically, a fully sparse network is constructed to extract SemDBs from individual agents; a temporal fusion approach with a relative temporal encoding mechanism is utilized to obtain the comprehensive spatiotemporal features. Extensive experiments on the V2XSet and OPV2V datasets demonstrate that Which2comm consistently outperforms other state-of-the-art methods on both perception performance and communication cost, exhibiting better robustness to real-world latency. These results present that for multi-agent collaborative 3D object detection, transmitting only object-level sparse features is sufficient to achieve high-precision and robust performance.

cs.CV↗

arXiv2024

CCDepth: A Lightweight Self-supervised Depth Estimation Network with Enhanced Interpretability

Self-supervised depth estimation, which solely requires monocular image sequence as input, has become increasingly popular and promising in recent years. Current research primarily focuses on enhancing the prediction accuracy of the models. However, the excessive number of parameters impedes the universal deployment of the model on edge devices. Moreover, the emerging neural networks, being black-box models, are difficult to analyze, leading to challenges in understanding the rationales for performance improvements. To mitigate these issues, this study proposes a novel hybrid self-supervised depth estimation network, CCDepth, comprising convolutional neural networks (CNNs) and the white-box CRATE (Coding RAte reduction TransformEr) network. This novel network uses CNNs and the CRATE modules to extract local and global information in images, respectively, thereby boosting learning efficiency and reducing model size. Furthermore, incorporating the CRATE modules into the network enables a mathematically interpretable process in capturing global features. Extensive experiments on the KITTI dataset indicate that the proposed CCDepth network can achieve performance comparable with those state-of-the-art methods, while the model size has been significantly reduced. In addition, a series of quantitative and qualitative analyses on the inner features in the CCDepth network further confirm the effectiveness of the proposed method.

cs.CV↗

arXiv2024

CVVLSNet: Vehicle Location and Speed Estimation Using Partial Connected Vehicle Trajectory Data

Real-time estimation of vehicle locations and speeds is crucial for developing many beneficial transportation applications in traffic management and control, e.g., adaptive signal control. Recent advances in communication technologies facilitate the emergence of connected vehicles (CVs), which can share traffic information with nearby CVs or infrastructures. At the early stage of connectivity, only a portion of vehicles are CVs. The locations and speeds for those non-CVs (NCs) are not accessible and must be estimated to obtain the full traffic information. To address the above problem, this paper proposes a novel CV-based Vehicle Location and Speed estimation network, CVVLSNet, to simultaneously estimate the vehicle locations and speeds exclusively using partial CV trajectory data. A road cell occupancy (RCO) method is first proposed to represent the variable vehicle state information. Spatiotemporal interactions can be integrated by simply fusing the RCO representations. Then, CVVLSNet, taking the Coding-RAte TransformEr (CRATE) network as a backbone, is introduced to estimate the vehicle locations and speeds. Moreover, physical vehicle size constraints are also considered in loss functions. Extensive experiments indicate that the proposed method significantly outperformed the existing method under various CV penetration rates, signal timings, and volume-to-capacity ratios.

cs.CV↗

arXiv2024

Multi-V2X: A Large Scale Multi-modal Multi-penetration-rate Dataset for Cooperative Perception

Cooperative perception through vehicle-to-everything (V2X) has garnered significant attention in recent years due to its potential to overcome occlusions and enhance long-distance perception. Great achievements have been made in both datasets and algorithms. However, existing real-world datasets are limited by the presence of few communicable agents, while synthetic datasets typically cover only vehicles. More importantly, the penetration rate of connected and autonomous vehicles (CAVs) , a critical factor for the deployment of cooperative perception technologies, has not been adequately addressed. To tackle these issues, we introduce Multi-V2X, a large-scale, multi-modal, multi-penetration-rate dataset for V2X perception. By co-simulating SUMO and CARLA, we equip a substantial number of cars and roadside units (RSUs) in simulated towns with sensor suites, and collect comprehensive sensing data. Datasets with specified CAV penetration rates can be obtained by masking some equipped cars as normal vehicles. In total, our Multi-V2X dataset comprises 549k RGB frames, 146k LiDAR frames, and 4,219k annotated 3D bounding boxes across six categories. The highest possible CAV penetration rate reaches 86.21%, with up to 31 agents in communication range, posing new challenges in selecting agents to collaborate with. We provide comprehensive benchmarks for cooperative 3D object detection tasks. Our data and code are available at https://github.com/RadetzkyLi/Multi-V2X .

