New Links | ML News

ML Newsnew | past | best | rss | submit

841.	Sparsely gated tiny linear experts (arxiv.org)
	3 points by E-Reverance 118 days ago \| hide \| past \| pdf \| discuss
842.	A Categorical Framework for Agentic Artificial Intelligence (arxiv.org)
	1 point by ssivark 119 days ago \| hide \| past \| pdf \| 1 comment
843.	1D Image Tokenizers and Autoregressive Models for Dynamic Resolution Generations (arxiv.org)
	2 points by PaulHoule 119 days ago \| hide \| past \| pdf \| discuss
844.	Expert Selections in MoE Transformer Models Reveal Almost as Much as Text (arxiv.org)
	5 points by busserweiser 119 days ago \| hide \| past \| pdf \| discuss
845.	MemGraphRAG: Memory-Based Multi-Agent System for Graph RAG (arxiv.org)
	2 points by Anon84 119 days ago \| hide \| past \| pdf \| discuss
846.	If LLMs Have Human-Like Attributes, Then So Does Age of Empires II (arxiv.org)
	118 points by ketchup32613 119 days ago \| hide \| past \| pdf \| 121 comments
847.	Mitigating the LLM Rerun Crisis for Minimized-Inference-Cost Web Automation (arxiv.org)
	3 points by root-parent 119 days ago \| hide \| past \| pdf \| discuss
848.	The Price Reversal Phenomenon: When Cheaper Reasoning Models Cost More (arxiv.org)
	3 points by root-parent 119 days ago \| hide \| past \| pdf \| discuss
849.	If LLMs Have Human-Like Attributes, Then So Does Age of Empires II (arxiv.org)
	3 points by Luc 119 days ago \| hide \| past \| pdf \| discuss
850.	Efficient and Training-Free Single-Image Diffusion Models (arxiv.org)
	52 points by yorwba 119 days ago \| hide \| past \| pdf \| discuss
851.	Memory Caching: RNNs with Growing Memory (arxiv.org)
	3 points by dmichulke 119 days ago \| hide \| past \| pdf \| discuss
852.	How do AI agents spend your money? (arxiv.org)
	2 points by haemdahl 119 days ago \| hide \| past \| pdf \| discuss
853.	Tokenomics: Quantifying Where Tokens Are Used in Agentic Software Engineering (arxiv.org)
	173 points by Anon84 119 days ago \| hide \| past \| pdf \| 75 comments
854.	Gaia2: Benchmarking LLM Agents on Dynamic and Asynchronous Environments (arxiv.org)
	2 points by Anon84 119 days ago \| hide \| past \| pdf \| discuss
855.	If LLMs Have Human-Like Attributes, Then So Does Age of Empires II (arxiv.org)
	7 points by doener 120 days ago \| hide \| past \| pdf \| discuss
856.	Learn from Your Mistakes: Tree-Like Self-Play for Secure Code LLMs (arxiv.org)
	2 points by Extropy_ 120 days ago \| hide \| past \| pdf \| discuss
857.	Multi-Robot Cooperative Spatial Reasoning with Multimodal Large Language Models (arxiv.org)
	3 points by yogthos 120 days ago \| hide \| past \| pdf \| discuss
858.	If LLMs Have Human-Like Attributes, Then So Does Age of Empires II (arxiv.org)
	5 points by gekoxyz 120 days ago \| hide \| past \| pdf \| discuss
859.	Benchmarks in Leipzig (arxiv.org)
	138 points by root-parent 120 days ago \| hide \| past \| pdf \| 49 comments
860.	Paper: A Persona-Based Evaluation Framework for Generative AI Alignment (arxiv.org)
	2 points by atahankaragoz 120 days ago \| hide \| past \| pdf \| discuss
861.	Trees to Flows and Back: Unifying Decision Trees and Diffusion Models (arxiv.org)
	54 points by rsn243 120 days ago \| hide \| past \| pdf \| 11 comments
862.	Rethinking the Value of Generated Tests for LLM Software Engineering Agents (arxiv.org)
	2 points by zuzululu 120 days ago \| hide \| past \| pdf \| discuss
863.	Unlocking Non-Uniform KV Cache for Efficient Multi-Turn LLM Serving (arxiv.org)
	2 points by johnbarron 120 days ago \| hide \| past \| pdf \| discuss
864.	Discrete Tilt Matching (arxiv.org)
	3 points by PaulHoule 121 days ago \| hide \| past \| pdf \| discuss
865.	HRM-Text: Efficient Pretraining Beyond Scaling (arxiv.org)
	2 points by cubefox 121 days ago \| hide \| past \| pdf \| discuss
866.	A Framework for Confident Model Migration in Production Systems (arxiv.org)
	1 point by PaulHoule 121 days ago \| hide \| past \| pdf \| discuss
867.	iPhone Deployment of End-to-End Perception via Auto-Labeled Synthetic Data (arxiv.org)
	1 point by PaulHoule 121 days ago \| hide \| past \| pdf \| discuss
868.	AI Agents Enable Adaptive Computer Worms (arxiv.org)
	6 points by u1hcw9nx 121 days ago \| hide \| past \| pdf \| discuss
869.	Dense Contexts Are Hard: Lexical Density Limits LLM Context Windows (arxiv.org)
	2 points by sbulaev 121 days ago \| hide \| past \| pdf \| discuss
870.	RobotValues: Evaluating Household Robots When Human Values Conflict (arxiv.org)
	2 points by berlianta 121 days ago \| hide \| past \| pdf \| discuss
	More