Searcharxiv⌕ Search

arXiv subjects

Donghyun Koh

Publications and source records attributed to Donghyun Koh.

4 recordsLinked to original sources

Structured AI ideation yields physical strategies for epithelial barrier repair

AI systems increasingly support literature analysis, candidate evaluation and hypothesis refinement, but enabling researchers to explore research directions beyond established disciplinary approaches remains challenging. We developed Abelio, an AI system designed to generate novel research directions by expanding investigators' avenues of inquiry. Abelio reformulates research objectives, uses these alternative formulations to identify relevant elements outside conventional disciplinary boundaries, and refines the resulting hypotheses. Each stage integrates divergent exploration with convergent selection through a dedicated subsystem. In quantitative evaluations, proposals generated by the Ideation Core (Abelio's hypothesis-generation core) outperformed those of four frontier large language models in scientific soundness and hypothesis diversity, and three of four in distance from existing literature. Subsystem ablation showed that each subsystem contributes to the property it targets, with the contribution of Element Selection measurable before Refinement. To investigate intestinal epithelial barrier restoration, Abelio proposed physical interventions involving membrane-tethered poly(ethylene glycol) (PEG) and cholesterol-anchored complementary DNA. Both proposals were archived before experimentation and subsequently tested independently in damaged Caco-2 monolayers. PEG preserved barrier function in a membrane-surface-dependent manner, whereas complementary DNA enabled sequence-specific restoration that was reversible on demand. These findings demonstrate how structured research ideation can identify experimentally testable approaches beyond established disciplinary conventions.

cs.AI↗

Operon: Incremental Construction of Ragged Data via Named Dimensions

Modern data processing workflows frequently encounter ragged data: multidimensional collections whose inner lengths vary and are revealed only at runtime. Ragged data is prevalent in domains throughout science and computing, yet existing workflow engines treat it as nested containers. This representation leaves shape semantics ambiguous, obscures task dependencies when upstream coordinates are not yet enumerated, and imposes coarse synchronization barriers that stall independent work across tasks. We argue that ragged data is fundamentally a flat function over a coordinate space, and that making this view explicit resolves all three difficulties at once. We realize this insight in Operon, a statically verifiable workflow engine built around a formalism of named dimensions with explicit dependency relations. Users declare pipelines in the Operon DSL by annotating data flow with dimension names, where the static checker verifies that every task does not include faulty iterations regardless of runtime lengths. At runtime, the system models in-progress arrays as partial functions over downward-closed coordinate domains, which provides a natural representation for partially-unknown data states, an exact notion of per-task indegree before all upstream coordinates are enumerated, and a sound basis for fault recovery without programmer intervention.

cs.PL↗

Risk-Calibrated Proposal Transport for Finite-Particle Diffusion Steering

Inference-time steering combines pretrained diffusion experts or rewards without retraining by changing the dynamics that transport noise to data. Feynman-Kac correction compensates for proposal mismatch through importance-weighted sequential Monte Carlo (SMC), whose finite-particle behavior depends on the proposal. Variance-controlling guidance (VCG) improves that proposal by fitting a linear drift correction to minimize empirical log-weight-rate variance. Although its population optimum cannot worsen residual variance, finite-particle VCG can nearly eliminate its fitting residual while increasing residual risk on new states by orders of magnitude. The resulting update can degrade unweighted generation or accelerate particle collapse. We show that the centered Feynman-Kac rate is the normalized transport residual and that expected out-of-fit benefit is exactly population headroom minus coefficient-estimation penalty. Under regularity assumptions, a Wasserstein analysis bounds the unweighted proposal's terminal error using this residual. These results motivate Risk-Calibrated Proposal Transport (RCPT), which uses deletion leave-one-out residuals to calibrate the retained fraction of the VCG update, adding no model calls and only small linear-algebra overhead. Experiments on 2D checker distributions, scaffold decoration, molecular property optimization, and class-conditional CIFAR-10 generation demonstrate recovery from harmful fitted updates. Across molecular and image domains, RCPT mitigates harmful fitted updates and improves a broad range of terminal metrics relative to uncalibrated VCG.

stat.ML↗

Spacer: Towards Engineered Scientific Inspiration

Recent advances in LLMs have made automated scientific research the next frontline in the path to artificial superintelligence. However, these systems are bound either to tasks of narrow scope or the limited creative capabilities of LLMs. We propose Spacer, a scientific discovery system that develops creative and factually grounded concepts without external intervention. Spacer attempts to achieve this via 'deliberate decontextualization,' an approach that disassembles information into atomic units - keywords - and draws creativity from unexplored connections between them. Spacer consists of (i) Nuri, an inspiration engine that builds keyword sets, and (ii) the Manifesting Pipeline that refines these sets into elaborate scientific statements. Nuri extracts novel, high-potential keyword sets from a keyword graph built with 180,000 academic publications in biological fields. The Manifesting Pipeline finds links between keywords, analyzes their logical structure, validates their plausibility, and ultimately drafts original scientific concepts. According to our experiments, the evaluation metric of Nuri accurately classifies high-impact publications with an AUROC score of 0.737. Our Manifesting Pipeline also successfully reconstructs core concepts from the latest top-journal articles solely from their keyword sets. An LLM-based scoring system estimates that this reconstruction was sound for over 85% of the cases. Finally, our embedding space analysis shows that outputs from Spacer are significantly more similar to leading publications compared with those from SOTA LLMs.

cs.AI↗