Generalization Is Stability, Not Accuracy: Multi-Axis Evaluation of LLMs
Paper • 2610.01428 • Published • 9
🔄 In a Training Loop
Joel Wang
joelhenwang
AI & ML interests
None yet
Recent Activity
upvoted a paper 1 day ago
Generalization Is Stability, Not Accuracy: Multi-Axis Evaluation of LLMs upvoted a paper 1 day ago
It Takes Workflows to Evolve Better WorkflowsOrganizations
upvoted 15
papers 1 day ago
It Takes Workflows to Evolve Better Workflows
Paper • 2610.01026 • Published • 6
Prompt2Skill: Unsupervised Skill Optimization From Natural Language Instructions
Paper • 2609.38593 • Published • 8
Personalized Image Generation with Reasoning and Reflection
Paper • 2610.00737 • Published • 7
E-MoE: Enhanced Mixture-of-Experts for Non-Factorized Diffusion Language Models
Paper • 2609.37533 • Published • 55
Pretrain Once, Route Anywhere: Towards a Foundation Model for LLM Routing
Paper • 2609.37362 • Published • 13
Smaller Models, Better Rejects: Preference Distillation Scaling
Paper • 2609.38987 • Published • 15
RPTune: Learned Context Curation for LLM Catalog Search
Paper • 2610.00964 • Published • 20
Scaling and Distilling Text Embeddings for Better Diffusibility
Paper • 2610.01016 • Published • 40
Retrieval-Augmented Skill Optimization via Cross-Harness Adaptation
Paper • 2609.38024 • Published • 45
Sharpening Tax in Post-Training
Paper • 2610.01509 • Published • 76
Hierarchical Continuous Diffusion Language Models
Paper • 2610.02193 • Published • 77
Beyond Memory: Harnessing Long-Horizon Agents with Explicit Belief States
Paper • 2610.01415 • Published • 78
AREX-2: Advancing Self-Improving Agents through Long-Horizon Reflective Tasks
Paper • 2609.38288 • Published • 128
RSIGame: Autonomous Agentic Game Development with Recursive Self-improvement
Paper • 2609.39045 • Published • 80
upvoted 5
papers 3 days ago
Rethinking Training-Inference Mismatch in LLM Reinforcement Learning: Where It Arises and How to Correct It
Paper • 2609.32444 • Published • 30
How Reproducible Are Evaluation Conclusions? A Self-Audit of LLM-Inferred Prompt Structure
Paper • 2609.30074 • Published • 2
Adaptive Consistency Graph for Long-Horizon Agents
Paper • 2609.32754 • Published • 3
Self-Play Search Distillation for Large Language Model Reasoning
Paper • 2609.30936 • Published • 4
WhiteMatter: All-to-All Cross-Layer Connections via KV Source Mixing
Paper • 2608.18486 • Published • 4