Thinking in a Low-Resource Language: What SFT Builds, What RL Fixes, What Accuracy Cannot See
Paper • 2608.17744 • Published • 13
Matthew Lewis
Matthew-Lewis
AI & ML interests
None yet
Recent Activity
upvoted a paper about 18 hours ago
Thinking in a Low-Resource Language: What SFT Builds, What RL Fixes, What Accuracy Cannot See upvoted a paper 3 days ago
FM-Bench: A Benchmark for Long-Horizon Management with Competing Agents upvoted a paper 6 days ago
Alaya-EVOKE: From Linear-Scaling Supervision to Endless WorldOrganizations
None yet