Breaking Bad Molecules: Are MLLMs Ready for Structure-Level Molecular Detoxification?
Paper ā¢ 2506.10912 ā¢ Published
HydroSophy
non-profit
AI & ML interests
AI for Science, Molecular Modeling, Large Language Models, Multimodal Learning, Dataset Benchmarking, Drug Design, and Structural Biology.
Recent Activity
View all activity
CusyoungĀ
authored 11
papers 24 days ago
Robotic Visual Instruction
Paper ā¢ 2505.00693 ā¢ Published ā¢ 1
MM-CRITIC: A Holistic Evaluation of Large Multimodal Models as Multimodal Critique
Paper ā¢ 2511.09067 ā¢ Published ā¢ 2
Interleave-VLA: Enhancing Robot Manipulation with Interleaved Image-Text Instructions
Paper ā¢ 2505.02152 ā¢ Published
IGen: Scalable Data Generation for Robot Learning from Open-World Images
Paper ā¢ 2512.01773 ā¢ Published ā¢ 1
ACE-Brain-0: Spatial Intelligence as a Shared Scaffold for Universal Embodiments
Paper ā¢ 2603.03198 ā¢ Published ā¢ 4
Out of the Memory Barrier: A Highly Memory Efficient Training System for LLMs with Million-Token Contexts
Paper ā¢ 2602.02108 ā¢ Published
SpaceDG: Benchmarking Spatial Intelligence under Visual Degradation
Paper ā¢ 2605.22536 ā¢ Published ā¢ 28
ToxiEval-ZKP: A Structure-Private Verification Framework for Molecular Toxicity Repair Tasks
Paper ā¢ 2508.12035 ā¢ Published
SkillOpt: Executive Strategy for Self-Evolving Agent Skills
Paper ā¢ 2605.23904 ā¢ Published ā¢ 236
From Raw Experience to Skill Consumption: A Systematic Study of Model-Generated Agent Skills
Paper ā¢ 2605.23899 ā¢ Published ā¢ 29
feilin-mustĀ
updated a
Space 25 days ago
feilin-mustĀ
updated a
dataset about 1 month ago
CusyoungĀ
published a
dataset about 1 year ago
CusyoungĀ
updated a
dataset about 1 year ago
CusyoungĀ
authored 5
papers about 1 year ago
CoDA: Instructive Chain-of-Domain Adaptation with Severity-Aware Visual Prompt Tuning
Paper ā¢ 2403.17369 ā¢ Published ā¢ 2
Can Generative Geospatial Diffusion Models Excel as Discriminative Geospatial Foundation Models?
Paper ā¢ 2503.07890 ā¢ Published ā¢ 2
Earth-Adapter: Bridge the Geospatial Domain Gaps with Mixture of Frequency Adaptation
Paper ā¢ 2504.06220 ā¢ Published ā¢ 1
SpaCE-10: A Comprehensive Benchmark for Multimodal Large Language Models in Compositional Spatial Intelligence
Paper ā¢ 2506.07966 ā¢ Published ā¢ 1
Visual Embodied Brain: Let Multimodal Large Language Models See, Think, and Control in Spaces
Paper ā¢ 2506.00123 ā¢ Published ā¢ 35