BZPEERPapers, people, evidence and research paths
Menu

Discover

SearchFind papers, people, topics, institutions and opportunities from one place.GraphSee how papers, authors, topics and evidence connect.

Research tools

HomeContinue from the papers, people and topics that matter now.CollectionsTurn saved papers into reading lists, evidence maps and shareable context.ResearchReconstruct the path that led you from search to paper to question.CollaborationMove from a paper, topic or expert request into a focused thread.PublishCreate full-text research articles with metadata, formulas and versions.

Network

ExpertsFind specialists whose work and reviews explain why they can help.CommunitiesJoin research groups organized around papers, topics and shared evidence.

Opportunities

ListingsBrowse roles, calls and collaborations connected to real research context.

Account

Log inReturn to your saved papers, graph views and active threads.Create accountStart saving papers, building a research trail and joining teams.
Log inCreate account

Source author record

Ling Feng

Ling Feng appears in the imported research catalog. Authorship, coauthor and topic links are available while profile ownership is still unclaimed.

ResearcherUnclaimed source record
Machine Learningphysics.soc-phSocial and Information NetworksDatabasesComputation and LanguageComputer Visioncond-mat.stat-mechDiscrete MathematicsHuman-Computer InteractionInformation Retrieval

Catalog footprint

What is connected

12works
10topics
4close collaborators

Actions

Connect this record

Log in to claim
Open graphBrowse works

Research graph

See the researcher in context

Open full explorer

Inspect adjacent papers, topics, institutions and collaborators without losing the researcher page.

Building this map preview

BZPEER is loading the nearby papers, people, topics and institutions for this page.

Published work

12 published item(s)

preprint2026arXiv

A Unified Graph Language Model for Multi-Domain Multi-Task Graph Alignment Instruction Tuning

Leveraging Graph Neural Networks (GNNs) as graph encoders and aligning the resulting representations with Large Language Models (LLMs) through alignment instruction tuning has become a mainstream paradigm for constructing Graph Language Models (GLMs), combining the generalization ability of LLMs with the structural modeling capacity of GNNs. However, existing GLMs that adopt GNNs as graph encoders largely overlook the problem of aligning GNN-encoded representations across domains and tasks with the LLM token space to obtain unified graph tokens, thereby limiting their ability to generalize across diverse graph data. To bridge this gap, we aim to incorporate a multi-domain, multi-task GNN encoder into GLMs and align its representations with LLMs to enable multi-domain, multi-task graph alignment instruction tuning. This alignment problem remains underexplored and poses two key challenges: 1) learning GNN-encoded representations that are simultaneously generalizable across domains and tasks and well aligned with textual semantics is difficult, due to substantial variations in graph structures, feature distributions, and supervision signals, together with the lack of textual-semantic alignment guidance in task-specific GNN training; 2) diverse graph data and task-specific instructions can exhibit different degrees of compatibility with the LLM token space during instruction tuning, leading to varying alignment difficulty and rendering a fixed alignment strategy suboptimal. To tackle these challenges, we propose UniGraphLM, a Unified Graph Language Model that incorporates a multi-domain, multi-task GNN encoder to learn generalizable graph representations aligned with textual semantics, and then adaptively aligns these representations with the LLM.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

Chaining the Evidence: Robust Reinforcement Learning for Deep Search Agents with Citation-Aware Rubric Rewards

Reinforcement learning (RL) has emerged as a critical technique for enhancing LLM-based deep search agents. However, existing approaches primarily rely on binary outcome rewards, which fail to capture the comprehensiveness and factuality of agents' reasoning process, and often lead to undesirable behaviors such as shortcut exploitation and hallucinations. To address these limitations, we propose \textbf{Citation-aware Rubric Rewards (CaRR)}, a fine-grained reward framework for deep search agents that emphasizes reasoning comprehensiveness, factual grounding, and evidence connectivity. CaRR decomposes complex questions into verifiable single-hop rubrics and requires agents to satisfy these rubrics by explicitly identifying hidden entities, supporting them with correct citations, and constructing complete evidence chains that link to the predicted answer. We further introduce \textbf{Citation-aware Group Relative Policy Optimization (C-GRPO)}, which combines CaRR and outcome rewards for training robust deep search agents. Experiments show that C-GRPO consistently outperforms standard outcome-based RL baselines across multiple deep search benchmarks. Our analysis also validates that C-GRPO effectively discourages shortcut exploitation, promotes comprehensive, evidence-grounded reasoning, and exhibits strong generalization to open-ended deep research tasks. Our code and data are available at https://github.com/THUDM/CaRR.

