New Links | ML News

ML Newsnew | past | best | rss | submit

1471.	Agents of Chaos (arxiv.org)
	3 points by wslh 222 days ago \| hide \| past \| pdf \| discuss
1472.	PersonaLive Expressive Portrait Image Animation for Live Streaming (arxiv.org)
	2 points by tamnd 223 days ago \| hide \| past \| pdf \| discuss
1473.	Sanity Checks for Sparse Autoencoders: Do SAEs Beat Random Baselines? (arxiv.org)
	2 points by yorwba 223 days ago \| hide \| past \| pdf \| discuss
1474.	Towards a Science of AI Agent Reliability (arxiv.org)
	2 points by smartmic 223 days ago \| hide \| past \| pdf \| discuss
1475.	Improving Chain-of-Thought Monitorability Through Information Theory (arxiv.org)
	1 point by simonpure 223 days ago \| hide \| past \| pdf \| discuss
1476.	The Landscape of Non-Equilibrium Memories with Neural Cellular Automata (arxiv.org)
	1 point by PaulHoule 223 days ago \| hide \| past \| pdf \| discuss
1477.	Fast and Optimal Mapping for Accelerator Modeling and Evaluation (arxiv.org)
	2 points by PaulHoule 223 days ago \| hide \| past \| pdf \| discuss
1478.	Agents of Chaos: Breaches of trust in autonomous LLM agents (arxiv.org)
	4 points by cool-RR 223 days ago \| hide \| past \| pdf \| 1 comment
1479.	Computer-Using World Model (arxiv.org)
	1 point by steamboatwillie 223 days ago \| hide \| past \| pdf \| discuss
1480.	VisPhyWorld: Probing Physical Reasoning via Code-Driven Video Reconstruction (arxiv.org)
	1 point by PaulHoule 223 days ago \| hide \| past \| pdf \| discuss
1481.	The Statistical Signature of LLMs (arxiv.org)
	1 point by bikenaga 224 days ago \| hide \| past \| pdf \| discuss
1482.	Towards Compressive and Scalable Recurrent Memory (arxiv.org)
	2 points by PaulHoule 224 days ago \| hide \| past \| pdf \| discuss
1483.	A Visual Document Benchmark for Scientific Retrieval and Question Answering (arxiv.org)
	2 points by bobvanluijt 224 days ago \| hide \| past \| pdf \| discuss
1484.	Unified Latents (UL): How to train your latents (arxiv.org)
	2 points by pama 224 days ago \| hide \| past \| pdf \| discuss
1485.	Who's in Charge? Disempowerment Patterns in Real-World LLM Usage (arxiv.org)
	2 points by Gillesray 224 days ago \| hide \| past \| pdf \| 1 comment
1486.	The Principles of Deep Learning Theory (2021) (arxiv.org)
	2 points by vinhnx 224 days ago \| hide \| past \| pdf \| discuss
1487.	HLE-Verified: A Verification and Revision of Humanity's Last Exam (arxiv.org)
	6 points by ravenical 224 days ago \| hide \| past \| pdf \| discuss
1488.	Realistic Adversarial Testing of Computer-Use Agents in Web-OS Environments (arxiv.org)
	2 points by yakkomajuri 224 days ago \| hide \| past \| pdf \| discuss
1489.	Large-scale online deanonymization with LLMs (including HN users) (arxiv.org)
	3 points by salkahfi 225 days ago \| hide \| past \| pdf \| 2 comments
1490.	Stress Tests Reveal Fragile Grounding in Video-Language Models (arxiv.org)
	2 points by PaulHoule 225 days ago \| hide \| past \| pdf \| discuss
1491.	Surprising Effectiveness of Masking Updates in Adaptive Optimizers (arxiv.org)
	2 points by energy123 225 days ago \| hide \| past \| pdf \| discuss
1492.	Ferret-UI Lite – Apple on-device end-to-end GUI agent (arxiv.org)
	1 point by twalichiewicz 225 days ago \| hide \| past \| pdf \| discuss
1493.	What Language Is This? Ask Your Tokenizer (arxiv.org)
	2 points by tigoo 225 days ago \| hide \| past \| pdf \| discuss
1494.	Interactive Tools for Gaussian Splat Selection with AI and Human in the Loop (arxiv.org)
	2 points by PaulHoule 225 days ago \| hide \| past \| pdf \| discuss
1495.	End-to-End Test-Time Training for Long Context (arxiv.org)
	3 points by handfuloflight 225 days ago \| hide \| past \| pdf \| discuss
1496.	Large-scale online deanonymization with LLMs (arxiv.org)
	1 point by paulpauper 226 days ago \| hide \| past \| pdf \| discuss
1497.	Task Specific Knowledge Graphs (arxiv.org)
	1 point by alansaber 226 days ago \| hide \| past \| pdf \| discuss
1498.	Biases in the Blind Spot: Detecting What LLMs Fail to Mention (arxiv.org)
	3 points by mpweiher 226 days ago \| hide \| past \| pdf \| discuss
1499.	Large Language Model Reasoning Failures (arxiv.org)
	40 points by T-A 226 days ago \| hide \| past \| pdf \| 82 comments
1500.	The Fundamental Limits of LLMs at Scale (arxiv.org)
	4 points by o4c 226 days ago \| hide \| past \| pdf \| discuss
	More