AI.info

Emad Barsoum

Explore Emad Barsoum on AI.info.

• DiffBench Meets DiffAgent: End-to-End LLM-Driven Diffusion Acceleration Code Generation
• Training-Free Loosely Speculative Decoding: Accepting Semantically Correct Drafts Beyond Exact Match
• CaptionQA: Is Your Caption as Useful as the Image Itself?
• Training Foundation Models on a Full-Stack AMD Platform: Compute, Networking, and System Design
• Instella: Fully Open Language Models with Stellar Performance
• DRIFT: Transferring Reasoning Priors for Efficient MLLM Fine-Tuning
• XModBench: Benchmarking Cross-Modal Capabilities and Consistency in Omni-Language Models