AI Paper Atlas

Research map / Large language models / Agents, code and math

Surgical AI Copilot: Energy-Based Fourier Gradient Low-Rank Adaptation for Surgical LLM Agent Reasoning and Planning

Jiayuan Huang, Runlong He, Danyal Zaman Khan, Evangelos B. Mazomenos, Danail Stoyanov, Hani Marcus, Linzhe Jiang, Matthew John Clarkson, Mobarak I. Hoque

AAAI 2026 · Large language models › Agents, code and math · approach: LLM-driven embodied and driving agents · 7 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use DEFT-GaLore instead of GaLoreLLaMA-3.2-3B planner · PitAgentBLEU-4 (%): 70.68 -> 71.88Improved
use DEFT-GaLore instead of GaLoreLLaMA-3.2-3B planner · PitAgentmodel selection ACC (%): 94.94 -> 96.25Improved
use DEFT-GaLore instead of GaLoreQwen-2.5-1.5B planner · PitAgentBLEU-4 (%): 47.68 -> 55.53 (text says +8.85)Mixed
use DEFT-GaLore instead of GaLoreQwen-2.5-1.5B planner · PitAgentF1 (%): 88.67 -> 95.33 (text says +12.89)Mixed
use DEFT-GaLore instead of GaLore (training time)LLaMA-3.2-3B · PitAgenttraining time per epoch (s): 8762.43 -> 3355.75Improved
use DEFT-GaLore instead of GaLore (training time)Qwen-2.5-1.5B · PitAgenttraining time per epoch (s): 2733.62 -> 1764.88Improved
use DEFT-GaLore instead of DCT-GaLoreLLaMA-3.2-3B planner · PitAgenttraining time per epoch (s): 3535.69 -> 3355.75Improved
use DEFT-GaLore instead of GaLore 2LLaMA-3.2-3B planner · PitAgentmodel selection ACC (%): 94.85 -> 96.25Improved
use GaLore-family projection instead of LoRA/DoRA/MoRALLaMA-3.2-3B planner · PitAgentBLEU-4 (%): 46.32 (DoRA) -> 70.68 (GaLore)Improved
use DEFT-GaLore rank 64 instead of 128 (ablation)DEFT-GaLore · PitAgentBLEU-4 (%): 71.88 -> 65.71Hurt
use DEFT-GaLore rank 256 instead of 128 (ablation)DEFT-GaLore · PitAgentBLEU-4 (%): 71.88 -> 69.04Hurt
use DEFT-GaLore prompts instead of GaLore prompts for downstream VQAPitVQA++ Worker · PitVQABLEU-4 (%): 67.31 -> 70.73Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy