New Links | ML News

ML Newsnew | past | best | rss | submit

1771.	Multivariate Information Bottleneck – A Framework for Variational Losses (arxiv.org)
	2 points by QueensGambit 273 days ago \| hide \| past \| pdf \| discuss
1772.	Evolution Without an Oracle: Driving Effective Evolution with LLM Judges (arxiv.org)
	2 points by PaulHoule 273 days ago \| hide \| past \| pdf \| discuss
1773.	Beyond Language Models: Byte Models Are Digital World Simulators (2024) (arxiv.org)
	1 point by optimalsolver 273 days ago \| hide \| past \| pdf \| discuss
1774.	KGGen: Extracting Knowledge Graphs from Plain Text with Language Models (arxiv.org)
	20 points by delichon 274 days ago \| hide \| past \| pdf \| 4 comments
1775.	Dynamic Large Concept Models: Latent Reasoning in an Adaptive Semantic Space (arxiv.org)
	2 points by ferriswil 274 days ago \| hide \| past \| pdf \| discuss
1776.	What Drives Success in Physical Planning with JEPA World Models? (arxiv.org)
	4 points by johnsutor 274 days ago \| hide \| past \| pdf \| discuss
1777.	Scaling Latent Reasoning via Looped Language Models (arxiv.org)
	84 points by remexre 275 days ago \| hide \| past \| pdf \| 15 comments
1778.	FakeParts: A New Family of AI-Generated DeepFakes (arxiv.org)
	1 point by ColinWright 275 days ago \| hide \| past \| pdf \| discuss
1779.	Attention Is Not What You Need (arxiv.org)
	3 points by shikhr 275 days ago \| hide \| past \| pdf \| discuss
1780.	Recursive Language Models (arxiv.org)
	161 points by schmuhblaster 275 days ago \| hide \| past \| pdf \| 23 comments
1781.	The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks (2018) (arxiv.org)
	121 points by felineflock 276 days ago \| hide \| past \| pdf \| 27 comments
1782.	MHC: Manifold-Constrained Hyper-Connections (arxiv.org)
	1 point by sonabinu 276 days ago \| hide \| past \| pdf \| discuss
1783.	Acoustic Side Channel Attack on Keyboards (2023) (arxiv.org)
	4 points by perceptronas 276 days ago \| hide \| past \| pdf \| discuss
1784.	Online Planning Method Integrating LLMs into Nested Rollout Policy Adaptation (arxiv.org)
	2 points by PaulHoule 276 days ago \| hide \| past \| pdf \| discuss
1785.	Firmhive: LLMs as Firmware Experts, a Runtime-Grown Tree-of-Agents Framework (arxiv.org)
	2 points by transpute 276 days ago \| hide \| past \| pdf \| discuss
1786.	Measuring Agents in Production (arxiv.org)
	3 points by sonabinu 276 days ago \| hide \| past \| pdf \| discuss
1787.	Sophia: A Persistent Agent Framework of Artificial Life (arxiv.org)
	2 points by mpweiher 276 days ago \| hide \| past \| pdf \| discuss
1788.	Cognitive Diagnosis Framework for Evaluating Financial Large Language Models (arxiv.org)
	3 points by gmays 277 days ago \| hide \| past \| pdf \| discuss
1789.	MHC: Manifold-Constrained Hyper-Connections (arxiv.org)
	12 points by tamnd 277 days ago \| hide \| past \| pdf \| 1 comment
1790.	The Bayesian Geometry of Transformer Attention (arxiv.org)
	4 points by samwillis 277 days ago \| hide \| past \| pdf \| 1 comment
1791.	Fantastic Reasoning Behaviors and Where to Find Them (arxiv.org)
	5 points by frozenseven 277 days ago \| hide \| past \| pdf \| discuss
1792.	MHC: Manifold-Constrained Hyper-Connections (arxiv.org)
	32 points by ipnon 277 days ago \| hide \| past \| pdf \| 3 comments
1793.	Building Domain-Specific Small Language Models via Guided Data Generation (arxiv.org)
	1 point by PaulHoule 278 days ago \| hide \| past \| pdf \| discuss
1794.	Exposing LLM-Generated Logical Flaws in Reasoning via Automated Theorem Proving (arxiv.org)
	2 points by StatsAreFun 278 days ago \| hide \| past \| pdf \| discuss
1795.	Bayesian Geometry of Transformer Attention (arxiv.org)
	1 point by brandonb 278 days ago \| hide \| past \| pdf \| discuss
1796.	Sophia: A Persistent Agent Framework of Artificial Life (arxiv.org)
	2 points by mpweiher 278 days ago \| hide \| past \| pdf \| discuss
1797.	MTTR-A: Measuring Cognitive Recovery Latency in Multi-Agent Systems (arxiv.org)
	3 points by PaulHoule 278 days ago \| hide \| past \| pdf \| discuss
1798.	VL-JEPA: Joint Embedding Predictive Architecture for Vision-Language (arxiv.org)
	3 points by hbarka 278 days ago \| hide \| past \| pdf \| discuss
1799.	Stable-Pretraining-v1: Foundation Model Research Made Simple (arxiv.org)
	7 points by PaulHoule 279 days ago \| hide \| past \| pdf \| discuss
1800.	ReCollab: Retrieval-Augmented LLMs for Cooperative Ad-Hoc Teammate Modeling (arxiv.org)
	1 point by StatsAreFun 279 days ago \| hide \| past \| pdf \| discuss
	More