New Links | ML News

ML Newsnew | past | best | rss | submit

1171.	Toward Autonomous Long-Horizon Engineering for ML Research (arxiv.org)
	1 point by Anon84 169 days ago \| hide \| past \| pdf \| discuss
1172.	Huoziime: An On-Device LLM-Enhanced Input Method for Deep Personalization (arxiv.org)
	1 point by Brajeshwar 169 days ago \| hide \| past \| pdf \| discuss
1173.	Mastering Page-Level Chinese Calligraphy via Layout-Guided Spatial Planning (arxiv.org)
	4 points by PaulHoule 170 days ago \| hide \| past \| pdf \| discuss
1174.	Generating Hierarchical JSON Representations of Scientific Sentences Using LLMs (arxiv.org)
	9 points by PaulHoule 170 days ago \| hide \| past \| pdf \| 1 comment
1175.	Event Tensor: A Unified Abstraction for Compiling Dynamic Megakernel (arxiv.org)
	2 points by mfiguiere 170 days ago \| hide \| past \| pdf \| discuss
1176.	Long-Tail Knowledge in Large Language Models (arxiv.org)
	1 point by wslh 170 days ago \| hide \| past \| pdf \| discuss
1177.	Toward Autonomous Long-Horizon Engineering for ML Research (arxiv.org)
	1 point by gmays 170 days ago \| hide \| past \| pdf \| discuss
1178.	Tessera: Unlocking Heterogeneous GPUs Through Kernel-Granularity Disaggregation (arxiv.org)
	1 point by matt_d 171 days ago \| hide \| past \| pdf \| discuss
1179.	Lyra 2.0: Explorable Generative 3D Worlds (arxiv.org)
	4 points by gmays 171 days ago \| hide \| past \| pdf \| discuss
1180.	Sir-Bench – benchmark for security incident response agents (arxiv.org)
	6 points by dan_l2 171 days ago \| hide \| past \| pdf \| 2 comments
1181.	Mechanisms of introspective awareness in LLMs [pdf] (arxiv.org)
	2 points by ryeights 171 days ago \| hide \| past \| pdf \| 2 comments
1182.	Sparser, Faster, Lighter Transformer Language Models (arxiv.org)
	3 points by matt_d 171 days ago \| hide \| past \| pdf \| discuss
1183.	Elastic Looped Transformers for Visual Generation (arxiv.org)
	1 point by gmays 171 days ago \| hide \| past \| pdf \| discuss
1184.	LLM risk spreading misinformation to humans who are least able to identify it (arxiv.org)
	4 points by sailingcode 171 days ago \| hide \| past \| pdf \| 1 comment
1185.	Target Policy Optimization (arxiv.org)
	1 point by t55 171 days ago \| hide \| past \| pdf \| discuss
1186.	LLM Personalization Breaks Down in High-Stakes Finance (arxiv.org)
	2 points by yashsawant22 171 days ago \| hide \| past \| pdf \| discuss
1187.	Show HN: Do Thought Streams Matter? A Benchmark of VLM Reasoning in Gemini 2.5 (arxiv.org)
	3 points by ashu_trv 172 days ago \| hide \| past \| pdf \| discuss
1188.	Interpreting Negation in GPT-2: Layer- and Head-Level Causal Analysis (arxiv.org)
	1 point by PaulHoule 172 days ago \| hide \| past \| pdf \| discuss
1189.	A Survey of Workflow Optimization for LLM Agents (arxiv.org)
	2 points by PaulHoule 172 days ago \| hide \| past \| pdf \| discuss
1190.	Lyra 2.0: Explorable Generative 3D Worlds (arxiv.org)
	5 points by aanet 172 days ago \| hide \| past \| pdf \| 2 comments
1191.	Pragma: Revolut Foundation Model (arxiv.org)
	2 points by matthieu_bl 172 days ago \| hide \| past \| pdf \| discuss
1192.	A 129FPS Full HD Real-Time Accelerator for 3D Gaussian Splatting (arxiv.org)
	3 points by rbanffy 173 days ago \| hide \| past \| pdf \| discuss
1193.	A Comparative Study of Power-Capping Nvidia H100 and H200 (arxiv.org)
	1 point by rbanffy 173 days ago \| hide \| past \| pdf \| discuss
1194.	Learnability and Privacy Vulnerability Are Entangled in a Few Critical Weights (arxiv.org)
	2 points by PaulHoule 173 days ago \| hide \| past \| pdf \| discuss
1195.	Can LLMs Perform Synthesis? (arxiv.org)
	4 points by PaulHoule 173 days ago \| hide \| past \| pdf \| discuss
1196.	ASI-Evolve: AI Accelerates AI (arxiv.org)
	1 point by foruhar 173 days ago \| hide \| past \| pdf \| discuss
1197.	Automated Conjecture Resolution with Formal Verification (arxiv.org)
	2 points by throwaway81523 174 days ago \| hide \| past \| pdf \| discuss
1198.	Process-Driven Image Generation via Interleaved Reasoning (arxiv.org)
	2 points by gmays 174 days ago \| hide \| past \| pdf \| discuss
1199.	SAM3-I: Segment Anything with Instructions (arxiv.org)
	4 points by usernomdeguerre 174 days ago \| hide \| past \| pdf \| discuss
1200.	HiFloat4 Format for Language Model Pre-Training on Ascend NPUs (arxiv.org)
	3 points by rbanffy 174 days ago \| hide \| past \| pdf \| discuss
	More