cs.CV↗

arXiv2023

Unify Change Point Detection and Segment Classification in a Regression Task for Transportation Mode Identification

Identifying travelers' transportation modes is important in transportation science and location-based services. It's appealing for researchers to leverage GPS trajectory data to infer transportation modes with the popularity of GPS-enabled devices, e.g., smart phones. Existing studies frame this problem as classification task. The dominant two-stage studies divide the trip into single-one mode segments first and then categorize these segments. The over segmentation strategy and inevitable error propagation bring difficulties to classification stage and make optimizing the whole system hard. The recent one-stage works throw out trajectory segmentation entirely to avoid these by directly conducting point-wise classification for the trip, whereas leaving predictions dis-continuous. To solve above-mentioned problems, inspired by YOLO and SSD in object detection, we propose to reframe change point detection and segment classification as a unified regression task instead of the existing classification task. We directly regress coordinates of change points and classify associated segments. In this way, our method divides the trip into segments under a supervised manner and leverage more contextual information, obtaining predictions with high accuracy and continuity. Two frameworks, TrajYOLO and TrajSSD, are proposed to solve the regression task and various feature extraction backbones are exploited. Exhaustive experiments on GeoLife dataset show that the proposed method has competitive overall identification accuracy of 0.853 when distinguishing five modes: walk, bike, bus, car, train. As for change point detection, our method increases precision at the cost of drop in recall. All codes are available at https://github.com/RadetzkyLi/TrajYOLO-SSD.

cs.CV↗

arXiv2023

The Qitai Radio Telescope

This study presents a general outline of the Qitai radio telescope (QTT) project. Qitai, the site of the telescope, is a county of Xinjiang Uygur Autonomous Region of China, located in the east Tianshan Mountains at an elevation of about 1800 m. The QTT is a fully steerable, Gregorian type telescope with a standard parabolic main reflector of 110 m diameter. The QTT has adopted an um-brella support, homology-symmetric lightweight design. The main reflector is active so that the deformation caused by gravity can be corrected. The structural design aims to ultimately allow high-sensitivity observations from 150 MHz up to 115 GHz. To satisfy the requirements for early scientific goals, the QTT will be equipped with ultra-wideband receivers and large field-of-view mul-ti-beam receivers. A multi-function signal-processing system based on RFSoC and GPU processor chips will be developed. These will enable the QTT to operate in pulsar, spectral line, continuum and Very Long Baseline Interferometer (VLBI) observing modes. Electromagnetic compatibility (EMC) and radio frequency interference (RFI) control techniques are adopted throughout the system design. The QTT will form a world-class observational platform for the detection of low-frequency (nanoHertz) gravitational waves through pulsar timing array (PTA) techniques, pulsar surveys, the discovery of binary black-hole systems, and exploring dark matter and the origin of life in the universe.

astro-ph.IM↗

arXiv2022

Multi-dimensional Racism Classification during COVID-19: Stigmatization, Offensiveness, Blame, and Exclusion

