Kiều Sơn Tùng

codemaivanngu's activity

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

upvoted 4 papers 3 days ago

Learn What's Left, Not What's Mastered: Saturation Aware Advantage Reweighting for Multi-Reward Policy Optimization

Paper • 2608.16072 • Published 5 days ago • 147

DFM Mimir v1: An Open HRM Delivering Frontier Performance at 1B Parameters Using Only Permissible Post-Training Data

Paper • 2608.13517 • Published 9 days ago • 29

Improving the matrix multiplication exponent with modern optimization and AlphaEvolve

Paper • 2608.16884 • Published 5 days ago • 16

Modular Cognitive Architecture Emerges in Large Language Models

Paper • 2608.13567 • Published Jun 27 • 14

upvoted a paper 10 days ago

Stealing Reasoning Traces from Proprietary LLM APIs

Paper • 2608.09867 • Published 12 days ago • 111

upvoted 2 papers 19 days ago

Mage-VL: An Efficient Codec-Native Streaming Multimodal Foundation Model

Paper • 2607.24904 • Published 26 days ago • 37

Chimera: Designing and Chinchilla-Scaling Hybrid Visual Diffusion Transformers

Paper • 2607.28611 • Published 23 days ago • 22

upvoted a paper 21 days ago

Multi-Head Attention Residuals

Paper • 2607.27230 • Published about 1 month ago • 11

upvoted 3 papers 25 days ago

Molt: A Scalable PyTorch-Native Training Framework for Agentic Reinforcement Learning

Paper • 2607.21653 • Published about 1 month ago • 32

Closing the Loop: Training-Free Revisit Consistency for Autoregressive Generative Rendering

Paper • 2607.21848 • Published 30 days ago • 9

DataPrep-Bench: Benchmarking LLMs as Training Data Preparators

Paper • 2607.20465 • Published May 19 • 56

upvoted a paper 27 days ago

Scaling Laws for Hypernetwork-Based Knowledge Injection in Large Language Models

Paper • 2607.19604 • Published Jul 21 • 17

upvoted 2 papers 28 days ago

Visual Contrastive Self-Distillation

Paper • 2607.21556 • Published 30 days ago • 52

Predictive Divergence Masks for LLM RL

Paper • 2607.10848 • Published Jul 12 • 11

upvoted 4 papers 30 days ago

SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD

Paper • 2607.20145 • Published about 1 month ago • 74

Generative World Renderer at the Speed of Play

Paper • 2607.18703 • Published Jul 21 • 83

Environment-free Synthetic Data Generation for API-Calling Agents

Paper • 2607.16900 • Published Jul 18 • 21

SciForma: Structure-Faithful Generation of Scientific Diagrams

Paper • 2607.18091 • Published Jul 20 • 24

upvoted 2 papers about 1 month ago

Loop the Loopies!

Paper • 2607.16051 • Published Jul 17 • 77

RoboTTT: Context Scaling for Robot Policies

Paper • 2607.15275 • Published Jul 16 • 23