July 15, 2026 front

ML Newsnew | past | best | rss | submit

Stories from July 15, 2026 (UTC)

Go back a day, month, or year. Go forward a day.

1.	LLM-as-a-Verifier: A General-Purpose Verification Framework (arxiv.org)
	5 points by root-parent 81 days ago \| hide \| past \| pdf \| discuss
2.	Neural Texture Compression Using Hypernetworks (arxiv.org)
	5 points by ibobev 81 days ago \| hide \| past \| pdf \| discuss
3.	Skills That Don't Exist: A Large-Scale Study of Hallucinated Skill (arxiv.org)
	4 points by sbulaev 81 days ago \| hide \| past \| pdf \| discuss
4.	Trust but Verify? Uncovering the Security Debt of Autonomous Coding Agents (arxiv.org)
	4 points by Timofeibu 81 days ago \| hide \| past \| pdf \| discuss
5.	Detecting Prompt Injection Attacks on Purpose-Specific LLM Agents (arxiv.org)
	3 points by zhinit 81 days ago \| hide \| past \| pdf \| discuss
6.	GPU-Tile-SIM: Tile-Centric GPU Simulation for LLM Hardware-Software Co-Design (arxiv.org)
	3 points by rbanffy 81 days ago \| hide \| past \| pdf \| discuss
7.	Unsupervised Representation Learning with Deep Convolutional GANs (arxiv.org)
	3 points by ronfriedhaber 81 days ago \| hide \| past \| pdf \| discuss
8.	Remember When It Matters: Proactive Memory Agent for Long-Horizon Agents (arxiv.org)
	2 points by gmays 81 days ago \| hide \| past \| pdf \| discuss
9.	Mako: A Self-Evolving Agentic Operating System for Autonomous Web Exploitation (arxiv.org)
	2 points by praneethn 81 days ago \| hide \| past \| pdf \| discuss