AI Paper Atlas

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

CP-Agent: Context‑Aware Multimodal Reasoning for Cellular Morphological Profiling under Chemical Perturbations

Yuxin Zhang, Yiyao Li, Ping Shu Ho, Simon See, Zhenqin Wu, Kevin Kin-Man Tsia

ICLR 2026 · Large language models › Agents, code and math · approach: LLMs for scientific discovery · 0 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 CP-CLIP context-aware training instead of plain CLIPCLIP ViT-B/16 · Unseen-drug matchingaverage cosine similarity: 0.286 -> 0.432Improved
use continuous descriptor drug encoding instead of binary fingerprint (ablation)CP-CLIP ViT-B/16 · Unseen-drug matchingaverage cosine similarity: 0.360 -> 0.432Improved
scale vision encoder from ViT-B/16 to ViT-L/16 (ablation)CP-CLIP (descriptor) · Unseen-drug matchingaverage cosine similarity: 0.432 -> 0.444Improved
use sigmoid (SigLIP) objective instead of CLIP softmax contrastive loss (ablation)CP-CLIP (descriptor) · Unseen-drug matchingaverage cosine similarity: 0.432 -> 0.414Hurt
scale vision encoder from ViT-B/16 to ViT-L/16 (ablation)CP-CLIP (descriptor) · Seen-drug compound classificationmacro-avg F1: 0.896 -> 0.891No clear effect
use fingerprint instead of descriptor drug encoding (ablation)CP-CLIP ViT-B/16 · Seen-drug compound classificationmacro-avg F1: 0.896 -> 0.887No clear effect
use CP-CLIP descriptor instead of CLIP ViT-B/16CLIP · Seen-drug compound classificationmacro-avg F1: 0.657 -> 0.896Improved
use CP-CLIP instead of general MLLMs (Gemini-2.5-Pro)CP-CLIP ViT-B/16 (descriptor) · Seen-drug compound classificationmacro-avg F1: 0.007 -> 0.896Improved
use CP-CLIP ViT-B/16 (descriptor) instead of CLIPCLIP · Seen-drug similarity (averaged)cosine similarity: 0.467 -> 0.549Improved
fine-tune VISTA-2D on Cell Painting dataVISTA-2D · Instance segmentationPQ: 0.151 -> 0.682Improved
fine-tune VISTA-2D on Cell Painting dataVISTA-2D · Instance segmentationIoU: 0.272 -> 0.824Improved

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