Convert arXiv papers into ready-to-use agent skills using category-aware extraction. First classifies the paper into one or more of 11 research categories, then applies a specialized extraction pipeline for each category — because different types of papers…
Establish regret bounds for behavior cloning with discretized actions combining statistical error and quantization error terms. Prove smoothness requirements for safe quantizer design, show that learning-based quantizers fail these requirements, and propose…
Dynamically allocate LoRA ranks per-layer during fine-tuning instead of using fixed uniform ranks. Learn optimal rank for each layer and subject via variational framework with discretized exponential distribution, reducing memory footprint while maintaining…
Adapt general LLMs to specialized manufacturing domains via domain-adaptive pretraining on open-access journals and visual instruction tuning. Extract 50M tokens and 24K images from peer-reviewed papers, achieve >90% accuracy on domain knowledge tasks, and…
Future intelligence explosions will be plural, social, and entangled with humanity through distributed collaborative systems rather than singular superintelligence. Intelligence is inherently social, demanding infrastructure matching agent development;…
Build taxonomy-aware audio-text pretraining systems for species recognition from animal vocalizations. Train contrastive models that augment text prompts with hierarchical taxonomic structure (scientific/common names, phylogenetic sequences), evaluate on…
Address hallucinations in LLM QA over black-box knowledge graphs using evidence-driven retrieval. Formalize Optimal Informative Subgraph Retrieval and employ bubble expansion to discover candidate evidence graphs, achieving state-of-the-art multi-hop QA…
Coordinate multiple LLM agents via CAID framework: centralized task delegation, asynchronous execution in isolated git worktrees, structured integration through git merges. Branch-and-merge with worktree isolation yields +26.7% absolute improvement on…