Tencent

Verified

AI & ML interests

None defined yet.

Recent Activity

cjeen submitted a paper 1 day ago

Rollout-Marginal Distillation for Long-Horizon Autoregressive Video Generation

EddieYang428 submitted a paper 5 days ago

Adaptive Reward Routing: Dynamic Multi-Reward Optimization for Joint Audio-Video Diffusion via Forward-Process RL

Svard submitted a paper 8 days ago

Draft-KV: Learning Useful Latent Communication Between Language Models

View all activity

Papers

Rollout-Marginal Distillation for Long-Horizon Autoregressive Video Generation

Adaptive Reward Routing: Dynamic Multi-Reward Optimization for Joint Audio-Video Diffusion via Forward-Process RL

View all Papers

submitted a paper to Daily Papers 1 day ago

Rollout-Marginal Distillation for Long-Horizon Autoregressive Video Generation

Paper • 2609.37925 • Published 8 days ago • 18

submitted a paper to Daily Papers 5 days ago

Adaptive Reward Routing: Dynamic Multi-Reward Optimization for Joint Audio-Video Diffusion via Forward-Process RL

Paper • 2609.37200 • Published 8 days ago • 137

submitted a paper to Daily Papers 8 days ago

Draft-KV: Learning Useful Latent Communication Between Language Models

Paper • 2609.34754 • Published 9 days ago • 8

submitted a paper to Daily Papers 8 days ago

Just MLPs: Efficient Visual State Reconstruction for Multimodal Language Models

Paper • 2609.34972 • Published 9 days ago • 30

submitted a paper to Daily Papers 8 days ago

AdaTutoRank: Learning to Rerank Document Sets via Adaptive Tutoring Optimization for RAG and Deep Research

Paper • 2609.32472 • Published 11 days ago • 19

submitted a paper to Daily Papers 9 days ago

SLCA-GRPO: Resolving Cross-Segment Credit Misattribution in Tool-Calling RL

Paper • 2609.29050 • Published 13 days ago • 13

submitted a paper to Daily Papers 13 days ago

RewardVerse: Rubric-Guided Policy Optimization for Video Reward Modeling

Paper • 2609.22947 • Published 18 days ago • 43

xiaoxiaoshadiao

updated 2 models 15 days ago

tencent/EVIE-8B

Visual Document Retrieval • 8B • Updated 15 days ago • 1.14k • 31

tencent/EVIE-4.5B

Visual Document Retrieval • 5B • Updated 15 days ago • 2.44k • 33

submitted a paper to Daily Papers 19 days ago

WeVisDoc: From Coverage to Capability for Robust End-to-End Document Parsing

Paper • 2609.20423 • Published 20 days ago • 48

updated a collection 19 days ago

WeVisDoc

3 items • Updated 15 days ago • 15

updated 2 models 19 days ago

tencent/WeVisDoc-4B

4B • Updated 19 days ago • 1.98k • 50

tencent/WeVisDoc-2B

2B • Updated 19 days ago • 15.4k • 27

published 2 models 19 days ago

tencent/WeVisDoc-4B

4B • Updated 19 days ago • 1.98k • 50

tencent/WeVisDoc-2B

2B • Updated 19 days ago • 15.4k • 27

updated a collection 20 days ago

WeVisDoc

3 items • Updated 15 days ago • 15

in tencent/WeMM-Embedding-2B 22 days ago

Image vs video document input: large gap in text→moment retrieval quality (with measurements)

#3 opened about 1 month ago by

authored a paper 22 days ago

SAS: Simple Attention Sparsification via End-to-End Optimization of Context Ranking

Paper • 2609.13141 • Published 26 days ago • 69

published a model 23 days ago

tencent/Simple-Attention-Sparsification

Text Generation • Updated 23 days ago • 11