Heng Lian

Pixelieee's activity

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

upvoted 3 papers 15 days ago

Repo0: Design-Driven Zero-to-All Code Generation

Paper • 2608.19854 • Published 30 days ago • 22

ParaTempo: Efficient Parallel Reasoning via Temporal Confidence

Paper • 2608.16425 • Published Aug 17 • 40

EarlyEval: Cheaper Agent Evaluation via Early Outcome Prediction

Paper • 2609.02783 • Published 17 days ago • 61

upvoted 5 papers 29 days ago

SWE-Bench ProMax: Benchmarking Agents on Large-Scale Multilingual Code Refactoring

Paper • 2608.09802 • Published Aug 10 • 83

Second Thought: Reasoning in Parallel as LLM Agents Act and Observe

Paper • 2608.13667 • Published Aug 13 • 17

SkillForge: Self-Distilling Agents for Project-Specific Issue Resolution

Paper • 2608.18933 • Published about 1 month ago • 13

Know Before Fix: QA-Driven Repository Knowledge Acquisition for Software Issue Resolution

Paper • 2607.11111 • Published Jul 13 • 16

SWE-Pruner Pro: The Coder LLM Already Knows What to Prune

Paper • 2607.18213 • Published Jul 20 • 47

upvoted 4 papers 3 months ago

Dockerless: Environment-Free Program Verifier for Coding Agents

Paper • 2606.28436 • Published Jun 26 • 86

FastContext: Training Efficient Repository Explorer for Coding Agents

Paper • 2606.14066 • Published Jun 12 • 96

LLM Agents Can See Code Repositories

Paper • 2606.14061 • Published Jun 12 • 21

SWE-Explore: Benchmarking How Coding Agents Explore Repositories

Paper • 2606.07297 • Published Jun 5 • 124

upvoted 2 papers 7 months ago

Modality Gap-Driven Subspace Alignment Training Paradigm For Multimodal Large Language Models

Paper • 2602.07026 • Published Feb 2 • 141

Spider-Sense: Intrinsic Risk Sensing for Efficient Agent Defense with Hierarchical Adaptive Screening

Paper • 2602.05386 • Published Feb 5 • 52

upvoted 6 papers 8 months ago

Idea2Story: An Automated Pipeline for Transforming Research Concepts into Complete Scientific Narratives

Paper • 2601.20833 • Published Jan 28 • 135

SWE-Pruner: Self-Adaptive Context Pruning for Coding Agents

Paper • 2601.16746 • Published Jan 23 • 74

Controlled Self-Evolution for Algorithmic Code Optimization

Paper • 2601.07348 • Published Jan 12 • 79

KnowMe-Bench: Benchmarking Person Understanding for Lifelong Digital Companions

Paper • 2601.04745 • Published Jan 8 • 42

MemGovern: Enhancing Code Agents through Learning from Governed Human Experiences

Paper • 2601.06789 • Published Jan 11 • 65

Watching, Reasoning, and Searching: A Video Deep Research Benchmark on Open Web for Agentic Video Reasoning

Paper • 2601.06943 • Published Jan 11 • 196