collaborators

11 papers

cs.CL2026

PolyAlign: Conditional Human-Distribution Alignment

L. D. M. S. Sai Teja, Ufaq Khan, Sathira Silva +2

Post-training methods such as supervised fine-tuning (SFT) and preference optimization typically align language models toward a single global assistant behavior. While effective fo…

cs.CL2026

RLBFF: Binary Flexible Feedback to bridge between Human Feedback & Verifiable Rewards

Zhilin Wang, Jiaqi Zeng, Olivier Delalleau +6

Reinforcement Learning with Human Feedback (RLHF) and Reinforcement Learning with Verifiable Rewards (RLVR) are the main RL paradigms used in LLM post-training, each offering disti…

cs.CL2026

Diverging Preferences: When do Annotators Disagree and do Models Know?

Michael JQ Zhang, Zhilin Wang, Jena D. Hwang +6

We examine diverging preferences in human-labeled preference datasets. We develop a taxonomy of disagreement sources spanning ten categories across four high-level classes and find…

cs.CV2026

PhyCritic: Multimodal Critic Models for Physical AI

Tianyi Xiong, Shihao Wang, Guilin Liu +5

With the rapid development of large multimodal models, reliable judge and critic models have become essential for open-ended evaluation and preference alignment, providing pairwise…

cs.CV2026

REF-VLM: Triplet-Based Referring Paradigm for Unified Visual Decoding

Yan Tai, Luhao Zhu, Yunan Ding +4

Multimodal Large Language Models (MLLMs) demonstrate robust zero-shot capabilities across diverse vision-language tasks after training on mega-scale datasets. However, dense predic…

cs.CL2025

HelpSteer3-Preference: Open Human-Annotated Preference Data across Diverse Tasks and Languages

Zhilin Wang, Jiaqi Zeng, Olivier Delalleau +6

Preference datasets are essential for training general-domain, instruction-following language models with Reinforcement Learning from Human Feedback (RLHF). Each subsequent data re…