Retrieval-Augmented Generation (RAG) integrates external knowledge to enhance Large Language Models (LLMs), yet systems remain susceptible to two critical flaws: providing correct answers without expl...

A common take I’ve been hearing is: “LLMs are especially good at math because math is easy to verify”. But that story doesn’t make much sense.…

A living survey of benchmarks that compare large language models with humans.

...or how to make Qwen learn query optimization via agentic reinforcement learning

The proof of a decades-old conjecture has given researchers a new way to understand complex networks.

Multi-agent reinforcement learning (MARL) has exploded in popularity in recent years. While numerous approaches have been developed, they can be broadly categorized into three main types: centralized ...

What must a neural system be capable of to implement language? Current research annotates stimuli with linguistic variables and tests which electrodes, voxels, or language-model layers predict neural ...

Our CI job volume increased 25x over 6 months. We patched our test selection service three times before finding a sustainable solution.

We study a novel language model architecture that is capable of scaling test-time computation by implicitly reasoning in latent space. Our model works by iterating a recurrent block, thereby unrolling...

This is in response to Ben Thompson’s recent piece where he said distillation is happening during RL and becoming more important to model performance.

There remains no chatbot arena for robotics

Neural networks often learn task-specific latent representations that fail to generalize to novel settings or tasks. Conversely, humans learn discrete representations (i.e., concepts or words) at a va...

Geotagged Twitter data allows us to investigate correlations of geographic language variation, both at an interlingual and intralingual level. Based on data-driven studies of such relationships, this…

Bioplastics derived from biomass show promise as sustainable alternatives to petrochemical plastics, but their adoption is hindered by their inferior mechanical properties and processability. Here, th...

Empirical conclusions depend not only on data but on analytic decisions made throughout the research process. Many-analyst studies have quantified this dependence: independent teams testing the same h...

Join the discussion on this paper page