13 papers
Distributionally Robust Mixture-of-Experts Training
Xin Teng, Muxiao Li, Hongyi Wen
Mixture-of-Experts (MoE) transformers scale capacity by activating only a few experts per token, but this sparsity creates a hidden reliability problem: when routing is imperfect,…
Coherence-Aware Distributional Evaluation of Open-Ended Text Generation
Jinnuo Liu, Junhao Zhu, Weifeng Jiang +2
Existing open-ended generation metrics measure likelihood, lexical diversity, or distributional similarity in generic representation space, yet can miss fundamental dimensions of q…
EvoGenUI-Bench: Evaluating LLMs as Multi-Turn Generative UI Assistants
Yue Peng, Lanke Xia, Zihan Wang +3
Large language models can generate interactive web interfaces, but reliable generative UI requires maintaining an executable artifact as user requests evolve. We introduce EvoGenUI…
Toward Latent Language Model Skills Steering and Optimization: An Empirical Study
Xunyi Jiang, Junda Wu, Yuxin Xiong +6
Skills, as a useful abstraction for the procedural capabilities of large language models (LLMs), capture how models perform structured, multi-step reasoning and program execution.…
Histogram-constrained Image Generation
Haoming Liu, Yuanhe Guo, Yijia Cao +2
Diffusion models have emerged as a dominant paradigm in generative modeling, enabling high-fidelity sampling from complex data distributions. Despite impressive capabilities, contr…
Evaluating Interactivity: Toward Automated Assessment of AI-Generated Explorable Explanations
Xiaozao Wang, Zhewei Wang, Hongyi Wen
While large language models now enable rapid generation of interactive learning materials, evaluating the interaction quality of these explorable explanations remains an open chall…
NovelAPIBench: Diagnosing How A Code LLM Learns to Use Novel APIs
Jinnuo Liu, Yue Peng, Jinhan Niu +1
Rapidly evolving software libraries require coding language models to use unfamiliar APIs. Yet failed solutions alone tell us little about what API knowledge models need or how to…
SHAPE: Unifying Safety, Helpfulness and Pedagogy for Educational LLMs
Sihang Zhao, Kangrui Yu, Youliang Yuan +2
Large Language Models (LLMs) have been widely explored in educational scenarios. We identify a critical vulnerability in current educational LLMs, pedagogical jailbreaks, where stu…
An Analysis of Large Language Models for Simulating User Responses in Surveys
Ziyun Yu, Yiru Zhou, Chen Zhao +1
Using Large Language Models (LLMs) to simulate user opinions has received growing attention. Yet LLMs, especially trained with reinforcement learning from human feedback (RLHF), ar…
From Navigation to Refinement: Revealing the Two-Stage Nature of Flow-based Diffusion Models through Oracle Velocity
Haoming Liu, Jinnuo Liu, Yanhao Li +5
Flow-based diffusion models have emerged as a leading paradigm for training generative models across images and videos. However, their memorization-generalization behavior remains…
ImageGem: In-the-wild Generative Image Interaction Dataset for Generative Model Personalization
Yuanhe Guo, Linxi Xie, Zhuoran Chen +5
We introduce ImageGem, a dataset for studying generative models that understand fine-grained individual preferences. We posit that a key challenge hindering the development of such…
Reveal and Release: Iterative LLM Unlearning with Self-generated Data
Linxi Xie, Xin Teng, Shichang Ke +2
Large language model (LLM) unlearning has demonstrated effectiveness in removing the influence of undesirable data (also known as forget data). Existing approaches typically assume…
Diffusion Cocktail: Mixing Domain-Specific Diffusion Models for Diversified Image Generations
Haoming Liu, Yuanhe Guo, Shengjie Wang +1
Diffusion models, capable of high-quality image generation, receive unparalleled popularity for their ease of extension. Active users have created a massive collection of domain-sp…