papers

Publications (11)

cs.CL2026

Olmo 3

Team Olmo, :, Allyson Ettinger +66

We introduce Olmo 3, a family of state-of-the-art, fully-open language models at the 7B and 32B parameter scales. Olmo 3 model construction targets long-context reasoning, function…

cs.CL2026

PanCanBench: A Comprehensive Benchmark for Evaluating Large Language Models in Pancreatic Oncology

Yimin Zhao, Sheela R. Damle, Simone E. Dekker +13

Large language models (LLMs) have achieved expert-level performance on standardized examinations, yet multiple-choice accuracy poorly reflects real-world clinical utility and safet…

cs.AI2026

Spurious Rewards: Rethinking Training Signals in RLVR

Rulin Shao, Shuyue Stella Li, Rui Xin +11

We show that reinforcement learning with verifiable rewards (RLVR) can elicit strong mathematical reasoning in certain language models even with spurious rewards that have little,…

cs.AI2025

The Delta Learning Hypothesis: Preference Tuning on Weak Data can Yield Strong Gains

Scott Geng, Hamish Ivison, Chun-Liang Li +4

Improvements in language models are often driven by improving the quality of the data we train them on, which can be limiting when strong supervision is scarce. In this work, we sh…

cs.CR2022

NeuDep: Neural Binary Memory Dependence Analysis

Kexin Pei, Dongdong She, Michael Wang +6

Determining whether multiple instructions can access the same memory location is a critical task in binary analysis. It is challenging as statically computing precise alias informa…

cs.CV2025

The Unmet Promise of Synthetic Training Images: Using Retrieved Real Images Performs Better

Scott Geng, Cheng-Yu Hsieh, Vivek Ramanujan +4

Generative text-to-image models enable us to synthesize unlimited amounts of images in a controllable manner, spurring many recent efforts to train vision models with synthetic dat…

cs.LG2026

Weak-to-Strong Generalization is Nearly Inevitable (in Linear Models)

Scott Geng, Dutch Hansen, Jerry Li

Weak-to-strong generalization is a phenomenon in post-training whereby a strong student model, when finetuned solely with feedback from a weaker teacher, can not only surpass the t…

cs.CV2025

Self-Improving VLM Judges Without Human Annotations

Inna Wanyin Lin, Yushi Hu, Shuyue Stella Li +5

Effective judges of Vision-Language Models (VLMs) are crucial for model development. Current methods for training VLM judges mainly rely on large-scale human preference annotations…

cs.CV2023

Understanding Zero-Shot Adversarial Robustness for Large-Scale Models

Chengzhi Mao, Scott Geng, Junfeng Yang +2

Pretrained large-scale vision-language models like CLIP have exhibited strong generalization over unseen tasks. Yet imperceptible adversarial perturbations can significantly reduce…

cs.CV2023

Affective Faces for Goal-Driven Dyadic Communication

Scott Geng, Revant Teotia, Purva Tendulkar +2

We introduce a video framework for modeling the association between verbal and non-verbal communication during dyadic conversation. Given the input speech of a speaker, our approac…

cs.LG2024

Exploiting Code Symmetries for Learning Program Semantics

Kexin Pei, Weichen Li, Qirui Jin +5

This paper tackles the challenge of teaching code semantics to Large Language Models (LLMs) for program analysis by incorporating code symmetries into the model architecture. We in…