Shaobai Jiang

shaobaij's activity

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

upvoted 3 papers about 8 hours ago

You Don't Need Strong Assumptions: Visual Representation Learning via Temporal Differences

Paper • 2606.15956 • Published 7 days ago • 12

Spectrum-Adaptive Generalization Bounds for Trained Deep Transformers

Paper • 2605.07297 • Published May 8 • 2

ExpRL: Exploratory RL for LLM Mid-Training

Paper • 2606.17024 • Published 6 days ago • 5

upvoted a paper about 10 hours ago

MyPCBench: A Benchmark for Personally Intelligent Computer-Use Agents

Paper • 2606.16748 • Published 6 days ago • 5

upvoted an article about 10 hours ago

view article

Article

GLM-5.2: Built for Long-Horizon Tasks

• 

zai-org

•

4 days ago

• 81

upvoted a paper about 10 hours ago

From AGI to ASI

Paper • 2606.12683 • Published 11 days ago • 35

upvoted a paper about 17 hours ago

VibeThinker-3B: Exploring the Frontier of Verifiable Reasoning in Small Language Models

Paper • 2606.16140 • Published 6 days ago • 102

upvoted a paper about 18 hours ago

Normalized Architectures are Natively 4-Bit

Paper • 2605.06067 • Published May 7 • 2

upvoted a paper about 19 hours ago

Models That Know How Evaluations Are Designed Score Safer

Paper • 2605.28591 • Published 25 days ago • 10

upvoted 2 papers 1 day ago

Self-Evolving Multi-Agent Systems via Decentralized Memory

Paper • 2605.22721 • Published May 21 • 1

HarnessX: A Composable, Adaptive, and Evolvable Agent Harness Foundry

Paper • 2606.14249 • Published 9 days ago • 45

upvoted 9 papers 5 days ago

Prescriptive Scaling Laws for Data Constrained Training

Paper • 2605.01640 • Published May 2 • 8

UniPool: A Globally Shared Expert Pool for Mixture-of-Experts

Paper • 2605.06665 • Published May 7 • 13

Continuous Latent Diffusion Language Model

Paper • 2605.06548 • Published May 7 • 84

Hierarchical Abstract Tree for Cross-Document Retrieval-Augmented Generation

Paper • 2605.00529 • Published May 1 • 6

Rethinking Reasoning-Intensive Retrieval: Evaluating and Advancing Retrievers in Agentic Search Systems

Paper • 2605.04018 • Published May 5 • 41

TIDE: Every Layer Knows the Token Beneath the Context

Paper • 2605.06216 • Published May 7 • 11

MiA-Signature: Approximating Global Activation for Long-Context Understanding

Paper • 2605.06416 • Published May 7 • 57

HERMES++: Toward a Unified Driving World Model for 3D Scene Understanding and Generation

Paper • 2604.28196 • Published Apr 30 • 74

UniVidX: A Unified Multimodal Framework for Versatile Video Generation via Diffusion Priors

Paper • 2605.00658 • Published May 1 • 86