0 citations0 reviewsNo code linkedOpen access
preprint2025arXiv

Spatial-aware Vision Language Model for Autonomous Driving

While Vision-Language Models (VLMs) show significant promise for end-to-end autonomous driving by leveraging the common sense embedded in language models, their reliance on 2D image cues for complex scene understanding and decision-making presents a critical bottleneck for safety and reliability. Current image-based methods struggle with accurate metric spatial reasoning and geometric inference, leading to unreliable driving policies. To bridge this gap, we propose LVLDrive (LiDAR-Vision-Language), a novel framework specifically designed to upgrade existing VLMs with robust 3D metric spatial understanding for autonomous driving by incoperating LiDAR point cloud as an extra input modality. A key challenge lies in mitigating the catastrophic disturbance introduced by disparate 3D data to the pre-trained VLMs. To this end, we introduce a Gradual Fusion Q-Former that incrementally injects LiDAR features, ensuring the stability and preservation of the VLM's existing knowledge base. Furthermore, we develop a spatial-aware question-answering (SA-QA) dataset to explicitly teach the model advanced 3D perception and reasoning capabilities. Extensive experiments on driving benchmarks demonstrate that LVLDrive achieves superior performance compared to vision-only counterparts across scene understanding, metric spatial perception, and reliable driving decision-making. Our work highlights the necessity of explicit 3D metric data for building trustworthy VLM-based autonomous systems.

0 citations0 reviewsNo code linkedOpen access
preprint2023arXiv

FedSSC: Shared Supervised-Contrastive Federated Learning

Federated learning is widely used to perform decentralized training of a global model on multiple devices while preserving the data privacy of each device. However, it suffers from heterogeneous local data on each training device which increases the difficulty to reach the same level of accuracy as the centralized training. Supervised Contrastive Learning which outperform cross-entropy tries to minimizes the difference between feature space of points belongs to the same class and pushes away points from different classes. We propose Supervised Contrastive Federated Learning in which devices can share the learned class-wise feature spaces with each other and add the supervised-contrastive learning loss as a regularization term to foster the feature space learning. The loss tries to minimize the cosine similarity distance between the feature map and the averaged feature map from another device in the same class and maximizes the distance between the feature map and that in a different class. This new regularization term when added on top of the moon regularization term is found to outperform the other state-of-the-art regularization terms in solving the heterogeneous data distribution problem.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Collaborative Inference for Efficient Remote Monitoring

While current machine learning models have impressive performance over a wide range of applications, their large size and complexity render them unsuitable for tasks such as remote monitoring on edge devices with limited storage and computational power. A naive approach to resolve this on the model level is to use simpler architectures, but this sacrifices prediction accuracy and is unsuitable for monitoring applications requiring accurate detection of the onset of adverse events. In this paper, we propose an alternative solution to this problem by decomposing the predictive model as the sum of a simple function which serves as a local monitoring tool, and a complex correction term to be evaluated on the server. A sign requirement is imposed on the latter to ensure that the local monitoring function is safe, in the sense that it can effectively serve as an early warning system. Our analysis quantifies the trade-offs between model complexity and performance, and serves as a guidance for architecture design. We validate our proposed framework on a series of monitoring experiments, where we succeed at learning monitoring models with significantly reduced complexity that minimally violate the safety requirement. More broadly, our framework is useful for learning classifiers in applications where false negatives are significantly more costly compared to false positives.

0 citations0 reviewsNo code linkedOpen access
preprint2016arXiv

A Method to Support Difficult Re-finding Tasks

Re-finding electronic documents from a personal computer is a frequent demand to users. In a simple re-finding task, people can use many methods to retrieve a document, such as navigating directly to the document's folder, searching with a desktop search engine, or checking the Recent Files List. However, when encountering a difficult re-finding task, people usually cannot remember the attributes used by conventional re-finding methods, such as file path, file name, keywords etc., the re-finding would fail. We propose a new method to support difficult re-finding tasks. When a user is reading a document, we collect all kinds of possible memory pieces of the user about the document, such as number of pages, number of images, number of math formulas, cumulative reading time, reading frequency, printing experiences etc. If the user wants to re-find a document later, we use these collected attributes to filter out the target document. To alleviate the user's cognitive burden, we use a question and answer wizard interface and provide recommendations to the answers for the user, the recommendations are generated by analyzing the collected attributes of each document and the user's experiences about them.

0 citations0 reviewsNo code linkedOpen access
preprint2015arXiv

A Simplified Self-Consistent Probabilities Framework to Characterize Percolation Phenomena on Interdependent Networks : An Overview

Interdependent networks are ubiquitous in our society, ranging from infrastructure to economics, and the study of their cascading behaviors using percolation theory has attracted much attention in the recent years. To analyze the percolation phenomena of these systems, different mathematical frameworks have been proposed including generating functions, eigenvalues among some others. These different frameworks approach the phase transition behaviors from different angles, and have been very successful in shaping the different quantities of interest including critical threshold, size of the giant component, order of phase transition and the dynamics of cascading. These methods also vary in their mathematical complexity in dealing with interdependent networks that have additional complexity in terms of the correlation among different layers of networks or links. In this work, we review a particular approach of simple self-consistent probability equations, and illustrate that it can greatly simplify the mathematical analysis for systems ranging from single layer network to various different interdependent networks. We give an overview on the detailed framework to study the nature of the critical phase transition, value of the critical threshold and size of the giant component for these different systems.

