Learning Regularization for Graph Inverse Problems
Comments AAAI 2025 (Oral)
期刊&会议
AAAI
AAAI Conference on Artificial Intelligence · 会议 · Artificial Intelligence
The Distributional Reward Critic Framework for Reinforcement Learning Under Perturbed Rewards
Comments published in AAAI 2025
Hierarchical Cross-Modal Alignment for Open-Vocabulary 3D Object Detection
Comments AAAI 2025 (Extented Version). Project Page: https://youjunzhao.github.io/HCMA/
Bi-Directional Mental Model Reconciliation for Human-Robot Interaction with Large Language Models
Comments Advancing Artificial Intelligence through Theory of Mind Workshop at AAAI 2025
Weak Supervision for Improved Precision in Search Systems
Comments Accepted to the AAAI 2025 Workshop on Computational Jobs Marketplace
Asymmetric Visual Semantic Embedding Framework for Efficient Vision-Language Alignment
Comments 9 pages, 5 figures, The 39th Annual AAAI Conference on Artificial Intelligence
Capture Global Feature Statistics for One-Shot Federated Learning
Comments AAAI 2025
VLScene: Vision-Language Guidance Distillation for Camera-Based 3D Semantic Scene Completion
Comments Accept by AAAI-2025(Oral)
CUPCase: Clinically Uncommon Patient Cases and Diagnoses Dataset
Comments Accepted to AAAI 2025
Bridging Molecular Graphs and Large Language Models
Comments AAAI 2025 camera ready version
TimeCAP: Learning to Contextualize, Augment, and Predict Time Series Events with Large Language Model Agents
Comments AAAI 2025
Enhancing LLMs for Governance with Human Oversight: Evaluating and Aligning LLMs on Expert Classification of Climate Misinformation for Detecting False or Misleading Claims about Climate Change
Comments International Workshop on AI Governance: Alignment, Morality and Law (AIGOV) 2025. AAAI Conference on Artificial Intelligence
CoMT: A Novel Benchmark for Chain of Multi-modal Thought on Large Vision-Language Models
Comments Accepted at AAAI 2025; Project Page: https://github.com/czhhzc/CoMT
Attend and Enrich: Enhanced Visual Prompt for Zero-Shot Learning
Comments Accepted by AAAI 2025
Explore In-Context Segmentation via Latent Diffusion Models
Comments AAAI 2025
ResAdapter: Domain Consistent Resolution Adapter for Diffusion Models
Comments Accepted by AAAI 2025
Vision-aware Multimodal Prompt Tuning for Uploadable Multi-source Few-shot Domain Adaptation
Comments Accepted by AAAI 2025
Multi-Attribute Multi-Grained Adaptation of Pre-Trained Language Models for Text Understanding from Bayesian Perspective
Comments Extended version accepted by AAAI 2025
Data-Free Black-Box Federated Learning via Zeroth-Order Gradient Estimation
Comments Accepted by AAAI 2025
AI Mentors for Student Projects: Spotting Early Issues in Computer Science Proposals
Comments Accepted for oral presentation at Workshop on Innovation and Responsibility in AI-Supported Education (iRAISE), AAAI 2025
Hierarchical Document Parsing via Large Margin Feature Matching and Heuristics
Comments DocUI@AAAI-25, 2 pages, technical report
What Are Step-Level Reward Models Rewarding? Counterintuitive Findings from MCTS-Boosted Mathematical Reasoning
Comments AAAI 2025
Maximizing Signal in Human-Model Preference Alignment
Comments Presented at AAAI 2025, special track on AI Alignment
E4: Energy-Efficient DNN Inference for Edge Video Analytics Via Early-Exit and DVFS
Comments 9 pages, 5 figures, to be published in AAAI 2025
FloNa: Floor Plan Guided Embodied Visual Navigation
Comments Accepted by AAAI 2025
Bias Unveiled: Investigating Social Bias in LLM-Generated Code
Comments accepted for publication in the Association for the Advancement of Artificial Intelligence (AAAI), 2025
Are AI Detectors Good Enough? A Survey on Quality of Datasets With Machine-Generated Texts
Comments Presented at Preventing and Detecting LLM Misinformation (PDLM) at AAAI 2025
An Information-theoretic Multi-task Representation Learning Framework for Natural Language Understanding
Comments 11 pages, accepted to AAAI 2025 (main conference), the code is available at https://github.com/zerohd4869/InfoMTL
DM-Adapter: Domain-Aware Mixture-of-Adapters for Text-Based Person Retrieval
Comments 9 pages, 5 figures, accepted by AAAI 2025
Enhancing Vietnamese VQA through Curriculum Learning on Raw and Augmented Text Representations
Comments 10 pages, 3 figures, AAAI-25 Workshop on Document Understanding and Intelligence
