New Links | ML News

ML Newsnew | past | best | rss | submit

151.	Neuro-Formal Verification: Agentic Language-Agnostic Formal Program Reasoning (arxiv.org)
	3 points by matt_d 18 days ago \| hide \| past \| pdf \| discuss
152.	Dart: Denoising Autoregressive Transformer (arxiv.org)
	1 point by E-Reverance 18 days ago \| hide \| past \| pdf \| discuss
153.	StepAudio 3 Gen Technical Report (arxiv.org)
	2 points by gmays 18 days ago \| hide \| past \| pdf \| discuss
154.	GRP-Obliteration: Unaligning LLMs with a Single Unlabeled Prompt (arxiv.org)
	24 points by vital101 18 days ago \| hide \| past \| pdf \| 9 comments
155.	Breaking the Token Ceiling (arxiv.org)
	2 points by sonabinu 18 days ago \| hide \| past \| pdf \| discuss
156.	The Misery of Mechanistic Interpretability: A Formal Perspective (arxiv.org)
	1 point by sbulaev 18 days ago \| hide \| past \| pdf \| discuss
157.	Can Theoretical Physics Research Benefit from Language Agents? (arxiv.org)
	3 points by num42 18 days ago \| hide \| past \| pdf \| discuss
158.	KnowBench: Evaluating clinical AI with effort reduction (arxiv.org)
	5 points by kangjl888 18 days ago \| hide \| past \| pdf \| 2 comments
159.	Shuffling Is Not Enough: Breaking Permutation-Based Model Confidentiality (arxiv.org)
	1 point by sbulaev 19 days ago \| hide \| past \| pdf \| discuss
160.	Discrete Beckmann Transport Models for One-Step Language Modeling and Reasoning (arxiv.org)
	1 point by E-Reverance 19 days ago \| hide \| past \| pdf \| discuss
161.	RoofLang: Enabling AI-Driven Architecting of LLM Inference Systems (arxiv.org)
	7 points by matt_d 19 days ago \| hide \| past \| pdf \| discuss
162.	Co-Evolving Harnesses and Models (arxiv.org)
	3 points by gmays 19 days ago \| hide \| past \| pdf \| discuss
163.	Can AI agents conduct open-ended AI research? (arxiv.org)
	3 points by Betelbuddy 19 days ago \| hide \| past \| pdf \| discuss
164.	NCP-ArchPreview: 8.9B latent LM matches OLMo-3-7B on 51% of tokens (arxiv.org)
	2 points by iamsyr 19 days ago \| hide \| past \| pdf \| discuss
165.	Intelligence per Watt: Measuring Intelligence Efficiency of Local AI (arxiv.org)
	169 points by pythonic_hell 19 days ago \| hide \| past \| pdf \| 65 comments
166.	The Last AI Built by Humans: Toward Genuine Recursive Self-Improvement (arxiv.org)
	2 points by jonbaer 19 days ago \| hide \| past \| pdf \| discuss
167.	How Good Are Frontier Models at Physics? Expert Re-Grading Reveals Broken (arxiv.org)
	4 points by sbulaev 19 days ago \| hide \| past \| pdf \| discuss
168.	Meta$^N$: Recursive Self-Improvement Through Emergent Depth (arxiv.org)
	10 points by Anon84 20 days ago \| hide \| past \| pdf \| 2 comments
169.	The Last AI Built by Humans: Toward Genuine Recursive Self-Improvement (arxiv.org)
	3 points by pella 20 days ago \| hide \| past \| pdf \| discuss
170.	Solve the Loop: Attractor Models for Language and Reasoning (arxiv.org)
	2 points by jerlendds 20 days ago \| hide \| past \| pdf \| 1 comment
171.	MOBA: Mixture of Block Attention for Long-Context LLMs (arxiv.org)
	2 points by ur-whale 20 days ago \| hide \| past \| pdf \| discuss
172.	Signing the Transaction but Not the Decision: Whisper Attacks and a Binding (arxiv.org)
	1 point by sbulaev 20 days ago \| hide \| past \| pdf \| discuss
173.	Neural Turing Machines (2014) (arxiv.org)
	4 points by peter_d_sherman 20 days ago \| hide \| past \| pdf \| discuss
174.	The Last AI Built by Humans: Toward Genuine Recursive Self-Improvement (arxiv.org)
	2 points by mlmonkey 21 days ago \| hide \| past \| pdf \| 2 comments
175.	Datasets for Large Language Models: A Comprehensive Survey (arxiv.org)
	2 points by Anon84 21 days ago \| hide \| past \| pdf \| discuss
176.	Domain-Specific Hallucination Detection in Large Language Models (arxiv.org)
	2 points by Betelbuddy 21 days ago \| hide \| past \| pdf \| 1 comment
177.	From Neural Networks to Logical Theories (arxiv.org)
	2 points by measurablefunc 21 days ago \| hide \| past \| pdf \| discuss
178.	CascadeLUT: Info.-Ordered Streaming Inference for Bandwidth-Constrained FPGAs (arxiv.org)
	1 point by matt_d 22 days ago \| hide \| past \| pdf \| discuss
179.	Beyond Solver Verdicts: Generative Reward Models for Autoformalizations (arxiv.org)
	2 points by vikashjohn2505 22 days ago \| hide \| past \| pdf \| discuss
180.	You Only Cache Once: Decoder-Decoder Architectures for Language Models (2024) (arxiv.org)
	1 point by theanonymousone 22 days ago \| hide \| past \| pdf \| discuss
	More