Shaobai Jiang

shaobaij's activity

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

upvoted a paper 6 minutes ago

Compositional Skill Routing for LLM Agents: Decompose, Retrieve, and Compose

Paper • 2606.18051 • Published 27 days ago • 1

upvoted 19 papers about 2 hours ago

HYDRA-X: Native Unified Multimodal Models with Holistic Visual Tokenizers

Paper • 2606.13289 • Published Jun 11 • 30

On Subquadratic Architectures: From Applications to Principles

Paper • 2606.12364 • Published Jun 10 • 24

Redesign Mixture-of-Experts Routers with Manifold Power Iteration

Paper • 2606.12397 • Published Jun 10 • 90

Demystifying Hidden-State Recurrence: Switchable Latent Reasoning with On-Policy Reinforcement Learning

Paper • 2606.13106 • Published Jun 11 • 22

TRACE: A Unified Rollout Budget Allocation Framework for Efficient Agentic Reinforcement Learning

Paper • 2606.11119 • Published Jun 9 • 19

N-GRPO: Embedding-Level Neighbor Mixing for Enhanced Policy Optimization

Paper • 2606.10768 • Published Jun 9 • 25

Rethinking the Divergence Regularization in LLM RL

Paper • 2606.09821 • Published Jun 8 • 34

MaxProof: Scaling Mathematical Proof with Generative-Verifier RL and Population-Level Test-Time Scaling

Paper • 2606.13473 • Published Jun 11 • 93

MoVerse: Real-Time Video World Modeling with Panoramic Gaussian Scaffold

Paper • 2606.13376 • Published Jun 11 • 16

World Model Self-Distillation: Training World Models to Solve General Tasks

Paper • 2606.12072 • Published Jun 10 • 15

World Pilot: Steering Vision-Language-Action Models with World-Action Priors

Paper • 2606.12403 • Published Jun 10 • 27

One Token per Multimodal Evidence: Latent Memory for Resource-Constrained QA

Paper • 2606.10572 • Published Jun 9 • 17

Attention Amnesia in Hybrid LLMs: When CoT Fine-Tuning Breaks Long-Range Recall, and How to Fix It

Paper • 2606.11052 • Published Jun 9 • 17

Echo-Memory: A Controlled Study of Memory in Action World Models

Paper • 2606.09803 • Published Jun 8 • 33

SearchSwarm: Towards Delegation Intelligence in Agentic LLMs for Long-Horizon Deep Research

Paper • 2606.09730 • Published Jun 8 • 55

Bayesian-Agent: Posterior-Guided Skill Evolution for LLM Agent Harnesses

Paper • 2606.08348 • Published Jun 6 • 16

EEVEE: Towards Test-time Prompt Learning in the Real World for Self-Improving Agents

Paper • 2606.11182 • Published Jun 9 • 19

Retrospective Harness Optimization: Improving LLM Agents via Self-Preference over Trajectory Rollouts

Paper • 2606.05922 • Published Jun 4 • 70

The Hidden Power of Scaling Factor in LoRA Optimization

Paper • 2606.12883 • Published Jun 11 • 10