activity
20242026
collaborators

9 papers

cs.CV2026

LongHorizon-Harness: Advancing Long-Horizon Agents for Real-World Tasks

Ziyu Ma, Hailang Huang, Shun Zou +5

Large language model (LLM) agents increasingly undertake long-horizon tasks that require sustained reasoning, tool use, and revision across many interdependent steps. However, exis…

cs.AI2026

ReSum: Synergizing LLM Reasoning and Summarization with Reinforcement Learning

Xucong Wang, Ziyu Ma, Yong Wang +5

Reinforcement Learning with Verifiable Rewards (RLVR) is a central technique for improving long-horizon reasoning in Large Language Models (LLMs). However, existing RLVR methods of…

cs.CV2026

LD-RPS: Zero-Shot Unified Image Restoration via Latent Diffusion Recurrent Posterior Sampling

Huaqiu Li, Yong Wang, Tongwen Huang +3

Unified image restoration is a significantly challenging task in low-level vision. Existing methods either make tailored designs for specific tasks, limiting their generalizability…

cs.LG2026

GPG: A Simple and Strong Reinforcement Learning Baseline for Model Reasoning

Xiangxiang Chu, Hailang Huang, Xiao Zhang +2

Reinforcement Learning (RL) can directly enhance the reasoning capabilities of large language models without extensive reliance on Supervised Fine-Tuning (SFT). In this work, we re…

cs.CV2026

Thinking with Map: Reinforced Parallel Map-Augmented Agent for Geolocalization

Yuxiang Ji, Yong Wang, Ziyu Ma +6

The image geolocalization task aims to predict the location where an image was taken anywhere on Earth using visual clues. Existing large vision-language model (LVLM) approaches le…

cs.LG2025

AdaCuRL: Adaptive Curriculum Reinforcement Learning with Invalid Sample Mitigation and Historical Revisiting

Renda Li, Hailang Huang, Fei Wei +3

Reinforcement learning (RL) has demonstrated considerable potential for enhancing reasoning in large language models (LLMs). However, existing methods suffer from Gradient Starvati…