4 papers
Med-R2: An Adversarial Benchmark for Evidence-Grounded Reasoning in Medical VLMs
Wen Ma, Fucheng Niu, Zhiting Fan +3
Vision-language models have demonstrated impressive capabilities in general medical visual question answering, yet due to limited interpretability, it remains unclear whether their…
HICT: High-precision 3D CBCT reconstruction from a single X-ray
Wen Ma, Jiaxiang Liu, Zikai Xiao +3
Accurate 3D dental imaging is vital for diagnosis and treatment planning, yet CBCT's high radiation dose and cost limit its accessibility. Reconstructing 3D volumes from a single l…
LongWeave: A Long-Form Generation Benchmark Bridging Real-World Relevance and Verifiability
Zikai Xiao, Fei Huang, Jianhong Tu +7
Generating long, informative, and factual outputs remains a major challenge for Large Language Models (LLMs). Existing benchmarks for long-form generation typically assess real-wor…
Mitigating Posterior Salience Attenuation in Long-Context LLMs with Positional Contrastive Decoding
Zikai Xiao, Ziyang Wang, Wen Ma +5
While Large Language Models (LLMs) support long contexts, they struggle with performance degradation within the context window. Current solutions incur prohibitive training costs,…