InnoGym: Benchmarking the Innovation Potential of AI Agents Paper • 2512.01822 • Published Dec 1, 2025 • 35
LightMem: Lightweight and Efficient Memory-Augmented Generation Paper • 2510.18866 • Published Oct 21, 2025 • 111
EPO: Entropy-regularized Policy Optimization for LLM Agents Reinforcement Learning Paper • 2509.22576 • Published Sep 26, 2025 • 134
RAG-Gym: Optimizing Reasoning and Search Agents with Process Supervision Paper • 2502.13957 • Published Feb 19, 2025 • 1
Benchmarking Retrieval-Augmented Generation for Chemistry Paper • 2505.07671 • Published May 12, 2025 • 1
Cell-o1: Training LLMs to Solve Single-Cell Reasoning Puzzles with Reinforcement Learning Paper • 2506.02911 • Published Jun 3, 2025
Knowledgeable Preference Alignment for LLMs in Domain-specific Question Answering Paper • 2311.06503 • Published Nov 11, 2023
Rethinking Uncertainly Missing and Ambiguous Visual Modality in Multi-Modal Entity Alignment Paper • 2307.16210 • Published Jul 30, 2023
Molecular Contrastive Learning with Chemical Element Knowledge Graph Paper • 2112.00544 • Published Dec 1, 2021
Knowledge Graphs Meet Multi-Modal Learning: A Comprehensive Survey Paper • 2402.05391 • Published Feb 8, 2024
Knowledge-informed Molecular Learning: A Survey on Paradigm Transfer Paper • 2202.10587 • Published Feb 17, 2022
BioT5+: Towards Generalized Biological Understanding with IUPAC Integration and Multi-task Tuning Paper • 2402.17810 • Published Feb 27, 2024 • 1
DUET: Cross-modal Semantic Grounding for Contrastive Zero-shot Learning Paper • 2207.01328 • Published Jul 4, 2022
LaKo: Knowledge-driven Visual Question Answering via Late Knowledge-to-Text Injection Paper • 2207.12888 • Published Jul 26, 2022