Transcending the binary categorization of racist texts, our study takes cues from social science theories to develop a multi-dimensional model for racism detection, namely stigmatization, offensiveness, blame, and exclusion. With the aid of BERT and topic modeling, this categorical detection enables insights into the underlying subtlety of racist discussion on digital platforms during COVID-19. Our study contributes to enriching the scholarly discussion on deviant racist behaviours on social media. First, a stage-wise analysis is applied to capture the dynamics of the topic changes across the early stages of COVID-19 which transformed from a domestic epidemic to an international public health emergency and later to a global pandemic. Furthermore, mapping this trend enables a more accurate prediction of public opinion evolvement concerning racism in the offline world, and meanwhile, the enactment of specified intervention strategies to combat the upsurge of racism during the global public health crisis like COVID-19. In addition, this interdisciplinary research also points out a direction for future studies on social network analysis and mining. Integration of social science perspectives into the development of computational methods provides insights into more accurate data detection and analytics.

cs.CY↗

arXiv2021

DMRVisNet: Deep Multi-head Regression Network for Pixel-wise Visibility Estimation Under Foggy Weather

Scene perception is essential for driving decision-making and traffic safety. However, fog, as a kind of common weather, frequently appears in the real world, especially in the mountain areas, making it difficult to accurately observe the surrounding environments. Therefore, precisely estimating the visibility under foggy weather can significantly benefit traffic management and safety. To address this, most current methods use professional instruments outfitted at fixed locations on the roads to perform the visibility measurement; these methods are expensive and less flexible. In this paper, we propose an innovative end-to-end convolutional neural network framework to estimate the visibility leveraging Koschmieder's law exclusively using the image data. The proposed method estimates the visibility by integrating the physical model into the proposed framework, instead of directly predicting the visibility value via the convolutional neural work. Moreover, we estimate the visibility as a pixel-wise visibility map against those of previous visibility measurement methods which solely predict a single value for an entire image. Thus, the estimated result of our method is more informative, particularly in uneven fog scenarios, which can benefit to developing a more precise early warning system for foggy weather, thereby better protecting the intelligent transportation infrastructure systems and promoting its development. To validate the proposed framework, a virtual dataset, FACI, containing 3,000 foggy images in different concentrations, is collected using the AirSim platform. Detailed experiments show that the proposed method achieves performance competitive to those of state-of-the-art methods.

cs.CV↗

arXiv2021

Beyond a binary of (non)racist tweets: A four-dimensional categorical detection and analysis of racist and xenophobic opinions on Twitter in early Covid-19

Transcending the binary categorization of racist and xenophobic texts, this research takes cues from social science theories to develop a four dimensional category for racism and xenophobia detection, namely stigmatization, offensiveness, blame, and exclusion. With the aid of deep learning techniques, this categorical detection enables insights into the nuances of emergent topics reflected in racist and xenophobic expression on Twitter. Moreover, a stage wise analysis is applied to capture the dynamic changes of the topics across the stages of early development of Covid-19 from a domestic epidemic to an international public health emergency, and later to a global pandemic. The main contributions of this research include, first the methodological advancement. By bridging the state-of-the-art computational methods with social science perspective, this research provides a meaningful approach for future research to gain insight into the underlying subtlety of racist and xenophobic discussion on digital platforms. Second, by enabling a more accurate comprehension and even prediction of public opinions and actions, this research paves the way for the enactment of effective intervention policies to combat racist crimes and social exclusion under Covid-19.

cs.SI↗

arXiv2021

Self-supervised Depth Estimation Leveraging Global Perception and Geometric Smoothness Using On-board Videos

Self-supervised depth estimation has drawn much attention in recent years as it does not require labeled data but image sequences. Moreover, it can be conveniently used in various applications, such as autonomous driving, robotics, realistic navigation, and smart cities. However, extracting global contextual information from images and predicting a geometrically natural depth map remain challenging. In this paper, we present DLNet for pixel-wise depth estimation, which simultaneously extracts global and local features with the aid of our depth Linformer block. This block consists of the Linformer and innovative soft split multi-layer perceptron blocks. Moreover, a three-dimensional geometry smoothness loss is proposed to predict a geometrically natural depth map by imposing the second-order smoothness constraint on the predicted three-dimensional point clouds, thereby realizing improved performance as a byproduct. Finally, we explore the multi-scale prediction strategy and propose the maximum margin dual-scale prediction strategy for further performance improvement. In experiments on the KITTI and Make3D benchmarks, the proposed DLNet achieves performance competitive to those of the state-of-the-art methods, reducing time and space complexities by more than $62\%$ and $56\%$, respectively. Extensive testing on various real-world situations further demonstrates the strong practicality and generalization capability of the proposed model.

