Yuxiang Ji

Yux1ang's activity

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

upvoted a paper 4 days ago

On GRPO Collapse in Search-R1: The Lazy Likelihood-Displacement Death Spiral

Paper • 2512.04220 • Published 6 days ago • 10

upvoted a paper 6 days ago

Qwen3-VL Technical Report

Paper • 2511.21631 • Published 13 days ago • 117

upvoted a paper 14 days ago

Budget-Aware Tool-Use Enables Effective Agent Scaling

Paper • 2511.17006 • Published 19 days ago • 25

upvoted 3 papers about 1 month ago

AgentFold: Long-Horizon Web Agents with Proactive Context Management

Paper • 2510.24699 • Published Oct 28 • 67

Tongyi DeepResearch Technical Report

Paper • 2510.24701 • Published Oct 28 • 97

DeepAgent: A General Reasoning Agent with Scalable Toolsets

Paper • 2510.21618 • Published Oct 24 • 99

upvoted 6 papers about 2 months ago

Search Self-play: Pushing the Frontier of Agent Capability without Supervision

Paper • 2510.18821 • Published Oct 21 • 17

Agentic Entropy-Balanced Policy Optimization

Paper • 2510.14545 • Published Oct 16 • 104

Scaling Instruction-Based Video Editing with a High-Quality Synthetic Dataset

Paper • 2510.15742 • Published Oct 17 • 50

ImagerySearch: Adaptive Test-Time Search for Video Generation Beyond Semantic Dependency Constraints

Paper • 2510.14847 • Published Oct 16 • 55

Advancing End-to-End Pixel Space Generative Modeling via Self-supervised Pre-training

Paper • 2510.12586 • Published Oct 14 • 108

Thinking with Camera: A Unified Multimodal Model for Camera-Centric Understanding and Generation

Paper • 2510.08673 • Published Oct 9 • 125

upvoted 4 papers 2 months ago

Tree Search for LLM Agent Reinforcement Learning

Paper • 2509.21240 • Published Sep 25 • 87

CE-GPPO: Controlling Entropy via Gradient-Preserving Clipping Policy Optimization in Reinforcement Learning

Paper • 2509.20712 • Published Sep 25 • 19

Hunyuan3D-Omni: A Unified Framework for Controllable Generation of 3D Assets

Paper • 2509.21245 • Published Sep 25 • 38

Seedream 4.0: Toward Next-generation Multimodal Image Generation

Paper • 2509.20427 • Published Sep 24 • 80

upvoted a paper 3 months ago

From Editor to Dense Geometry Estimator

Paper • 2509.04338 • Published Sep 4 • 92

upvoted 3 papers 4 months ago

S^2-Guidance: Stochastic Self Guidance for Training-Free Enhancement of Diffusion Models

Paper • 2508.12880 • Published Aug 18 • 46

Omni-Effects: Unified and Spatially-Controllable Visual Effects Generation

Paper • 2508.07981 • Published Aug 11 • 58

Group Sequence Policy Optimization

Paper • 2507.18071 • Published Jul 24 • 315