Zechen Sun

Mintszc's activity

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

upvoted a paper 13 days ago

Iris: Climbing to the Search Frontier

Paper • 2609.04304 • Published 20 days ago • 70

upvoted a paper 15 days ago

Verify Before You Distill: Prompt-Level Teacher Gating for On-Policy Distillation

Paper • 2609.02998 • Published 21 days ago • 17

upvoted a paper 26 days ago

PILOT in the Loop: Live Self-Improvement for Long-Horizon Agents

Paper • 2608.26530 • Published 27 days ago • 35

authored 3 papers 27 days ago

D$^3$-MOPD: Adaptive Dynamic Domain ScheDuling for Efficient Multi-Teacher Distillation

Paper • 2608.24987 • Published 29 days ago • 28

QP-OneModel: A Unified Generative LLM for Multi-Task Query Understanding in Xiaohongshu Search

Paper • 2602.09901 • Published Feb 10 • 6

LOGO -- Long cOntext aliGnment via efficient preference Optimization

Paper • 2410.18533 • Published Oct 24, 2024 • 43

upvoted a paper 27 days ago

D^3-MOPD: Adaptive Dynamic Domain ScheDuling for Efficient Multi-Teacher Distillation

Paper • 2608.24987 • Published 29 days ago • 28

upvoted a collection 7 months ago

XDLM

Collection

XDLM papers and weights • 4 items • Updated Mar 27 • 2

upvoted a paper 7 months ago

Balancing Understanding and Generation in Discrete Diffusion Models

Paper • 2602.01362 • Published Feb 1 • 17

upvoted 3 papers 8 months ago

Vision-DeepResearch Benchmark: Rethinking Visual and Textual Search for Multimodal Large Language Models

Paper • 2602.02185 • Published Feb 2 • 105

Vision-DeepResearch: Incentivizing DeepResearch Capability in Multimodal Large Language Models

Paper • 2601.22060 • Published Jan 29 • 115

MemoryRewardBench: Benchmarking Reward Models for Long-Term Memory Management in Large Language Models

Paper • 2601.11969 • Published Jan 17 • 27

upvoted a paper 11 months ago

RedOne 2.0: Rethinking Domain-specific LLM Post-Training in Social Networking Services

Paper • 2511.07070 • Published Nov 10, 2025 • 20

upvoted 2 papers 12 months ago

LongRM: Revealing and Unlocking the Context Boundary of Reward Modeling

Paper • 2510.06915 • Published Oct 8, 2025 • 16

Revisiting Long-context Modeling from Context Denoising Perspective

Paper • 2510.05862 • Published Oct 7, 2025 • 21

upvoted a paper almost 2 years ago

LOGO -- Long cOntext aliGnment via efficient preference Optimization

Paper • 2410.18533 • Published Oct 24, 2024 • 43