New Links | ML News

ML Newsnew | past | best | rss | submit

1381.	Automatic Pronunciation Error Detection and Correction of the Holy Quran (arxiv.org)
	2 points by handfuloflight 208 days ago \| hide \| past \| pdf \| 1 comment
1382.	Towards a Neural Debugger for Python (arxiv.org)
	1 point by E-Reverance 208 days ago \| hide \| past \| pdf \| discuss
1383.	Scalable Training of Mixture-of-Experts Models with Megatron Core (arxiv.org)
	2 points by matt_d 208 days ago \| hide \| past \| pdf \| discuss
1384.	How Well Does Agent Development Reflect Real-World Work? (arxiv.org)
	1 point by fauigerzigerk 208 days ago \| hide \| past \| pdf \| discuss
1385.	PolyBlocks: A Compiler Infrastructure for AI Chips and Programming Frameworks (arxiv.org)
	3 points by matt_d 209 days ago \| hide \| past \| pdf \| discuss
1386.	Latent Context Compilation: Distilling Long Context into Compact Portable Memory (arxiv.org)
	2 points by PaulHoule 209 days ago \| hide \| past \| pdf \| discuss
1387.	Random-Bridges as Stochastic Transports for Generative Models (arxiv.org)
	2 points by sesenai 209 days ago \| hide \| past \| pdf \| 1 comment
1388.	Can AI Agents Agree? (arxiv.org)
	1 point by tanelpoder 209 days ago \| hide \| past \| pdf \| discuss
1389.	Current Large Audio Language Models largely transcribe rather than listen (arxiv.org)
	1 point by PaulHoule 209 days ago \| hide \| past \| pdf \| discuss
1390.	AutoSkill: Experience-Driven Lifelong Learning via Skill Self-Evolution (arxiv.org)
	1 point by granoIacowboy 210 days ago \| hide \| past \| pdf \| 1 comment
1391.	Building AI Coding Agents for the Terminal (arxiv.org)
	3 points by Anon84 210 days ago \| hide \| past \| pdf \| discuss
1392.	Comprehensive Benchmarking of Agentic Systems Across 104 Real-World Challenges (arxiv.org)
	1 point by wek 210 days ago \| hide \| past \| pdf \| discuss
1393.	Real Money, Fake Models: Deceptive Model Claims in Shadow APIs (arxiv.org)
	2 points by cxplay 210 days ago \| hide \| past \| pdf \| discuss
1394.	Towards a Science of Scaling Agent Systems (arxiv.org)
	1 point by Anon84 210 days ago \| hide \| past \| pdf \| discuss
1395.	Skill-Inject: Measuring Agent Vulnerability to Skill File Attacks (arxiv.org)
	1 point by lbeurerkellner 211 days ago \| hide \| past \| pdf \| 1 comment
1396.	SWE-CI: Evaluating Agent Capabilities in Maintaining Codebases via CI (arxiv.org)
	125 points by mpweiher 211 days ago \| hide \| past \| pdf \| 41 comments
1397.	Multimodal Coding Agents as In-Context Policy Learners for Robot Manipulation (arxiv.org)
	1 point by vaishak2future 211 days ago \| hide \| past \| pdf \| 1 comment
1398.	SWE-CI: Evaluating Agent Capabilities in Maintaining Codebases via CI (arxiv.org)
	2 points by stepri 211 days ago \| hide \| past \| pdf \| discuss
1399.	Let It Flow: Agentic Crafting on Rock and Roll (arxiv.org)
	3 points by killerdhmo 211 days ago \| hide \| past \| pdf \| discuss
1400.	Agents of Chaos (arxiv.org)
	28 points by pagade 211 days ago \| hide \| past \| pdf \| 7 comments
1401.	Specialization After Generalization: Towards Understanding Test-Time Training (arxiv.org)
	1 point by teleforce 212 days ago \| hide \| past \| pdf \| discuss
1402.	MLP Memory: A Retriever-Pretrained Memory for Large Language Models (arxiv.org)
	1 point by teleforce 212 days ago \| hide \| past \| pdf \| discuss
1403.	Semi-formal reasoning helps agents reason about code without executing the code (arxiv.org)
	1 point by dnw 212 days ago \| hide \| past \| pdf \| discuss
1404.	Why Language Models Hallucinate (2025) (arxiv.org)
	2 points by doener 212 days ago \| hide \| past \| pdf \| discuss
1405.	Nested Training for Mutual Adaptation in Human-AI Teaming (arxiv.org)
	2 points by PaulHoule 212 days ago \| hide \| past \| pdf \| discuss
1406.	Cybersecurity Data Extraction from Common Crawl (arxiv.org)
	5 points by PaulHoule 212 days ago \| hide \| past \| pdf \| discuss
1407.	Artificial Hivemind: The Open-Ended Homogeneity of Language Models (and Beyond) (arxiv.org)
	2 points by mpweiher 213 days ago \| hide \| past \| pdf \| discuss
1408.	Next Embedding Prediction Makes World Models Stronger (arxiv.org)
	1 point by lucrbvi 213 days ago \| hide \| past \| pdf \| discuss
1409.	V1: Unifying Generation and Self-Verification for Parallel Reasoners (ArXiv) (arxiv.org)
	2 points by harman2607 213 days ago \| hide \| past \| pdf \| 1 comment
1410.	Beyond Language Modeling: An Exploration of Multimodal Pretraining (arxiv.org)
	1 point by gmays 213 days ago \| hide \| past \| pdf \| discuss
	More