Recursive self-improvement (RSI) allows agents to carry useful changes across generations. Maintaining safety across these generations involves both preventing unsafe behavior from persisting and enabling recovery when failures occur. We study these challenges through a controlled testbed of stateful authorization task...
Yun-Bei Zhang, Janet Wang, Saiyue Lyu et al.· 0 citations
Can structured text replace vision for diagram reasoning? A wrong answer after textualization can arise because the representation omits information the question needs, or because the solver fails to use information that is present. We introduce a diagnostic protocol to distinguish these explanations. Using the same so...
Yun-Bei Zhang, Janet Wang, J. Hamm et al.· 0 citations
Multi-agent systems derive their capabilities from sharing evidence, delegating tasks, and combining information across agents. The same process creates a safety problem: contributions that are admissible in isolation can jointly enable a prohibited use. Blocking every sensitive action avoids disclosure but defeats the...
Yun-Bei Zhang, Saiyue Lyu, Janet Wang et al.· 0 citations
World-model planners typically scale outward by rolling farther, sampling more trajectories, or optimizing longer, while assigning the same computation to every imagined transition. We show that making every transition uniformly deeper wastes computation and can degrade planning because useful refinement is concentrate...
Zi-Jian Jin, Yun-Bei Zhang, Yuan-Zhe Liu et al.· 0 citations
These results support a state-based view of robot memory: effective memory for control is not simply retained visual history, but compact task-relevant state derived from the interaction history.
Yu-You Zhang, Yun-Bei Zhang, Miao Li et al.· 0 citations
A mechanistic analysis of the VLM model's internal attention patterns shows that a simple describe-then-decide prompting strategy increases vision attention by 30-40% during generation, and task-specific fine-tuning improves dermatology classification but reduces cross-domain medical question-answering performance in t...
Janet Wang, Yun-Bei Zhang, Xiao Wang et al.· 0 citations
Robots must often continue a task after a target moves, the viewpoint shifts, or an obstacle appears, even though their earlier observations and committed actions reflect the previous scene. Many simulation robustness benchmarks fix external conditions at reset, leaving this temporal challenge underexamined. We introdu...
Yun-Bei Zhang, Zi-Jian Jin, Yuan-Zhe Liu et al.· 0 citations
ForGE is proposed, a unified framework for adapting frozen models through per-query routing over a joint action space that spans both support form and thinking depth and improves accuracy at 42-45% lower token cost on both main hosts.
Xi Xiao, Yun-Bei Zhang, Chen Liu et al.· 0 citations
Inspired by the Information Bottleneck principle, Prompted Information Bottlenecks (PIB) is introduced, a framework that regularizes layer-wise compression-sufficiency trade-offs and promotes a more coherent cross-layer information path.
Yuqi Li, Xi Xiao, Yun-Bei Zhang et al.· arXiv.org· 10 citations
The ability of AI systems to improve their behavior during deployment is becoming increasingly important. As inference moves beyond the static execution of a fixed trained model, a growing body of work studies how models can refine their behavior on the fly by exploiting test-time information and additional computation...
Shuai-Cheng Niu, Guo-Hao Chen, Yaofo Chen et al.· 2 citations
Dynamic Hub-and-Spoke Memory is proposed, a training-free framework that represents distant history as structured textual memory while preserving the recent frames as visual tokens for fine-grained perception in streaming video understanding.
Xin-Ru Jiang, Lin Zhao, Xi Xiao et al.· 4 citations
Diversify, Anchor, and Filter (DAF), a stabilization framework that augments entropy-based adaptation with a marginal diversity loss that resists collapse, a cross-modal anchor consistency loss that constrains feature drift relative to a frozen source model, and feature salience filtering that skips low-value backward...
Chandler Timm C. Doloriel, Yun-Bei Zhang, Sarthak Kumar Maharana et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
