We have 9 of 129 papers
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
R$^{2}$Adapter is a lightweight plug-in Routing and Rewriting Adapter designed to allocate queries between vanilla and graph-based RAG dynamically, providing an efficient and adaptive solution for hybrid RAG systems.
Temporal Semantic Memory is proposed, a memory framework that models semantic time for point-wise memory and supports the construction and utilization of durative memory and incorporates the query's temporal intent on the semantic timeline.
An adversarially robust zero-shot image classifier that boosts the SOTA robustness by a large margin and is the first purification method in multi-modal latent space and CLIPure-Cos is the first purification method that is not based on generative models, which substantially improves defense efficiency.
HiDiffTIR is proposed, a Hierarchical Difficulty-aware policy optimization framework for multi-turn TIR that consistently improves multi-turn TIR performance and tool invocation accuracy over strong RL baselines, highlighting the necessity of difficulty-aware credit assignment for effective policy optimization in tool-...
It is shown that popularity-related signals can mitigate overconfidence and improve overall confidence estimation, and incorporate knowledge popularity reduces average confidence on incorrect answers and improves overall confidence estimation.
DeepRepro dynamically transforms evolving repository states and runtime feedback into fine-grained implementation subplans, keeping planning aligned with execution throughout repository construction, and consistently outperforms strong scientific and commercial code-agent baselines.
TokenWall is proposed, a runtime defense framework that acts as a semantic firewall over agent token flows, demonstrating that semantic runtime containment can achieve a practical security-utility trade-off for persistent AI agents.
This work conducts a systematic study of overthinking and overretrieval in search agents from a scaling perspective and proposes a lightweight post-hoc reflection framework that converts the proposed evaluation signals into explicit feedback rewards to guide agents' reasoning trajectories.
This paper introduces Search in the Model, a novel training-free framework that performs fine-grained identification and rectification of vulnerable neurons directly within the model, and develops a maximum marginal vulnerability criterion to precisely locate the top-K neurons most responsible for model vulnerability.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
