6 papers
D-Loop: Looped Diffusion Drafting for Speculative Decoding
Kecheng Chen, Yuyang He, Cheng Gong +8
Block diffusion accelerates speculative decoding by drafting multiple tokens in one forward pass. However, each position predicts a marginal distribution without observing earlier…
Visual Parallel Search: Learning to Search High-Resolution Images with Parallel Tile Inspection and Adaptive Zoom
Xijia Tao, Yihua Teng, Xinyu Fu +5
High-resolution visual question answering often fails because a multimodal model does not acquire the small, spatially localized evidence needed to answer a question. Sequential zo…
SAP: State-Guided Data Synthesis with Argument Provenance for Multi-Turn Tool Use
Zichen Tian, Jinpeng Chen, Cheng Gong +2
High-quality multi-turn tool-use data is essential for training agentic models, yet existing data synthesis methods often underrepresent the argument-level dependencies that are cr…
CoVe: Training Interactive Tool-Use Agents via Constraint-Guided Verification
Jinpeng Chen, Cheng Gong, Hanbo Li +9
Developing multi-turn interactive tool-use agents is challenging because real-world user needs are often complex and ambiguous, yet agents must execute deterministic actions to sat…
Efficient Reasoning via Reward Model
Yuhao Wang, Xiaopeng Li, Cheng Gong +4
Reinforcement learning with verifiable rewards (RLVR) has been shown to enhance the reasoning capabilities of large language models (LLMs), enabling the development of large reason…
GHPO: Adaptive Guidance for Stable and Efficient LLM Reinforcement Learning
Ziru Liu, Cheng Gong, Xinyu Fu +7
Reinforcement Learning with Verifiable Rewards (RLVR) has recently emerged as a powerful paradigm for facilitating the self-improvement of large language models (LLMs), particularl…