arXiv subjects

Xudong Gong

Publications and source records attributed to Xudong Gong.

6 recordsLinked to original sources

arXiv2026

Resilience Matters for Embodied Agents System: New Metrics, Systematic Evaluation, and Optimization

Embodied Agents System (EAS) are increasingly deployed in open-world physical domains, where reliability directly dictates deployment quality and human-agent trust. However, existing evaluations rely on outcome-centric metrics as success rate or safety scores that collapse diverse execution trajectories into coarse scores, obscuring the dynamic processes underlying agent behavior. Therefore, they ignore a critical property of EAS -- which we define as the Resilience -- that reflects how EASs recover, stabilize, and extend under perturbations and across iterative updates. The lack of resilience is particularly critical in open-world environments due to continuous unexpected disruptions, thus directly affecting the quality of EAS deployment. To address this problem, we gain insight from the resilience-engineering concepts to EAS groundings and propose a novel resilience evaluation framework that can be flexibly applied to any EAS. Specifically, we define the first comprehensive resilience metrics suite for EASs system that exposes Rebound, Stability, and Graceful Extensibility across embodied tasks execution, providing a practical grounding for EAS resilience analysis. We further implement the resilience evaluation layer that transforms execution process into assessments for diagnosis and optimization. Across 400 household tasks with 10 EAS, we reveal the process-level distinction hidden by outcome metrics, including recovery cost differences among successful episodes ($ΔC_{rec}=25.2$), increased instability and task-family degradation. Metrics-guided optimizations reduce recovery cost and increase stability, graceful extensibility completion, showing the diagnostic effect of resilience evaluation. Our results reveal a trade-off among resilience characteristics, suggesting that a resilient EAS construction should be configured according to deployment-specific requirements.

cs.RO↗

arXiv2026

Beyond Scores: Diagnostic LLM Evaluation via Fine-Grained Abilities

Current evaluations of large language models aggregate performance across diverse tasks into single scores. This obscures fine-grained ability variation, limiting targeted model improvement and ability-guided selection for specific tasks. Motivated by this gap, we propose a cognitive diagnostic framework that estimates model abilities across multiple fine-grained dimensions. For mathematics, we construct a 35-dimensional ability taxonomy grounded in cognitive theory and domain knowledge. The framework employs multidimensional Item Response Theory with an item-ability association matrix to estimate fine-grained ability levels, which in turn enable prediction of performance on unseen items (questions of benchmark). Evaluated on 41 models, our approach demonstrates strong criterion validity, consistent ability estimates across benchmarks, and accurate prediction of unseen items with AUC ranging from 0.80 to 0.89 within benchmarks and from 0.77 to 0.86 across benchmarks, substantially exceeding trivial baselines. The framework generalizes across scientific domains, producing consistent diagnostic performance in physics (27 dimensions), chemistry (58 dimensions), and computer science (12 dimensions). This work establishes a principled framework for fine-grained assessment of abilities, with potential applications in targeted training, ability-guided model selection, and ability-aware benchmark design.

cs.AI↗

arXiv2024

Optimistic Model Rollouts for Pessimistic Offline Policy Optimization

Model-based offline reinforcement learning (RL) has made remarkable progress, offering a promising avenue for improving generalization with synthetic model rollouts. Existing works primarily focus on incorporating pessimism for policy optimization, usually via constructing a Pessimistic Markov Decision Process (P-MDP). However, the P-MDP discourages the policies from learning in out-of-distribution (OOD) regions beyond the support of offline datasets, which can under-utilize the generalization ability of dynamics models. In contrast, we propose constructing an Optimistic MDP (O-MDP). We initially observed the potential benefits of optimism brought by encouraging more OOD rollouts. Motivated by this observation, we present ORPO, a simple yet effective model-based offline RL framework. ORPO generates Optimistic model Rollouts for Pessimistic offline policy Optimization. Specifically, we train an optimistic rollout policy in the O-MDP to sample more OOD model rollouts. Then we relabel the sampled state-action pairs with penalized rewards and optimize the output policy in the P-MDP. Theoretically, we demonstrate that the performance of policies trained with ORPO can be lower-bounded in linear MDPs. Experimental results show that our framework significantly outperforms P-MDP baselines by a margin of 30%, achieving state-of-the-art performance on the widely-used benchmark. Moreover, ORPO exhibits notable advantages in problems that require generalization.

