Researcher Jindong Wang and Associate Professor Steven Euijong Whang explore the NeurIPS 2024 work ERBench. ERBench leverages relational databases to create LLM benchmarks that can verify model rationale via keywords in addition to checking answer correctness.
Next-token prediction trains a language model on all tokens in a sequence. VP Weizhu Chen discusses his team’s 2024 NeurIPS paper on how distinguishing between useful and “noisy” tokens in pretraining can improve token efficiency and model performance.
Can existing algorithms designed for simple reinforcement learning problems be used to solve more complex RL problems? Researcher Dylan Foster discusses the modular approach he and his coauthors explored in their 2024 NeurIPS paper on RL under latent dynamics.
Pranjal Chitale discusses the 2024 NeurIPS work CVQA. Spanning 31 languages and the cultures of 30 countries, this VQA benchmark was created with native speakers and cultural experts to evaluate model performance across diverse linguistic and cultural contexts.
When research manager Nicole Immorlica discovered she could use math to make the world a better place for people, she was all in. She discusses working in computer science theory and economics, including studying the impact of algorithms and AI on markets.
Research manager Karin Strauss and members of the DNA Data Storage Project reflect on the path to developing a synthetic DNA–based system for archival data storage, including the recent open-source release of its most powerful algorithm for DNA error correction.
The efficient simulation of molecules has the potential to change how the world understands biological systems and designs new drugs and biomaterials. Tong Wang discusses AI2BMD, an AI-based system designed to simulate large biomolecules with speed and accuracy.
Researcher Siddharth Suri and professor David Holtz give a brief history of prompt engineering, discuss the debate behind their recent collaboration, and share what they found from studying how people’s approaches to prompting change as models advance.
Researchers Chris Hawblitzel and Jay Lorch share how progress in programming languages and verification approaches are bringing bug-free software within reach. Their work on the Rust verification tool Verus won the Distinguished Artifact Award at SOSP ’24.
In their 2024 SOSP paper, researchers explore a common—though often undertested—software system issue: retry bugs. Research manager Shan Lu and PhD candidate Bogdan Stoica share how they’re combining traditional program analysis and LLMs to address the challenge.
Undergrad Angela Busheska has a passion for sustainability. She talks with researcher Vaishnavi Ranganathan about the why behind her drive, the work she did at Microsoft on a platform for tracking land use, and her advice for making the internship experience count.
The personalizable object recognizer Find My Things was recently recognized for accessible design. Researcher Daniela Massiceti and software development engineer Martin Grayson talk about the research project’s origins and the tech advances making it possible.
