Stefano Ermon
PulseAugur coverage of Stefano Ermon — every cluster mentioning Stefano Ermon across labs, papers, and developer communities, ranked by signal.
2 day(s) with sentiment data
-
Autoregressive vs. Diffusion Models: AI Writing Approaches Compared
Two distinct approaches to AI text generation are autoregressive models and diffusion models. Autoregressive models generate text token by token, with each new token depending on the preceding ones, making them suitable…
-
Inception's Mercury 3 diffusion model claims 1000+ tokens/sec speed, challenging LLM leaders
Inception has launched Mercury 3, a diffusion-based language model that claims to achieve 1,068 tokens per second, significantly faster than traditional transformer models. The company states Mercury 3 matches or surpas…
-
Generative cloning policies struggle with multimodal expert behavior
Researchers have investigated the challenges of generative behavioral cloning when expert actions are multimodal, meaning a single observation can lead to multiple valid actions. Their work reveals that latent-variable …
-
Stat/Prob ML Researchers Seek New Venues Amid LLM Dominance in Top Conferences
A researcher in statistical and probabilistic machine learning is observing a significant shift in top-tier ML conferences, with LLM-based works and agentic approaches dominating poster sessions and workshops. This tren…