New Links | ML News

ML Newsnew | past | best | rss | submit

1921.	Generative Graph Vocabularies for Robust Graph Foundation Models Fine-Tuning (arxiv.org)
	1 point by PaulHoule 305 days ago \| hide \| past \| pdf \| discuss
1922.	Idea-Gated Transformers: open-source semantic gating trick (2025) (arxiv.org)
	1 point by DARSHANFOFADIYA 305 days ago \| hide \| past \| pdf \| discuss
1923.	Π-Attention: Periodic Sparse Transformers for Efficient Long-Context Modeling (arxiv.org)
	1 point by PaulHoule 305 days ago \| hide \| past \| pdf \| discuss
1924.	Replacing Attention to Phase-Locking to Overcome Catastrophic Forgetting [pdf] (arxiv.org)
	1 point by Yujivus 305 days ago \| hide \| past \| pdf \| 1 comment
1925.	Condorcet's Theorem and an LLM Jury: Diminishing returns as group sizes increase (arxiv.org)
	1 point by dandelionv1bes 305 days ago \| hide \| past \| pdf \| discuss
1926.	AI agent achieves Rank 1 across major CTFs – a defining moment for cybersecurity (arxiv.org)
	2 points by vmayoral 306 days ago \| hide \| past \| pdf \| 1 comment
1927.	Ragas: Automated Evaluation of Retrieval Augmented Generation (arxiv.org)
	4 points by Anon84 306 days ago \| hide \| past \| pdf \| discuss
1928.	From Moderation to Mediation: Can LLMs Serve as Mediators in Online Flame Wars? (arxiv.org)
	2 points by kelseyfrog 306 days ago \| hide \| past \| pdf \| discuss
1929.	Transformers know more than they can tell: Learning the Collatz sequence (arxiv.org)
	129 points by Xcelerate 306 days ago \| hide \| past \| pdf \| 45 comments
1930.	LatentMAS – agent collaboration from token space into the model's latent space (arxiv.org)
	3 points by vismit2000 306 days ago \| hide \| past \| pdf \| 1 comment
1931.	From Code Foundation Models to Agents and Applications: A Practical Guide (arxiv.org)
	2 points by eunos 307 days ago \| hide \| past \| pdf \| discuss
1932.	Step-by-Step Diffusion: An Elementary Tutorial (arxiv.org)
	2 points by Anon84 307 days ago \| hide \| past \| pdf \| discuss
1933.	Intelligence per Watt: Measuring Intelligence Efficiency of Local AI (arxiv.org)
	3 points by mzl 307 days ago \| hide \| past \| pdf \| discuss
1934.	Meta Superintelligence Labs: Scaling Agent Learning via Experience Synthesis (arxiv.org)
	2 points by babelfish 308 days ago \| hide \| past \| pdf \| discuss
1935.	Byte-Level Tokenizers Unavoidably Enable LLMs to Generate Ill-Formed UTF-8 (arxiv.org)
	2 points by PaulHoule 308 days ago \| hide \| past \| pdf \| 1 comment
1936.	Z-Image: An Efficient Image Generation Foundation Model [pdf] (arxiv.org)
	3 points by SerCe 308 days ago \| hide \| past \| pdf \| discuss
1937.	Pose-free 3D Gaussian splatting via shape-ray estimation (arxiv.org)
	36 points by PaulHoule 308 days ago \| hide \| past \| pdf \| 3 comments
1938.	Paper shows scientific foundation model learns general abstract physics (arxiv.org)
	2 points by iRoygbiv 308 days ago \| hide \| past \| pdf \| 1 comment
1939.	Evo-Memory: Benchmarking LLM Agent Test-Time Learning with Self-Evolving Memory (arxiv.org)
	1 point by simonpure 308 days ago \| hide \| past \| pdf \| discuss
1940.	Omnilingual ASR: Open-Source Multilingual Speech Recognition for 1600 Languages (arxiv.org)
	2 points by PaulHoule 308 days ago \| hide \| past \| pdf \| discuss
1941.	Butter-Bench: Evaluating LLM Controlled Robots for Practical Intelligence (arxiv.org)
	1 point by prisenco 309 days ago \| hide \| past \| pdf \| discuss
1942.	Training Foundation Models on a Full-Stack AMD Platform (arxiv.org)
	26 points by ngaut 309 days ago \| hide \| past \| pdf \| 1 comment
1943.	Program-of-Thought Prompting Outperforms Chain-of-Thought by 15% (2022) (arxiv.org)
	136 points by mkagenius 309 days ago \| hide \| past \| pdf \| 36 comments
1944.	Gated Attention for Large Language Models (arxiv.org)
	1 point by xnhbx 309 days ago \| hide \| past \| pdf \| discuss
1945.	Continuous Thought Machines (arxiv.org)
	3 points by Anon84 310 days ago \| hide \| past \| pdf \| discuss
1946.	One Thousand Layer Networks for Self-Supervised RL (arxiv.org)
	1 point by johnsutor 310 days ago \| hide \| past \| pdf \| discuss
1947.	Evolution Strategies at the Hyperscale (arxiv.org)
	9 points by azhenley 311 days ago \| hide \| past \| pdf \| 1 comment
1948.	Nvidia ToolOrchestra – 8B model "manager" improves intelligence and efficiency (arxiv.org)
	5 points by hereme888 311 days ago \| hide \| past \| pdf \| discuss
1949.	Dynamic and Parametric Retrieval-Augmented Generation (arxiv.org)
	1 point by felineflock 311 days ago \| hide \| past \| pdf \| discuss
1950.	Adversarial Captcha for Breaking MLLM-Powered AI Agents (arxiv.org)
	3 points by bron123 311 days ago \| hide \| past \| pdf \| 2 comments
	More