collaborators

8 papers

cs.CV2026

DIVE: Dynamic Iterative Visual Evidence Construction for Efficient Vision-Language Models

Chen Zhong, Xiao An, Zijie Wang +3

Visual inputs in vision-language models (VLMs) are often encoded into substantially longer token sequences than text, making visual tokens a major bottleneck for efficient inferenc…

cs.CL2026

Convolution for Large Language Models

Yuchuan Tian, Yingte Shu, Wei He +7

Large language models (LLMs) largely rely on Transformers, where self-attention provides global token interaction but does not explicitly encode the locality of natural language. W…

cs.CL2026

Agentic Routing: The Harness-Native Data Flywheel

Xinchen Liu, Hang Zhou, Yingjie Zong +12

The paper introduces a step‑level routing framework for large language model agents that selects the most suitable model(s) based on the full execution harness state, using logged…

cs.LG2026

Claw-SWE-Bench: A Benchmark for Evaluating OpenClaw-style Agent Harnesses on Coding Tasks

Mengyu Zheng, Kai Han, Boxun Li +13

General-purpose agents such as OpenClaw are increasingly used as autonomous tool users, but their coding ability is difficult to measure under SWE-bench: a generic agent does not b…

cs.CV2026

Self-Consistent Latent Reasoning: Long Latent Sequence Reasoning for Vision-Language Model

Chenfeng Wang, Wei He, Xuhan Zhu +10

In language reasoning, longer chains of thought consistently yield better performance, which naturally suggests that visual latent reasoning may likewise benefit from longer latent…

cs.CV2026

SenseBench: A Benchmark for Remote Sensing Low-Level Visual Perception and Description in Large Vision-Language Models

Chen Zhong, Xiao An, Jiaxing Sun +3

Low-level visual perception underpins reliable remote sensing (RS) image analysis, yet current image quality assessment (IQA) methods output uninterpretable scalar scores rather th…