arxiv:2408.01415
Xiaolong J PRO
Bruce-Jin
AI & ML interests
AI security
Recent Activity
upvoted a paper about 3 hours ago
StateM: Reaching 95.3% Raw Accuracy, or a \$15 Frontier Run, on Terminal-Bench 2.1 via Harness Scaling updated a model about 2 months ago
Bruce-Jin/swe-rl-trajectory_entropy updated a model about 2 months ago
Bruce-Jin/swe-rl-token_entropyOrganizations
models 30
Bruce-Jin/swe-rl-random-grpo-random
Updated
Bruce-Jin/swe-rl-token_entropy
Updated
Bruce-Jin/swe-rl-intuitor
Updated
Bruce-Jin/swe-rl-prob_disparity
Updated
Bruce-Jin/swe-rl-grpo
Updated
Bruce-Jin/swe-rl-trajectory_entropy
Updated
Bruce-Jin/swe-rl-trajectory_entropy-kl
Updated
Bruce-Jin/r1-1.5b-8k-random-grpo-random
Updated
Bruce-Jin/swe-rl-intuitor-kl
Updated
Bruce-Jin/swe-rl-prob_disparity-kl
Updated
datasets 6
Bruce-Jin/BigCodeArena-with-screenshots
Viewer • Updated • 4.73k • 20
Bruce-Jin/judge-results-dataset
Viewer • Updated • 141k • 108
Bruce-Jin/BigCodeArena
Viewer • Updated • 4.73k • 32
Bruce-Jin/BigCodeArena-raw
Viewer • Updated • 14.1k • 27
Bruce-Jin/swe-dataset-dedup
Viewer • Updated • 4.88k • 31
Bruce-Jin/Code-Arena
Updated • 26