activity
20242026
collaborators

5 papers

cs.CV2026

Suppressing Prior-Comparison Hallucinations in Radiology Report Generation via Semantically Decoupled Latent Steering

Ao Li, Rui Liu, Mingjie Li +6

Automated radiology report generation using vision-language models (VLMs) is limited by the risk of prior-comparison hallucination, where the model generates historical findings un…

cs.LG2025

Fractional Reasoning via Latent Steering Vectors Improves Inference Time Compute

Sheng Liu, Tianlang Chen, Pan Lu +4

Test-time compute has emerged as a powerful paradigm for improving the performance of large language models (LLMs), where generating multiple outputs or refining individual chains…

cs.LG2025

OctoTools: An Agentic Framework with Extensible Tools for Complex Reasoning

Pan Lu, Bowen Chen, Sheng Liu +3

Solving complex reasoning tasks may involve visual understanding, domain knowledge retrieval, numerical calculation, and multi-step reasoning. Existing methods augment large langua…

cs.CV2024

Reducing Hallucinations in Vision-Language Models via Latent Space Steering

Sheng Liu, Haotian Ye, Lei Xing +1

Hallucination poses a challenge to the deployment of large vision-language models (LVLMs) in applications. Unlike in large language models (LLMs), hallucination in LVLMs often aris…

cs.LG2024

TFG: Unified Training-Free Guidance for Diffusion Models

Haotian Ye, Haowei Lin, Jiaqi Han +6

Given an unconditional diffusion model and a predictor for a target property of interest (e.g., a classifier), the goal of training-free guidance is to generate samples with desira…