New Links | ML News

ML Newsnew | past | best | rss | submit

1351.	Generative Video Compression with One-Dimensional Latent Representation (arxiv.org)
	2 points by selimonder 202 days ago \| hide \| past \| pdf \| discuss
1352.	Kimi introduces Attention Residuals: 1.25x compute performance at <2% overhead (arxiv.org)
	9 points by nekofneko 202 days ago \| hide \| past \| pdf \| discuss
1353.	Flash-KMeans: Fast and Memory-Efficient Exact K-Means (arxiv.org)
	185 points by matt_d 202 days ago \| hide \| past \| pdf \| 14 comments
1354.	True 4-Bit Quantized CNN Training on CPU – 92.34% on Cifar-10 (arxiv.org)
	3 points by shivnathtathe 202 days ago \| hide \| past \| pdf \| 3 comments
1355.	Brain-Of: An Omnifunctional Foundation Model for fMRI, EEG and Meg (arxiv.org)
	2 points by PaulHoule 202 days ago \| hide \| past \| pdf \| discuss
1356.	LLM Agent Framework for Simulating Personalized User Tweeting Behavior (arxiv.org)
	1 point by PaulHoule 202 days ago \| hide \| past \| pdf \| discuss
1357.	Language model teams as distributed systems (arxiv.org)
	104 points by jryio 202 days ago \| hide \| past \| pdf \| 46 comments
1358.	Automated Test Case Generation for Vulnerabilities in Competitive Programming (arxiv.org)
	1 point by PaulHoule 202 days ago \| hide \| past \| pdf \| discuss
1359.	TDAD – Compiling Tool-Using Agents from Behavioral Specifications (arxiv.org)
	2 points by tzafrir 202 days ago \| hide \| past \| pdf \| 1 comment
1360.	Fine-Pruning: A Biologically Inspired Algorithm for Personalization of MLModels (arxiv.org)
	1 point by PaulHoule 202 days ago \| hide \| past \| pdf \| discuss
1361.	Multi-agent cooperation through in-context co-player inference (arxiv.org)
	1 point by simonpure 203 days ago \| hide \| past \| pdf \| discuss
1362.	Weak-Form Evolutionary Kolmogorov-Arnold Networks for Solving PDEs (arxiv.org)
	1 point by PaulHoule 203 days ago \| hide \| past \| pdf \| discuss
1363.	Invariant Risk Minimization (2020) (arxiv.org)
	2 points by gone35 204 days ago \| hide \| past \| pdf \| discuss
1364.	Can RL Improve Generalization of LLM Agents? An Empirical Study (arxiv.org)
	3 points by tsurg_dot_com 204 days ago \| hide \| past \| pdf \| 1 comment
1365.	Benchmarking Language Modeling for Lossless Compression of Full-Fidelity Audio (arxiv.org)
	3 points by ogurechny 205 days ago \| hide \| past \| pdf \| discuss
1366.	End-to-End Hardware-Driven Graph Preprocessing for Enhanced GNN Performance (arxiv.org)
	5 points by PaulHoule 205 days ago \| hide \| past \| pdf \| discuss
1367.	AutoHarness: Improving LLM agents by automatically synthesizing a code harness (arxiv.org)
	10 points by simonpure 205 days ago \| hide \| past \| pdf \| discuss
1368.	LDP: Identity-Aware Routing for Multi-Agent LLMs – 37% Less Tokens (arxiv.org)
	2 points by prakashsunil 205 days ago \| hide \| past \| pdf \| discuss
1369.	Lost in Backpropagation: The LM Head Is a Gradient Bottleneck (arxiv.org)
	4 points by famouswaffles 205 days ago \| hide \| past \| pdf \| discuss
1370.	When Models Examine Themselves: Vocabulary-Activation Correspondence (arxiv.org)
	1 point by tcbrah 205 days ago \| hide \| past \| pdf \| discuss
1371.	Private LLM Inference on Consumer Blackwell GPUs (arxiv.org)
	3 points by rohansood15 206 days ago \| hide \| past \| pdf \| discuss
1372.	Native CLI scaffolds consistently outper-form OpenCode when using the same model (arxiv.org)
	1 point by xdotli 206 days ago \| hide \| past \| pdf \| 1 comment
1373.	We Automated RL Environment Engineering for $10 (arxiv.org)
	2 points by milkkarten 206 days ago \| hide \| past \| pdf \| discuss
1374.	Whole-Brain Connectomic Graph Model Enables Whole-Body Locomotion Control in Fly (arxiv.org)
	2 points by sosodev 206 days ago \| hide \| past \| pdf \| discuss
1375.	Lost in the Middle at Birth: An Exact Theory of Transformer Context Bias (arxiv.org)
	2 points by borundev 207 days ago \| hide \| past \| pdf \| 2 comments
1376.	Surgical Repair of Collapsed Attention Heads in ALiBi Transformers (arxiv.org)
	3 points by palmerschallon 207 days ago \| hide \| past \| pdf \| 2 comments
1377.	OmniCode: A Benchmark for Evaluating Software Development Agents (arxiv.org)
	2 points by foma-roje 207 days ago \| hide \| past \| pdf \| discuss
1378.	The Token Games: Evaluating Language Model Reasoning with Puzzle Duels (arxiv.org)
	2 points by PaulHoule 207 days ago \| hide \| past \| pdf \| discuss
1379.	Covenant-72B: Pre-Training a 72B LLM with Trustless Peers Over-the-Internet (arxiv.org)
	5 points by bilsbie 208 days ago \| hide \| past \| pdf \| 2 comments
1380.	I designed a bfloat16/FP8 alternative in a week using LLMs (arxiv.org)
	3 points by k1832 208 days ago \| hide \| past \| pdf \| 4 comments
	More