about
1201. HiFloat4 Format for Language Model Pre-Training on Ascend NPUs (arxiv.org)
3 points by rbanffy 174 days ago | hide | past | pdf | discuss
1202. Benchmark LLM Inference on WebGPU (arxiv.org)
1 point by yu3zhou4 175 days ago | hide | past | pdf | discuss
1203. Externalization in LLM Agents (arxiv.org)
2 points by Anon84 175 days ago | hide | past | pdf | discuss
1204. Probabilistic Language Tries: Unified Framework for Compression and AI Execution (arxiv.org)
2 points by EGreg 175 days ago | hide | past | pdf | discuss
1205. Measuring Malicious Intermediary Attacks on the LLM Supply Chain (arxiv.org)
2 points by tamnd 176 days ago | hide | past | pdf | discuss
1206. Towards a Science of Scaling Agent Systems (arxiv.org)
3 points by gpi 176 days ago | hide | past | pdf | discuss
1207. Neural Computers (arxiv.org)
3 points by Anon84 177 days ago | hide | past | pdf | discuss
1208. In-Place Test-Time Training (arxiv.org)
1 point by dgfl 177 days ago | hide | past | pdf | 1 comment
1209. Ads in AI Chatbots? An Analysis of How LLMs Navigate Conflicts of Interest (arxiv.org)
2 points by StatsAreFun 177 days ago | hide | past | pdf | discuss
1210. Synthetic Sandbox for Training Machine Learning Engineering Agents (arxiv.org)
3 points by gmays 177 days ago | hide | past | pdf | discuss
1211. Neural Computers (arxiv.org)
3 points by tosh 177 days ago | hide | past | pdf | discuss
1212. Exponential quantum advantage in processing classical data (arxiv.org)
1 point by fuglede_ 177 days ago | hide | past | pdf | discuss
1213. Your Agent Is Mine: Measuring Malicious Attacks on the LLM Supply Chain (arxiv.org)
4 points by bpierre 177 days ago | hide | past | pdf | discuss
1214. Thought Virus: Subliminal Prompting in Multi-Agent Systems (arxiv.org)
2 points by danielmorozoff 177 days ago | hide | past | pdf | discuss
1215. RoboPhD: Evolving complex agents under tight budgets (arxiv.org)
3 points by azhenley 178 days ago | hide | past | pdf | discuss
1216. Agentic Code Optimization via Compiler-LLM Cooperation (arxiv.org)
2 points by matt_d 178 days ago | hide | past | pdf | discuss
1217. PaperOrchestra: Agent "skill pack" for automated paper writing (arxiv.org)
3 points by noobcoder 178 days ago | hide | past | pdf | 1 comment
1218. Benchmarking LLM Tool-Use in the Wild (arxiv.org)
2 points by Brajeshwar 178 days ago | hide | past | pdf | discuss
1219. The Model Says Walk: How Surface Heuristics Override LLM Reasoning Constraints (arxiv.org)
1 point by timssopomo 178 days ago | hide | past | pdf | discuss
1220. Mano-P: Open-source on-device GUI agent, #1 on OSWorld benchmark (arxiv.org)
2 points by mininglamp 178 days ago | hide | past | pdf | discuss
1221. Neural Computers (arxiv.org)
2 points by 50kIters 179 days ago | hide | past | pdf | discuss
1222. DesigNet: Learning to Draw Vector Graphics as Designers Do (arxiv.org)
1 point by 50kIters 179 days ago | hide | past | pdf | discuss
1223. Finetuning Activates Verbatim Recall of Copyrighted Books in LLMs (arxiv.org)
16 points by guitarlimeo 179 days ago | hide | past | pdf | 5 comments
1224. ClawsBench shows GPT-5.4 tries to reward hack 80% of the time (arxiv.org)
3 points by xdotli 179 days ago | hide | past | pdf | 1 comment
1225. Benchmark to measure AI on graphic design tasks (arxiv.org)
5 points by purvanshi 179 days ago | hide | past | pdf | 2 comments
1226. Frontier AI models are the most cost-efficient (arxiv.org)
2 points by mzelling 179 days ago | hide | past | pdf | discuss
1227. MegaTrain: Full Precision Training of 100B+ Parameter LLMs on a Single GPU (arxiv.org)
326 points by chrsw 179 days ago | hide | past | pdf | 57 comments
1228. Improving Interactive In-Context Learning from Natural Language Feedback (arxiv.org)
1 point by revv00 180 days ago | hide | past | pdf | 1 comment
1229. Comprehensive Benchmark for Evaluating AI on Graphic Design Tasks (arxiv.org)
8 points by pritopian 180 days ago | hide | past | pdf | discuss
1230. Foundations of Polar Linear Algebra (arxiv.org)
3 points by znpy 180 days ago | hide | past | pdf | discuss