New Links | ML News

ML Newsnew | past | best | rss | submit

391.	Adversarial Creation and Detection of AI-Generated Social Bot Content (arxiv.org)
	1 point by Anon84 49 days ago \| hide \| past \| pdf \| discuss
392.	Agentic Reasoning for Large Language Models (arxiv.org)
	1 point by Anon84 50 days ago \| hide \| past \| pdf \| discuss
393.	The Embedder's Dilemma: LLMs Are Better, but at What Cost? (arxiv.org)
	3 points by sbulaev 50 days ago \| hide \| past \| pdf \| discuss
394.	Towards a Risk Assessment of Malicious Skill Files in Coding Agents (arxiv.org)
	5 points by Beko2210 50 days ago \| hide \| past \| pdf \| discuss
395.	CAKE: Compiler-Agent Co-Design for Frontier Kernel Evolution (arxiv.org)
	8 points by matt_d 50 days ago \| hide \| past \| pdf \| discuss
396.	A Contract-Grade Verifier for LLM-Generated GPU Kernels (arxiv.org)
	46 points by Jimmc414 50 days ago \| hide \| past \| pdf \| discuss
397.	V-RAE: Rethinking Video Latent Spaces for Generation (arxiv.org)
	3 points by selimonder 50 days ago \| hide \| past \| pdf \| discuss
398.	Hypothetical Document Embeddings (arxiv.org)
	3 points by kaycebasques 50 days ago \| hide \| past \| pdf \| discuss
399.	Adversarial Paraphrasing: Attack for Humanizing AI-Generated Text (2025) (arxiv.org)
	2 points by 0x_rs 50 days ago \| hide \| past \| pdf \| discuss
400.	Reasoning Jury: Multi-Model Consensus for Evaluating Reasoning Traces (arxiv.org)
	2 points by sonabinu 50 days ago \| hide \| past \| pdf \| discuss
401.	We tested every venue in 2 Bali regions against 4 AI assistants (arxiv.org)
	2 points by fspunch 50 days ago \| hide \| past \| pdf \| discuss
402.	StoryScope: Investigating Idiosyncrasies in AI Fiction (arxiv.org)
	1 point by dgellow 51 days ago \| hide \| past \| pdf \| discuss
403.	A Probe Direction Is a Property of Its Prompt (arxiv.org)
	1 point by sbulaev 51 days ago \| hide \| past \| pdf \| discuss
404.	Agent Safety Should Be a Runtime Contract (arxiv.org)
	1 point by sbulaev 51 days ago \| hide \| past \| pdf \| discuss
405.	Why Does Claude.md Keep Growing? Catastrophic Remembering in Agentic Coding (arxiv.org)
	1 point by oskrim 51 days ago \| hide \| past \| pdf \| 1 comment
406.	Spec Sheets Are Not Kernels: INT8 Availability on Nvidia Blackwell Ultra (arxiv.org)
	2 points by Jimmc414 51 days ago \| hide \| past \| pdf \| discuss
407.	From Weak Cues to Real Identities: Evaluating Inference-Driven De-Anonymization (arxiv.org)
	1 point by mhrsntrk 51 days ago \| hide \| past \| pdf \| discuss
408.	Information Abundance Paradox: Long-Context Training Undermines Parametric (arxiv.org)
	2 points by sbulaev 52 days ago \| hide \| past \| pdf \| discuss
409.	AI Agents Enable Adaptive Computer Worms (arxiv.org)
	4 points by reasonableklout 52 days ago \| hide \| past \| pdf \| discuss
410.	Stealing Reasoning Traces from Proprietary LLM APIs [pdf] (arxiv.org)
	1 point by j1436go 52 days ago \| hide \| past \| pdf \| discuss
411.	The Wording Effect: Quantifying Two-Way Drift in LLM Benchmark Performance (arxiv.org)
	1 point by sbulaev 52 days ago \| hide \| past \| pdf \| discuss
412.	The Measure of Intelligence (arxiv.org)
	1 point by andsoitis 52 days ago \| hide \| past \| pdf \| discuss
413.	Self-Evolving Coding Agents (arxiv.org)
	2 points by yruzin 52 days ago \| hide \| past \| pdf \| discuss
414.	Natural Language Processing Almost from Scratch (arxiv.org)
	2 points by Anon84 52 days ago \| hide \| past \| pdf \| discuss
415.	Stealing Reasoning Traces from Proprietary LLM APIs (arxiv.org)
	6 points by shikharbhardwaj 52 days ago \| hide \| past \| pdf \| discuss
416.	Base Models Look Human to AI Detectors (arxiv.org)
	2 points by ekaesmem 52 days ago \| hide \| past \| pdf \| discuss
417.	Why Does Claude.md Keep Growing? Catastrophic Remembering in Agentic Coding (arxiv.org)
	4 points by sbulaev 53 days ago \| hide \| past \| pdf \| discuss
418.	Measuring the Wrong Thing: Internal Harmfulness Scores Anti-Rank Successful (arxiv.org)
	2 points by sbulaev 53 days ago \| hide \| past \| pdf \| discuss
419.	SWE-Bench ProMax: Benchmarking Agents on Large-Scale Code Refactoring (arxiv.org)
	2 points by williamjinq 53 days ago \| hide \| past \| pdf \| discuss
420.	Stealing Reasoning Traces from Proprietary LLM APIs (arxiv.org)
	2 points by vismit2000 53 days ago \| hide \| past \| pdf \| discuss
	More