about
Stories from March 20, 2025 (UTC)
Go back a day, month, or year. Go forward a day.
1. Measuring AI Ability to Complete Long Tasks (arxiv.org)
5 points by mellosouls on Mar 20, 2025 | hide | past | pdf | discuss
2. Aardvark weather: end-to-end data-driven weather forecasting (arxiv.org)
2 points by cyberlimerence on Mar 20, 2025 | hide | past | pdf | discuss
3. Tapered Off-Policy Reinforce: Stable and Efficient RL for LLMs (arxiv.org)
2 points by pama on Mar 20, 2025 | hide | past | pdf | discuss
4. Empowering LLMs for Time Series Forecasting with Temporal Patterns and Semantics (arxiv.org)
1 point by PaulHoule on Mar 20, 2025 | hide | past | pdf | discuss
5. Why Do Multi-Agent LLM Systems Fail? (arxiv.org)
1 point by amrrs on Mar 20, 2025 | hide | past | pdf | discuss
6. WinClick: GUI Grounding with Multimodal Large Language Models (arxiv.org)
1 point by PaulHoule on Mar 20, 2025 | hide | past | pdf | discuss
7. An Inference and Training Framework for WiFi-Based Human Activity Recognition (arxiv.org)
1 point by PaulHoule on Mar 20, 2025 | hide | past | pdf | discuss