WebWorld Collection The browser as a world model for self-improving web code: certificate-verified SFT data, evaluator and models to follow. • 1 item • Updated 29 days ago
AutoMemoryBench Collection State-contract evaluation for auditable agent memory. • 1 item • Updated Aug 20
MIRA: Mid-training Rubric Anchoring for Source-Aware Data Selection Paper • 2605.30288 • Published May 29 • 22
LoopCoder-v2: Only Loop Once for Efficient Test-Time Computation Scaling Paper • 2606.18023 • Published Jun 16 • 161
LoopCoder-v2: Only Loop Once for Efficient Test-Time Computation Scaling Paper • 2606.18023 • Published Jun 16 • 161
Grammar-Constrained Decoding Can Jailbreak LLMs into Generating Malicious Code Paper • 2606.11817 • Published Jun 10 • 18
InCoder-32B-Thinking: Industrial Code World Model for Thinking Paper • 2604.03144 • Published Apr 3 • 143
InCoder-32B-Thinking: Industrial Code World Model for Thinking Paper • 2604.03144 • Published Apr 3 • 143
InCoder-32B: Code Foundation Model for Industrial Scenarios Paper • 2603.16790 • Published Mar 17 • 189
InCoder-32B: Code Foundation Model for Industrial Scenarios Paper • 2603.16790 • Published Mar 17 • 189