Does Learning Protein Folding Generalize to Broader Reasoning?
cs.LG, cs.AI
Submitted: 2026-09-30
Updated: 2026-09-30
Code: https://github.com/GENTEL-lab/Fold2Reason
Sources
- Structure-Aligned Protein Language Model
- SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- Talk like a Graph: Encoding Graphs for Large Language Models
- Does Math Reasoning Improve General LLM Capabilities? Understanding Transferability of LLM Reasoning
- LAB-Bench: Measuring Capabilities of Language Models for Biology Research
- Towards Next-Generation LLM Training: From the Data-Centric Perspective
- Paying Less Generalization Tax: A Cross-Domain Generalization Study of RL Training for LLM Agents
- Language Models Improve When Pretraining Data Matches Target Tasks
- Scaling Data-Constrained Language Models
- Aligning Large Language Models and Geometric Deep Models for Protein Representation
- SpatialViz-Bench: A Cognitively-Grounded Benchmark for Diagnosing Spatial Visualization in MLLMs
- InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency
- ProteinGPT: Multimodal LLM for Protein Property Prediction and Structure Understanding
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks