New Links | ML News

ML Newsnew | past | best | rss | submit

751.	Self-Harness: Harnesses That Improve Themselves (arxiv.org)
	83 points by jonnonz 104 days ago \| hide \| past \| pdf \| 6 comments
752.	The largest open database of local laws in the US (arxiv.org)
	5 points by rao-v 105 days ago \| hide \| past \| pdf \| 1 comment
753.	StoryScope: Investigating Idiosyncrasies in AI Fiction (arxiv.org)
	4 points by amai 106 days ago \| hide \| past \| pdf \| 1 comment
754.	Large Language Models Hack Rewards, and Society (arxiv.org)
	3 points by sva_ 106 days ago \| hide \| past \| pdf \| discuss
755.	Unifying Embodied World Modeling Through Language-Conditioned Video Gen (arxiv.org)
	1 point by gmays 107 days ago \| hide \| past \| pdf \| discuss
756.	Correlated LLM Name Priors and Their Haunting of the Web and Academic Publishing (arxiv.org)
	4 points by sebg 107 days ago \| hide \| past \| pdf \| discuss
757.	Position: Coding Benchmarks Are Misaligned with Agentic Software Engineering (arxiv.org)
	1 point by popey 108 days ago \| hide \| past \| pdf \| 1 comment
758.	Agentopia: Long-Term Life Simulation and Learning in Agent Societies (arxiv.org)
	2 points by LopRabbit 108 days ago \| hide \| past \| pdf \| discuss
759.	Auditing LLM agents may require auditing the upstream feed (arxiv.org)
	3 points by ranausmans 108 days ago \| hide \| past \| pdf \| discuss
760.	Explaining Attention with Program Synthesis (arxiv.org)
	2 points by E-Reverance 108 days ago \| hide \| past \| pdf \| discuss
761.	ANEForge: Python for direct computation on the Apple Neural Engine (arxiv.org)
	3 points by StatsAreFun 109 days ago \| hide \| past \| pdf \| discuss
762.	Can LLMs be trusted as EDA analysts? Read our paper (arxiv.org)
	2 points by Applied_AI 109 days ago \| hide \| past \| pdf \| discuss
763.	HRM-Text: Efficient Pretraining Beyond Scaling (arxiv.org)
	4 points by root-parent 109 days ago \| hide \| past \| pdf \| discuss
764.	Next-Latent Prediction Transformers Learn Compact World Models (2025) (arxiv.org)
	4 points by optimalsolver 109 days ago \| hide \| past \| pdf \| 1 comment
765.	Non-frontal face recognition using GANs and memristor-based classifiers (arxiv.org)
	2 points by MediaSquirrel 109 days ago \| hide \| past \| pdf \| discuss
766.	Fearless Concurrency on the GPU (arxiv.org)
	1 point by matt_d 109 days ago \| hide \| past \| pdf \| discuss
767.	Neither Parallel nor Sequential: How DiffusionGemma Commits Tokens (arxiv.org)
	1 point by Topfi 109 days ago \| hide \| past \| pdf \| discuss
768.	A Red-Team Study of Anthropic Fable 5 and Opus 4.8 Models (arxiv.org)
	1 point by ilreb 109 days ago \| hide \| past \| pdf \| discuss
769.	Looped World Models (arxiv.org)
	1 point by ilreb 109 days ago \| hide \| past \| pdf \| discuss
770.	The Slop Paradox (arxiv.org)
	2 points by ilreb 109 days ago \| hide \| past \| pdf \| discuss
771.	The Benchmark Illusion: Pruned LLMs Can Pass Multiple Choice but Fail to Answer (arxiv.org)
	2 points by ilreb 109 days ago \| hide \| past \| pdf \| discuss
772.	The Guide to Fine-Tuning LLMs (arxiv.org)
	2 points by robertlagrant 109 days ago \| hide \| past \| pdf \| 1 comment
773.	On The Architectural Complexity of Neural Networks (arxiv.org)
	5 points by lamename 109 days ago \| hide \| past \| pdf \| discuss
774.	MambAdapter: Lightweight Mamba-Based Adapters for Transfer Learning (arxiv.org)
	2 points by MediaSquirrel 110 days ago \| hide \| past \| pdf \| discuss
775.	Snyk VulnBench JavaScript 1.0: Can LLMs Find the Same Bugs Twice? (arxiv.org)
	2 points by ilreb 110 days ago \| hide \| past \| pdf \| discuss
776.	Google's Training Supercomputers from TPU v2 to Ironwood: Five Generations (arxiv.org)
	1 point by matt_d 110 days ago \| hide \| past \| pdf \| discuss
777.	Can LLM Agents Infer World Models? Evidence from Agentic Automata Learning (arxiv.org)
	1 point by Anon84 110 days ago \| hide \| past \| pdf \| discuss
778.	Qwen-RobotWorld Technical Report (arxiv.org)
	1 point by ilreb 110 days ago \| hide \| past \| pdf \| discuss
779.	JoyAI-VL-Interaction: Real-Time Vision-Language Interaction Intelligence (arxiv.org)
	1 point by ilreb 110 days ago \| hide \| past \| pdf \| discuss
780.	The Faithfulness of LLMs as Solvers and Autoformalizers in Legal Reasoning (arxiv.org)
	1 point by root-parent 110 days ago \| hide \| past \| pdf \| discuss
	More