d1: Scaling Reasoning in Diffusion Large Language Models via Reinforcement Learning

no code implementations • 16 Apr 2025 • Siyan Zhao, Devaansh Gupta, Qinqing Zheng, Aditya Grover

Recent large language models (LLMs) have demonstrated strong reasoning capabilities that benefits from online reinforcement learning (RL).

Language Modeling Language Modelling +2

Do LLMs Recognize Your Preferences? Evaluating Personalized Preference Following in LLMs

1 code implementation • 13 Feb 2025 • Siyan Zhao, Mingyi Hong, Yang Liu, Devamanyu Hazarika, Kaixiang Lin

We introduce PrefEval, a benchmark for evaluating LLMs' ability to infer, memorize and adhere to user preferences in a long-context conversational setting.

Benchmarking Retrieval

MedMax: Mixed-Modal Instruction Tuning for Training Biomedical Assistants

1 code implementation • 17 Dec 2024 • Hritik Bansal, Daniel Israel, Siyan Zhao, Shufan Li, Tung Nguyen, Aditya Grover

To address these gaps, we present MedMax, the first large-scale multimodal biomedical instruction-tuning dataset for mixed-modal foundation models.

Image Captioning Question Answering +1

Analyzing Nobel Prize Literature with Large Language Models

no code implementations • 22 Oct 2024 • Zhenyuan Yang, Zhengliang Liu, Jing Zhang, Cen Lu, Jiaxin Tai, Tianyang Zhong, Yiwei Li, Siyan Zhao, Teng Yao, Qing Liu, Jinlin Yang, Qixin Liu, Zhaowei Li, Kexin Wang, Longjun Ma, Dajiang Zhu, Yudan Ren, Bao Ge, Wei zhang, Ning Qiang, Tuo Zhang, Tianming Liu

This study examines the capabilities of advanced Large Language Models (LLMs), particularly the o1 model, in the context of literary analysis.

DODT: Enhanced Online Decision Transformer Learning through Dreamer's Actor-Critic Trajectory Forecasting

no code implementations • 15 Oct 2024 • Eric Hanchen Jiang, Zhi Zhang, Dinghuai Zhang, Andrew Lizarraga, Chenheng Xu, Yasi Zhang, Siyan Zhao, Zhengjie Xu, Peiyu Yu, Yuer Tang, Deqian Kong, Ying Nian Wu

Advancements in reinforcement learning have led to the development of sophisticated models capable of learning complex decision-making tasks.

Decision Making Model-based Reinforcement Learning +3

Probing the Decision Boundaries of In-context Learning in Large Language Models

1 code implementation • 17 Jun 2024 • Siyan Zhao, Tung Nguyen, Aditya Grover

In-context learning is a key paradigm in large language models (LLMs) that enables them to generalize to new tasks and domains by simply prompting these models with a few exemplars without explicit parameter updates.

Binary Classification In-Context Learning

Prepacking: A Simple Method for Fast Prefilling and Increased Throughput in Large Language Models

1 code implementation • 15 Apr 2024 • Siyan Zhao, Daniel Israel, Guy Van Den Broeck, Aditya Grover

In this work, we highlight the following pitfall of prefilling: for batches containing high-varying prompt lengths, significant computation is wasted by the standard practice of padding sequences to the maximum length.

Group Preference Optimization: Few-Shot Alignment of Large Language Models

1 code implementation • 17 Oct 2023 • Siyan Zhao, John Dang, Aditya Grover

We introduce Group Preference Optimization (GPO), an alignment framework that steers language models to preferences of individual groups in a few-shot manner.

Few-Shot Learning