New Links | ML News

ML Newsnew | past | best | rss | submit

1501.	The Fundamental Limits of LLMs at Scale (arxiv.org)
	4 points by o4c 226 days ago \| hide \| past \| pdf \| discuss
1502.	Multi-Turn Intent Detection for LLM and Agent Security (ArXiv) (arxiv.org)
	1 point by sharathr 226 days ago \| hide \| past \| pdf \| 1 comment
1503.	Prompt Repetition Improves Non-Reasoning LLMs (arxiv.org)
	1 point by elorant 226 days ago \| hide \| past \| pdf \| discuss
1504.	Multi-agent cooperation through in-context co-player inference (arxiv.org)
	2 points by gmays 226 days ago \| hide \| past \| pdf \| discuss
1505.	Performance of Deep Material Networks for Multiscale Material Modeling (arxiv.org)
	1 point by PaulHoule 226 days ago \| hide \| past \| pdf \| discuss
1506.	Large-scale online deanonymization with LLMs (arxiv.org)
	3 points by DalasNoin 227 days ago \| hide \| past \| pdf \| discuss
1507.	Monolith – The research paper behind TikToks algorithm (2022) (arxiv.org)
	2 points by Alifatisk 227 days ago \| hide \| past \| pdf \| discuss
1508.	Soft Contamination Means Benchmarks Test Shallow Generalization (arxiv.org)
	2 points by gmays 227 days ago \| hide \| past \| pdf \| discuss
1509.	The Existence and Behavior of Secondary Attention Sinks (arxiv.org)
	1 point by thw20 227 days ago \| hide \| past \| pdf \| discuss
1510.	Improving Interactive In-Context Learning from Natural Lang Feedback – DeepMind (arxiv.org)
	2 points by zerop 227 days ago \| hide \| past \| pdf \| discuss
1511.	Fast KV Compaction via Attention Matching (arxiv.org)
	73 points by cbracketdash 227 days ago \| hide \| past \| pdf \| 15 comments
1512.	Prompt Repetition Improves Non-Reasoning LLMs (arxiv.org)
	1 point by beatthatflight 227 days ago \| hide \| past \| pdf \| discuss
1513.	When Models Manipulate Manifolds: The Geometry of a Counting Task [pdf] (arxiv.org)
	1 point by vinhnx 227 days ago \| hide \| past \| pdf \| discuss
1514.	Towards Industrial-Scale Verification: LLM-Driven Theorem Proving on SeL4 (arxiv.org)
	1 point by lr0 227 days ago \| hide \| past \| pdf \| discuss
1515.	Surprising Effectiveness of Masking Updates in Adaptive Optimizers (arxiv.org)
	5 points by gmays 227 days ago \| hide \| past \| pdf \| discuss
1516.	GLM-5: From Vibe Coding to Agentic Engineering (arxiv.org)
	1 point by gmays 228 days ago \| hide \| past \| pdf \| discuss
1517.	Prompt Repetition Improves Non-Reasoning LLMs [pdf] (arxiv.org)
	1 point by 8ig8 228 days ago \| hide \| past \| pdf \| discuss
1518.	LongCLI-Bench: Benchmark and Study for Long-Horizon Agentic Programming in CLIs (arxiv.org)
	2 points by simonpure 228 days ago \| hide \| past \| pdf \| discuss
1519.	Can We Trust LLM Detectors? (arxiv.org)
	3 points by PaulHoule 228 days ago \| hide \| past \| pdf \| discuss
1520.	Persona: Controlling LLM Personality with Vector Algebra (arxiv.org)
	3 points by mldev_exe 228 days ago \| hide \| past \| pdf \| discuss
1521.	GR3EN: Generative Relighting for 3D Environments (arxiv.org)
	2 points by PaulHoule 228 days ago \| hide \| past \| pdf \| discuss
1522.	WebWorld: A Large-Scale World Model for Web Agent Training (arxiv.org)
	2 points by gmays 228 days ago \| hide \| past \| pdf \| discuss
1523.	A benchmark for vericoding: formally verified program synthesis (arxiv.org)
	3 points by luskira 228 days ago \| hide \| past \| pdf \| discuss
1524.	Constructing Unlearnable Data with Solely Linear Classifiers (arxiv.org)
	2 points by PaulHoule 229 days ago \| hide \| past \| pdf \| discuss
1525.	Experiential Reinforcement Learning (arxiv.org)
	3 points by geophile 229 days ago \| hide \| past \| pdf \| discuss
1526.	Identity, Cooperation and Framing Within Groups of Real and Simulated Humans (arxiv.org)
	2 points by PaulHoule 229 days ago \| hide \| past \| pdf \| discuss
1527.	Language Models Entangle Language and Culture (arxiv.org)
	1 point by paraschopra 229 days ago \| hide \| past \| pdf \| discuss
1528.	Does Socialization Emerge in AI Agent Society? A Case Study of Moltbook (arxiv.org)
	1 point by simonpure 229 days ago \| hide \| past \| pdf \| 1 comment
1529.	Biases in the Blind Spot: Detecting What LLMs Fail to Mention (arxiv.org)
	2 points by azalemeth 229 days ago \| hide \| past \| pdf \| discuss
1530.	Prompt Repetition Improves Non Reasoning LLM (arxiv.org)
	2 points by jdthedisciple 229 days ago \| hide \| past \| pdf \| discuss
	More