6 papers
Adaptive Test-Time Compute Allocation via Learned Heuristics over Categorical Structure
Shuhui Qu
Test-time computation has become a primary driver of progress in large language model (LLM) reasoning, but it is increasingly bottlenecked by expensive verification. In many reason…
Active Epistemic Control for Query-Efficient Verified Planning
Shuhui Qu
Planning in interactive environments is challenging under partial observability: task-critical preconditions (e.g., object locations or container states) may be unknown at decision…
VDLM: Variable Diffusion LMs via Robust Latent-to-Text Rendering
Shuhui Qu
Autoregressive language models decode left-to-right with irreversible commitments, limiting revision during multi-step reasoning. We propose \textbf{VDLM}, a modular variable diffu…
Fuzzy Categorical Planning: Autonomous Goal Satisfaction with Graded Semantic Constraints
Shuhui Qu
Natural-language planning often involves vague predicates (e.g., suitable substitute, stable enough) whose satisfaction is inherently graded. Existing category-theoretic planners p…
Teaching LLMs to Ask: Self-Querying Category-Theoretic Planning for Under-Specified Reasoning
Shuhui Qu
Inference-time planning with large language models frequently breaks under partial observability: when task-critical preconditions are not specified at query time, models tend to h…
GoMS: Graph of Molecule Substructure Network for Molecule Property Prediction
Shuhui Qu, Cheolwoo Park
While graph neural networks have shown remarkable success in molecular property prediction, current approaches like the Equivariant Subgraph Aggregation Networks (ESAN) treat molec…