New Links | ML News

ML Newsnew | past | best | rss | submit

2011.	TiDAR: Think in Diffusion, Talk in Autoregression (arxiv.org)
	130 points by internetguy 324 days ago \| hide \| past \| pdf \| 22 comments
2012.	Autoregressive or Diffusion Language Models, Why Choose? (arxiv.org)
	5 points by mimida 325 days ago \| hide \| past \| pdf \| discuss
2013.	Quantifying Long-Range Information for Long-Context LLM Pretraining Data (arxiv.org)
	2 points by PaulHoule 325 days ago \| hide \| past \| pdf \| discuss
2014.	Questioning Representational Optimism in Deep Learning (arxiv.org)
	1 point by vatsachak 325 days ago \| hide \| past \| pdf \| 1 comment
2015.	StutterZero: Speech Conversion for Stuttering Transcription and Correction (arxiv.org)
	1 point by internetguy 325 days ago \| hide \| past \| pdf \| discuss
2016.	First Agentic System to Solve a Million-Step Reasoning Problem with Zero Errors (arxiv.org)
	3 points by jarrattp31 325 days ago \| hide \| past \| pdf \| 1 comment
2017.	Black-Box On-Policy Distillation of Large Language Models (arxiv.org)
	1 point by Jimmc414 325 days ago \| hide \| past \| pdf \| discuss
2018.	EnvTrace: Simulation-Based Semantic Evaluation of LLM Code (arxiv.org)
	1 point by amscotti 325 days ago \| hide \| past \| pdf \| discuss
2019.	Can we bootstrap AI Safety despite being unable to even define it? (arxiv.org)
	2 points by cryptohell 326 days ago \| hide \| past \| pdf \| 2 comments
2020.	Whisper leak: a side-channel attack on large language models (arxiv.org)
	3 points by neapolisbeach 326 days ago \| hide \| past \| pdf \| discuss
2021.	Probing Knowledge Holes in Unlearned LLMs (arxiv.org)
	2 points by PaulHoule 326 days ago \| hide \| past \| pdf \| discuss
2022.	Source-Optimal Training Is Transfer-Suboptimal (arxiv.org)
	1 point by ceh123 326 days ago \| hide \| past \| pdf \| 1 comment
2023.	Pictographic Character Reconstruction with Bézier Curves (arxiv.org)
	2 points by PaulHoule 326 days ago \| hide \| past \| pdf \| discuss
2024.	LeJEPA: Provable and Scalable Self-Supervised Learning Without the Heuristics (arxiv.org)
	2 points by samstevens 326 days ago \| hide \| past \| pdf \| discuss
2025.	Automated Contiguous Layer Pruning for Large Language Models (arxiv.org)
	1 point by PaulHoule 326 days ago \| hide \| past \| pdf \| discuss
2026.	Hadsf: Aspect Aware Semantic Control for Explainable Recommendation (arxiv.org)
	1 point by PaulHoule 326 days ago \| hide \| past \| pdf \| discuss
2027.	How far are we from scaling up next-pixel prediction? (arxiv.org)
	1 point by Hard_Space 327 days ago \| hide \| past \| pdf \| discuss
2028.	Continuous Autoregressive Language Models (arxiv.org)
	2 points by badmonster 327 days ago \| hide \| past \| pdf \| discuss
2029.	Jasmine: A Simple, Performant and Scalable Jax-Based World Modeling Codebase (arxiv.org)
	24 points by PaulHoule 327 days ago \| hide \| past \| pdf \| 1 comment
2030.	Restructuring Vector Quantization with the Rotation Trick (arxiv.org)
	1 point by fzliu 327 days ago \| hide \| past \| pdf \| discuss
2031.	Miro: MultI-Reward cOnditioned pretraining improves T2I quality and efficiency (arxiv.org)
	3 points by PaulHoule 327 days ago \| hide \| past \| pdf \| discuss
2032.	StutterZero: Speech Conversion for Stuttering Transcription and Correction (arxiv.org)
	3 points by e_iris 327 days ago \| hide \| past \| pdf \| discuss
2033.	LLM Output Drift in Financial Workflows: Validation and Mitigation (arXiv) (arxiv.org)
	24 points by raffisk 327 days ago \| hide \| past \| pdf \| 26 comments
2034.	LeJEPA: Provable and Scalable Self-Supervised Learning Without the Heuristics (arxiv.org)
	5 points by XTXinverseXTY 327 days ago \| hide \| past \| pdf \| 2 comments
2035.	Tiny Model, Big Logic: Large-Model Reasoning Ability in VibeThinker-1.5B (arxiv.org)
	4 points by trott 327 days ago \| hide \| past \| pdf \| discuss
2036.	Show HN: CellARC Measuring Intelligence with Cellular Automata (arxiv.org)
	1 point by mireklzicar 328 days ago \| hide \| past \| pdf \| discuss
2037.	Embedding Symbolic Equivalence into Symbolic Regression via Equality Graph (arxiv.org)
	3 points by ahsillyme 328 days ago \| hide \| past \| pdf \| discuss
2038.	Measuring What Matters: Construct Validity in Large Language Model Benchmarks (arxiv.org)
	1 point by Cynddl 328 days ago \| hide \| past \| pdf \| discuss
2039.	Too Good to Be Bad: On the Failure of LLMs to Role-Play Villains [pdf] (arxiv.org)
	1 point by SerCe 329 days ago \| hide \| past \| pdf \| discuss
2040.	AI Feynman: A Physics-Inspired Method for Symbolic Regression (arxiv.org)
	4 points by openquery 329 days ago \| hide \| past \| pdf \| discuss
	More