Zijun

TranSirius's activity

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

upvoted a paper 14 days ago

Chaining the Evidence: Robust Reinforcement Learning for Deep Search Agents with Citation-Aware Rubric Rewards

Paper • 2601.06021 • Published 17 days ago • 43

upvoted 2 papers 4 months ago

StockBench: Can LLM Agents Trade Stocks Profitably In Real-world Markets?

Paper • 2510.02209 • Published Oct 2, 2025 • 54

SIRI: Scaling Iterative Reinforcement Learning with Interleaved Compression

Paper • 2509.25176 • Published Sep 29, 2025 • 14

upvoted a paper 7 months ago

LongWriter-Zero: Mastering Ultra-Long Text Generation via Reinforcement Learning

Paper • 2506.18841 • Published Jun 23, 2025 • 56

upvoted 3 papers 8 months ago

SuperWriter: Reflection-Driven Long-Form Generation with Large Language Models

Paper • 2506.04180 • Published Jun 4, 2025 • 33

SageAttention3: Microscaling FP4 Attention for Inference and An Exploration of 8-Bit Training

Paper • 2505.11594 • Published May 16, 2025 • 75

AdaptThink: Reasoning Models Can Learn When to Think

Paper • 2505.13417 • Published May 19, 2025 • 83

commented a paper 9 months ago

An LMM for Efficient Video Understanding via Reinforced Compression of Video Cubes

Paper • 2504.15270 • Published Apr 21, 2025 • 9 •

3

upvoted a paper 9 months ago

An LMM for Efficient Video Understanding via Reinforced Compression of Video Cubes

Paper • 2504.15270 • Published Apr 21, 2025 • 9

upvoted 2 papers 11 months ago

Agentic Reward Modeling: Integrating Human Preferences with Verifiable Correctness Signals for Reliable Reward Systems

Paper • 2502.19328 • Published Feb 26, 2025 • 23

NAVIG: Natural Language-guided Analysis with Vision Language Models for Image Geo-localization

Paper • 2502.14638 • Published Feb 20, 2025 • 11

published 2 models 12 months ago

THU-KEG/OpenSAE-LLaMA-3.1-Layer_05-shift_back

2B • Updated Jan 28, 2025

THU-KEG/OpenSAE-LLaMA-3.1-Layer_04-shift_back

2B • Updated Jan 28, 2025 • 1

updated a collection 12 months ago

OpenSAE-LLaMA-3.1-8B

Collection

OpenSAE checkpoints for LLaMA 3.1 8B base model • 38 items • Updated Jan 29, 2025 • 5

updated 3 models 12 months ago

THU-KEG/OpenSAE-LLaMA-3.1-Layer_05-shift_back

2B • Updated Jan 28, 2025

THU-KEG/OpenSAE-LLaMA-3.1-Layer_04-shift_back

2B • Updated Jan 28, 2025 • 1

THU-KEG/OpenSAE-LLaMA-3.1-Layer_03-shift_back

2B • Updated Jan 28, 2025 • 2

published a model 12 months ago

THU-KEG/OpenSAE-LLaMA-3.1-Layer_03-shift_back

2B • Updated Jan 28, 2025 • 2

updated a collection 12 months ago

OpenSAE-LLaMA-3.1-8B

Collection

OpenSAE checkpoints for LLaMA 3.1 8B base model • 38 items • Updated Jan 29, 2025 • 5