0 citations0 reviewsNo code linkedOpen access
preprint2014arXiv

A 2D based Partition Strategy for Solving Ranking under Team Context (RTP)

In this paper, we propose a 2D based partition method for solving the problem of Ranking under Team Context(RTC) on datasets without a priori. We first map the data into 2D space using its minimum and maximum value among all dimensions. Then we construct window queries with consideration of current team context. Besides, during the query mapping procedure, we can pre-prune some tuples which are not top ranked ones. This pre-classified step will defer processing those tuples and can save cost while providing solutions for the problem. Experiments show that our algorithm performs well especially on large datasets with correctness.

0 citations0 reviewsNo code linkedOpen access
preprint2014arXiv

Competing for Attention in Social Media under Information Overload Conditions

Although the many forms of modern social media have become major channels for the dissemination of information, they are becoming overloaded because of the rapidly-expanding number of information feeds. We analyze the expanding user-generated content in Sina Weibo, the largest micro-blog site in China, and find evidence that popular messages often follow a mechanism that differs from that found in the spread of disease, in contrast to common believe. In this mechanism, an individual with more friends needs more repeated exposures to spread further the information. Moreover, our data suggest that in contrast to epidemics, for certain messages the chance of an individual to share the message is proportional to the fraction of its neighbours who shared it with him/her. Thus the greater the number of friends an individual has the greater the number of repeated contacts needed to spread the message, which is a result of competition for attention. We model this process using a fractional susceptible infected recovered (FSIR) model, where the infection probability of a node is proportional to its fraction of infected neighbors. Our findings have dramatic implications for information contagion. For example, using the FSIR model we find that real-world social networks have a finite epidemic threshold. This is in contrast to the zero threshold that conventional wisdom derives from disease epidemic models. This means that when individuals are overloaded with excess information feeds, the information either reaches out the population if it is above the critical epidemic threshold, or it would never be well received, leading to only a handful of information contents that can be widely spread throughout the population.

0 citations0 reviewsNo code linkedOpen access
preprint2014arXiv

Object Selection under Team Context

Context-aware database has drawn increasing attention from both industry and academia recently by taking users' current situation and environment into consideration. However, most of the literature focus on individual context, overlooking the team users. In this paper, we investigate how to integrate team context into database query process to help the users' get top-ranked database tuples and make the team more competitive. We introduce naive and optimized query algorithm to select the suitable records and show that they output the same results while the latter is more computational efficient. Extensive empirical studies are conducted to evaluate the query approaches and demonstrate their effectiveness and efficiency.

0 citations0 reviewsNo code linkedOpen access
preprint2014arXiv

On the Real-time Prediction Problems of Bursting Hashtags in Twitter

Hundreds of thousands of hashtags are generated every day on Twitter. Only a few become bursting topics. Among the few, only some can be predicted in real-time. In this paper, we take the initiative to conduct a systematic study of a series of challenging real-time prediction problems of bursting hashtags. Which hashtags will become bursting? If they do, when will the burst happen? How long will they remain active? And how soon will they fade away? Based on empirical analysis of real data from Twitter, we provide insightful statistics to answer these questions, which span over the entire lifecycles of hashtags.

0 citations0 reviewsNo code linkedOpen access
preprint2012arXiv

A New Weighted Spearman's Footrule as A Measure of Distance between Rankings

Many applications motivate the distance measure between rankings, such as comparing top-k lists and rank aggregation for voting, and intrigue great interest to researchers. For example, for a search engine, the use of different ranking algorithms may return different ranking lists. The effect of a ranking algorithm can be estimated by computing the distance (similarity) between the result ranking it returns and the appropriate ranking people expect. People may be interested in only the first few items of result ranking, therefore the metric for measuring the distance should emphasize on the items in higher positions. Besides, in an extreme case, if a result ranking is the total reverse of the expected ranking, then it is considered to be the worst ranking with the maximum distance. Therefore, a metric is called for, which can satisfy both of the two intuitions. To address this problem, we present a weighted metric based on the classical Spearman's footrule metric to measure the distance between two permutations of n objects. This metric can be applied in rank aggregation problem with a polynomial time algorithm, and produces a 2-approximation for adopting the weighted Kendall's tau distance proposed by Farnoud et al.

0 citations0 reviewsNo code linkedOpen access