New Links | ML News

ML Newsnew | past | best | rss | submit

91.	Emergent Collusion in Long-Horizon LLM Agent Interaction (arxiv.org)
	1 point by sbulaev 10 days ago \| hide \| past \| pdf \| discuss
92.	Measuring behavioral signals of LLM through psychometric profiling (arxiv.org)
	1 point by anigbrowl 10 days ago \| hide \| past \| pdf \| discuss
93.	Temporal Straightening for Latent Planning (arxiv.org)
	2 points by gmays 11 days ago \| hide \| past \| pdf \| discuss
94.	DeepSeek Elastic Compute:A Sandbox Infrastructure for Effective Agentic Training (arxiv.org)
	5 points by eunos 11 days ago \| hide \| past \| pdf \| discuss
95.	Scaling Discovery Through Test-Time Communication (arxiv.org)
	1 point by marojejian 11 days ago \| hide \| past \| pdf \| 1 comment
96.	Xeno-Interpretability: Investigating the Alien Minds of LLMs (arxiv.org)
	3 points by potent_latent 11 days ago \| hide \| past \| pdf \| discuss
97.	A self-evolving agentic system for automated execution of biological protocols (arxiv.org)
	1 point by lawrenceyan 11 days ago \| hide \| past \| pdf \| discuss
98.	Do small language models know what they don't know? (arxiv.org)
	3 points by Brajeshwar 11 days ago \| hide \| past \| pdf \| discuss
99.	Show HN: Training a model to identify AI web content from structure alone (arxiv.org)
	74 points by jochenmadler 11 days ago \| hide \| past \| pdf \| 28 comments
100.	Agents That Edit Documents: Measuring Agentic PDF Forgery Against a Non-Agentic (arxiv.org)
	1 point by sbulaev 11 days ago \| hide \| past \| pdf \| discuss
101.	RRSI: Regularized Recursive Self-Improvement of Agent Harnesses (arxiv.org)
	1 point by Betelbuddy 11 days ago \| hide \| past \| pdf \| discuss
102.	Et Tu, Brute? Economic Misalignment in Personal AI Agents (arxiv.org)
	1 point by sbulaev 11 days ago \| hide \| past \| pdf \| discuss
103.	Complex KDA:Understanding and Enhancing the Expressivity of Kimi Delta Attention (arxiv.org)
	2 points by jul8234 11 days ago \| hide \| past \| pdf \| discuss
104.	Loopjacking: Hijacking Human-in-the-Loop Approval (arxiv.org)
	4 points by sbulaev 11 days ago \| hide \| past \| pdf \| discuss
105.	ArtifactBench: Evaluating AI Music Detectors Under Distribution Shift (arxiv.org)
	1 point by unohee 11 days ago \| hide \| past \| pdf \| discuss
106.	Scaling Discovery Through Test-Time Communication (arxiv.org)
	2 points by simonpure 12 days ago \| hide \| past \| pdf \| discuss
107.	An Introduction to Compression-Based Machine Learning (arxiv.org)
	2 points by jackhurwitz 12 days ago \| hide \| past \| pdf \| discuss
108.	Steerable Cultural Preference Optimization of Reward Models (arxiv.org)
	2 points by measurablefunc 12 days ago \| hide \| past \| pdf \| discuss
109.	Atria Dawn: The Dawn of Agentic Superintelligence (arxiv.org)
	3 points by simonpure 12 days ago \| hide \| past \| pdf \| discuss
110.	The Pain Axis: LLMs Represent Self-Directed Harm and Act to Relieve It (arxiv.org)
	1 point by Anon84 13 days ago \| hide \| past \| pdf \| discuss
111.	Tracking Capabilities for Safer Agents (arxiv.org)
	3 points by verdverm 13 days ago \| hide \| past \| pdf \| 1 comment
112.	Inference-Engine Fingerprinting Attacks Are Practical (arxiv.org)
	5 points by sbulaev 13 days ago \| hide \| past \| pdf \| discuss
113.	The Pain Axis: LLMs Represent Self-Directed Harm and Act to Relieve It (arxiv.org)
	5 points by droidjj 14 days ago \| hide \| past \| pdf \| discuss
114.	Solving rubiks cubes "without search" (arxiv.org)
	4 points by E-Reverance 14 days ago \| hide \| past \| pdf \| discuss
115.	The Pain Axis: LLMs Represent Self-Directed Harm and Act to Relieve It (arxiv.org)
	11 points by amichail 14 days ago \| hide \| past \| pdf \| 1 comment
116.	A Black-Box Audit of Provider-Side Token Inflation in LLM Services (arxiv.org)
	2 points by donk8r 14 days ago \| hide \| past \| pdf \| discuss
117.	Reality Is the Final Verifier: On Two Key Gaps in Agentic Software Engineering (arxiv.org)
	3 points by matt_d 14 days ago \| hide \| past \| pdf \| discuss
118.	Federated Learning Is Not Private for Google GBoard Next Word Prediction [pdf] (arxiv.org)
	2 points by thunderbong 15 days ago \| hide \| past \| pdf \| discuss
119.	Score Centering Stabilizes Off-Policy Reinforcement Learning (arxiv.org)
	3 points by zagwdt 15 days ago \| hide \| past \| pdf \| discuss
120.	The Pain Axis: LLMs Represent Self-Directed Harm and Act to Relieve It (arxiv.org)
	8 points by 1317 15 days ago \| hide \| past \| pdf \| 1 comment
	More