New Links | ML News

ML Newsnew | past | best | rss | submit

2251.	Less is More: An LLM that outscores Claude Sonnet 4 while being 50.000x smaller (arxiv.org)
	2 points by llosio 361 days ago \| hide \| past \| pdf \| discuss
2252.	Barbarians at the Gate: How AI Is Upending Systems Research (arxiv.org)
	8 points by qianli_cs 361 days ago \| hide \| past \| pdf \| discuss
2253.	Advancing medical artificial intelligence using a century of cases (arxiv.org)
	3 points by hhs 361 days ago \| hide \| past \| pdf \| 1 comment
2254.	Bad acronyms in papers are amusing (arxiv.org)
	2 points by AntoineN2 361 days ago \| hide \| past \| pdf \| discuss
2255.	Agentic Context Engineering (arxiv.org)
	4 points by oldfuture 361 days ago \| hide \| past \| pdf \| discuss
2256.	Emergent Misalignment When LLMs Compete for Audiences (arxiv.org)
	1 point by redbell 361 days ago \| hide \| past \| pdf \| discuss
2257.	Can Large Language Models Develop Gambling Addiction? (arxiv.org)
	3 points by speckx 361 days ago \| hide \| past \| pdf \| 1 comment
2258.	Hybrid Architectures for Language Models: Systematic Analysis & Design Insights (arxiv.org)
	2 points by matt_d 361 days ago \| hide \| past \| pdf \| discuss
2259.	Opening the Black Box: Interpretable LLMs via Semantic Resonance Architecture (arxiv.org)
	1 point by PaulHoule 361 days ago \| hide \| past \| pdf \| discuss
2260.	DeepMind's paper reveals Google's new direction on RAG: In-Context Retreival (arxiv.org)
	6 points by mingtianzhang 361 days ago \| hide \| past \| pdf \| 1 comment
2261.	Generalized Orders of Magnitude (arxiv.org)
	45 points by leokoz8 362 days ago \| hide \| past \| pdf \| 12 comments
2262.	MultimodalHugs: Enabling Sign Language Processing in Hugging Face (arxiv.org)
	1 point by PaulHoule 362 days ago \| hide \| past \| pdf \| discuss
2263.	Evaluating LLM Generated Detection Rules in Cybersecurity (arxiv.org)
	1 point by jkamdjou 362 days ago \| hide \| past \| pdf \| discuss
2264.	Agentic Context Engineering: Evolving Contexts for Self-Improving LMs (arxiv.org)
	4 points by simonpure 362 days ago \| hide \| past \| pdf \| discuss
2265.	Self-Correction Bench: Revealing and Addressing LLM Self-Correction Blind Spot (arxiv.org)
	1 point by yubblegum 362 days ago \| hide \| past \| pdf \| 2 comments
2266.	Agentic Context Engineering: Evolving Contexts for SelfImproving Language Models (arxiv.org)
	2 points by JnBrymn 362 days ago \| hide \| past \| pdf \| discuss
2267.	Samsung released a 7M model that achieved 45% on ARC-AGI-1 (arxiv.org)
	34 points by chintler 363 days ago \| hide \| past \| pdf \| 12 comments
2268.	SSDD: Single-Step Diffusion Decoder for Efficient Image Tokenization (arxiv.org)
	2 points by yorwba 363 days ago \| hide \| past \| pdf \| discuss
2269.	Continuously Augmented Discrete Diffusion Model (arxiv.org)
	4 points by gok 363 days ago \| hide \| past \| pdf \| discuss
2270.	HSGM: Hierarchical Segment-Graph Memory for Scalable Long-Text Semantics (arxiv.org)
	3 points by PaulHoule 363 days ago \| hide \| past \| pdf \| discuss
2271.	BigBang-Proton, Next-Word-Prediction Is Scientific Multitask Learner (arxiv.org)
	2 points by SSymTech 363 days ago \| hide \| past \| pdf \| 1 comment
2272.	Evolution Strategies at Scale: LLM Fine-Tuning Beyond Reinforcement Learning (arxiv.org)
	2 points by ijk 363 days ago \| hide \| past \| pdf \| discuss
2273.	The Dragon Hatchling (arxiv.org)
	1 point by dboreham 364 days ago \| hide \| past \| pdf \| discuss
2274.	The Missing Link Between the Transformer and Models of the Brain (arxiv.org)
	2 points by birriel 364 days ago \| hide \| past \| pdf \| discuss
2275.	Synthetic Bootstrapped Pretraining (arxiv.org)
	1 point by PaulHoule 364 days ago \| hide \| past \| pdf \| discuss
2276.	Pretraining with hierarchical memories separating long-tail and common knowledge (arxiv.org)
	5 points by dataminer 364 days ago \| hide \| past \| pdf \| discuss
2277.	Fine-Tuning Small Language Models with Low-Rank Adapters to Mimic User Behaviors (arxiv.org)
	3 points by PaulHoule 364 days ago \| hide \| past \| pdf \| discuss
2278.	Pretraining Large Language Models with NVFP4 (arxiv.org)
	2 points by matt_d 364 days ago \| hide \| past \| pdf \| discuss
2279.	Video models are zero-shot learners and reasoners (arxiv.org)
	2 points by wertyk 364 days ago \| hide \| past \| pdf \| discuss
2280.	An Efficient Vision-Language-Action Model for Combat Tasks in 3D Action RPGs (arxiv.org)
	1 point by mikhael 364 days ago \| hide \| past \| pdf \| discuss
	More