6 papers
Making AI Scientists Auditable from Evidence to Claim
Zijian Wang, Hanqi Li, Ziyue Yang +17
AI research systems can report improved results without establishing that the tested implementation matches the method described in their conclusions. We introduce Xcientist, a res…
DeepSurvey: Agent-Oriented Automated Survey Generation with Analytical Depth and Citation Reliability
Ziyue Yang, Da Ma, Hanqi Li +8
As scientific literature grows rapidly and research increasingly involves AI agents, automated survey generation has become a key capability for both agents and human researchers.…
When Stored Evidence Stops Being Usable: Scale-Conditioned Evaluation of Agent Memory
Jiaqi Shao, Yiyi Lu, Yunzhen Zhang +1
Memory-agent evaluations report fixed-snapshot accuracy or retrieval quality, but these scores do not show whether evidence remains usable as irrelevant sessions (sessions not anno…
Cross-Modality Controlled Molecule Generation with Diffusion Language Model
Yunzhe Zhang, Yifei Wang, Khanh Vinh Nguyen +1
The increasing variety of molecular data creates a need for generative models that can flexibly incorporate heterogeneous constraints across modalities. However, existing SMILES-ba…
How does Contrastive Learning Organize Images?
Yunzhe Zhang, Yao Lu, Qi Xuan
Contrastive learning, a dominant self-supervised technique, emphasizes similarity in representations between augmentations of the same input and dissimilarity for different ones. A…
Understanding the Dynamics of DNNs Using Graph Modularity
Yao Lu, Wen Yang, Yunzhe Zhang +5
There are good arguments to support the claim that deep neural networks (DNNs) capture better feature representations than the previous hand-crafted feature engineering, which lead…