We have 7 of 14 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.
Constrained-option scoring reads a model's probabilities for a fixed set of permitted answers, so it returns a score even when the model is about to write something else. We study a prompt that quotes a multiple-choice item, ending in the item's own answer instruction, and asks for a forecast of whether a reader model...
An agentic search framework for geoscience data discovery that takes a natural-language research query and returns matching datasets and tools and demonstrates that, in the era of large language models, the latent value of knowledge graphs can be substantially amplified through agentic search.
Staged Depth Training (SDT), which trains a shallow prefix under a temporary physics-informed head, discards the head, and freezes the learned prefix while adding depth, supports representation curriculum as a promising training strategy for improving PINNs while preserving the deployed architecture and inference cost.
To the knowledge, AgonAlpha is the first alpha-mining system to combine verified artifact search, a fresh-context adversarial reviewer with re-execution and veto authority, and pending-aware parallel budget allocation, together with a complete public evidence trail.
This work provides an open measurement framework deployable on any model exposing block identities, and introduces a dense-calibrated counterfactual audit using matched probe cards to isolate the sparsification-specific effect.
Automatic Symbolic Regression (AutoSR), a fully automated system that instantiates Research-Space Symbolic Regression by searching persistent scientific investigations by searching persistent scientific investigations rather than isolated equations, is introduced.
A three-role Monte Carlo Tree Search (MCTS) framework that treats the Lean 4 compiler purely as a reward oracle using compiler output as a scalar signal for UCB-guided tree updates without feeding error content into the generation context is proposed.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
