Tencent Hunyuan

AI & ML interests

The official organization of Tencent Hunyuan team

Recent Activity

zli12321 submitted a paper 5 days ago

Long-Horizon-Terminal-Bench: Testing the Limits of Agents on Long-Horizon Terminal Tasks with Dense Reward-Based Grading

tangmen submitted a paper 10 days ago

TurnOPD: Making On-Policy Distillation Turn-Aware for Efficient Long-Horizon Agent Training

rayleizhu submitted a paper 10 days ago

Hierarchical Sparse Attention Done Right: Toward Infinite Context Modeling

View all activity

Papers

MeanFlowNFT: Bringing Forward-Process RL to Average-Velocity Generators

Harness Handbook: Making Evolving Agent Harnesses Readable,Navigable, and Editable

View all Papers

submitted a paper to Daily Papers 5 days ago

Long-Horizon-Terminal-Bench: Testing the Limits of Agents on Long-Horizon Terminal Tasks with Dense Reward-Based Grading

Paper • 2607.08964 • Published 9 days ago • 72

submitted a paper to Daily Papers 10 days ago

TurnOPD: Making On-Policy Distillation Turn-Aware for Efficient Long-Horizon Agent Training

Paper • 2607.05804 • Published 11 days ago • 18

submitted a paper to Daily Papers 10 days ago

Hierarchical Sparse Attention Done Right: Toward Infinite Context Modeling

Paper • 2607.02980 • Published 15 days ago • 78

submitted a paper to Daily Papers 15 days ago

When Search Agents Should Ask: DiscoBench for Clarification-Aware Deep Search

Paper • 2606.27669 • Published 22 days ago • 15

rhli

submitted a paper to Daily Papers 15 days ago

Optimizing Visual Generative Models via Distribution-wise Rewards

Paper • 2607.02291 • Published 16 days ago • 18

submitted a paper to Daily Papers 17 days ago

GEAR: Guided End-to-End AutoRegression for Image Synthesis

Paper • 2606.32039 • Published 18 days ago • 34

submitted a paper to Daily Papers 17 days ago

PolyFlow: Continuous Topology Embedding Flow Matching for Artist-style Mesh Generation

Paper • 2606.30673 • Published 23 days ago • 12

submitted a paper to Daily Papers 18 days ago

GUICrafter: Weakly-Supervised GUI Agent Leveraging Massive Unannotated Screenshots

Paper • 2606.29705 • Published 19 days ago • 16

submitted a paper to Daily Papers 22 days ago

ViQ: Text-Aligned Visual Quantized Representations at Any Resolution

Paper • 2606.27313 • Published 23 days ago • 38

submitted a paper to Daily Papers 23 days ago

VeriEvol: Scaling Multimodal Mathematical Reasoning via Verifiable Evol-Instruct

Paper • 2606.23543 • Published 26 days ago • 6

submitted a paper to Daily Papers 25 days ago

FastMix: Fast Data Mixture Optimization via Gradient Descent

Paper • 2606.14971 • Published Jun 12 • 3

submitted a paper to Daily Papers 25 days ago

Training Open Models for Agentic Phone Use

Paper • 2606.23049 • Published 26 days ago • 17

submitted a paper to Daily Papers 29 days ago

STARE: Surprisal-Guided Token-Level Advantage Reweighting for Policy Entropy Stability

Paper • 2606.19236 • Published about 1 month ago • 13

submitted a paper to Daily Papers about 1 month ago

Stream3D-VLM: Online 3D Spatial Understanding with Incremental Geometry Priors

Paper • 2606.06891 • Published Jun 5 • 4

submitted a paper to Daily Papers about 2 months ago

GEM: Generative Supervision Helps Embodied Intelligence

Paper • 2605.28548 • Published May 27 • 32

in Tencent-Hunyuan/HunyuanDiT about 2 months ago

[Admin maintenance] Support new ZeroGPU hardware

#7 opened about 2 months ago by

submitted a paper to Daily Papers about 2 months ago

Reinforcing Few-step Generators via Reward-Tilted Distribution Matching

Paper • 2605.26108 • Published May 25 • 7

submitted a paper to Daily Papers 2 months ago

Learning to Foresee: Unveiling the Unlocking Efficiency of On-Policy Distillation

Paper • 2605.11739 • Published May 13 • 60

submitted a paper to Daily Papers 2 months ago

Unlocking Dense Metric Depth Estimation in VLMs

Paper • 2605.15876 • Published May 15 • 14

dmux

submitted a paper to Daily Papers 2 months ago

Debiased Model-based Representations for Sample-efficient Continuous Control

Paper • 2605.11711 • Published May 12 • 9