collaborators

5 papers

cs.CL2026

In-Context Optimization for Retrieval-Augmented Generation: A Gradient-Descent Perspective

Mingchen Li, Jiatan Huang, Chuxu Zhang +2

In-context learning has recently been linked to implicit gradient descent in linear self-attention models, suggesting that context can induce a forward-pass update. Retrieval-augme…

cs.LG2026

Multimodal Representation Learning Conditioned on Semantic Relations

Yang Qiao, Yuntong Hu, Bowen Zhu +2

Multimodal representation learning has been largely driven by contrastive models such as CLIP, which learn a shared embedding space by aligning paired image-text samples. While eff…

cs.IR2026

LARGER: Lexically Anchored Repository Graph Exploration and Retrieval

Yuntong Hu, Tongli Su, Liang Zhao +2

Repository-level coding agents must first localize the files and symbols relevant to a task; failures at this stage can cascade across downstream objectives ranging from patch gene…

cs.CL2026

Decompose, Look, and Reason: Reinforced Latent Reasoning for VLMs

Mengdan Zhu, Senhao Cheng, Liang Zhao

Vision-Language Models often struggle with complex visual reasoning due to the visual information loss in textual CoT. Existing methods either add the cost of tool calls or rely on…

cs.IR2026

RAG without Forgetting: Continual Query-Infused Key Memory

Yuntong Hu, Sha Li, Naren Ramakrishnan +1

Retrieval-augmented generation (RAG) systems commonly improve robustness via query-time adaptations such as query expansion and iterative retrieval. While effective, these approach…