collaborators

11 papers

cs.LG2026

Simultaneous Multi-objective Alignment Across Verifiable and Non-verifiable Rewards

Yiran Shen, Yu Xia, Jonathan Chang +1

Aligning large language models to human preferences is inherently multidimensional, yet most pipelines collapse heterogeneous signals into a single objective. We seek to answer wha…

cs.LG2026

Introspective X Training: Feedback Conditioning Improves Scaling Across all LLM Training Stages

Brandon Cui, Ximing Lu, Jaehun Jung +7

We tackle the question of how to scale more efficiently across the many, ever-growing stages of current LLM training pipelines. Our guiding intuition stems from the fact that the d…

cs.RO2026

How to Instruct Your Robot: Dense Language Annotations Power Robot Policy Learning

Bosung Kim, Ruiyi Wang, David Acuna +5

Scaling robot policy learning is bottlenecked by the cost of collecting demonstrations, while language annotations for existing demonstrations are comparatively cheap. We study lan…

cs.LG2026

MASS-DPO: Multi-negative Active Sample Selection for Direct Policy Optimization

Rohan Surana, Xintong Li, Sheldon Yu +7

Multi-negative preference optimization under the Plackett--Luce (PL) model extends Direct Preference Optimization (DPO) by leveraging comparative signals across one preferred and m…

cs.CV2026

Long Grounded Thoughts: Synthesizing Visual Problems and Reasoning Chains at Scale

David Acuna, Chao-Han Huck Yang, Yuntian Deng +6

Despite rapid progress, multimodal reasoning still lacks a systematic approach to synthesize large-scale vision-centric datasets beyond visual math. We introduce a framework able t…

cs.AI2026

Golden Goose: A Simple Trick to Synthesize Unlimited RLVR Tasks from Unverifiable Internet Text

Ximing Lu, David Acuna, Jaehun Jung +12

Reinforcement Learning with Verifiable Rewards (RLVR) has become a cornerstone for unlocking complex reasoning in Large Language Models (LLMs). Yet, scaling up RL is bottlenecked b…