New Links | ML News

ML Newsnew | past | best | rss | submit

1681.	Towards Execution-Grounded Automated AI Research (arxiv.org)
	2 points by abracos 255 days ago \| hide \| past \| pdf \| discuss
1682.	The unreasonable effectiveness of pattern matching (arxiv.org)
	3 points by chbint 255 days ago \| hide \| past \| pdf \| 2 comments
1683.	Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in CLIs (arxiv.org)
	2 points by matt_d 256 days ago \| hide \| past \| pdf \| discuss
1684.	Us-vs-Them Bias in Large Language Models (arxiv.org)
	1 point by geox 256 days ago \| hide \| past \| pdf \| discuss
1685.	Reasoning Models Generate Societies of Thought (arxiv.org)
	3 points by Anon84 256 days ago \| hide \| past \| pdf \| discuss
1686.	Convolutional-neural-operator-based transfer learning for solving PDEs (arxiv.org)
	2 points by PaulHoule 256 days ago \| hide \| past \| pdf \| 1 comment
1687.	SlimEdge: Lightweight Distributed DNN Deployment on Constrained Hardware (arxiv.org)
	1 point by PaulHoule 256 days ago \| hide \| past \| pdf \| discuss
1688.	DiffRatio: A SOTA one-step Diffusion model with 50% less GPU memory (arxiv.org)
	1 point by LoMoGan 256 days ago \| hide \| past \| pdf \| discuss
1689.	Human-Like Working Memory from Artificial Intrinsic Plasticity Neurons (arxiv.org)
	1 point by PaulHoule 257 days ago \| hide \| past \| pdf \| discuss
1690.	Delegated Authorization Constraining Agents to Semantic Task-to-Scope Matching (arxiv.org)
	1 point by mooreds 257 days ago \| hide \| past \| pdf \| discuss
1691.	DiffRatio – A One-Step Diffusion Model with SOTA quality and 50% less memory (arxiv.org)
	4 points by LoMoGan 257 days ago \| hide \| past \| pdf \| 1 comment
1692.	Provably unmasking malicious behavior through execution traces (arxiv.org)
	46 points by PaulHoule 258 days ago \| hide \| past \| pdf \| 5 comments
1693.	The Legal Embedding Benchmark (MLEB) (arxiv.org)
	1 point by fzliu 258 days ago \| hide \| past \| pdf \| discuss
1694.	WildCAT3D: Appearance-Aware Multi-View Diffusion in the Wild (arxiv.org)
	3 points by PaulHoule 258 days ago \| hide \| past \| pdf \| discuss
1695.	Repeating your prompt twice before sending it to an LLM improves accuracy (arxiv.org)
	2 points by daviducolo 258 days ago \| hide \| past \| pdf \| discuss
1696.	Perturb Your Data: Paraphrase-Guided Training Data Watermarking (arxiv.org)
	1 point by PaulHoule 258 days ago \| hide \| past \| pdf \| discuss
1697.	Fair is Better than Sensational:Man is to Doctor as Woman is to Doctor (2019) (arxiv.org)
	1 point by bhickey 258 days ago \| hide \| past \| pdf \| discuss
1698.	DiffusionBlocks: Block-Wise Neural Network Training (arxiv.org)
	3 points by E-Reverance 259 days ago \| hide \| past \| pdf \| 5 comments
1699.	The Assistant Axis: Situating/Stabilizing the Default Persona of Language Models (arxiv.org)
	1 point by lawrenceyan 259 days ago \| hide \| past \| pdf \| discuss
1700.	The unreasonable effectiveness of pattern matching (arxiv.org)
	7 points by headalgorithm 259 days ago \| hide \| past \| pdf \| 1 comment
1701.	Prompt Repetition Improves Non-Reasoning LLMs (arxiv.org)
	3 points by Tomte 259 days ago \| hide \| past \| pdf \| discuss
1702.	Do You Trust Me? Cognitive-Affective Signatures of Trustworthiness in LLMs (arxiv.org)
	4 points by 7777777phil 259 days ago \| hide \| past \| pdf \| discuss
1703.	Too Helpful to Be Safe: User-Mediated Attacks on Planning and Web-Use Agents (arxiv.org)
	4 points by 7777777phil 259 days ago \| hide \| past \| pdf \| discuss
1704.	From Code Foundation Models to Agents and Applications (arxiv.org)
	2 points by tamnd 260 days ago \| hide \| past \| pdf \| discuss
1705.	Verbalized Sampling: How to Mitigate Mode Collapse and Unlock LLM Diversity (arxiv.org)
	1 point by ycombiredd 260 days ago \| hide \| past \| pdf \| 2 comments
1706.	VaultGemma: A Differentially Private LLM (arxiv.org)
	3 points by todsacerdoti 260 days ago \| hide \| past \| pdf \| discuss
1707.	Prompt Repetition Improves Non-Reasoning LLMs (arxiv.org)
	2 points by UntitledNo4 261 days ago \| hide \| past \| pdf \| discuss
1708.	Private LLM Inference on Consumer Blackwell GPUs (arxiv.org)
	3 points by Teever 261 days ago \| hide \| past \| pdf \| discuss
1709.	Categorizing Variants of Goodhart's Law (arxiv.org)
	1 point by foster_nyman 261 days ago \| hide \| past \| pdf \| discuss
1710.	Future-as-Label: Scalable Supervision from Real-World Outcomes (arxiv.org)
	17 points by bturtel 262 days ago \| hide \| past \| pdf \| discuss
	More