Jiachun Li

Septzzz's activity

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

upvoted 2 papers 4 days ago

The Physics of Multi-Turn Long-Horizon Planning: From Pre-training to Post-training via Single- and Multi-Teacher On-Policy Agentic Distillation

Paper • 2607.24720 • Published 11 days ago • 26

Qwen-UI-Agent Technical Report: Toward Next-Generation Real-World Centric Foundation GUI Agents

Paper • 2607.28227 • Published 8 days ago • 301

published a dataset 20 days ago

Septzzz/Gympedia

Updated Jul 1 • 3.53k

updated a dataset about 1 month ago

Septzzz/Gympedia

Updated Jul 1 • 3.53k

upvoted 2 papers about 1 month ago

Why Multi-Step Tool-Use Reinforcement Learning Collapses and How Supervisory Signals Fix It

Paper • 2606.26027 • Published Jun 24 • 18

Look Light, Think Heavy: What Multimodal Chain-of-Thought Reasoning Can and Cannot Do

Paper • 2606.22565 • Published Jun 21 • 9

authored a paper about 2 months ago

Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Application

Paper • 2606.12191 • Published Jun 10 • 71

upvoted a paper about 2 months ago

Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Application

Paper • 2606.12191 • Published Jun 10 • 71

published a dataset 3 months ago

Septzzz/MentalGrid

Updated Apr 24 • 18

upvoted a paper 5 months ago

Think While Watching: Online Streaming Segment-Level Memory for Multi-Turn Video Reasoning in Multimodal Large Language Models

Paper • 2603.11896 • Published Mar 12 • 10

authored 4 papers 5 months ago

MIRAGE: Evaluating and Explaining Inductive Reasoning Process in Language Models

Paper • 2410.09542 • Published Oct 12, 2024

Focus on Your Question! Interpreting and Mitigating Toxic CoT Problems in Commonsense Reasoning

Paper • 2402.18344 • Published Feb 28, 2024 • 1

Towards Better Chain-of-Thought: A Reflection on Effectiveness and Faithfulness

Paper • 2405.18915 • Published May 29, 2024

MMR-Life: Piecing Together Real-life Scenes for Multimodal Multi-image Reasoning

Paper • 2603.02024 • Published Mar 2 • 47

updated a dataset 5 months ago

Septzzz/MMR-Life

Viewer • Updated Mar 3 • 2.85k • 372 • 3

upvoted a paper 5 months ago

MMR-Life: Piecing Together Real-life Scenes for Multimodal Multi-image Reasoning

Paper • 2603.02024 • Published Mar 2 • 47

submitted a paper to Daily Papers 5 months ago

MMR-Life: Piecing Together Real-life Scenes for Multimodal Multi-image Reasoning

Paper • 2603.02024 • Published Mar 2 • 47

authored 3 papers 6 months ago

RWKU: Benchmarking Real-World Knowledge Unlearning for Large Language Models

Paper • 2406.10890 • Published Jun 16, 2024 • 1

Omni-Reward: Towards Generalist Omni-Modal Reward Modeling with Free-Form Preferences

Paper • 2510.23451 • Published Oct 27, 2025 • 28

Fixing the Broken Compass: Diagnosing and Improving Inference-Time Reward Modeling

Paper • 2503.05188 • Published Mar 7, 2025