19 papers
MR-Bench: A Unified Benchmark for Evidence-Grounded Multimodal Metaphor Understanding
Hong Jiang, Junnan Zhu, Jingwang Huang +9
Multimodal metaphor understanding requires identifying cross-domain Target-Source mappings and inferring sentiment from visual and textual evidence. However, existing benchmarks la…
SafeSteer: A Decoding-level Defense Mechanism for Multimodal Large Language Models
Xinyi Zeng, Xue Yang, Jingyuan Zhang +5
Multimodal large language models (MLLMs) are gaining increasing attention. Due to the heterogeneity of their input features, they face significant challenges in terms of jailbreak…
MentalSeek-Dx: Towards Progressive Hypothetico-Deductive Reasoning for Real-world Psychiatric Diagnosis
Xiao Sun, Yuming Yang, Junnan Zhu +3
Mental health disorders represent a burgeoning global public health challenge. While Large Language Models (LLMs) have demonstrated potential in psychiatric assessment, their clini…
Do Models Hear Like Us? Probing the Representational Alignment of Audio LLMs and Naturalistic EEG
Haoyun Yang, Xin Xiao, Jiang Zhong +5
Audio Large Language Models (Audio LLMs) have demonstrated strong capabilities in integrating speech perception with language understanding. However, whether their internal represe…
Me-Agent: A Personalized Mobile Agent with Two-Level User Habit Learning for Enhanced Interaction
Shuoxin Wang, Chang Liu, Gowen Loo +5
Large Language Model (LLM)-based mobile agents have made significant performance advancements. However, these agents often follow explicit user instructions while overlooking perso…
ES-Mem: Event Segmentation-Based Memory for Long-Term Dialogue Agents
Huhai Zou, Tianhao Sun, Chuanjiang He +6
Memory is critical for dialogue agents to maintain coherence and enable continuous adaptation in long-term interactions. While existing memory mechanisms offer basic storage and re…
DiffER: Diffusion Entity-Relation Modeling for Reversal Curse in Diffusion Large Language Models
Shaokai He, Kaiwen Wei, Xinyi Zeng +5
The "reversal curse" refers to the phenomenon where large language models (LLMs) exhibit predominantly unidirectional behavior when processing logically bidirectional relationships…
ReasonTabQA: A Comprehensive Benchmark for Table Question Answering from Real World Industrial Scenarios
Changzai Pan, Jie Zhang, Kaiwen Wei +15
Recent advancements in Large Language Models (LLMs) have significantly catalyzed table-based question answering (TableQA). However, existing TableQA benchmarks often overlook the i…
GeoViS: Geospatially Rewarded Visual Search for Remote Sensing Visual Grounding
Peirong Zhang, Yidan Zhang, Luxiao Xu +6
Recent advances in multimodal large language models(MLLMs) have led to remarkable progress in visual grounding, enabling fine-grained cross-modal alignment between textual queries…
Automated Network Protocol Testing with LLM Agents
Yunze Wei, Kaiwen Wei, Shibo Du +7
Network protocol testing is fundamental for modern network infrastructure. However, traditional network protocol testing methods are labor-intensive and error-prone, requiring manu…
CFVBench: A Comprehensive Video Benchmark for Fine-grained Multimodal Retrieval-Augmented Generation
Kaiwen Wei, Xiao Liu, Jie Zhang +11
Multimodal Retrieval-Augmented Generation (MRAG) enables Multimodal Large Language Models (MLLMs) to generate responses with external multimodal evidence, and numerous video-based…
T2R-bench: A Benchmark for Generating Article-Level Reports from Real World Industrial Tables
Jie Zhang, Changzai Pan, Kaiwen Wei +12
Extensive research has been conducted to explore the capabilities of large language models (LLMs) in table reasoning. However, the essential task of transforming tables information…
Exploring Similarity between Neural and LLM Trajectories in Language Processing
Xin Xiao, Kaiwen Wei, Jiang Zhong +2
Understanding the similarity between large language models (LLMs) and human brain activity is crucial for advancing both AI and cognitive neuroscience. In this study, we provide a…
From Past To Path: Masked History Learning for Next-Item Prediction in Generative Recommendation
KaiWen Wei, Kejun He, Xiaomian Kang +7
Generative recommendation, which directly generates item identifiers, has emerged as a promising paradigm for recommendation systems. However, its potential is fundamentally constr…
Learning to Shop Like Humans: A Review-driven Retrieval-Augmented Recommendation Framework with LLMs
Kaiwen Wei, Jinpeng Gao, Jiang Zhong +3
Large language models (LLMs) have shown strong potential in recommendation tasks due to their strengths in language understanding, reasoning and knowledge integration. These capabi…
GraphFedMIG: Tackling Class Imbalance in Federated Graph Learning via Mutual Information-Guided Generation
Xinrui Li, Qilin Fan, Tianfu Wang +3
Federated graph learning (FGL) enables multiple clients to collaboratively train powerful graph neural networks without sharing their private, decentralized graph data. Inherited f…
MIRAGE: Scaling Test-Time Inference with Parallel Graph-Retrieval-Augmented Reasoning Chains
Kaiwen Wei, Rui Shan, Dongsheng Zou +4
Large reasoning models (LRMs) have shown significant progress in test-time scaling through chain-of-thought prompting. Current approaches like search-o1 integrate retrieval augment…
Benchmarking Multimodal RAG through a Chart-based Document Question-Answering Generation Framework
Yuming Yang, Jiang Zhong, Li Jin +7
Multimodal Retrieval-Augmented Generation (MRAG) enhances reasoning capabilities by integrating external knowledge. However, existing benchmarks primarily focus on simple image-tex…
Latent Distribution Decoupling: A Probabilistic Framework for Uncertainty-Aware Multimodal Emotion Recognition
Jingwang Huang, Jiang Zhong, Qin Lei +5
Multimodal multi-label emotion recognition (MMER) aims to identify the concurrent presence of multiple emotions in multimodal data. Existing studies primarily focus on improving fu…