CMU researchers are presenting 143 papers at the Thirteenth International Conference on Learning Representations (ICLR 2025), held from April 24 - 28 at the Singapore EXPO. Here is a quick overview of...

Figure 1. Copilot Arena is a VSCode extension that collects human preferences of code directly from developers.  As model capabilities improve, large language models (LLMs) are increasingly integra...

The open-source AI models you can fine-tune, distill and deploy anywhere. Choose from our collection of models: Llama 4 Maverick and Llama 4 Scout.

Dissecting Adversarial Robustness of Multimodal LM Agents

#GenAIUCSD25

Figure 1: Training models to optimize test-time compute and learn "how to discover" correct responses, as opposed to the traditional learning paradigm of learning "what answer" to output. The major...

TL;DR: The brain may have evolved a modular architecture for daily tasks, with circuits featuring functionally specialized modules that match the task structure. We hypothesize that this architecture ...

TL;DR: LLM web agents are designed to predict a sequence of actions to complete a user-specified task. Most existing agents are built on top of general-purpose, proprietary models like GPT-4 and rely ...

Carnegie Mellon University is proud to present 194 papers at the 38th conference on Neural Information Processing Systems (NeurIPS 2024), held from December 10-15 at the Vancouver Convention Center. H...

Machine unlearning is a key requirement of many data protection regulations such as GDPR. Prior work on unlearning has mostly considered superficial unlearning tasks where a single or a few related pi...