LiveClawBench: Benchmarking LLM Agents on Complex, Real-World Assistant Tasks

Xiang Long, Li Du, Yilong Xu +11

Trust Region On-Policy Distillation

Xingrun Xing, Haoqing Wang, Boyan Gao +2

Revisiting the Parameter Efficiency of Adapters from the Perspective of Precision Redundancy

Shibo Jie, Haoqing Wang, Zhi-Hong Deng

Masked Image Modeling with Local Multi-Scale Reconstruction

Haoqing Wang, Yehui Tang, Yunhe Wang +3

Rethinking Minimal Sufficient Representation in Contrastive Learning

Haoqing Wang, Xun Guo, Zhi-Hong Deng +1

Fast Structured Decoding for Sequence Models

Zhiqing Sun, Zhuohan Li, Haoqing Wang +3

Few-shot Learning with LSSVM Base Learner and Transductive Modules

Haoqing Wang, Zhi-Hong Deng

FaithEyes: Towards Faithful Tool Use via Multi-Agent Process-Image Verification

Haoqing Wang, Xingrun Xing, Wei Xia +2

FaithEyes proposes a multi‑agent framework where a vision‑language model judges its own tool calls to ensure they are useful, improving both accuracy and tool faithfulness on visua…

When Do LLMs Reason? A Dynamical Systems View via Entropy Phase Transitions

Wei Xia, Haoqing Wang, Zhi-Hong Deng +1

MemTrain: Self-Supervised Context Memory Training

Ziheng Li, Xingrun Xing, Haoqing Wang +2

To Mix or To Merge: Toward Multi-Domain Reinforcement Learning for Large Language Models

Haoqing Wang, Xiang Long, Ziheng Li +3

Cross-Domain Few-Shot Classification via Adversarial Task Augmentation

Haoqing Wang, Zhi-Hong Deng

Mage-VL: An Efficient Codec-Native Streaming Multimodal Foundation Model

Senqiao Yang, Kaichen Zhang, Zhaoyang Jia +20