activity
20242026
collaborators

8 papers

cs.CV2026

Crafter: A Multi-Agent Harness for Editable Scientific Figure Generation from Diverse Inputs

Haozhe Zhao, Shuzheng Si, Zhenhailong Wang +6

Scientific figures are among the most effective means of communicating complex research ideas, yet producing publication-quality illustrations remains one of the most labor-intensi…

cs.CV2026

MENTOR: Efficient Multimodal-Conditioned Tuning for Autoregressive Vision Generation Models

Haozhe Zhao, Zefan Cai, Shuzheng Si +5

Recent text-to-image models produce high-quality results but still struggle with precise visual control, balancing multimodal inputs, and requiring extensive training for complex m…

cs.CL2026

FaithLens: Detecting and Explaining Faithfulness Hallucination

Shuzheng Si, Qingyi Wang, Haozhe Zhao +8

Recognizing whether outputs from large language models (LLMs) contain faithfulness hallucination is crucial for real-world applications, e.g., retrieval-augmented generation and su…

cs.CL2026

A Goal Without a Plan Is Just a Wish: Efficient and Effective Global Planner Training for Long-Horizon Agent Tasks

Shuzheng Si, Haozhe Zhao, Kangyang Luo +5

Agents based on large language models (LLMs) struggle with brainless trial-and-error and generating hallucinatory actions due to a lack of global planning in long-horizon tasks. In…

cs.CL2025

MMGR: Multi-Modal Generative Reasoning

Zefan Cai, Haoyi Qiu, Tianyi Ma +9

Video foundation models generate visually realistic and temporally coherent content, but their reliability as world simulators depends on whether they capture physical, logical, an…

cs.CL2025

Teaching Large Language Models to Maintain Contextual Faithfulness via Synthetic Tasks and Reinforcement Learning

Shuzheng Si, Haozhe Zhao, Cheng Gao +11

Teaching large language models (LLMs) to be faithful in the provided context is crucial for building reliable information-seeking systems. Therefore, we propose a systematic framew…