Yinhong Liu

yinhongliu's activity

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

authored 10 papers 6 days ago

From Chains to Graphs: Self-Structured Reasoning for General-Domain LLMs

Paper • 2601.03597 • Published Jan 7

MDSEval: A Meta-Evaluation Benchmark for Multimodal Dialogue Summarization

Paper • 2510.01659 • Published Oct 2, 2025

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

Paper • 2605.18703 • Published May 18 • 51

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

Paper • 2606.13106 • Published Jun 11 • 23

Operadic consistency: a label-free signal for compositional reasoning failures in LLMs

Paper • 2606.13649 • Published Jun 11

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

Paper • 2606.17682 • Published Jun 16 • 27

Fairer Preferences Elicit Improved Human-Aligned Large Language Model Judgments

Paper • 2406.11370 • Published Jun 17, 2024

Prompt Compression for Large Language Models: A Survey

Paper • 2410.12388 • Published Oct 17, 2024

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

Paper • 2610.21463 • Published 7 days ago • 24

Action-Space Shaping for LLM Agents: Measuring and Mitigating Tool-Schema Bias

Paper • 2609.34971 • Published 24 days ago

upvoted a paper 6 days ago

Mosaic: Multi-Session Agentic Reinforcement Learning

Paper • 2610.22174 • Published 7 days ago • 63

upvoted a paper 4 months ago

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

Paper • 2606.13106 • Published Jun 11 • 23

upvoted a paper 5 months ago

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

Paper • 2605.18703 • Published May 18 • 51

upvoted a paper about 1 year ago

Depth-Breadth Synergy in RLVR: Unlocking LLM Reasoning Gains with Adaptive Exploration

Paper • 2508.13755 • Published Aug 19, 2025 • 14

upvoted a paper over 1 year ago

Visual Planning: Let's Think Only with Images

Paper • 2505.11409 • Published May 16, 2025 • 59

authored 3 papers about 2 years ago

Instruct-SCTG: Guiding Sequential Controlled Text Generation through Instructions

Paper • 2312.12299 • Published Dec 19, 2023

Aligning with Human Judgement: The Role of Pairwise Preference in Large Language Model Evaluators

Paper • 2403.16950 • Published Mar 25, 2024 • 4

MR-BEN: A Comprehensive Meta-Reasoning Benchmark for Large Language Models

Paper • 2406.13975 • Published Jun 20, 2024

updated a model about 2 years ago

yinhongliu/sft_openassistant-guanaco

Updated Aug 30, 2024

New activity in yinhongliu/mistral_pairwise_summeval_v0.1 about 2 years ago

Upload 2 json files

#2 opened about 2 years ago by

tl569