New Links | ML News

ML Newsnew | past | best | rss | submit

1651.	DeepMind: Linear representations in LMs can change dramatically (arxiv.org)
	1 point by simonpure 248 days ago \| hide \| past \| pdf \| discuss
1652.	VulnLLM-R: Specialized Reasoning LLM with Agent Scaffold for Vuln Detection (arxiv.org)
	1 point by gquere 248 days ago \| hide \| past \| pdf \| 1 comment
1653.	ProToken: Token-Level Attribution for Federated Large Language Models (arxiv.org)
	2 points by onurkanbkrc 248 days ago \| hide \| past \| pdf \| discuss
1654.	One-step pixel space image generation (arxiv.org)
	2 points by E-Reverance 248 days ago \| hide \| past \| pdf \| discuss
1655.	Masked Depth Modeling for Spatial Perception (arxiv.org)
	2 points by mountainview 248 days ago \| hide \| past \| pdf \| discuss
1656.	Benchmarking Reward Hack Detection in Code Environments via Contrastive Analysis (arxiv.org)
	1 point by darshandesh1504 249 days ago \| hide \| past \| pdf \| 1 comment
1657.	Verge: Formal Refinement and Guidance Engine for Verifiable LLM Reasoning (arxiv.org)
	2 points by vikashjohn2505 249 days ago \| hide \| past \| pdf \| 2 comments
1658.	Anthropic: Who's in Charge? Disempowerment Patterns in Real-World LLM Usage (arxiv.org)
	2 points by remexre 249 days ago \| hide \| past \| pdf \| 1 comment
1659.	Where Do AI Coding Agents Fail? (arxiv.org)
	2 points by kioku 249 days ago \| hide \| past \| pdf \| 3 comments
1660.	A Decoder-Based Framework for 3D-Printable Object Synthesis (arxiv.org)
	1 point by PaulHoule 249 days ago \| hide \| past \| pdf \| discuss
1661.	The Shape of Reasoning: Topological Analysis of Large Language Models (arxiv.org)
	3 points by oldfuture 249 days ago \| hide \| past \| pdf \| discuss
1662.	Show HN: If You Want Coherence, Orchestrate a Team of Rivals: Multi-Agent " (arxiv.org)
	10 points by gopalv 250 days ago \| hide \| past \| pdf \| discuss
1663.	Attention Is Not What You Need (arxiv.org)
	3 points by hnmouse 250 days ago \| hide \| past \| pdf \| 2 comments
1664.	Lightweight Transformer Architectures for Edge Devices in Real-Time Applications (arxiv.org)
	2 points by PaulHoule 250 days ago \| hide \| past \| pdf \| discuss
1665.	Attention Is Not What You Need (arxiv.org)
	4 points by bilsbie 250 days ago \| hide \| past \| pdf \| discuss
1666.	Gaming the Answer Matcher: Text Manipulation vs. Automated Judgment (arxiv.org)
	1 point by PaulHoule 251 days ago \| hide \| past \| pdf \| discuss
1667.	Hallucination Stations: On Some Basic Limitations of Transformer-Based Language (arxiv.org)
	2 points by todsacerdoti 251 days ago \| hide \| past \| pdf \| 1 comment
1668.	Agent Skills in the Wild an Empirical Study of Security Vulnerabilities at Scale (arxiv.org)
	1 point by knoxa2511 252 days ago \| hide \| past \| pdf \| discuss
1669.	TTT-Discover, Learning to Discover at Test Time (arxiv.org)
	2 points by vinhnx 252 days ago \| hide \| past \| pdf \| 1 comment
1670.	Some Basic Limitations of Transformer-Based Language Models (arxiv.org)
	1 point by RansomStark 252 days ago \| hide \| past \| pdf \| discuss
1671.	Can AI Predict Stories? Learning to Reason for Long-Form Story Generation (arxiv.org)
	3 points by kjellsbells 253 days ago \| hide \| past \| pdf \| discuss
1672.	Apex-Agents – Benchmark Productivity of Agents (arxiv.org)
	1 point by hereme888 253 days ago \| hide \| past \| pdf \| discuss
1673.	Challenges and Research Directions for Large Language Model Inference Hardware (arxiv.org)
	123 points by transpute 253 days ago \| hide \| past \| pdf \| 23 comments
1674.	Agentic Reasoning for Large Language Models (arxiv.org)
	1 point by simonpure 254 days ago \| hide \| past \| pdf \| discuss
1675.	Hallucination Stations: Limitations of Transformer-Based Language Models (2025) (arxiv.org)
	1 point by cainxinth 254 days ago \| hide \| past \| pdf \| discuss
1676.	Forgotten Polygons: Multimodal Large Language Models Are Shape-Blind (arxiv.org)
	2 points by chbint 254 days ago \| hide \| past \| pdf \| discuss
1677.	GPT OSS Beat Humans in TriMul Competition via TTT (arxiv.org)
	2 points by demirbey05 254 days ago \| hide \| past \| pdf \| discuss
1678.	AI agent generates rebuttals for papers (arxiv.org)
	1 point by meander_water 254 days ago \| hide \| past \| pdf \| discuss
1679.	The unreasonable effectiveness of pattern matching (arxiv.org)
	2 points by georgecmu 255 days ago \| hide \| past \| pdf \| discuss
1680.	Agentic Reasoning for Large Language Models (arxiv.org)
	1 point by Anon84 255 days ago \| hide \| past \| pdf \| 1 comment
	More