Shaobai Jiang

shaobaij's activity

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

upvoted 2 papers 35 minutes ago

A Hippocampus for Linear Attention: An Exact Memory for What the Recurrent State Forgets

Paper • 2607.02303 • Published 12 days ago • 1

Always-OnAgents:A Survey of Persistent Memory, State, and Governance in LLMAgents

Paper • 2606.30306 • Published 15 days ago • 1

upvoted a paper 37 minutes ago

Causal Discovery in the Era of Agents

Paper • 2606.23608 • Published 22 days ago • 8

upvoted a paper 38 minutes ago

Toward Open Weight Models Without Risks: Separating Public and Private Capabilities in LLMs

Paper • 2606.21638 • Published 25 days ago • 8

upvoted a paper 39 minutes ago

Deeper is Not Always Better: Mitigating the Alignment Tax via Confident Layer Decoding

Paper • 2606.21906 • Published 24 days ago • 25

upvoted a paper 40 minutes ago

Tapered Language Models

Paper • 2606.23670 • Published 22 days ago • 10

upvoted a paper 41 minutes ago

HydraHead: From Head-Level Functional Heterogeneity to Specialized Attention Hybridization

Paper • 2606.20097 • Published 26 days ago • 19

upvoted 5 papers about 1 hour ago

Grouped Query Experts: Mixture-of-Experts on GQA Self-Attention

Paper • 2606.20945 • Published 26 days ago • 80

S-Agent: Spatial Tool-Use Elicits Reasoning for Spatial Intelligence

Paper • 2606.20515 • Published 26 days ago • 41

Native Active Perception as Reasoning for Omni-Modal Understanding

Paper • 2606.19341 • Published 27 days ago • 19

Learning from the Self-future: On-policy Self-distillation for dLLMs

Paper • 2606.18195 • Published 28 days ago • 77

Learning from Your Own Mistakes: Constructing Learnable Micro-Reflective Trajectories for Self-Distillation

Paper • 2606.18844 • Published 27 days ago • 20

upvoted 8 papers about 4 hours ago

FAPO: Fully Autonomous Prompt Optimization of Multi-Step LLM Pipelines

Paper • 2606.19605 • Published 27 days ago • 11

Training Open Models for Agentic Phone Use

Paper • 2606.23049 • Published 22 days ago • 17

CalVerT: Augmenting Agents with Calibrated Verifier Telemetry Improves Action and Learning in Knowledge-Intensive Tasks

Paper • 2606.21777 • Published 25 days ago • 5

OPD-Evolver: Cultivating Holistic Agent Evolver via On-Policy Distillation

Paper • 2606.17628 • Published 28 days ago • 29

Connect the Dots: Training LLMs for Long-Lifecycle Agents with Cross-Domain Generalization Via Reinforcement Learning

Paper • 2606.20002 • Published 26 days ago • 10

EvoEmbedding: Evolvable Representations for Long-Context Retrieval and Agentic Memory

Paper • 2606.21649 • Published 25 days ago • 34

Self-Compacting Language Model Agents

Paper • 2606.23525 • Published 22 days ago • 19

OpenRath: Session-Centered Runtime State for Agent Systems

Paper • 2606.19409 • Published 27 days ago • 78