agentic learning ai lab

research areas

learning from visual experience

Embodied AI; Self-supervised learning; Continual learning; Representation learning; Multimodal learning.

adaptive foundation models

Personalized AI; Few-shot, continual, meta learning; Memorization and forgetting; Future news forecasting.

concept learning and abstraction

Few-shot concept learning; Visual reasoning; Relational abstraction; Hierarchical abstraction and planning.

recent works

Are LLMs Prescient? A Continuous Evaluation using Daily News as Oracle

Our new benchmark, Daily Oracle, automatically generates question-answer (QA) pairs from daily news, challenging LLMs to predict “future” events based on pre-training data.

Publish Date: 2024-11-13

Learn more

PooDLe: Pooled and Dense Self-Supervised Learning from Naturalistic Videos

We propose PooDLe, a self-supervised learning method that combines an invariance-based objective on pooled representations with a dense SSL objective that enforces equivariance to optical flow warping.

Publish Date: 2024-08-20

Learn more

ProCreate, Don't Reproduce! Propulsive Energy Diffusion for Creative Generation

ProCreate is a simple and easy-to-implement method to improve sample diversity and creativity of diffusion-based image generative models and to prevent training data reproduction.

Publish Date: 2024-08-05

Learn more

Integrating Present and Past in Unsupervised Continual Learning

We formulate Osiris, a unifying framework for unsupervised continual learning (UCL), which disentangles learning objectives that encompass stability, plasticity, and cross-task consolidation.

Publish Date: 2024-04-29

Learn more

CoLLEGe: Concept Embedding Generation for Large Language Models

CoLLEGe is a meta-learning framework capable of generating flexible embeddings for new concepts using a small number of example sentences or definitions.

Publish Date: 2024-03-22

Learn more

Reawakening Knowledge: Anticipatory Recovery from Catastrophic Interference via Structured Training

We discover a curious and remarkable property of LLMs fine-tuned sequentially in this setting: they exhibit anticipatory behavior, recovering from the forgetting on documents before encountering them again.

Publish Date: 2024-03-14

Learn more

Self-Supervised Learning of Video Representations from a Child's Perspective

We train self-supervised video models on longitudinal, egocentric headcam recordings collected from a child over a two year period in their early development.

Publish Date: 2024-02-01

Learn more

Learning and Forgetting Unsafe Examples in Large Language Models

We explore the behavior of LLMs finetuned on noisy custom data containing unsafe content and propose a simple filtering algorithm for detecting harmful content based on the phenomenon of selective forgetting.

Publish Date: 2023-12-20

Learn more

LifelongMemory: Leveraging LLMs for Answering Queries in Long-form Egocentric Videos

LifelongMemory is a new framework for accessing long-form egocentric videographic memory through natural language question answering and retrieval.

Publish Date: 2023-12-07

Learn more