Author

Feng-Xian Ji

h-index 5 View on Semantic Scholar

We have 6 of 19 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.

Preprint Nov 2026

PRIME: Predictive Routing of Interventions by Modeling Effects for Scientific Ideation

Feedback-driven iteration is widely used to improve LLM-generated scientific ideas, but existing systems either leave revision decisions implicit in generation, align revisions with feedback-localized weaknesses, or restrict action selection to system-specific operations. This is problematic because problems, hypothese...

Feng-Xian Ji, Xie Yu, Zhe-Xuan Cui et al. · 0 citations

Preprint Oct 2026

CAMR: Compatibility-Aware Memory Replay for Continual Learning in Large Language Models

Continual learning requires large language models to acquire new knowledge and capabilities while retaining what they have learned. Fine-tuning and replay support acquisition and retention, but deciding whether incoming examples need supervision and which historical examples to revisit remains a challenge. We propose C...

Jing-Pu Yang, Tian-Hao Li, Feng-Xian Ji et al. · 0 citations

Preprint Aug 2026

GAAT: Geometry-Aware Alignment Transformer for Multimodal UAV Perception

GAAT (Geometry-Aware Alignment Transformer), an alignment-first pretrained model that estimates local correspondence reliability before cross-modal interaction, is proposed and introduced, establishing GAAT as a state-of-the-art multimodal foundation model for UAV perception.

Jing-Pu Yang, Deming Tang, Yi-Lin Sun et al. · 1 citation

Preprint Sep 2026

EgoSIS: From Factorized Visual Ego-Transitions to Motion-Canonical Spatial Evidence for UAV Reasoning

EgoSIS is presented, a pose-free adapter that converts RGB-derived bidirectional flow into motion-canonical visual evidence in three stages and provides an interpretable interface between optical flow and spatial reasoning.

Jing-Pu Yang, Feng-Xian Ji, Ming-Xuan Cui et al. · 0 citations

#artificial intelligence Preprint Sep 2026

FinCUABuild: Can Agents Build Reliable Benchmarks for Dynamic Financial Computer Use?

This work introduces FinCUABuildBench, a benchmark for evaluating financial CUA task construction, and introduces FinCUABuildAgent, a multi-agent system for automatically constructing dynamic financial CUA evaluation tasks.

Jing-Pu Yang, Feng-Xian Ji, Jinri Guo et al. · 0 citations

Preprint Aug 2026

Measure, Don't Optimize: Forecasting Recovery in LLM Unlearning

J-Access is proposed, an inference-time audit that uses the Jacobian lens to map intermediate representations into vocabulary space and measures how often target concepts remain accessible along the model's output pathway, positioning J-Access as a model-level diagnostic for assessing residual susceptibility in unlearn...

Zirui Song, Hua-Xing Liu, Xiang Wang et al. · 1 citation