Tencent

Verified

AI & ML interests

None defined yet.

Recent Activity

gatilin submitted a paper about 15 hours ago

YOLO-PEFT: Parameter-Efficient Fine-Tuning on YOLO Family

MarcusGu submitted a paper 5 days ago

WorldCycle: Self-Verifiable Reinforcement Learning for Long-Horizon Video World Models

Zonghao2025 submitted a paper 6 days ago

SkillJack: Persistent Skill Backdoors in Self-Evolving Agents

View all activity

Papers

YOLO-PEFT: Parameter-Efficient Fine-Tuning on YOLO Family

EnvACE: Internalizing Environment Dynamics via World Rehearsal for Agentic Reinforcement Learning

View all Papers

tencent 's papers 103

Submitted by

Xu Lin

YOLO-PEFT: Parameter-Efficient Fine-Tuning on YOLO Family

tencent

1

Submitted by

3

EnvACE: Internalizing Environment Dynamics via World Rehearsal for Agentic Reinforcement Learning

tencent

Submitted by

Fury James

WorldCycle: Self-Verifiable Reinforcement Learning for Long-Horizon Video World Models

tencent

Submitted by

Yushi SUN

When Memory Lies: An Empirical Study of Spatial Memory Staleness in VLM Agents

tencent

2

Submitted by

Zonghao Ying

SkillJack: Persistent Skill Backdoors in Self-Evolving Agents

tencent

Submitted by

Yuqing Li

A New Role for Relevance: Guiding Corpus Interaction in Agentic Search

tencent

Submitted by

taesiri

Tencent WorkBuddy Bench: A Multi-Domain Coding-Agent Benchmark with Contamination-Resistant Task Construction

tencent

Submitted by

tianlezeng

ReferTrack: Referring Then Tracking for Embodied Visual Tracking

tencent

Submitted by

Kailin Jiang

Beyond Relevance-Centric Retrieval: Rubric-Oriented Document Set Selection and Ranking

tencent

Submitted by

Jeff

EvolvingWorld: An Open-Schema Framework for Co-Evolving Role-Play Agents and World Model in Interactive Literary World

tencent

Submitted by

Niels Rogge

HunyuanOCR-1.5: Making Lightweight OCR VLMs Faster and Better

tencent

Submitted by

Zican Hu

Bridging Interleaved Multi-Modal Reasoning as a Unified Decision Process

tencent