4 papers
VLM-in-Sandbox: Visual Workspaces for Agentic Visual Reasoning
Hexiong Yang, Mingrui Chen, Jie Cao +1
Sandboxed computer environments support multi-step reasoning with tools, executable programs, and persistent files, yet their extension from language models to vision-language mode…
Think 360°: Evaluating the Width-centric Reasoning Capability of MLLMs Beyond Depth
Mingrui Chen, Hexiong Yang, Haogeng Liu +2
In this paper, we present a holistic multimodal benchmark that evaluates the reasoning capabilities of MLLMs with an explicit focus on reasoning width, a complementary dimension to…
AWPO: Enhancing Tool-Use of Large Language Models through Adaptive Integration of Reasoning Rewards
Zihan Lin, Xiaohan Wang, Hexiong Yang +5
While Reinforcement Learning (RL) shows promise in training tool-use Large Language Models (LLMs) using verifiable outcome rewards, existing methods largely overlook the potential…
HAD: Hybrid Architecture Distillation Outperforms Teacher in Genomic Sequence Modeling
Hexiong Yang, Mingrui Chen, Huaibo Huang +4
Inspired by the great success of Masked Language Modeling (MLM) in the natural language domain, the paradigm of self-supervised pre-training and fine-tuning has also achieved remar…