cs.LG↗

arXiv2022

Real-time Short Video Recommendation on Mobile Devices

Short video applications have attracted billions of users in recent years, fulfilling their various needs with diverse content. Users usually watch short videos on many topics on mobile devices in a short period of time, and give explicit or implicit feedback very quickly to the short videos they watch. The recommender system needs to perceive users' preferences in real-time in order to satisfy their changing interests. Traditionally, recommender systems deployed at server side return a ranked list of videos for each request from client. Thus it cannot adjust the recommendation results according to the user's real-time feedback before the next request. Due to client-server transmitting latency, it is also unable to make immediate use of users' real-time feedback. However, as users continue to watch videos and feedback, the changing context leads the ranking of the server-side recommendation system inaccurate. In this paper, we propose to deploy a short video recommendation framework on mobile devices to solve these problems. Specifically, we design and deploy a tiny on-device ranking model to enable real-time re-ranking of server-side recommendation results. We improve its prediction accuracy by exploiting users' real-time feedback of watched videos and client-specific real-time features. With more accurate predictions, we further consider interactions among candidate videos, and propose a context-aware re-ranking method based on adaptive beam search. The framework has been deployed on Kuaishou, a billion-user scale short video application, and improved effective view, like and follow by 1.28%, 8.22% and 13.6% respectively.

cs.IR↗

arXiv2013

Integrity Verification for Outsourcing Uncertain Frequent Itemset Mining

In recent years, due to the wide applications of uncertain data (e.g., noisy data), uncertain frequent itemsets (UFI) mining over uncertain databases has attracted much attention, which differs from the corresponding deterministic problem from the generalized definition and resolutions. As the most costly task in association rule mining process, it has been shown that outsourcing this task to a service provider (e.g.,the third cloud party) brings several benefits to the data owner such as cost relief and a less commitment to storage and computational resources. However, the correctness integrity of mining results can be corrupted if the service provider is with random fault or not honest (e.g., lazy, malicious, etc). Therefore, in this paper, we focus on the integrity and verification issue in UFI mining problem during outsourcing process, i.e., how the data owner verifies the mining results. Specifically, we explore and extend the existing work on deterministic FI outsourcing verification to uncertain scenario. For this purpose, We extend the existing outsourcing FI mining work to uncertain area w.r.t. the two popular UFI definition criteria and the approximate UFI mining methods. Specifically, We construct and improve the basic/enhanced verification scheme with such different UFI definition respectively. After that, we further discuss the scenario of existing approximation UFP mining, where we can see that our technique can provide good probabilistic guarantees about the correctness of the verification. Finally, we present the comparisons and analysis on the schemes proposed in this paper.

cs.DB↗

arXiv2013

A Secure Distributed Authentication scheme based on CRT-VSS and Trusted Computing in MANET

With the rapid development of MANET, secure and practical authentication is becoming increasingly important. The existing works perform the research from two aspects, i.e., (a)secure key division and distributed storage, (b)secure distributed authentication. But there still exist several unsolved problems. Specifically, it may suffer from cheating problems and fault authentication attack, which can result in authentication failure and DoS attack towards authentication service. Besides, most existing schemes are not with satisfactory efficiency due to exponential arithmetic based on Shamir's scheme. In this paper, we explore the property of verifiable secret sharing(VSS) schemes with Chinese Remainder Theorem (CRT), then propose a secret key distributed storage scheme based on CRT-VSS and trusted computing for MANET. Specifically, we utilize trusted computing technology to solve two existing cheating problems in secret sharing area before. After that, we do the analysis of homomorphism property with CRT-VSS and design the corresponding shares-product sharing scheme with better concision. On such basis, a secure distributed Elliptic Curve-Digital Signature Standard signature (ECC-DSS) authentication scheme based on CRT-VSS scheme and trusted computing is proposed. Furthermore, as an important property of authentication scheme, we discuss the refreshing property of CRT-VSS and do thorough comparisons with Shamir's scheme. Finally, we provide formal guarantees towards our schemes proposed in this paper.

cs.CR↗