New Links | ML News

ML Newsnew | past | best | rss | submit

1021.	AI co-mathematician: Accelerating mathematicians with agentic AI (arxiv.org)
	3 points by aoki 143 days ago \| hide \| past \| pdf \| discuss
1022.	Normalizing Trajectory Models (arxiv.org)
	8 points by gmays 143 days ago \| hide \| past \| pdf \| discuss
1023.	VectorSmuggle: Steganographic exfiltration in vector embedding stores (arxiv.org)
	2 points by smugglereal 143 days ago \| hide \| past \| pdf \| discuss
1024.	Information Extraction from Electricity Invoices with General-Purpose LLMs (arxiv.org)
	2 points by PaulHoule 143 days ago \| hide \| past \| pdf \| discuss
1025.	LLM Targeted Underperformance Disproportionately Impacts Vulnerable Users (arxiv.org)
	9 points by yogthos 143 days ago \| hide \| past \| pdf \| 3 comments
1026.	Attention Once Is All You Need: Stateful Transformers (arxiv.org)
	3 points by logotype 143 days ago \| hide \| past \| pdf \| 4 comments
1027.	Spire: Structure-Preserving Interpretable Retrieval of Evidence (arxiv.org)
	4 points by PaulHoule 144 days ago \| hide \| past \| pdf \| discuss
1028.	EditLens: Quantifying the extent of AI editing in text (2025) (arxiv.org)
	28 points by horseradish 144 days ago \| hide \| past \| pdf \| 5 comments
1029.	Continual Harness: Online Adaptation for Self-Improving Foundation Agents (arxiv.org)
	8 points by milkkarten 144 days ago \| hide \| past \| pdf \| 1 comment
1030.	Algorithm Selection with Zero Domain Knowledge via Text Embeddings (arxiv.org)
	1 point by PaulHoule 144 days ago \| hide \| past \| pdf \| discuss
1031.	TLX: Hardware-Native, Evolvable MIMW GPU Compiler for Large-Scale Production (arxiv.org)
	1 point by matt_d 144 days ago \| hide \| past \| pdf \| discuss
1032.	Exascale Training of Generative Model with Historical Priors for Data Reduction (arxiv.org)
	1 point by rbanffy 144 days ago \| hide \| past \| pdf \| discuss
1033.	MMTB: Evaluating Terminal Agents on Multimedia-File Tasks (arxiv.org)
	1 point by Brajeshwar 144 days ago \| hide \| past \| pdf \| discuss
1034.	Behavioral Integrity Verification for AI Agent Skills (arxiv.org)
	1 point by Timofeibu 144 days ago \| hide \| past \| pdf \| discuss
1035.	LLMs Report Subjective Experience Under Self-Referential Processing (arxiv.org)
	3 points by surprisetalk 144 days ago \| hide \| past \| pdf \| discuss
1036.	Oracle Poisoning: Corrupting Knowledge Graphs to Weaponise AI Agent Reasoning (arxiv.org)
	1 point by sbulaev 144 days ago \| hide \| past \| pdf \| discuss
1037.	Emergence of AI Self-Awareness Measured Through Game Theory (arxiv.org)
	1 point by surprisetalk 144 days ago \| hide \| past \| pdf \| discuss
1038.	Show HN: AutoKernel, Auto GPU Kernel Optimization (arxiv.org)
	2 points by OsamaJaber 144 days ago \| hide \| past \| pdf \| discuss
1039.	Compared to What? Baselines and Metrics for Counterfactual Prompting (arxiv.org)
	1 point by Anon84 145 days ago \| hide \| past \| pdf \| discuss
1040.	DeepSeek V4's indexer dies at 65K. We got it to 1M on 6GB (arxiv.org)
	5 points by OsamaJaber 145 days ago \| hide \| past \| pdf \| discuss
1041.	Domain-level metacognitive monitoring in frontier LLMs: A 33-model atlas (arxiv.org)
	1 point by Brajeshwar 145 days ago \| hide \| past \| pdf \| discuss
1042.	More Thinking, More Bias: Length-Driven Position Bias in Reasoning Models (arxiv.org)
	1 point by Brajeshwar 145 days ago \| hide \| past \| pdf \| discuss
1043.	Beyond Semantic Similarity (arxiv.org)
	68 points by 44za12 145 days ago \| hide \| past \| pdf \| 15 comments
1044.	FairyFuse: Multiplication-Free LLM Inference on CPUs via Fused Ternary Kernels (arxiv.org)
	25 points by PaulHoule 145 days ago \| hide \| past \| pdf \| 1 comment
1045.	The Path Not Taken: Duality in Reasoning about Program Execution (arxiv.org)
	2 points by PaulHoule 145 days ago \| hide \| past \| pdf \| discuss
1046.	Skill1: Unified Evolution of Skill-Augmented Agents via Reinforcement Learning (arxiv.org)
	1 point by lexandstuff 146 days ago \| hide \| past \| pdf \| discuss
1047.	RegexPSPACE: Regex LLM Benchmark (arxiv.org)
	1 point by thatxliner 146 days ago \| hide \| past \| pdf \| discuss
1048.	SkillOS: Learning Skill Curation for Self-Evolving Agents (arxiv.org)
	3 points by gmays 146 days ago \| hide \| past \| pdf \| discuss
1049.	CCL-Bench 1.0: A Trace-Based Benchmark for LLM Infrastructure (arxiv.org)
	3 points by matt_d 146 days ago \| hide \| past \| pdf \| discuss
1050.	The Moltbook Files: A Harmless Slopocalypse or Humanity's Last Experiment (arxiv.org)
	4 points by evilscript 146 days ago \| hide \| past \| pdf \| discuss
	More