…From Open-World Threats to Safer Computer-Use Agents Published on Jun 2 Submitted by YunHao-Feng on Jun 4 Ant Group Authors: , , , , , , , , , , , , , , , Abstract BraveGuard is a self-evolving defense framework that…
…Toward a Self-Governing Epistemic Singularity Abstract This proposal outlines Apex Veritas Meta, an architecture that shifts the locus of AI singularity from raw computational power to epistemic autonomy. We combine quantum…
…In a controlled Cityscapes experiment, Uniform Phase Marginalization provides a modest compute-matched advantage over generic shift-based four-forward test-time augmentation (TTA) (+0.31 mean Intersection-over-Union over the…
Papers arxiv:2606.06735 A Geometric Account of Activation Steering through Angle-Norm Decomposition Published on Jun 4 Submitted by Georgii Aparin on Jun 9 HUAWEI Noah's Ark Lab Authors: Georgii…
…An Interaction-Native Knowledge Harness for Financial LLM Agents Published on Jun 1 Submitted by Sofia on Jun 5 INC4 Authors: , , , , , Sofiia Pidturkina , Abstract Financial AI agents struggle with user complexity, but…
Papers arxiv:2605.00623 Recovering Hidden Reward in Diffusion-Based Policies Published on May 1 Submitted by Yanbiao Ji on May 8 Authors: Yanbiao Ji , , , , , , , , , Abstract EnergyFlow unifies generative action modeling with…
Papers arxiv:2605.07825 Anisotropic Modality Align Published on May 8 Submitted by Yu_xm on May 11 Authors: Xiaomin Yu , , , , , , , , , , Abstract Research addresses the modality gap in multimodal models by proposing…
…A Self-Evolving Framework for Automated Machine Learning Algorithm Discovery Published on Jun 4 Submitted by taesiri on Jun 5 Authors: , , , , Shiyang Feng , , , , , , , , , Abstract MLEvolve is an LLM-based multi-agent framework…
Papers arxiv:2606.07867 The Cold-Start Safety Gap in LLM Agents Published on Jun 5 Submitted by Chung-En, Sun on Jun 12 Authors: Chung-En Sun , , Abstract Tool-calling language…
…Impact of Model-Internalized Priors on Annotation Task Performance Published on May 30 Submitted by Rafal Kocielnik on Jun 12 California institute of technology Authors: , Rafal Kocielnik , Abstract Large language models exhibit…
To show you the most relevant results, we’ve omitted some entries very similar to those already shown. Repeat the search with the omitted results included.