activity
20242026
most citedMap++: Towards User-Participatory Visual SLAM Systems with Efficient Map Expansion and Sharing

11 citations · 12 across the 13 of their papers we have counts for

collaborators

13 papers

cs.CL2026

-Bench: Can Large Language Models Engineer the Infrastructure That Powers Them?

Leilei Ding, Shumin Wang, Yuting Huang +10

Large language models (LLMs) have demonstrated remarkable capabilities in reasoning and code generation, raising the prospect that they could assist in developing and optimizing th…

cs.AI2026

More Rejective, Not More Discriminative: The Unit of Verification in Pre-Execution LLM Oversight

Yuchen Han, Cheng Yan, Wuyang Zhang

Pre-execution oversight is core to trusted monitoring in AI control: a fallible LLM monitor vets planned actions before irreversible execution. Over-blocking forfeits usefulness an…

cs.AI2026

UPAIR: Diagnosing Reasoning States via Uncertainty-Progress Alignment for Selective Intervention

Cheng Yan, Zhijun Fan, Guangyang Ye +4

While test-time scaling improves the problem-solving ability of large reasoning models (LRMs) through additional inference-time computation, it can also exacerbate overthinking and…

cs.CV2026

Beyond Global Routing Aggregation: Phase-Aware Expert Merging for MoE Vision-Language Models

Hongyu Zhang, Cheng Yan, Xiang Xia +1

Mixture-of-experts vision-language models (MoE-VLMs) increase model capacity with sparse expert activation, yet deployment requires storing the full expert pool. Training-free expe…

cs.CV2026

DAVET: Denoising-Aware Visual Evidence Trajectory Allocation for Diffusion Vision-Language Models

Yongkang Zhou, Xiang Xia, Cheng Yan +2

Diffusion vision-language models (dVLMs) iteratively denoise masked responses while conditioning each denoising step on visual evidence, making visual conditioning a substantial re…

cs.AI2026

REFLEX: Rethinking MoE Inference as Refinement-Aware Compute Allocation in Diffusion Language Models

Xiang Xia, Cheng Yan, Yiming Zhang +3

Mixture-of-experts (MoE) models increase parameter capacity by activating only a small subset of experts for each token. This conditional-computation paradigm has enabled autoregre…