New Links | ML News

ML Newsnew | past | best | rss | submit

991.	Positive Alignment: Artificial Intelligence for Human Flourishing (arxiv.org)
	1 point by lexandstuff 137 days ago \| hide \| past \| pdf \| discuss
992.	Customizing an LLM for Enterprise Software Engineering (arxiv.org)
	1 point by azhenley 138 days ago \| hide \| past \| pdf \| discuss
993.	Optimize_anything: A Universal API for Optimizing Any Text Parameter (arxiv.org)
	4 points by LakshyAAAgrawal 138 days ago \| hide \| past \| pdf \| 1 comment
994.	Direction-Preserving Number Representations (arxiv.org)
	1 point by matt_d 138 days ago \| hide \| past \| pdf \| discuss
995.	LLMs can answer multiple choice questions by only seeing the answers (arxiv.org)
	3 points by rbanffy 138 days ago \| hide \| past \| pdf \| 1 comment
996.	Understanding, Analyzing, and Optimizing Agentic AI: A CPU-Centric Perspective (arxiv.org)
	2 points by matt_d 138 days ago \| hide \| past \| pdf \| discuss
997.	Agent Bazaar: Enabling Economic Alignment in Multi-Agent Marketplaces (arxiv.org)
	3 points by milkkarten 138 days ago \| hide \| past \| pdf \| 1 comment
998.	ICRA: We Turned iPhones into Spatial Data Capture Rigs (arxiv.org)
	2 points by satpal 138 days ago \| hide \| past \| pdf \| discuss
999.	Darwin Family: MRI-Trust-Weighted Evolutionary Merging (arxiv.org)
	2 points by cheuv 138 days ago \| hide \| past \| pdf \| discuss
1000.	People who use ChatGPT for writing are accurate detectors of AI text (2025) (arxiv.org)
	3 points by lexandstuff 139 days ago \| hide \| past \| pdf \| discuss
1001.	Alignment pretraining: AI discourse creates self-fulfilling (mis)alignment (arxiv.org)
	81 points by anigbrowl 139 days ago \| hide \| past \| pdf \| 30 comments
1002.	AI-Mediated Communication Can Steer Collective Opinion (arxiv.org)
	2 points by sbulaev 139 days ago \| hide \| past \| pdf \| discuss
1003.	One Pass Is Not Enough: Recursive Latent Refinement for Generative Models (arxiv.org)
	3 points by selimonder 139 days ago \| hide \| past \| pdf \| discuss
1004.	UGen: An Agentic Framework for Generating Microarchitectural Attack PoCs (arxiv.org)
	2 points by Timofeibu 139 days ago \| hide \| past \| pdf \| discuss
1005.	Asymmetric Flow Models (arxiv.org)
	3 points by yorwba 139 days ago \| hide \| past \| pdf \| discuss
1006.	Grounding AI shopping agents using personas learned from raw clickstream data (arxiv.org)
	2 points by memoriesdotzip 140 days ago \| hide \| past \| pdf \| 1 comment
1007.	Self-Distillation Enables Continual Learning [pdf] (arxiv.org)
	109 points by teleforce 141 days ago \| hide \| past \| pdf \| 26 comments
1008.	Distance Marching for Generative Modeling (arxiv.org)
	1 point by E-Reverance 141 days ago \| hide \| past \| pdf \| discuss
1009.	Ada-MK: Adaptive MegaKernel Optimization via DAG-Based Search for LLM Inference (arxiv.org)
	1 point by matt_d 141 days ago \| hide \| past \| pdf \| discuss
1010.	FutureSim: Replaying World Events to Evaluate Adaptive Agents (arxiv.org)
	2 points by famouswaffles 141 days ago \| hide \| past \| pdf \| discuss
1011.	Agent Behavioral Contracts (arxiv.org)
	1 point by reiter 141 days ago \| hide \| past \| pdf \| discuss
1012.	A Single Neuron Is Sufficient to Bypass Safety Alignment in LLMs (arxiv.org)
	3 points by stared 141 days ago \| hide \| past \| pdf \| discuss
1013.	δ-mem: Efficient Online Memory for Large Language Models (arxiv.org)
	240 points by 44za12 141 days ago \| hide \| past \| pdf \| 60 comments
1014.	ExploitGym: Can AI agents turn bugs into exploits? (arxiv.org)
	3 points by p_stuart82 142 days ago \| hide \| past \| pdf \| discuss
1015.	Demystifying the Silence of Correctness Bugs in PyTorch Compiler (arxiv.org)
	3 points by matt_d 142 days ago \| hide \| past \| pdf \| discuss
1016.	Negation Neglect: When models fail to learn negations in training (arxiv.org)
	3 points by Timofeibu 142 days ago \| hide \| past \| pdf \| discuss
1017.	AI Agents Modulate Their Language When Framed as Being Watched (arxiv.org)
	2 points by vinicius-covas 142 days ago \| hide \| past \| pdf \| discuss
1018.	Qwen-Image-2.0 Technical Report (arxiv.org)
	2 points by gmays 142 days ago \| hide \| past \| pdf \| discuss
1019.	Known by Their Actions: Fingerprinting LLM Browser Agents via UI Traces (arxiv.org)
	3 points by sbulaev 142 days ago \| hide \| past \| pdf \| 1 comment
1020.	Systematically Auditing AI Agent Benchmarks with BenchJack (arxiv.org)
	1 point by matt_d 142 days ago \| hide \| past \| pdf \| discuss
	More