1 citations · 6 across the 25 of their papers we have counts for
26 papers
Resilience Matters for Embodied Agents System: New Metrics, Systematic Evaluation, and Optimization
Yapeng Liu, Yuanzhao Zhai, Xudong Gong +4
Embodied Agents System (EAS) are increasingly deployed in open-world physical domains, where reliability directly dictates deployment quality and human-agent trust. However, existi…
ReFrame: Evidence-Guided Test-Time Safety Alignment in Multimodal Large Language Models
Wenzheng Jiang, Xuankun Rong, Yuanzhao Zhai +2
While multimodal large language models (MLLMs) extend model capabilities beyond text, they also make safety alignment increasingly challenging. Multimodal safety alignment methods…
An Empirical Study on the Impact of Normalized Use-Case Specifications on Traceability
Luoyuan Shi, Yuanzhao Zhai, Dawei Feng +4
Traceability link recovery between requirements and source code is vital for software quality assurance and evolution analysis. Although automated traceability techniques have adva…
Energy-Structured Latent World Models with Neural Time Fields for Physically Constistent Open-World Motion Planning
Yapeng Liu, Yuanzhao Zhai, Bo Ding +2
Physically consistent motion planning remains a fundamental challenge in embodied AI, as generated trajectories must strictly conform to real-world execution dynamics. While latent…
MCPEvol-Bench: Benchmarking LLM Agent Performance Across Dynamic Evolutions of MCP Servers
Huanxi Liu, Kun Hu, Jiaqi Liao +6
As Model Context Protocol (MCP) servers emerge as the core infrastructure for connecting LLMs with external tools, existing benchmarks leverage real-world MCP servers to evaluate L…
From Objectives to Applications: Aligning Architectural Biases in Audio Self-Supervised Learning
Kele Xu, Yulu Fang, Boda Zhou +6
This paper examines audio self-supervised learning (SSL) through the alignment between pretraining objectives, architectural inductive biases, and downstream applications. Rather t…
MAny: Merge Anything for Multimodal Continual Instruction Tuning
Zijian Gao, Wangwang Jia, Xingxing Zhang +6
Multimodal Continual Instruction Tuning (MCIT) is essential for sequential task adaptation of Multimodal Large Language Models (MLLMs) but is severely restricted by catastrophic fo…
Scaffold-Conditioned Preference Triplets for Controllable Molecular Optimization with Large Language Models
Yi Xiong, Liang Xiong, Xiaohong Ji +4
Molecular property optimization is central to drug discovery, yet many deep learning methods rely on black-box scoring and offer limited control over scaffold preservation, often p…
Ranking Constraints via Topological Dual-Directional Search in Evolutionary Multi-Objective Optimization
Ruiqing Sun, Dawei Feng, Sheng Qi +6
Existing evolutionary algorithms for Constrained Multi-objective Optimization Problems (CMOPs) typically treat all constraints uniformly, overlooking their distinct geometric relat…
Silent Speech Interfaces in the Era of Large Language Models: A Comprehensive Taxonomy and Systematic Review
Kele Xu, Yifan Wang, Ming Feng +5
Human-computer interaction has traditionally relied on the acoustic channel, a dependency that introduces systemic vulnerabilities to environmental noise, privacy constraints, and…
Data-driven active learning approaches for accelerating materials discovery
Jiaxin Chen, Tianjiao Wan, Hui Geng +10
Materials discovery is a cornerstone of modern technological advancement, yet it remains constrained by traditional trial-and-error paradigms and the inherent bias of human intuiti…
Decoupling Constraints from Two Directions for Evolutionary Constrained Multi-objective Optimization
Ruiqing Sun, Dawei Feng, Xing Zhou +6
Real-world constrained multi-objective optimization problems (CMOPs) commonly involve multiple constraints, and understanding and exploiting their coupling relationships is crucial…
Diffusion-based Evolutionary Optimization for 3D Multi-Objective Molecular Generation
Ruiqing Sun, Dawei Feng, Sen Yang +5
Optimizing conflicting molecular properties while strictly adhering to complex 3D structural constraints constitutes a challenging Constrained Multi-Objective Optimization Problem…
Pay More Attention to the Robustness of Prompt for Instruction Data Mining
Qiang Wang, Dawei Feng, Xu Zhang +4
Instruction tuning has emerged as a paramount method for tailoring the behaviors of LLMs. Recent work has unveiled the potential for LLMs to achieve high performance through fine-t…
AutoFeedback: An LLM-based Framework for Efficient and Accurate API Request Generation
Huanxi Liu, Jiaqi Liao, Dawei Feng +2
Large Language Models (LLMs) leverage external tools primarily through generating the API request to enhance task completion efficiency. The accuracy of API request generation sign…
Enhancing Decision-Making for LLM Agents via Step-Level Q-Value Models
Yuanzhao Zhai, Tingkai Yang, Kele Xu +4
Agents significantly enhance the capabilities of standalone Large Language Models (LLMs) by perceiving environments, making decisions, and executing actions. However, LLM agents st…
Online Self-Preferring Language Models
Yuanzhao Zhai, Zhuo Zhang, Kele Xu +6
Aligning with human preference datasets has been critical to the success of large language models (LLMs). Reinforcement learning from human feedback (RLHF) employs a costly reward…
Optimistic Model Rollouts for Pessimistic Offline Policy Optimization
Yuanzhao Zhai, Yiying Li, Zijian Gao +5
Model-based offline reinforcement learning (RL) has made remarkable progress, offering a promising avenue for improving generalization with synthetic model rollouts. Existing works…
Uncertainty-Penalized Reinforcement Learning from Human Feedback with Diverse Reward LoRA Ensembles
Yuanzhao Zhai, Han Zhang, Yu Lei +5
Reinforcement learning from human feedback (RLHF) emerges as a promising paradigm for aligning large language models (LLMs). However, a notable challenge in RLHF is overoptimizatio…
Diversifying Message Aggregation in Multi-Agent Communication via Normalized Tensor Nuclear Norm Regularization
Yuanzhao Zhai, Kele Xu, Bo Ding +3
Aggregating messages is a key component for the communication of multi-agent reinforcement learning (Comm-MARL). Recently, it has witnessed the prevalence of graph attention networ…
Self-Supervised Exploration via Temporal Inconsistency in Reinforcement Learning
Zijian Gao, Kele Xu, Yuanzhao Zhai +4
Under sparse extrinsic reward settings, reinforcement learning has remained challenging, despite surging interests in this field. Previous attempts suggest that intrinsic reward ca…
Dynamic Memory-based Curiosity: A Bootstrap Approach for Exploration
Zijian Gao, YiYing Li, Kele Xu +5
The sparsity of extrinsic rewards poses a serious challenge for reinforcement learning (RL). Currently, many efforts have been made on curiosity which can provide a representative…
Trusted Multi-Scale Classification Framework for Whole Slide Image
Ming Feng, Kele Xu, Nanhui Wu +4
Despite remarkable efforts been made, the classification of gigapixels whole-slide image (WSI) is severely restrained from either the constrained computing resources for the whole…
Nuclear Norm Maximization Based Curiosity-Driven Learning
Chao Chen, Zijian Gao, Kele Xu +5
To handle the sparsity of the extrinsic rewards in reinforcement learning, researchers have proposed intrinsic reward which enables the agent to learn the skills that might come in…