Visual perception should be iterative and task-directed, with representations refined in response to the question and the need for further processing. While Vision-Language Models (VLMs) increasingly support extended reasoning, their visual tokens are still typically acquired in a single, task-agnostic encoder pass. Th...
Wen Ye, An-Ning Hu, Hong-Ye Fang et al.· 0 citations
Financial agents must form forecasts and investment judgments from decision-time evidence, with predictions evaluated against subsequent outcomes. Existing benchmarks assess financial knowledge, research workflows, or forecasting, but evaluating the full research process requires a strictly frozen information set and p...
Huang-Fei Jiang, An-Ning Hu, Kai Sheng et al.· 0 citations
Large language models (LLMs) are increasingly used as judges to assign scalar scores that drive downstream decision-making, including tasks such as paper review and recommendation. However, LLM-as-a-Judge pipelines are vulnerable to score-hijacking prompt injection embedded in evaluated content, which corrupts scoring...
An-Ning Hu, Yang-Yu Li, Yu-Qi Huang et al.· 0 citations
Q-learning Penalized Transformer policy (QPT), a framework that bridges conditional sequence modeling with constraint-aware value estimation, is proposed, characterizing how Q-penalized conditional generation improve safety and performance.
Sheng-Chao Hu, Peng Wang, Ji-Feng Hu et al.· 0 citations
ReFlux is introduced, a learnable feedback graph that dynamically selects and composes increment-carrying routes that establishes ReFlux as an efficient paradigm for unlocking the latent computational potential of LLMs, allowing them to revisit the same tokens with fresh representations.
Wen Ye, An-Ning Hu, Xiang-Dong Zhang 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.