New Links | ML News

ML Newsnew | past | best | rss | submit

1261.	The case for zero-error horizons in trustworthy LLMs (arxiv.org)
	79 points by daigoba66 185 days ago \| hide \| past \| pdf \| 116 comments
1262.	Attention Residuals (arxiv.org)
	1 point by jonbaer 186 days ago \| hide \| past \| pdf \| discuss
1263.	Neural Particle Automata: Learning Self-Organizing Particle Dynamics (arxiv.org)
	1 point by E-Reverance 186 days ago \| hide \| past \| pdf \| discuss
1264.	Sycophantic Chatbots Cause Delusional Spiraling, Even in Ideal Bayesians (arxiv.org)
	1 point by Anon84 186 days ago \| hide \| past \| pdf \| discuss
1265.	Finetuning Activates Verbatim Recall of Copyrighted Books in LLMs (arxiv.org)
	2 points by wesammikhail 186 days ago \| hide \| past \| pdf \| discuss
1266.	Adaptive Block-Scaled Data Types (arxiv.org)
	2 points by matt_d 187 days ago \| hide \| past \| pdf \| discuss
1267.	Sycophantic Chatbots Cause Delusional Spiraling, Even in Ideal Bayesians (arxiv.org)
	5 points by haltingproblem 187 days ago \| hide \| past \| pdf \| 1 comment
1268.	Rethinking Language Model Scaling Under Transferable Hypersphere Optimization (arxiv.org)
	2 points by matt_d 187 days ago \| hide \| past \| pdf \| discuss
1269.	The Last Fingerprint: How Markdown Training Shapes LLM Prose (arxiv.org)
	1 point by Er-c 187 days ago \| hide \| past \| pdf \| discuss
1270.	Geakg: Generative Executable Algorithm Knowledge Graphs (arxiv.org)
	1 point by camilochs 187 days ago \| hide \| past \| pdf \| discuss
1271.	An Alternative Trajectory for Generative AI (arxiv.org)
	1 point by Anon84 187 days ago \| hide \| past \| pdf \| discuss
1272.	Umwelt Engineering: Designing the Cognitive Worlds of Linguistic Agents (arxiv.org)
	2 points by rodspeed 187 days ago \| hide \| past \| pdf \| 3 comments
1273.	Effective Strategies for Asynchronous Software Engineering Agents (arxiv.org)
	3 points by simonpure 188 days ago \| hide \| past \| pdf \| discuss
1274.	d-HNSW: A High-Performance Vector Search Engine on Disaggregated Memory (arxiv.org)
	1 point by tanelpoder 188 days ago \| hide \| past \| pdf \| discuss
1275.	ARC-AGI-3: A New Challenge for Frontier Agentic Intelligence (arxiv.org)
	2 points by doener 188 days ago \| hide \| past \| pdf \| discuss
1276.	An Autonomous Agentic Secure Code Review for Immature Vulnerabilities Detection (arxiv.org)
	2 points by wslh 188 days ago \| hide \| past \| pdf \| discuss
1277.	An Alternative Trajectory for Generative AI (arxiv.org)
	3 points by haltingproblem 188 days ago \| hide \| past \| pdf \| discuss
1278.	Natural-Language Agent Harnesses (arxiv.org)
	2 points by Jimmc414 188 days ago \| hide \| past \| pdf \| discuss
1279.	Did You Forget What I Asked? Memory Failures in Large Language Models (arxiv.org)
	3 points by PaulHoule 188 days ago \| hide \| past \| pdf \| discuss
1280.	Galton's Law of Mediocrity: Why Large Language Models Regress to the Mean (arxiv.org)
	4 points by camillomiller 189 days ago \| hide \| past \| pdf \| discuss
1281.	PixelSmile: Toward Fine-Grained Facial Expression Editing (arxiv.org)
	1 point by ipotapov 189 days ago \| hide \| past \| pdf \| discuss
1282.	Stanford study reveals AI vision models invent images they never see (arxiv.org)
	49 points by LionTurtle13 189 days ago \| hide \| past \| pdf \| 1 comment
1283.	Subliminal learning: LLM transmit behavioral traits via hidden signals in data (arxiv.org)
	3 points by anigbrowl 189 days ago \| hide \| past \| pdf \| discuss
1284.	Security awareness in LLM agents: the NDAI zone case (arxiv.org)
	2 points by wslh 189 days ago \| hide \| past \| pdf \| discuss
1285.	LLMs Do Not Grade Essays Like Humans (arxiv.org)
	6 points by PretzelFisch 189 days ago \| hide \| past \| pdf \| 4 comments
1286.	Mirage Reasoning: The Illusion of Visual Understanding (arxiv.org)
	12 points by MrBuddyCasino 189 days ago \| hide \| past \| pdf \| 4 comments
1287.	Value Drifts: Tracing Value Alignment During LLM Post-Training (arxiv.org)
	2 points by antigrav_kids 190 days ago \| hide \| past \| pdf \| discuss
1288.	SlopCodeBench: Benchmarking How Coding Agents Degrade over Long-Horizon Tasks (arxiv.org)
	2 points by FiberBundle 191 days ago \| hide \| past \| pdf \| discuss
1289.	Security-by-Design for LLM-Based Code Generation (arxiv.org)
	2 points by abeppu 191 days ago \| hide \| past \| pdf \| 1 comment
1290.	Prompt Repetition Improves Non-Reasoning LLMs (arxiv.org)
	3 points by wslh 191 days ago \| hide \| past \| pdf \| discuss
	More