LATEST FROM AAIG
News
SAIL paper accepted to Interspeech 2026
A SAIL paper was accepted to Interspeech 2026 as an oral presentation.
SAIL paper accepted to ICML 2026
SAIL announced the acceptance of a paper to ICML 2026.
SAIL paper accepted to Findings of ACL 2026
SAIL announced the acceptance of a paper to Findings of ACL 2026.
Colla-Q: Toward Collaborative Experts in MoE Quantization via Minimax Precision Balancing
EMNLP 2026 publication from MMAI Lab.
Layer-wise Curriculum Learning for Efficient LLM Compression
EMNLP 2026 publication from MMAI Lab.
Re-calibrated Contrastive Loss for Transformation-Aware Prompt Conditioning in Vision-Language Models
BMVC 2026 publication from MMAI Lab.
Train Overcomplete, Deploy Compact: Scaling Recovery Capacity for Structured LLM Pruning
EMNLP 2026 publication from MMAI Lab.
Disentangling Spurious Correlations in Vision-Language-Action Models via Predicting Domain-Invariant Latent Lookahead
Predicting domain-invariant latent lookahead to separate spurious correlations in vision-language-action models.
Swipe to browse
AAIG research output
Publication Summary 2026
A quick view of regular conference papers currently listed in the AAIG archive.
View all publications ↗14papers
- EMNLP6
- ICML2
- ACL1
- BMVC1
- CoRL1
- ECCV1
- ICDM1
- Interspeech1
EMNLP 2026
Colla-Q: Toward Collaborative Experts in MoE Quantization via Minimax Precision Balancing
EMNLP 2026
Layer-wise Curriculum Learning for Efficient LLM Compression
BMVC 2026
Re-calibrated Contrastive Loss for Transformation-Aware Prompt Conditioning in Vision-Language Models
EMNLP 2026
Train Overcomplete, Deploy Compact: Scaling Recovery Capacity for Structured LLM Pruning
CoRL 2026
Disentangling Spurious Correlations in Vision-Language-Action Models via Predicting Domain-Invariant Latent Lookahead
RSS Workshop 2026
MicroVLA: Edge-Deployable Vision Language Action at 10M Parameters
CVPR Workshop 2026
Can Embodied Agents Remember What You Said? Evaluating Dialogue-Grounded Embodied Memory in 3D Environments
ECCV 2026
Learning Sample-wise Rank-Aware Interpolation Weights for Composed Visual Data Retrieval
Swipe to browse
Research Areas
- MMAI Lab
- iKnow Lab
- LAMDA Lab
Vision & Perception
Reliable visual understanding, representation learning, and perception across real-world environments.
- MMAI Lab
- SAIL
- iKnow Lab
- LAMDA Lab
Multimodal Understanding
Methods that connect visual, audio, language, and structured information to reason across modalities.
- MMAI Lab
- HEI Lab
- iKnow Lab
- LAMDA Lab
Learning Systems & Foundation Models
Efficient, scalable, and generalizable learning systems for language, vision, and physical intelligence.
- SAIL
- iKnow Lab
Speech & Language AI
Speech synthesis, spoken-language modeling, translation, and knowledge-aware language intelligence.
- MMAI Lab
- SAIL
Generative AI
Generative methods for audio, video, visual content, and interactive multimodal media.
- MMAI Lab
- HEI Lab
Embodied Intelligence & Robot Learning
Vision-language-action learning and adaptable robot skills for interaction in the physical world.
- SAIL
- HEI Lab
- iKnow Lab
Human-Centered AI
Human-aware systems that collaborate, communicate, and adapt to people in practical settings.
- iKnow Lab
- LAMDA Lab
Knowledge, Recommendation & Personalization
Personalized and knowledge-centered intelligence for recommendation, retrieval, and assistance.
- MMAI Lab
- HEI Lab
- LAMDA Lab
Applied AI for Industry & Health
Robust AI methods for industrial inspection, biomedical data, and dependable real-world deployment.
- LAMDA Lab
- MMAI Lab
- iKnow Lab
Data-Centric & Trustworthy AI
Explainable, robust, and efficient learning for heterogeneous data in biomedical, social, and practical settings.Swipe to browse