Wang, Kai

MLLMs-Augmented Visual-Language Representation Learning

Visual-language pre-training has achieved remarkable success in many multi-modal tasks, largely attributed to the availability of large-scale image-text datasets. In this work, we demonstrate that...

SLearnLLM: A Self-Learning Framework for Efficient Domain-Specific Adaptation of Large Language Models

When using supervised fine-tuning (SFT) to adapt large language models (LLMs) to specific domains, a significant challenge arises: should we use the entire SFT dataset for fine-tuning? Common...

ReCAST: Restoration-aware Cascaded Stage-wise Training for Obfuscated SMS Risk Classification

Trip+: Benchmarking Agents in Personalized Interactive Travel Planning

SkillSafetyBench: Evaluating Agent Safety under Skill-Facing Attack Surfaces

Understanding Training Data Attribution in RLVR: From the Perspective of Causal Inference

Are Large Language Models Suitable for Graph Computation? Progress and Prospects

EvoSQL: Memory-Augmented Critic-Generator Co-Evolution for Text-to-SQL

HEAL: Hindsight Entropy-Assisted Learning for Reasoning Distillation

Attend to Evidence: Evidence-Anchored Spatial Attention Supervision for Multimodal RLVR

Exploiting Salient Patterns for Question Detection and Question Retrieval in Community-based Question Answering

Domain-Assisted Product Aspect Hierarchy Generation: Towards Hierarchical Organization of Unstructured Consumer Reviews

BiSET: Bi-directional Selective Encoding with Template for Abstractive Summarization

Multi-Domain Dialogue Acts and Response Co-Generation

Low-Resource Generation of Multi-hop Reasoning Questions

Relational Graph Attention Network for Aspect-based Sentiment Analysis

基于图神经网络的汉语依存分析和语义组合计算联合模型(Joint Learning Chinese Dependency Parsing and Semantic Composition based on Graph Neural Network)

Hyperbolic Geometry is Not Necessary: Lightweight Euclidean-Based Models for Low-Dimensional Knowledge Graph Embeddings