Jiyuan He

QCPruner: Query-Conditioned Population Coverage for Visual Token Pruning

The high visual-token load in multimodal large language models (MLLMs) motivates training-free pruning to reduce later-layer computation, but under a fixed budget, pruning must preserve query-relevant evidence while avoiding redundancy. Existing methods rank tokens, diversify selected subsets, or optimize coverage with...

Trust, but Verify: Uncertainty-Driven Evidential Multimodal Representation Learning

Framework and Benchmark for Code-Driven Agentic Testing in Web Development

CAT is introduced, a paradigm in which the agent writes Playwright code to drive the browser, gathers feedback, and autonomously explores web applications to uncover bugs, revealing a clear gap between current VLM capabilities and the demands of real-world testing in AI web development.

Meta-Task: Turning Terminal Task Synthesis into a Terminal Task for Scalable Agent Training

Meta-Task is proposed, a framework that redefines terminal task synthesis as a Terminal-Bench-format task itself: an agent operates within a real container environment to iteratively generate, execute, and verify tasks, so that synthesized components are checked for internal consistency and executability within the gen...

ICAE-Bench: Evaluating Coding Agents as Interactive Project Builders

ICAE-Bench, a benchmark for evaluating coding agents under interactive project-building settings, starts from a fuzzy product requirement, simulating the dynamic paradigm with an automated User Agent, and introduces three key designs.