activity
20242026
collaborators

5 papers

cs.AI2026

HPFA: Hypergraph-Based Paired Failure Attribution for LLM Reasoning

Runchuan Zhu, Hongbin Lai, Bowen Jiang +4

Reflection is a powerful mechanism for LLM reasoning, yet its effectiveness hinges on accurately attributing failures to specific reasoning steps, a capability that current models…

cs.CR2026

POPS: Recovering Unlearned Multi-Modality Knowledge in MLLMs with Prompt-Optimized Parameter Shaking

Zhangheng LI, Jianing Zhu, Junyuan Hong +4

Multimodal Large Language Models (MLLMs) have demonstrated impressive performance on cross-modal tasks by jointly training on large-scale textual and visual data, where privacy-sen…

cs.CV2025

Ferret-UI 2: Mastering Universal User Interface Understanding Across Platforms

Zhangheng Li, Keen You, Haotian Zhang +7

Building a generalist model for user interface (UI) understanding is challenging due to various foundational issues, such as platform diversity, resolution variation, and data limi…

cs.CL2024

Decoding Compressed Trust: Scrutinizing the Trustworthiness of Efficient LLMs Under Compression

Junyuan Hong, Jinhao Duan, Chenhui Zhang +12

Compressing high-capability Large Language Models (LLMs) has emerged as a favored strategy for resource-efficient inferences. While state-of-the-art (SoTA) compression methods boas…

cs.LG2024

Shake to Leak: Fine-tuning Diffusion Models Can Amplify the Generative Privacy Risk

Zhangheng Li, Junyuan Hong, Bo Li +1

While diffusion models have recently demonstrated remarkable progress in generating realistic images, privacy risks also arise: published models or APIs could generate training ima…