Kiều Sơn Tùng

codemaivanngu's activity

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

upvoted a paper 16 days ago

Timestral

Paper • 2610.37585 • Published 19 days ago • 15

upvoted 2 papers 17 days ago

Can Discrete Tokens Serve as Semantically Lossless Representations of Visual Signals?

Paper • 2610.37662 • Published 19 days ago • 37

PDRVLA: A Vision-Language-Action Model with Physical Dynamics Representations

Paper • 2610.37381 • Published 19 days ago • 158

upvoted a paper 21 days ago

On the Limits of Scale: Inverse Scaling in Vision-Language Models

Paper • 2610.27360 • Published 27 days ago • 14

upvoted a paper 23 days ago

Large Flow Language Models

Paper • 2610.28559 • Published 26 days ago • 17

upvoted a paper 26 days ago

Can Visual Generation Expand What Unified Multimodal Models Know?

Paper • 2610.21459 • Published about 1 month ago • 28

upvoted a paper 29 days ago

AutoSFT: An Agentic System for Automated Data Research in Supervised Fine-Tuning

Paper • 2610.22194 • Published about 1 month ago • 41

upvoted 3 papers about 1 month ago

MC-Sparse: Deconstructing and Closing the Dense-Sparse Attention Gap in Diffusion Transformers

Paper • 2610.06801 • Published Oct 5 • 37

DC-SAE: Deep Compression Semantic Autoencoder for Faster Diffusion Convergence

Paper • 2609.39222 • Published Sep 30 • 24

How Far Are We from Removing the Visual Encoder? Scaling Laws for Encoder-Free Multimodal Pretraining

Paper • 2609.35457 • Published Sep 28 • 61

upvoted 4 papers about 2 months ago

Learning Native Reflection in Unified Models with Interleaved Reinforcement Learning

Paper • 2609.35767 • Published Sep 28 • 42

Just MLPs: Efficient Visual State Reconstruction for Multimodal Language Models

Paper • 2609.34972 • Published Sep 28 • 24

Rethinking Training-Inference Mismatch in LLM Reinforcement Learning: Where It Arises and How to Correct It

Paper • 2609.32444 • Published Sep 26 • 23

PACT: From Credit Assignment to Critic Alignment

Paper • 2609.26355 • Published Sep 22 • 21

upvoted 4 papers 2 months ago

SenseNova-U1.5: Towards Native Unified Visual Intelligence

Paper • 2609.11929 • Published Sep 10 • 139

SpatialBlock: Enhancing Spatial Intelligence in LVLMs via Synthetic Block-Stacking Problem

Paper • 2609.07064 • Published Sep 7 • 61

Causal Foundation Models

Paper • 2609.03003 • Published Sep 2 • 26

Don't Drop Dropout: Optimizing Layer Sparsity for Efficient LLM Training and Inference

Paper • 2609.05275 • Published Sep 4 • 23

upvoted a paper 3 months ago

TTPO: Test-Time Policy Optimization

Paper • 2608.27448 • Published Aug 27 • 82

upvoted a collection 3 months ago

Granite 4.2 Language Models

Collection

Efficient reasoning and thinking language models for multilingual generation, coding, and AI assistant workflows. • 27 items • Updated 26 days ago • 55