We have 7 of 24 papers
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
This work provides a theoretically grounded condition under which a self-evolved harness can be reliably adopted and proposes a validation rule to make the evolved system satisfy the reliable adoption condition with theoretical guarantees.
This work constructs a specialized dataset to demystify the emotional circuits underlying the three-stage ``Adapt-Aggregate-Execute''mechanism and discovers a functional decoupling: visual emotional cues are aggregated in middle layers via sentiment-specific attention heads, but are subsequently translated into narrati...
EvolveNet is introduced, a paradigm of collaborative harness evolution that moves experience extraction to the data and introduces scope-typed, evidence-guided program aggregation, which improves the shared harness in all five settings.
DRNOISE, a 100-task benchmark for answer recovery under misleading evidence, is introduced, a 100-task benchmark for answer recovery under misleading evidence that requires active reconciliation of direct claims with record-level evidence.
This work establishes a new paradigm for generated image detection by recasting the detection task as a problem of machine unlearning, and introduces two detection methods: data-free detection, which prunes model parameters to induce unlearning without data access, and data-driven detection, which optimizes LVMs to unl...
It is proved that the planner's suboptimality is bounded by twice this discrepancy between the predicted and the true plan-cost at the plan the planner commits to, whereas the data-averaged prediction error neither bounds nor tracks it.
Test-Time Harness Evolution is introduced, which treats the executable harness as the state of test-time adaptation for LLM agents as evolution over executable control programs and identifies execution-derived proxy reliability as a central challenge for robust unsupervised agent improvement.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
