HeuFouFT Preprint Uses Metaheuristics for Task-Guided Fourier Fine-Tuning
arXiv preprint from 2026-10-05 introduces HeuFouFT, a framework that searches for optimal frequency coordinates in Fourier fine-tuning via metaheuristic optimizers and…
More freedom.
More control.
The developments, the evidence, and why they matter.
202 stories
arXiv preprint from 2026-10-05 introduces HeuFouFT, a framework that searches for optimal frequency coordinates in Fourier fine-tuning via metaheuristic optimizers and…
A new workshop report from Google details open challenges in building trustworthy autonomous agents using Contextual Integrity theory. The October 2025 workshop brought…
arXiv preprint presents AgentPrivArena, a framework using authentic MCP tools and self-hosted services to evaluate privacy risks during multi-step LLM agent execution, plus…
A new arXiv preprint proposes activation alignment, a lightweight linear method trained on synthetic data to map partial-context activations toward full-context behavior in…
Abstract-only arXiv preprint presents MM-KG, a layered typed graph that explicitly links harmonized EHR text, imaging, genomic and biospecimen observations to UMLS concepts and…
A new preprint introduces DNAlign, a lightweight control-theoretic method that projects safety perturbations into a harmful-related subspace, reducing harmful outputs while…
An arXiv preprint dated October 2 2026 applies Many-Facet Rasch Models to summarization ratings and finds that moderate alignment in latent summary quality does not guarantee…
arXiv preprint presents RASPER, a reinforcement-learning method that tunes an LLM summarizer using downstream prediction loss as reward. A longitudinal encoder conditions…
arXiv preprint from 2026-10-02 introduces TaSQ, a method that tailors the vector quantization target space using query-guided channel weighting, cross-head normalization and…
An arXiv preprint dated October 2 2026 outlines SoftGene a framework using ESM protein language model embeddings in a hierarchical encoder to create soft prompts combined with…
Researchers describe a two-part system that converts opaque LLM outputs into named recruiter-actionable matching dimensions. An offline LLM labeler creates data while a…
An October 2 2026 arXiv preprint demonstrates that token-level and weight-level trigger-tag mechanisms for detecting misuse such as phishing in open-weight LLMs can be rendered…