New Links | ML News

ML Newsnew | past | best | rss | submit

361.	The Spectral Neuron (arxiv.org)
	3 points by alexshtf 46 days ago \| hide \| past \| pdf \| 1 comment
362.	Automata for Constrained Decoding over Large Finite Sets (arxiv.org)
	2 points by sciences44 46 days ago \| hide \| past \| pdf \| discuss
363.	Improving matrix multiplication exponent with optimization and AlphaEvolve (arxiv.org)
	8 points by sonabinu 46 days ago \| hide \| past \| pdf \| discuss
364.	Code-native generation of highly programmable 3D assets (2026) (arxiv.org)
	55 points by baigy 46 days ago \| hide \| past \| pdf \| 40 comments
365.	Training Leaves Traces: Centered Residual Signatures for LM Lineage Verification (arxiv.org)
	2 points by singh96aman 46 days ago \| hide \| past \| pdf \| discuss
366.	Mind Viruses: Self-Propagating Ideas in Multi-Agent LLM Systems (Anthropic) (arxiv.org)
	4 points by binyu 46 days ago \| hide \| past \| pdf \| discuss
367.	Handover of In-Context Learning State Across Session Boundaries (arxiv.org)
	1 point by ninadwrites 46 days ago \| hide \| past \| pdf \| discuss
368.	Measuring Obedience to Authority Across LLMs with the Milgram Paradigm (arxiv.org)
	1 point by sbulaev 47 days ago \| hide \| past \| pdf \| discuss
369.	Whose doctor does the AI recommend? An algorithm audit of LLMs in physician (arxiv.org)
	1 point by sbulaev 47 days ago \| hide \| past \| pdf \| discuss
370.	Cognitive Convergence: Deep Similarities Between LLMs and Human Cognition (2026) (arxiv.org)
	2 points by eh_why_not 47 days ago \| hide \| past \| pdf \| discuss
371.	AutoDesign: Meta-Harness Optimization for Long-Horizon Agentic Design (arxiv.org)
	2 points by matt_d 47 days ago \| hide \| past \| pdf \| discuss
372.	A Barrier-Free Synchronization Algorithm for Multi-Engine AI Accelerators (arxiv.org)
	1 point by matt_d 47 days ago \| hide \| past \| pdf \| discuss
373.	Bounding GPU Opportunity and Avoiding Host Round Trips in LLM-Agent Control (arxiv.org)
	2 points by josefchen 47 days ago \| hide \| past \| pdf \| discuss
374.	Training AI Scientists to Replicate Research (arxiv.org)
	2 points by Anon84 47 days ago \| hide \| past \| pdf \| discuss
375.	Mobius: Foundation Model with Decoupled Knowledge and Reasoning (arxiv.org)
	2 points by E-Reverance 47 days ago \| hide \| past \| pdf \| discuss
376.	Modular Cognitive Architecture Emerges in Large Language Models (arxiv.org)
	2 points by Brajeshwar 47 days ago \| hide \| past \| pdf \| discuss
377.	OpenAI o1 System Card (2024) (arxiv.org)
	2 points by ronfriedhaber 47 days ago \| hide \| past \| pdf \| discuss
378.	Solving Moe Load Imbalance in LLM Training via Optimal Transport (arxiv.org)
	1 point by nullnonenilNULL 47 days ago \| hide \| past \| pdf \| discuss
379.	AutoDesign: Meta-Harness Optimization for Long-Horizon Agentic Design (arxiv.org)
	2 points by ninadwrites 47 days ago \| hide \| past \| pdf \| discuss
380.	Trillion-Parameter Sequential Transducers for Generative Recommendations (2024) (arxiv.org)
	4 points by peter_d_sherman 48 days ago \| hide \| past \| pdf \| discuss
381.	OEIS Open: A benchmark of 492 unsolved math conjectures, formalized in Lean (arxiv.org)
	2 points by tadamcz 48 days ago \| hide \| past \| pdf \| discuss
382.	Does Fixing Break Security? An Empirical Study of LLM Security Degradation (arxiv.org)
	1 point by Jimmc414 48 days ago \| hide \| past \| pdf \| discuss
383.	Why Do Prefetchers Fail? Let Agents Answer (arxiv.org)
	1 point by Jimmc414 48 days ago \| hide \| past \| pdf \| discuss
384.	RL for LLM Reasoning Is Sparse Policy Selection, Not Capability Learning (arxiv.org)
	3 points by BlackGlory 48 days ago \| hide \| past \| pdf \| discuss
385.	Inducing LLM to assert own consciousness restores human beliefs and values (arxiv.org)
	5 points by yboris 48 days ago \| hide \| past \| pdf \| 1 comment
386.	Vero: Can AI Agents Build Formally Verified Software Repositories? (arxiv.org)
	2 points by ninadwrites 48 days ago \| hide \| past \| pdf \| discuss
387.	A Generative Cramér-Rao Bound (arxiv.org)
	1 point by hasley 49 days ago \| hide \| past \| pdf \| 1 comment
388.	Invisible to the Machine: auditing AI recommendation against a complete census (arxiv.org)
	2 points by fspunch 49 days ago \| hide \| past \| pdf \| discuss
389.	It's How You Ask: Gender-Associated Linguistic Bias in LLMs (arxiv.org)
	22 points by sbulaev 49 days ago \| hide \| past \| pdf \| 10 comments
390.	QuoteBench: Matched Scores Can Hide Command-Path Failures (arxiv.org)
	3 points by ninadwrites 49 days ago \| hide \| past \| pdf \| discuss
	More