Haykel Bargougui

Designed and implemented an AI agentic workflow for industrial scene understanding by integrating spatial information into LLMs. Processed and aligned 3D point cloud features with instruction-tuned LLMs using LoRA fine-tuning techniques. Tackled spatial reference resolution, question answering, and scene description to bridge 3D geometry and natural language. Trained and evaluated the system on AWS cloud infrastructure with H100 GPUs, achieving improvements in grounding accuracy and context-aware responses.

Designed and implemented an AI agentic workflow for industrial scene understanding by integrating spatial information into LLMs. Processed and aligned 3D point cloud features with instruction-tuned LLMs using LoRA fine-tuning techniques. Tackled spatial reference resolution, question answering, and scene description to bridge 3D geometry and natural language. Trained and evaluated the system on AWS cloud infrastructure with H100 GPUs, achieving improvements in grounding accuracy and context-aware responses.

Designed and implemented an AI agentic workflow for industrial scene understanding by integrating spatial information into LLMs. Processed and aligned 3D point cloud features with instruction-tuned LLMs using LoRA fine-tuning. Resolved spatial references, answered questions, and generated scene descriptions to bridge 3D geometry and natural language. Trained and evaluated on AWS with H100 GPUs, improving grounding accuracy and context-aware responses.