yilong xu

sapphirex's activity

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

upvoted a paper 2 days ago

PrismaCoder: Pushing the Boundaries of Open Multimodal Code Intelligence through Decomposed Rubric Synthesis

Paper • 2610.20538 • Published 10 days ago • 63

upvoted 2 papers 8 days ago

Trajectory-Level Speculation with Semantic Verification for Tool-Using Agents

Paper • 2610.21463 • Published 9 days ago • 25

Mosaic: Multi-Session Agentic Reinforcement Learning

Paper • 2610.22174 • Published 9 days ago • 64

upvoted 3 papers about 1 month ago

RULER: Instance-aware Rubric Rewards for SVG Generation

Paper • 2609.25270 • Published Sep 21 • 106

Confidence Comes from Experience: Experiential Confidence Estimation from Reasoning to Agents

Paper • 2609.17708 • Published Sep 15 • 82

SAS: Simple Attention Sparsification via End-to-End Optimization of Context Ranking

Paper • 2609.13141 • Published Sep 11 • 69

upvoted 2 papers 4 months ago

From Trainee to Trainer: LLM-Designed Training Environment for RL with Multi-Agent Reasoning

Paper • 2606.17682 • Published Jun 16 • 27

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

Paper • 2606.13106 • Published Jun 11 • 23

upvoted 4 papers 5 months ago

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

MemTrain: Self-Supervised Context Memory Training

Paper • 2606.03197 • Published Jun 2 • 19

Trust Region On-Policy Distillation

Paper • 2606.01249 • Published May 31 • 47

EnvFactory: Scaling Tool-Use Agents via Executable Environments Synthesis and Robust RL

Paper • 2605.18703 • Published May 18 • 51

upvoted a paper 8 months ago

CodeScaler: Scaling Code LLM Training and Test-Time Inference via Execution-Free Reward Models

Paper • 2602.17684 • Published Feb 4 • 25

upvoted a paper 9 months ago

MeKi: Memory-based Expert Knowledge Injection for Efficient LLM Scaling

Paper • 2602.03359 • Published Feb 3 • 10

upvoted a collection about 1 year ago

Annotation-Efficient Universal Honesty Alignment

Collection

Official Collections of paper "Annotation-Efficient Universal Honesty Alignment". • 5 items • Updated Oct 21, 2025 • 3

upvoted 3 papers about 1 year ago

Annotation-Efficient Universal Honesty Alignment

Paper • 2510.17509 • Published Oct 20, 2025 • 22

Training a Utility-based Retriever Through Shared Context Attribution for Retrieval-Augmented Language Models

Paper • 2504.00573 • Published Apr 1, 2025 • 2

RAVine: Reality-Aligned Evaluation for Agentic Search

Paper • 2507.16725 • Published Jul 22, 2025 • 31

upvoted a collection over 1 year ago

MiniCPM4

Collection

MiniCPM4: Ultra-Efficient LLMs on End Devices • 30 items • Updated Sep 15 • 87

upvoted a paper over 1 year ago

RefineX: Learning to Refine Pre-training Data at Scale from Expert-Guided Programs

Paper • 2507.03253 • Published Jul 4, 2025 • 19