Graphical User Interface (GUI) grounding is essential for autonomous agents to map natural language instructions to precise screen coordinates. However, existing supervised fine-tuning and reinforcement learning methods are constrained by the high cost of annotation, creating a scalability bottleneck. In this paper, we...
Yi-Zhou Liu, Fei Tang, Yuchen Yan et al.· 0 citations
LIMIT(Less Is More for Instruction Tuning in Text-to-SQL), a data-centric framework that demonstrates strong database reasoning can emerge from an extremely compact training set when examples are strategically selected, is proposed, suggesting that careful data curation, rather than scale, is the key to efficient Text-...
Hao-Yuan Ma, Heng-Wei Liu, Linjuan Wu et al.· 0 citations
Automatic translation quality metrics trained on general-domain corpora systematically fail on social media content, where communicative intent is encoded in culturally loaded expressions (internet slang, homophonic ciphers, and platform-specific idioms) rather than surface token patterns. We conduct a systematic empir...
Yi-Wen Qiu, Linjuan Wu, Ding-Ming Li et al.· 0 citations
Test-Time Policy Optimization is proposed, an asymmetric objective that distills agreeing rollouts via OPSD and penalizes disagreeing rollouts with Grouped RL and Token-level selection further refines both branches: distillation down-weights already-converged positions, while RL penalizes only confident errors.
Ao-Han Wang, Zhengxi Lu, Jianze Wang et al.· 0 citations
This work introduces PaperGym, a unified framework that turns each research paper into a complete training environment, and releases the pipeline, the 20,000-instance corpus PaperGym-20k, and the benchmarks PaperGym-Innov and PaperGym-Design.
Yu-Han Wang, Zhengxi Lu, Yuchen Yan et al.· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
