New Links | ML News

ML Newsnew | past | best | rss | submit

1711.	Categorizing Variants of Goodhart's Law (arxiv.org)
	1 point by foster_nyman 261 days ago \| hide \| past \| pdf \| discuss
1712.	Future-as-Label: Scalable Supervision from Real-World Outcomes (arxiv.org)
	17 points by bturtel 262 days ago \| hide \| past \| pdf \| discuss
1713.	Control Flow Integrity for Computer Use Agents (arxiv.org)
	1 point by iliaishacked 262 days ago \| hide \| past \| pdf \| 1 comment
1714.	Learning Latent Action World Models in the Wild (arxiv.org)
	1 point by saswatms 262 days ago \| hide \| past \| pdf \| discuss
1715.	Towards a Science of Scaling Agent Systems (arxiv.org)
	1 point by handfuloflight 262 days ago \| hide \| past \| pdf \| 1 comment
1716.	A benchmark for LLM vericoding: formally verified program synthesis (arxiv.org)
	2 points by cpeterso 263 days ago \| hide \| past \| pdf \| discuss
1717.	Can LLMs Express Their Uncertainty? Not Really (arxiv.org)
	2 points by apwheele 263 days ago \| hide \| past \| pdf \| discuss
1718.	How Prompt Injections Gradually Evolved into a Multi-Step Malware (arxiv.org)
	4 points by 50kIters 263 days ago \| hide \| past \| pdf \| discuss
1719.	Prompt Repetition Improves Non-Reasoning LLMs (arxiv.org)
	1 point by jsphweid 264 days ago \| hide \| past \| pdf \| discuss
1720.	Ministral 3 – pruning via Cascade Distillation (arxiv.org)
	5 points by everlier 264 days ago \| hide \| past \| pdf \| discuss
1721.	WebGym: Scaling Training Environments for Visual Web Agents with Realistic Tasks (arxiv.org)
	1 point by gmays 264 days ago \| hide \| past \| pdf \| discuss
1722.	Prompt Repetition Improves Non-Reasoning LLMs (arxiv.org)
	2 points by Anon84 264 days ago \| hide \| past \| pdf \| discuss
1723.	HiGP: A high-performance Python package for Gaussian Process (arxiv.org)
	5 points by 7777777phil 264 days ago \| hide \| past \| pdf \| discuss
1724.	Conditional Memory via Scalable Lookup (arxiv.org)
	2 points by jonbaer 265 days ago \| hide \| past \| pdf \| discuss
1725.	MacPrompt: Maraconic-Guided Jailbreak Against Text-to-Image Models (arxiv.org)
	3 points by 7777777phil 265 days ago \| hide \| past \| pdf \| discuss
1726.	Sift or Get Off the PoC: Vulnerability Research via Information Retrieval (arxiv.org)
	1 point by noperator 266 days ago \| hide \| past \| pdf \| discuss
1727.	Quantization and distillation effects on code LLMs (arxiv.org)
	1 point by nkko 266 days ago \| hide \| past \| pdf \| discuss
1728.	Show HN: Two-line change, 30% RAG boost (arxiv.org)
	1 point by snasan 266 days ago \| hide \| past \| pdf \| discuss
1729.	iOS as Acceleration (arxiv.org)
	3 points by PaulHoule 267 days ago \| hide \| past \| pdf \| discuss
1730.	Confucius Code Agent: Scalable Agent Scaffolding for Real-World Codebases (arxiv.org)
	1 point by erhuve 267 days ago \| hide \| past \| pdf \| discuss
1731.	Extracting books from production language models (2026) (arxiv.org)
	75 points by logicprog 268 days ago \| hide \| past \| pdf \| 22 comments
1732.	Extracting books from production language models (arxiv.org)
	4 points by cleandreams 268 days ago \| hide \| past \| pdf \| 2 comments
1733.	Deep sequence models tend to memorize geometrically; it is unclear why (arxiv.org)
	1 point by erhuve 268 days ago \| hide \| past \| pdf \| discuss
1734.	One pixel attack for fooling deep neural networks (arxiv.org)
	3 points by rafaepta 268 days ago \| hide \| past \| pdf \| discuss
1735.	When AI Takes the Couch: Internal Conflict in Frontier Models (arxiv.org)
	1 point by Folcon 269 days ago \| hide \| past \| pdf \| discuss
1736.	Auto-Tuning Safety Guardrails for Black-Box Large Language Models (arxiv.org)
	1 point by PaulHoule 269 days ago \| hide \| past \| pdf \| discuss
1737.	Deep Delta Learning (arxiv.org)
	1 point by mfiguiere 269 days ago \| hide \| past \| pdf \| discuss
1738.	Mind Your Tone: Investigating How Prompt Politeness Affects LLM Accuracy (arxiv.org)
	1 point by CGMthrowaway 269 days ago \| hide \| past \| pdf \| 1 comment
1739.	Challenges and Research Directions for Large Language Model Inference Hardware (arxiv.org)
	2 points by matt_d 269 days ago \| hide \| past \| pdf \| discuss
1740.	Name That Part: 3D Part Segmentation and Naming (arxiv.org)
	2 points by unisub_guy 269 days ago \| hide \| past \| pdf \| 1 comment
	More