Publications (23)
Video Text Preservation with Synthetic Text-Rich Videos
Ziyang Liu, Kevin Valencia, Justin Cui
While Text-To-Video (T2V) models have advanced rapidly, they continue to struggle with generating legible and coherent text within videos. In particular, existing models often fail…
Have we unified image generation and understanding yet? An empirical study of GPT-4o's image generation ability
Ning Li, Jingran Zhang, Justin Cui
OpenAI's multimodal GPT-4o has demonstrated remarkable capabilities in image generation and editing, yet its ability to achieve world knowledge-informed semantic synthesis--seamles…
Concepts or Skills? Rethinking Instruction Selection for Multi-modal Models
Andrew Bai, Justin Cui, Ruochen Wang +1
Vision-language instruction tuning achieves two main purposes: learning visual concepts and learning visual skills. In this paper, we found that vision-language benchmarks fall int…
Reward-Forcing: Autoregressive Video Generation with Reward Feedback
Jingran Zhang, Ning Li, Yuanhao Ban +2
While most prior work in video generation relies on bidirectional architectures, recent efforts have sought to adapt these models into autoregressive variants to support near real-…
LOOM: Personalized Learning Informed by Daily LLM Conversations Toward Long-Term Mastery via a Dynamic Learner Memory Graph
Justin Cui, Kevin Pu, Tovi Grossman
Foundation models are increasingly used to personalize learning, yet many systems still assume fixed curricula or coarse progress signals, limiting alignment with learners' day-to-…
OR-Bench: An Over-Refusal Benchmark for Large Language Models
Justin Cui, Wei-Lin Chiang, Ion Stoica +1
Large Language Models (LLMs) require careful safety alignment to prevent malicious outputs. While significant research focuses on mitigating harmful content generation, the enhance…
A Simple but Effective Elaborative Query Reformulation Approach for Natural Language Recommendation
Qianfeng Wen, Yifan Liu, Justin Cui +4
Natural Language (NL) recommender systems aim to retrieve relevant items from free-form user queries and item descriptions. Existing systems often rely on dense retrieval (DR), whi…
Scaling Up Dataset Distillation to ImageNet-1K with Constant Memory
Justin Cui, Ruochen Wang, Si Si +1
Dataset Distillation is a newly emerging area that aims to distill large datasets into much smaller and highly informative synthetic ones to accelerate training and reduce storage.…
DC-BENCH: Dataset Condensation Benchmark
Justin Cui, Ruochen Wang, Si Si +1
Dataset Condensation is a newly emerging technique aiming at learning a tiny dataset that captures the rich information encoded in the original dataset. As the size of datasets con…
Multimodal Item Scoring for Natural Language Recommendation via Gaussian Process Regression with LLM Relevance Judgments
Yifan Liu, Qianfeng Wen, Jiazhou Liang +6
Natural Language Recommendation (NLRec) generates item suggestions based on the relevance between user-issued NL requests and NL item description passages. Existing NLRec approache…
Can Agent Conquer Web? Exploring the Frontiers of ChatGPT Atlas Agent in Web Games
Jingran Zhang, Ning Li, Justin Cui
OpenAI's ChatGPT Atlas introduces new capabilities for web interaction, enabling the model to analyze webpages, process user intents, and execute cursor and keyboard inputs directl…
Latent Video Dataset Distillation
Ning Li, Antai Andy Liu, Jingran Zhang +1
Dataset distillation has demonstrated remarkable effectiveness in high-compression scenarios for image datasets. While video datasets inherently contain greater redundancy, existin…
ViPO: Visual Preference Optimization at Scale
Ming Li, Jie Wu, Justin Cui +3
While preference optimization is crucial for improving visual generative models, how to effectively scale this paradigm remains largely unexplored. Current open-source preference d…
Data-Efficient Ensemble Weather Forecasting with Diffusion Models
Kevin Valencia, Ziyang Liu, Justin Cui
Although numerical weather forecasting methods have dominated the field, recent advances in deep learning methods, such as diffusion models, have shown promise in ensemble weather…
LoL: Longer than Longer, Scaling Video Generation to Hour
Justin Cui, Jie Wu, Ming Li +6
Recent research in long-form video generation has shifted from bidirectional to autoregressive models, yet these methods commonly suffer from error accumulation and a loss of long-…
Smart-GRPO: Smartly Sampling Noise for Efficient RL of Flow-Matching Models
Benjamin Yu, Jackie Liu, Justin Cui
Recent advancements in flow-matching have enabled high-quality text-to-image generation. However, the deterministic nature of flow-matching models makes them poorly suited for rein…
Mitigating Bias in Dataset Distillation
Justin Cui, Ruochen Wang, Yuanhao Xiong +1
Dataset Distillation has emerged as a technique for compressing large datasets into smaller synthetic counterparts, facilitating downstream training tasks. In this paper, we study…
ArXivBench: When You Should Avoid Using ChatGPT for Academic Writing
Ning Li, Jingran Zhang, Justin Cui
Large language models (LLMs) demonstrate strong capabilities in reasoning and question answering, yet their tendency to generate factually incorrect content remains a critical chal…
Retrieval-Augmented Conversational Recommendation with Prompt-based Semi-Structured Natural Language State Tracking
Sara Kemper, Justin Cui, Kai Dicarlantonio +4
Conversational recommendation (ConvRec) systems must understand rich and diverse natural language (NL) expressions of user preferences and intents, often communicated in an indirec…
One-Forcing: Towards Stable One-Step Autoregressive Video Generation
Jiaqi Feng, Justin Cui, Yuanhao Ban +1
Recent advances have substantially improved real-time interactive video generation in the autoregressive regime. However, most existing few-step autoregressive video generation met…
Self-Forcing++: Towards Minute-Scale High-Quality Video Generation
Justin Cui, Jie Wu, Ming Li +6
Diffusion models have revolutionized image and video generation, achieving unprecedented visual quality. However, their reliance on transformer architectures incurs prohibitively h…
Bayesian Active Learning with Gaussian Processes Guided by LLM Relevance Scoring for Dense Passage Retrieval
Junyoung Kim, Anton Korikov, Jiazhou Liang +5
While Large Language Models (LLMs) exhibit exceptional zero-shot relevance modeling, their high computational cost necessitates framing passage retrieval as a budget-constrained gl…
DD-Ranking: Rethinking the Evaluation of Dataset Distillation
Zekai Li, Xinhao Zhong, Samir Khaki +49
In recent years, dataset distillation has provided a reliable solution for data compression, where models trained on the resulting smaller synthetic datasets achieve performance co…