Qiushi

QiushiSun's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a paper 5 days ago

EvoCUA: Evolving Computer Use Agents via Learning from Scalable Synthetic Experience

Paper • 2601.15876 • Published 6 days ago • 88

upvoted a paper 6 days ago

MMDeepResearch-Bench: A Benchmark for Multimodal Deep Research Agents

Paper • 2601.12346 • Published 10 days ago • 48

upvoted a paper 15 days ago

OS-Symphony: A Holistic Framework for Robust and Generalist Computer-Using Agent

Paper • 2601.07779 • Published 16 days ago • 27

upvoted a paper 21 days ago

OpenNovelty: An LLM-powered Agentic System for Verifiable Scholarly Novelty Assessment

Paper • 2601.01576 • Published 24 days ago • 18

upvoted a paper 29 days ago

Dream-VL & Dream-VLA: Open Vision-Language and Vision-Language-Action Models with Diffusion Language Model Backbone

Paper • 2512.22615 • Published Dec 27, 2025 • 48

upvoted a paper about 2 months ago

PaCo-RL: Advancing Reinforcement Learning for Consistent Image Generation with Pairwise Reward Modeling

Paper • 2512.04784 • Published Dec 2, 2025 • 25

upvoted 4 papers 3 months ago

ARISE: An Adaptive Resolution-Aware Metric for Test-Time Scaling Evaluation in Large Reasoning Models

Paper • 2510.06014 • Published Oct 7, 2025 • 10

InteractScience: Programmatic and Visually-Grounded Evaluation of Interactive Scientific Demonstration Code Generation

Paper • 2510.09724 • Published Oct 10, 2025 • 10

OS-Sentinel: Towards Safety-Enhanced Mobile GUI Agents via Hybrid Validation in Realistic Workflows

Paper • 2510.24411 • Published Oct 28, 2025 • 72

JanusCoder: Towards a Foundational Visual-Programmatic Interface for Code Intelligence

Paper • 2510.23538 • Published Oct 27, 2025 • 97

upvoted 2 collections 3 months ago

JanusCoder

Collection

8 items • Updated 30 days ago • 11

OS-Sentinel

Collection

1 item • Updated Oct 29, 2025 • 1

upvoted 2 papers 3 months ago

Concerto: Joint 2D-3D Self-Supervised Learning Emerges Spatial Representations

Paper • 2510.23607 • Published Oct 27, 2025 • 178

QueST: Incentivizing LLMs to Generate Difficult Problems

Paper • 2510.17715 • Published Oct 20, 2025 • 35

upvoted a collection 4 months ago

DeepSeek-V3.2

Collection

4 items • Updated Dec 1, 2025 • 520

upvoted a paper 4 months ago

ScaleCUA: Scaling Open-Source Computer Use Agents with Cross-Platform Data

Paper • 2509.15221 • Published Sep 18, 2025 • 111

upvoted 4 papers 5 months ago

Harnessing Uncertainty: Entropy-Modulated Policy Gradients for Long-Horizon LLM Agents

Paper • 2509.09265 • Published Sep 11, 2025 • 47

CODA: Coordinating the Cerebrum and Cerebellum for a Dual-Brain Computer Use Agent with Decoupled Reinforcement Learning

Paper • 2508.20096 • Published Aug 27, 2025 • 37

Beyond Pass@1: Self-Play with Variational Problem Synthesis Sustains RLVR

Paper • 2508.14029 • Published Aug 19, 2025 • 118

DuPO: Enabling Reliable LLM Self-Verification via Dual Preference Optimization

Paper • 2508.14460 • Published Aug 20, 2025 • 85