Jingqi Tong

2 articles on SOTA Papers

Computer Science

Verifiable Rewards Improve Native Visual Reasoning Training

A 300-task procedural suite replaces preference-only judging with task-specific scorers, raising matched reinforcement-learning performance from 0.509 to 0.548.

cs.AIcs.LGcs.MM
Sep 4, 20264 min2608.26105
Computer Science

Automated Research Produces Reviewable Papers, With Weak Evidence

FARS runs ideation, planning, experiments, and writing end to end, producing 166 papers with 282 human reviews exposing quality and integrity gaps.

cs.AI
Jul 28, 20265 min2606.31651 Code available