Beam Search as Test-Time Self-Distillation via Counterfactual Contexts
Paper • 2609.37041 • Published • 7
Gregory Kell
greg-huawei
AI & ML interests
None yet
Recent Activity
upvoted a paper about 4 hours ago
Beam Search as Test-Time Self-Distillation via Counterfactual Contexts upvoted a paper about 4 hours ago
The Weakest Link: Distilling LLM Reasoning with Worst-Case Constrained Reinforcement Learning upvoted a paper about 4 hours ago
Composable Decoding on the Probability Simplex: Theory and ImplementationOrganizations
None yet
upvoted 4
papers about 4 hours ago
The Weakest Link: Distilling LLM Reasoning with Worst-Case Constrained Reinforcement Learning
Paper • 2610.00332 • Published • 10
Composable Decoding on the Probability Simplex: Theory and Implementation
Paper • 2609.34992 • Published • 10
Does This Action Still Explain the Task? Reverse Scoring for Diffusion Language Model Agents
Paper • 2609.38536 • Published • 10
upvoted a paper 4 months ago