SkillTFM: Gated Skill Evolution for Training-Free Adaptation of Tabular Foundation Models
Yi He, Zhengkang Guan, Anpeng Wu, Peng Cui, Fei Wu, Kun Kuang
cs.LG
Submitted: 2026-08-06
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
- A Gentle Introduction to Conformal Prediction and Distribution-Free Uncertainty Quantification
- DAG-FM: A Foundation Model for Causal Discovery under Heterogeneous Causal Mechanisms
- Real-TabPFN: Improving Tabular Foundation Models via Continued Pre-training With Real-World Data
- TabPFN-2.5: Advancing the State of the Art in Tabular Foundation Models
- DCD-PFN: A Decoupling-Aware Foundation Model for Causal Discovery
- A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks
- TabPFN: A Transformer That Solves Small Tabular Classification Problems in a Second
- SoK: Agentic Skills -- Beyond Tool Use in LLM Agents
- DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines
- CARTE: Pretraining and Transfer for Tabular Learning
- SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks
- Agent Skills: A Data-Driven Analysis of Claude Skills for Extending Large Language Model Functionality
- TabDPT: Scaling Tabular Foundation Models on Real Data
- Transformers Can Do Bayesian Inference
- MotherNet: Fast Training and Inference via Hyper-Network Transformers
- SkillOS: Learning Skill Curation for Self-Evolving Agents
- TabICL: A Tabular Foundation Model for In-Context Learning on Large Data
- Toolformer: Language Models Can Teach Themselves to Use Tools
- SKILLFOUNDRY: Building Self-Evolving Agent Skill Libraries from Heterogeneous Scientific Resources
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