ML Newsnew | past | best | rss | submit about
Stories from August 22, 2026 (UTC)
Go back a day, month, or year. Go forward a day.
1. A Year in LLM Serving: Workload Evolution, Caching and Load-Balancing (arxiv.org)
4 points by 1a1a11a 43 days ago | hide | past | pdf | discuss
2. FreeToken: Efficient Edge-Native Moe Serving with Bandwidth-Adaptive Execution (arxiv.org)
3 points by theanonymousone 43 days ago | hide | past | pdf | discuss
3. Intelligence per Watt: Measuring Intelligence Efficiency of Local AI (arxiv.org)
3 points by helsinkiandrew 43 days ago | hide | past | pdf | discuss
4. Improving matrix multiplication exponent w. modern optimization and AlphaEvolve (arxiv.org)
2 points by theanonymousone 43 days ago | hide | past | pdf | discuss
5. BDH-CQ: In-Context Learning with Recurrent Latent Reasoning (arxiv.org)
2 points by flaburgan 43 days ago | hide | past | pdf | discuss
6. The Fragility of Self-Improving Agents: Variance, Task Order (arxiv.org)
1 point by jdcaballerov 42 days ago | hide | past | pdf | discuss
7. EnvHarness: Awakening Static Worlds for Agent Learning (arxiv.org)
1 point by Alephinitesimal 43 days ago | hide | past | pdf | discuss
8. EchoCoT: Extracting Hidden Chain-of-Thought from Large Reasoning Models (arxiv.org)
1 point by sbulaev 43 days ago | hide | past | pdf | discuss
9. Towards Physics of Multimodal Pretraining (arxiv.org)
1 point by gmays 43 days ago | hide | past | pdf | discuss
About | RSS | RSS (all) | HN arXiv