collaborators

7 papers

cs.CV2026

ToolArtist: Tool-Using Unified Multimodal Models for Agentic Image Generation

Jiahao Zhao, Xiaomin Yu, Zhongxiang Sun +5

Text-to-image (T2I) models can produce visually compelling images, yet they remain limited on open-world tasks that require complex semantic understanding, multi-step reasoning, an…

cs.LG2026

Skip-Connected Policy Optimization for Implicit Advantage

Fengwei Teng, Jinyi Bai, Xinhao Yao +3

Group Relative Policy Optimization (GRPO) has proven effective in RLVR by using outcome-based rewards. While fine-grained dense rewards can theoretically improve performance, we re…

cs.CL2025

Atom of Thoughts for Markov LLM Test-Time Scaling

Fengwei Teng, Quan Shi, Zhaoyang Yu +4

Large Language Models (LLMs) have achieved significant performance gains through test-time scaling methods. However, existing approaches often incur redundant computations due to t…

cs.CL2025

InteractComp: Evaluating Search Agents With Ambiguous Queries

Mingyi Deng, Lijun Huang, Yani Fan +23

Language agents have demonstrated remarkable potential in web search and information retrieval. However, many search-agent benchmarks assume that user queries are complete and unam…

cs.LG2025

The Debate on RLVR Reasoning Capability Boundary: Shrinkage, Expansion, or Both? A Two-Stage Dynamic View

Xinhao Yao, Lu Yu, Xiaolin Hu +4

The ongoing debate on whether reinforcement learning with verifiable rewards (RLVR) expands or shrinks the reasoning capabilities of large language models (LLMs) remains unresolved…

cs.CL2025

Self-Supervised Prompt Optimization

Jinyu Xiang, Jiayi Zhang, Zhaoyang Yu +8

Well-designed prompts are crucial for enhancing Large language models' (LLMs) reasoning capabilities while aligning their outputs with task requirements across diverse domains. How…