5 papers
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…
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…
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…
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…
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…