New Links | ML News

ML Newsnew | past | best | rss | submit

2221.	Who Said Neural Networks Aren't Linear? (arxiv.org)
	2 points by ComplexSystems 356 days ago \| hide \| past \| pdf \| discuss
2222.	Are Foundation Models Ready for Industrial Defect Recognition? A Reality Check (arxiv.org)
	5 points by PaulHoule 356 days ago \| hide \| past \| pdf \| discuss
2223.	Agentic Context Engineering: Evolving Contexts for Self-Improving LLMs (arxiv.org)
	2 points by mooreds 357 days ago \| hide \| past \| pdf \| discuss
2224.	From Automation to Autonomy (arxiv.org)
	2 points by jruohonen 357 days ago \| hide \| past \| pdf \| 1 comment
2225.	AutoPR: Let's Automate Your Academic Promotion [pdf] (arxiv.org)
	2 points by SerCe 357 days ago \| hide \| past \| pdf \| 1 comment
2226.	StreamingVLM: Real-Time Understanding for Infinite Video Streams (arxiv.org)
	33 points by badmonster 357 days ago \| hide \| past \| pdf \| discuss
2227.	Mano: Multi-Modal Foundation Model and 3-Stage RL for SOTA GUI Automation (arxiv.org)
	2 points by jinqueeny 357 days ago \| hide \| past \| pdf \| discuss
2228.	Stronger Adaptive Attacks Bypass Defenses Against LLM Jailbreaks (arxiv.org)
	2 points by belter 357 days ago \| hide \| past \| pdf \| discuss
2229.	ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memory (arxiv.org)
	1 point by SweetSoftPillow 357 days ago \| hide \| past \| pdf \| discuss
2230.	LoCaL: Countering Surface Bias in Code Evaluation Metrics (arxiv.org)
	1 point by PaulHoule 358 days ago \| hide \| past \| pdf \| discuss
2231.	Barbarians at the Gate: How AI Is Upending Systems Research (arxiv.org)
	3 points by r4um 358 days ago \| hide \| past \| pdf \| discuss
2232.	LLMs Privacy Is Not Just Memorization (arxiv.org)
	1 point by oldfuture 358 days ago \| hide \| past \| pdf \| discuss
2233.	ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memory (arxiv.org)
	1 point by jonbaer 358 days ago \| hide \| past \| pdf \| discuss
2234.	Agent Learning via Early Experience (arxiv.org)
	1 point by jonbaer 358 days ago \| hide \| past \| pdf \| discuss
2235.	Google researchers introduce "ReasoningBank" AI agent reinforcement learning (arxiv.org)
	1 point by thorslilcuz 359 days ago \| hide \| past \| pdf \| discuss
2236.	Airbnb: Agent-in-the-Loop: Data Flywheel for LLM-Based Customer Support (arxiv.org)
	2 points by jamesblonde 359 days ago \| hide \| past \| pdf \| discuss
2237.	Agentic Context Engineering: Evolving Contexts for SelfImproving Language Models (arxiv.org)
	2 points by JnBrymn 359 days ago \| hide \| past \| pdf \| discuss
2238.	Paper2video: Automatic video generation from scientific papers (arxiv.org)
	91 points by jinqueeny 359 days ago \| hide \| past \| pdf \| 24 comments
2239.	Moloch's Bargain: Troubling emergent behavior in LLM (arxiv.org)
	2 points by ankit_mishra 359 days ago \| hide \| past \| pdf \| discuss
2240.	Large Language Models and Gambling Addiction (arxiv.org)
	3 points by jonbaer 360 days ago \| hide \| past \| pdf \| 1 comment
2241.	StreamTensor: Make Tensors Stream in Dataflow Accelerators for LLMs (arxiv.org)
	1 point by matt_d 360 days ago \| hide \| past \| pdf \| discuss
2242.	Impolite LLM prompts consistently outperform polite ones (arxiv.org)
	5 points by delichon 360 days ago \| hide \| past \| pdf \| 2 comments
2243.	Less is More: An LLM that outscores Claude Sonnet 4 while being 50.000x smaller (arxiv.org)
	5 points by llosio 360 days ago \| hide \| past \| pdf \| 1 comment
2244.	Moloch's Bargain: Emergent misalignment when LLMs compete for audiences (arxiv.org)
	2 points by felineflock 360 days ago \| hide \| past \| pdf \| discuss
2245.	LLMs Reproduce Human Purchase Intent via Semantic Similarity (arxiv.org)
	2 points by anavette 360 days ago \| hide \| past \| pdf \| 1 comment
2246.	New paper: A single character can make or break your LLM evals (arxiv.org)
	1 point by mark_yellow 361 days ago \| hide \| past \| pdf \| 1 comment
2247.	H1: Bootstrapping LLMs to Reason over Longer Horizons via Reinforcement Learning (arxiv.org)
	2 points by saynotocoffee 361 days ago \| hide \| past \| pdf \| discuss
2248.	Truth-Aware Decoding: Program Logic for Factual LMs (arxiv.org)
	2 points by HenryAI 361 days ago \| hide \| past \| pdf \| 1 comment
2249.	The Missing Link Between the Transformer and Models of the Brain (arxiv.org)
	4 points by Labo333 361 days ago \| hide \| past \| pdf \| 1 comment
2250.	Reasoning LLMs are wandering solution explorers (arxiv.org)
	90 points by Surreal4434 361 days ago \| hide \| past \| pdf \| 98 comments
	More