Deep Cognition and Language Research Lab

Research across Six Themes in AI

DeCLaRe is a research group at NTU working across Safety, Trustworthiness, Multimodality, AI for Science, Efficiency, and Embodied AI. Recent notable work includes online memory for LLMs, dynamic data selection for efficient ML training, vision-language-action models, text-to-audio generation, trustworthy RAG, and operational AI safety.

About DeCLaRe

DeCLaRe, short for Deep Cognition and Language Research, was founded by Soujanya Poria at the Singapore University of Technology and Design in 2019 with Navonil Majumder, Devamanyu Hazarika, and Deepanway Ghosal. The lab moved to Nanyang Technological University in 2025.

Lab's identity

The robot recalls early computing while forming 宣 (xuān), “to declare”: an intelligent social agent connecting computing’s history with collaborative AI.

Visual explanation of the DeCLaRe Lab identity Visual explanation of the DeCLaRe Lab identity

Hot Papers 🔥

Publication archive
arXiv 2026

δ-mem: Efficient Online Memory for Large Language Models

A compact online state gives language models working memory without extending the visible context.

ICLR 2026

OffTopicEval: When Large Language Models Enter the Wrong Chat, Almost Always!

An operational-safety benchmark for whether task-specific agents respect their intended boundaries.

ICML 2026

Data Agent: Learning to Select Data via End-to-End Dynamic Optimization

A training-aware policy selects useful data as the target model evolves.

ICLR 2025

Measuring and Enhancing Trustworthiness of LLMs in RAG

Trust-Score and Trust-Align evaluate and improve grounded attribution, citations, and refusal.

Funded Research Directions

Active and completed research support.