cs.CV↗

arXiv2020

Optimizing AD Pruning of Sponsored Search with Reinforcement Learning

Industrial sponsored search system (SSS) can be logically divided into three modules: keywords matching, ad retrieving, and ranking. During ad retrieving, the ad candidates grow exponentially. A query with high commercial value might retrieve a great deal of ad candidates such that the ranking module could not afford. Due to limited latency and computing resources, the candidates have to be pruned earlier. Suppose we set a pruning line to cut SSS into two parts: upstream and downstream. The problem we are going to address is: how to pick out the best $K$ items from $N$ candidates provided by the upstream to maximize the total system's revenue. Since the industrial downstream is very complicated and updated quickly, a crucial restriction in this problem is that the selection scheme should get adapted to the downstream. In this paper, we propose a novel model-free reinforcement learning approach to fixing this problem. Our approach considers downstream as a black-box environment, and the agent sequentially selects items and finally feeds into the downstream, where revenue would be estimated and used as a reward to improve the selection policy. To the best of our knowledge, this is first time to consider the system optimization from a downstream adaption view. It is also the first time to use reinforcement learning techniques to tackle this problem. The idea has been successfully realized in Baidu's sponsored search system, and online long time A/B test shows remarkable improvements on revenue.

cs.LG↗

arXiv2020

#Coronavirus or #Chinesevirus?!: Understanding the negative sentiment reflected in Tweets with racist hashtags across the development of COVID-19

Situated in the global outbreak of COVID-19, our study enriches the discussion concerning the emergent racism and xenophobia on social media. With big data extracted from Twitter, we focus on the analysis of negative sentiment reflected in tweets marked with racist hashtags, as racism and xenophobia are more likely to be delivered via the negative sentiment. Especially, we propose a stage-based approach to capture how the negative sentiment changes along with the three development stages of COVID-19, under which it transformed from a domestic epidemic into an international public health emergency and later, into the global pandemic. At each stage, sentiment analysis enables us to recognize the negative sentiment from tweets with racist hashtags, and keyword extraction allows for the discovery of themes in the expression of negative sentiment by these tweets. Under this public health crisis of human beings, this stage-based approach enables us to provide policy suggestions for the enactment of stage-specific intervention strategies to combat racism and xenophobia on social media in a more effective way.

cs.SI↗

arXiv2020

First SETI Observations with China's Five-hundred-meter Aperture Spherical radio Telescope (FAST)

The Search for Extraterrestrial Intelligence (SETI) attempts to address the possibility of the presence of technological civilizations beyond the Earth. Benefiting from high sensitivity, large sky coverage, an innovative feed cabin for China's Five-hundred-meter Aperture Spherical radio Telescope (FAST), we performed the SETI first observations with FAST's newly commisioned 19-beam receiver; we report preliminary results in this paper. Using the data stream produced by the SERENDIP VI realtime multibeam SETI spectrometer installed at FAST, as well as its off-line data processing pipelines, we identify and remove four kinds of radio frequency interference(RFI): zone, broadband, multi-beam, and drifting, utilizing the Nebula SETI software pipeline combined with machine learning algorithms. After RFI mitigation, the Nebula pipeline identifies and ranks interesting narrow band candidate ET signals, scoring candidates by the number of times candidate signals have been seen at roughly the same sky position and same frequency, signal strength, proximity to a nearby star or object of interest, along with several other scoring criteria. We show four example candidates groups that demonstrate these RFI mitigation and candidate selection. This preliminary testing on FAST data helps to validate our SETI instrumentation techniques as well as our data processing pipeline.

astro-ph.IM↗