Mike Cook

mtrc.bsky.social

08 August 2025 10:40

I have to provide comment on the GPT 5 launch later today, so I'm forcing myself to watch the livestream, and I forgot that the vibe their PR/design team always goes for for the streams is "business/cult fusion"

Valeriy M., PhD, MBA, CQF

predict-addict.bsky.social

12 July 2025 14:37

The Myth of "XGBoost is All You Need" – And Why Evidence Says Otherwise Kaggle fairytales 🧚‍♀️ - “XGBoost is all you need” But reality—backed by large-scale benchmarks—tells a completely different story.

Kaiser Sun

kaiserwholearns.bsky.social

16 June 2025 12:05

What happens when an LLM is asked to use information that contradicts its knowledge? We explore knowledge conflict in a new preprint📑 TLDR: Performance drops, and this could affect the overall performance of LLMs in model-based evaluation.📑🧵⬇️ 1/8 #NLProc #LLM #AIResearch

Martin JJ. Bucher

mnbucher.bsky.social

05 June 2025 10:06

✨What if you could create and redesign scenes by just talking to them? **ReSpace: Text-Driven 3D Scene Synthesis and Editing with Preference Alignment** Add, remove, and swap objects simply via natural language, e.g., "add tufted dark gray sofa". (1/8)

Antoine Wehenkel

awehwe.bsky.social

05 June 2025 10:06

📣 New paper alert — To be presented at ICML 2025! arxiv.org/abs/2405.08719 What does it really mean for a simulator to be misspecified, if our goal is to estimate parameters with calibrated uncertainty? A 🧵on our new method, RoPE, and what it means for real-world SBI ⬇️