New Links | ML News

ML Newsnew | past | best | rss | submit

871.	OPRD: On-Policy Representation Distillation (arxiv.org)
	2 points by berlianta 121 days ago \| hide \| past \| pdf \| discuss
872.	Constrained Adaptive Rejection Sampling (arxiv.org)
	3 points by matt_d 122 days ago \| hide \| past \| pdf \| discuss
873.	Do transformers need three projections? Systematic study of QKV variants (arxiv.org)
	225 points by Anon84 122 days ago \| hide \| past \| pdf \| 47 comments
874.	Latent Agents: A Post-Training Procedure for Internalized Multi-Agent Debate (arxiv.org)
	29 points by PaulHoule 122 days ago \| hide \| past \| pdf \| 1 comment
875.	Consciousness in AI: Insights from the Science of Consciousness (2023) (arxiv.org)
	4 points by i5heu 122 days ago \| hide \| past \| pdf \| 1 comment
876.	AutoLab: Can Frontier Models Solve Long-Horizon Auto Research Engineering Tasks? (arxiv.org)
	2 points by Anon84 122 days ago \| hide \| past \| pdf \| discuss
877.	Mellum2 Technical Report (arxiv.org)
	2 points by gmays 122 days ago \| hide \| past \| pdf \| discuss
878.	Simulation Theology: A Testable Framework for AI Alignment (arxiv.org)
	3 points by allangrant 122 days ago \| hide \| past \| pdf \| discuss
879.	LLM memory systems benchmark: high recall near-zero precision for tested systems (arxiv.org)
	4 points by decorner 122 days ago \| hide \| past \| pdf \| discuss
880.	Your AI Text is not Mine (arxiv.org)
	3 points by berlianta 122 days ago \| hide \| past \| pdf \| discuss
881.	Arithmetic Pedagogy for Language Models (arxiv.org)
	1 point by berlianta 122 days ago \| hide \| past \| pdf \| discuss
882.	Same Weights, Different Robot: A Deployment Safety View of VLA Policies (arxiv.org)
	1 point by sbulaev 122 days ago \| hide \| past \| pdf \| discuss
883.	Forge: Multi-Agent Graduated Exploitation and Detection Engineering (arxiv.org)
	1 point by sbulaev 122 days ago \| hide \| past \| pdf \| discuss
884.	Large AI Models in Dental Healthcare (arxiv.org)
	1 point by berlianta 122 days ago \| hide \| past \| pdf \| discuss
885.	A Primer in Post-Training Reasoning Data: What We Know About How It Works (arxiv.org)
	2 points by Anon84 122 days ago \| hide \| past \| pdf \| discuss
886.	AI Agents Enable Adaptive Computer Worms (arxiv.org)
	6 points by rbanffy 123 days ago \| hide \| past \| pdf \| 1 comment
887.	Can LLMs Reason Structurally? Benchmarking via the Lens of Data Structures (arxiv.org)
	2 points by matt_d 123 days ago \| hide \| past \| pdf \| discuss
888.	Aura: Action-Gated Memory for Robot Policies at Constant VRAM (arxiv.org)
	3 points by josefchen 123 days ago \| hide \| past \| pdf \| discuss
889.	ChartNet: A High-Quality Multimodal Dataset for Robust Chart Understanding (arxiv.org)
	5 points by droidjj 123 days ago \| hide \| past \| pdf \| discuss
890.	DMF: A Deterministic Memory Framework for Conversational AI Agents (arxiv.org)
	5 points by matstech 123 days ago \| hide \| past \| pdf \| 1 comment
891.	AI Agents Enable Adaptive Computer Worms (arxiv.org)
	6 points by droidjj 123 days ago \| hide \| past \| pdf \| discuss
892.	GPU Forecasters: Language Models as Selective Surrogates for Kernel Optimization (arxiv.org)
	1 point by matt_d 123 days ago \| hide \| past \| pdf \| discuss
893.	Benchmarking LLM-as-a-Judge for Long-Form Output Evaluation (arxiv.org)
	1 point by berlianta 123 days ago \| hide \| past \| pdf \| discuss
894.	Type-Error Ablation and AI Coding Agents (arxiv.org)
	1 point by matt_d 123 days ago \| hide \| past \| pdf \| discuss
895.	The Architecture of Errors (arxiv.org)
	4 points by sibmike 124 days ago \| hide \| past \| pdf \| discuss
896.	Spikes in LLMs Are Bias Vectors: Spike-Free Quantization (arxiv.org)
	4 points by sbulaev 124 days ago \| hide \| past \| pdf \| discuss
897.	Forget Attention: Importance-Aware Attention Is All You Need (arxiv.org)
	3 points by sbulaev 124 days ago \| hide \| past \| pdf \| discuss
898.	Lattice Deduction Transformers (arxiv.org)
	4 points by 44za12 124 days ago \| hide \| past \| pdf \| discuss
899.	O-POPE: High-Frequency Pipelined Outer Product based GEMM acceleration (arxiv.org)
	2 points by matt_d 124 days ago \| hide \| past \| pdf \| discuss
900.	Why are audio front ends still optimized for CPUs? (MelT) (arxiv.org)
	2 points by augustocamargo 124 days ago \| hide \| past \| pdf \| discuss
	More