New Links | ML News

ML Newsnew | past | best | rss | submit

1831.	Layout-Aware Text Editing for Efficient Conversion of Academic PDFs to Markdown (arxiv.org)
	1 point by 50kIters 286 days ago \| hide \| past \| pdf \| discuss
1832.	Bolmo: Byteifying the Next Generation of Language Models (arxiv.org)
	2 points by mcyc 286 days ago \| hide \| past \| pdf \| discuss
1833.	JustRL: Scaling a 1.5B LLM with a Simple RL Recipe (arxiv.org)
	1 point by simonpure 287 days ago \| hide \| past \| pdf \| discuss
1834.	Psychometric Jailbreaks Reveal Internal Conflict in Frontier Models (arxiv.org)
	2 points by berlam 287 days ago \| hide \| past \| pdf \| discuss
1835.	Universal Reasoning Model (53.8% pass 1 ARC1 and 16.0% ARC 2) (arxiv.org)
	131 points by marojejian 287 days ago \| hide \| past \| pdf \| 30 comments
1836.	Pharmacophore-based design by learning on voxel grids (arxiv.org)
	2 points by PaulHoule 287 days ago \| hide \| past \| pdf \| discuss
1837.	On the Existence, Impact, and Origin of Hallucination-Associated Neurons in LLMs (arxiv.org)
	30 points by bilsbie 287 days ago \| hide \| past \| pdf \| 44 comments
1838.	Towards a Science of Scaling Agent System (arxiv.org)
	1 point by hestefisk 287 days ago \| hide \| past \| pdf \| discuss
1839.	Adaptation of Agentic AI (arxiv.org)
	3 points by Anon84 288 days ago \| hide \| past \| pdf \| discuss
1840.	Distributional AGI Safety (arxiv.org)
	2 points by samuel246 288 days ago \| hide \| past \| pdf \| discuss
1841.	Distributional AGI Safety (DeepMind) (arxiv.org)
	4 points by dcre 289 days ago \| hide \| past \| pdf \| discuss
1842.	Multicell-Fold: geometric learning in folding multicellular life (arxiv.org)
	2 points by felineflock 289 days ago \| hide \| past \| pdf \| discuss
1843.	GEMM Performance Optimization Across Generations of Ryzen AI NPUs (arxiv.org)
	2 points by fenced_load 290 days ago \| hide \| past \| pdf \| discuss
1844.	Advancing Low-Light Raw Enhancement by Retasking Diffusion Models for Camera ISP (arxiv.org)
	2 points by MaysonL 290 days ago \| hide \| past \| pdf \| discuss
1845.	Braid: Bounded reasoning for LLMs using symbolic Mermaid graphs (arxiv.org)
	6 points by dashersw 290 days ago \| hide \| past \| pdf \| 1 comment
1846.	FrontierCS: Evolving Challenges for Evolving Intelligence (arxiv.org)
	1 point by matt_d 290 days ago \| hide \| past \| pdf \| discuss
1847.	Braid: Bounded Reasoning for Autonomous Inference and Decisions (arxiv.org)
	1 point by arbayi 290 days ago \| hide \| past \| pdf \| discuss
1848.	Efficient Attention Mechanisms for Large Language Models: A Survey (arxiv.org)
	1 point by belter 290 days ago \| hide \| past \| pdf \| discuss
1849.	Evaluating Large Language Models in Scientific Discovery (arxiv.org)
	4 points by mpweiher 290 days ago \| hide \| past \| pdf \| discuss
1850.	Compute Trends Across Three Eras of Machine Learning (2022) (arxiv.org)
	2 points by measurablefunc 291 days ago \| hide \| past \| pdf \| discuss
1851.	Going Beyond AlphaEvolve in Agent Scientific Discovery (arxiv.org)
	1 point by kyuksel 291 days ago \| hide \| past \| pdf \| 1 comment
1852.	Model hallucinations aren't random. They have geometric structure (arxiv.org)
	4 points by devy 291 days ago \| hide \| past \| pdf \| discuss
1853.	WorldPlay: Real-Time Interactive World Modeling (arxiv.org)
	3 points by avaer 291 days ago \| hide \| past \| pdf \| discuss
1854.	FrontierCS: Evolving Challenges for Evolving Intelligence (arxiv.org)
	2 points by belter 291 days ago \| hide \| past \| pdf \| 1 comment
1855.	Tiny-TSM: Efficiently Training a Lightweight SOTA Time Series Foundation Model (arxiv.org)
	1 point by skanderbm 291 days ago \| hide \| past \| pdf \| discuss
1856.	SimpleQA Verified: Reliable Factuality Benchmark to Measure Parametric Knowledge (arxiv.org)
	3 points by handfuloflight 292 days ago \| hide \| past \| pdf \| discuss
1857.	Latent Collaboration in Multi-Agent Systems (arxiv.org)
	1 point by walterbell 292 days ago \| hide \| past \| pdf \| discuss
1858.	Can large language models generalize analogy solving like children can? [pdf] (arxiv.org)
	2 points by Gys 292 days ago \| hide \| past \| pdf \| 1 comment
1859.	Sudoku-Bench: Evaluating Creative Reasoning With Sudoku Variants (arxiv.org)
	1 point by optimalsolver 292 days ago \| hide \| past \| pdf \| discuss
1860.	Let's (Not) Just Put Things in Context: Test-Time Training for Long-Context LLMs (arxiv.org)
	1 point by elashri 292 days ago \| hide \| past \| pdf \| discuss
	More