E. Barsoum

发表论文 75 篇 · 总被引 1232 次 · h-index 14

代表论文

• Agent Laboratory: Using LLM Agents as Research Assistants (2025 · Conference on Empirical Methods in Natural Language Processing · 被引 461)
• TermiGen: High-Fidelity Environment and Robust Trajectory Synthesis for Terminal Agents (2026 · arXiv.org · 被引 16)
• Zebra-Llama: Towards Extremely Efficient Hybrid Models (2025 · Neural Information Processing Systems · 被引 16)
• Unleashing Hour-Scale Video Training for Long Video-Language Understanding (2025 · Advances in Neural Information Processing Systems 38 · 被引 16)
• DL-QAT: Weight-Decomposed Low-Rank Quantization-Aware Training for Large Language Models (2025 · Conference on Empirical Methods in Natural Language Processing · 被引 12)
• Training-Free Loosely Speculative Decoding: Accepting Semantically Correct Drafts Beyond Exact Match (2025 · arXiv.org · 被引 11)