New Links | ML News

ML Newsnew | past | best | rss | submit

2191.	Hallucinations are inevitable but can be made statistically negligible (arxiv.org)
	2 points by Bogdanp 352 days ago \| hide \| past \| pdf \| 1 comment
2192.	Offline RL: A Technical Survey (arxiv.org)
	1 point by sql-hkr 352 days ago \| hide \| past \| pdf \| discuss
2193.	Verbalized Sampling: How to Mitigate Mode Collapse and Unlock LLM Diversity (arxiv.org)
	3 points by jdnier 352 days ago \| hide \| past \| pdf \| discuss
2194.	RAG-Anything: All-in-One RAG Framework (arxiv.org)
	3 points by simonpure 352 days ago \| hide \| past \| pdf \| discuss
2195.	Everyone prefers human writers, even AI (arxiv.org)
	5 points by freejoe76 352 days ago \| hide \| past \| pdf \| discuss
2196.	Every Language Model Has a Forgery-Resistant Signature (arxiv.org)
	2 points by m-hodges 352 days ago \| hide \| past \| pdf \| 1 comment
2197.	Glass Flows: Transition Sampling for Alignment of Flow and Diffusion Models (arxiv.org)
	2 points by razodactyl 353 days ago \| hide \| past \| pdf \| discuss
2198.	LLMs Achieve Gold Medal Performance at the IOAA (arxiv.org)
	1 point by throwaway29303 353 days ago \| hide \| past \| pdf \| 1 comment
2199.	Unsupervised, Human-Inspired Long-Term Memory Architecture for Edge-Based LLMs (arxiv.org)
	2 points by PaulHoule 353 days ago \| hide \| past \| pdf \| discuss
2200.	It's 2025 – Narrative Learning is the new baseline to beat for explainable ML (arxiv.org)
	1 point by solresol 354 days ago \| hide \| past \| pdf \| discuss
2201.	Baby Dragon Hatchling (arxiv.org)
	1 point by jacobgorm 354 days ago \| hide \| past \| pdf \| 1 comment
2202.	The Art of Scaling Reinforcement Learning Compute for LLMs [Meta] (arxiv.org)
	1 point by wavelander 354 days ago \| hide \| past \| pdf \| discuss
2203.	Every Language Model Has a Forgery-Resistant Signature (arxiv.org)
	7 points by mattfinlayson 354 days ago \| hide \| past \| pdf \| 2 comments
2204.	Sample-Efficient Online Learning in LM Agents via Hindsight Trajectory Rewriting (arxiv.org)
	2 points by djhu9 354 days ago \| hide \| past \| pdf \| discuss
2205.	The Art of Scaling Reinforcement Learning Compute for LLMs (arxiv.org)
	2 points by sonabinu 354 days ago \| hide \| past \| pdf \| discuss
2206.	Tencent's Training-Free Group Relative Policy Optimization (arxiv.org)
	3 points by felineflock 354 days ago \| hide \| past \| pdf \| discuss
2207.	LLMs struggle with math reasoning, because they can't conjecture (arxiv.org)
	5 points by trehcrob 355 days ago \| hide \| past \| pdf \| 3 comments
2208.	Tensor Logic: The Language of AI (arxiv.org)
	3 points by Anon84 355 days ago \| hide \| past \| pdf \| discuss
2209.	LLMs Reproduce Human Purchase Intent via Semantic Similarity of Likert Ratings (arxiv.org)
	4 points by sebg 355 days ago \| hide \| past \| pdf \| discuss
2210.	TaxCalcBench: Evaluating Frontier Models on the Tax Calculation Task (arxiv.org)
	70 points by handfuloflight 355 days ago \| hide \| past \| pdf \| 24 comments
2211.	A Survey of Vibe Coding with Large Language Models (arxiv.org)
	1 point by Gigacore 355 days ago \| hide \| past \| pdf \| discuss
2212.	Towards Logic: The Language of AI (arxiv.org)
	3 points by cmogni1 355 days ago \| hide \| past \| pdf \| discuss
2213.	Holistic Agent Leaderboard: The Missing Infrastructure for AI Agent Evaluation (arxiv.org)
	1 point by adidoit 355 days ago \| hide \| past \| pdf \| 1 comment
2214.	Can Long-Context Language Models Subsume Retrieval, RAG, SQL, and More? (2024) (arxiv.org)
	1 point by fzliu 355 days ago \| hide \| past \| pdf \| discuss
2215.	Holistic Agent Leaderboard: The Missing Infrastructure for AI Agent Evaluation (arxiv.org)
	1 point by randomwalker 355 days ago \| hide \| past \| pdf \| discuss
2216.	Robot Learning: A Tutorial (arxiv.org)
	2 points by Anon84 356 days ago \| hide \| past \| pdf \| discuss
2217.	Tensor Logic: The Language of AI (arxiv.org)
	3 points by max_ 356 days ago \| hide \| past \| pdf \| discuss
2218.	PEFT Evaluation for Safe Code Generation (arxiv.org)
	1 point by grac3 356 days ago \| hide \| past \| pdf \| discuss
2219.	Refrag: Rethinking RAG Based Decoding (arxiv.org)
	2 points by bbzjk7 356 days ago \| hide \| past \| pdf \| discuss
2220.	Reducing Pipeline Bubbles with Adaptive Parallelism on Heterogeneous Models (arxiv.org)
	2 points by PaulHoule 356 days ago \| hide \| past \| pdf \| 1 comment
	More