徐步强

Xubqpanda's activity

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

upvoted a paper 2 days ago

Learning to Evaluate Before Improving: Automatic Rubric Induction for Automatic Research Agents

Paper • 2608.31076 • Published 3 days ago • 18

upvoted a paper 17 days ago

MobileMem: Learning from a Year of Mobile Experiences

Paper • 2608.13606 • Published 23 days ago • 26

upvoted a paper 21 days ago

Mechanist: AI as a Scientific Instrument for Discovering the Mechanisms of Intelligence

Paper • 2608.12036 • Published 22 days ago • 86

upvoted a paper about 2 months ago

LightMem-Ego: Your AI Memory for Everyday Life

Paper • 2607.11487 • Published Jul 13 • 49

upvoted 2 articles about 2 months ago

view article

Article

Can Skills Improve Codex’s Data Analysis Capabilities?

• 

Ningyu

•

Jul 10

• 5

view article

Article

Can Codex Handle Real-World Data Analysis?

• 

Ningyu

•

Jul 10

• 5

upvoted 7 papers 3 months ago

TokenPilot: Cache-Efficient Context Management for LLM Agents

Paper • 2606.17016 • Published Jun 15 • 16

LabVLA: Grounding Vision-Language-Action Models in Scientific Laboratories

Paper • 2606.13578 • Published Jun 11 • 60

When Should Models Change Their Minds? Contextual Belief Management in Large Language Models

Paper • 2605.30219 • Published May 28 • 28

How LoRA Remembers? A Parametric Memory Law for LLM Finetuning

Paper • 2605.30260 • Published May 28 • 45

Rethinking Memory as Continuously Evolving Connectivity

Paper • 2605.28773 • Published May 27 • 35

MemTrace: Tracing and Attributing Errors in Large Language Model Memory Systems

Paper • 2605.28732 • Published May 27 • 41

SciAtlas: A Large-Scale Knowledge Graph for Automated Scientific Research

Paper • 2605.22878 • Published May 20 • 61

upvoted 2 papers 4 months ago

OceanPile: A Large-Scale Multimodal Ocean Corpus for Foundation Models

Paper • 2605.00877 • Published Apr 25 • 16

Chat2Workflow: A Benchmark for Generating Executable Visual Workflows with Natural Language

Paper • 2604.19667 • Published Apr 21 • 23

upvoted a paper 5 months ago

SkillX: Automatically Constructing Skill Knowledge Bases for Agents

Paper • 2604.04804 • Published Apr 6 • 35

upvoted a paper 6 months ago

SkillNet: Create, Evaluate, and Connect AI Skills

Paper • 2603.04448 • Published Feb 26 • 95

upvoted an article 6 months ago

view article

Article

Create, Evaluate, and Connect AI Skills | SkillNet: A Large-Scale Agentic "Skill Graph" Knowledge Base

• 

xzwnlp

•

Feb 28

• 13

upvoted 2 papers 7 months ago

From Data to Behavior: Predicting Unintended Model Behaviors Before Training

Paper • 2602.04735 • Published Feb 4 • 16

Why Steering Works: Toward a Unified View of Language Model Parameter Dynamics

Paper • 2602.02343 • Published Feb 2 • 13