Shaobai Jiang

shaobaij's activity

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

upvoted 3 papers about 14 hours ago

OBLIQ-Bench: Exposing Overlooked Bottlenecks in Modern Retrievers with Latent and Implicit Queries

Paper • 2605.06235 • Published 5 days ago • 1

Beyond Semantic Similarity: Rethinking Retrieval for Agentic Search via Direct Corpus Interaction

Paper • 2605.05242 • Published 9 days ago • 87

EMO: Pretraining Mixture of Experts for Emergent Modularity

Paper • 2605.06663 • Published 5 days ago • 9

upvoted a paper about 15 hours ago

The Information Geometry of Softmax: Probing and Steering

Paper • 2602.15293 • Published Feb 17 • 1

upvoted a paper about 22 hours ago

Video Generation with Predictive Latents

Paper • 2605.02134 • Published 8 days ago • 24

upvoted a paper about 23 hours ago

Hallucinations Undermine Trust; Metacognition is a Way Forward

Paper • 2605.01428 • Published 10 days ago • 22

upvoted 6 papers 1 day ago

On Training Large Language Models for Long-Horizon Tasks: An Empirical Study of Horizon Length

Paper • 2605.02572 • Published 8 days ago • 2

ProgramBench: Can Language Models Rebuild Programs From Scratch?

Paper • 2605.03546 • Published 7 days ago • 2

End-to-End Autoregressive Image Generation with 1D Semantic Tokenizer

Paper • 2605.00503 • Published 11 days ago • 11

Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation

Paper • 2604.24763 • Published 15 days ago • 69

Leveraging Verifier-Based Reinforcement Learning in Image Editing

Paper • 2604.27505 • Published 12 days ago • 57

LooGLE v2: Are LLMs Ready for Real World Long Dependency Challenges?

Paper • 2510.22548 • Published Oct 26, 2025 • 2

upvoted a paper 2 days ago

Attention to Mamba: A Recipe for Cross-Architecture Distillation

Paper • 2604.14191 • Published Apr 1 • 1

upvoted 7 papers 9 days ago

Synthetic Computers at Scale for Long-Horizon Productivity Simulation

Paper • 2604.28181 • Published 12 days ago • 18

Recursive Multi-Agent Systems

Paper • 2604.25917 • Published 14 days ago • 262

Accelerating RL Post-Training Rollouts via System-Integrated Speculative Decoding

Paper • 2604.26779 • Published 13 days ago • 13

GLM-5V-Turbo: Toward a Native Foundation Model for Multimodal Agents

Paper • 2604.26752 • Published 13 days ago • 104

Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis

Paper • 2604.24198 • Published 15 days ago • 21

World-R1: Reinforcing 3D Constraints for Text-to-Video Generation

Paper • 2604.24764 • Published 15 days ago • 116

LaDiR: Latent Diffusion Enhances LLMs for Text Reasoning

Paper • 2510.04573 • Published Oct 6, 2025 • 1