tran minh thang
thangtm
·
AI & ML interests
None yet
Recent Activity
updated a collection 23 days ago
reasoning_model updated a collection about 1 month ago
RL updated a collection about 1 month ago
roboticOrganizations
None yet
-
Dr. Zero: Self-Evolving Search Agents without Training Data
Paper • 2601.07055 • Published • 22 -
Self-Evolved Preference Optimization for Enhancing Mathematical Reasoning in Small Language Models
Paper • 2503.04813 • Published • 2 -
Absolute Zero: Reinforced Self-play Reasoning with Zero Data
Paper • 2505.03335 • Published • 191 -
SPICE: Self-Play In Corpus Environments Improves Reasoning
Paper • 2510.24684 • Published • 18
-
DataFlow: An LLM-Driven Framework for Unified Data Preparation and Workflow Automation in the Era of Data-Centric AI
Paper • 2512.16676 • Published • 222 -
Webscale-RL: Automated Data Pipeline for Scaling RL Data to Pretraining Levels
Paper • 2510.06499 • Published • 33 -
FLAMES: Improving LLM Math Reasoning via a Fine-Grained Analysis of the Data Synthesis Pipeline
Paper • 2508.16514 • Published • 1 -
Seed-Coder: Let the Code Model Curate Data for Itself
Paper • 2506.03524 • Published • 8
-
OpenMMReasoner: Pushing the Frontiers for Multimodal Reasoning with an Open and General Recipe
Paper • 2511.16334 • Published • 96 -
Parallel-R1: Towards Parallel Thinking via Reinforcement Learning
Paper • 2509.07980 • Published • 105 -
ParaThinker: Native Parallel Thinking as a New Paradigm to Scale LLM Test-time Compute
Paper • 2509.04475 • Published • 3 -
Stabilizing Reinforcement Learning with LLMs: Formulation and Practices
Paper • 2512.01374 • Published • 107
-
Rank-GRPO: Training LLM-based Conversational Recommender Systems with Reinforcement Learning
Paper • 2510.20150 • Published • 7 -
Tiny Model, Big Logic: Diversity-Driven Optimization Elicits Large-Model Reasoning Ability in VibeThinker-1.5B
Paper • 2511.06221 • Published • 135 -
We-Math 2.0: A Versatile MathBook System for Incentivizing Visual Mathematical Reasoning
Paper • 2508.10433 • Published • 146 -
Stabilizing Reinforcement Learning with LLMs: Formulation and Practices
Paper • 2512.01374 • Published • 107
-
PaddlePaddle/PaddleOCR-VL
Image-Text-to-Text • 1.0B • Updated • 8.32k • 1.62k -
nanonets/Nanonets-OCR2-3B
Image-Text-to-Text • 4B • Updated • 277k • 507 -
deepseek-ai/DeepSeek-OCR
Image-Text-to-Text • 3B • Updated • 2.81M • 3.27k -
MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing
Paper • 2509.22186 • Published • 165
-
ShowUI-π: Flow-based Generative Models as GUI Dexterous Hands
Paper • 2512.24965 • Published • 43 -
VLingNav: Embodied Navigation with Adaptive Reasoning and Visual-Assisted Linguistic Memory
Paper • 2601.08665 • Published • 8 -
HumanoidGen: Data Generation for Bimanual Dexterous Manipulation via LLM Reasoning
Paper • 2507.00833 • Published • 1 -
IGen: Scalable Data Generation for Robot Learning from Open-World Images
Paper • 2512.01773 • Published • 1
-
X-Coder: Advancing Competitive Programming with Fully Synthetic Tasks, Solutions, and Tests
Paper • 2601.06953 • Published • 47 -
Dr. Zero: Self-Evolving Search Agents without Training Data
Paper • 2601.07055 • Published • 22 -
Controlled Self-Evolution for Algorithmic Code Optimization
Paper • 2601.07348 • Published • 115
-
TiDAR: Think in Diffusion, Talk in Autoregression
Paper • 2511.08923 • Published • 129 -
Diffusion Language Models are Super Data Learners
Paper • 2511.03276 • Published • 132 -
What Makes Diffusion Language Models Super Data Learners?
Paper • 2510.04071 • Published -
LLaDA2.0: Scaling Up Diffusion Language Models to 100B
Paper • 2512.15745 • Published • 90
-
FuseAI/FuseO1-DeepSeekR1-QwQ-SkyT1-32B-Preview
33B • Updated • 51 • 129 -
Wait, We Don't Need to "Wait"! Removing Thinking Tokens Improves Reasoning Efficiency
Paper • 2506.08343 • Published • 54 -
Thinking-Free Policy Initialization Makes Distilled Reasoning Models More Effective and Efficient Reasoners
Paper • 2509.26226 • Published • 34
-
Dr. Zero: Self-Evolving Search Agents without Training Data
Paper • 2601.07055 • Published • 22 -
Self-Evolved Preference Optimization for Enhancing Mathematical Reasoning in Small Language Models
Paper • 2503.04813 • Published • 2 -
Absolute Zero: Reinforced Self-play Reasoning with Zero Data
Paper • 2505.03335 • Published • 191 -
SPICE: Self-Play In Corpus Environments Improves Reasoning
Paper • 2510.24684 • Published • 18
-
ShowUI-π: Flow-based Generative Models as GUI Dexterous Hands
Paper • 2512.24965 • Published • 43 -
VLingNav: Embodied Navigation with Adaptive Reasoning and Visual-Assisted Linguistic Memory
Paper • 2601.08665 • Published • 8 -
HumanoidGen: Data Generation for Bimanual Dexterous Manipulation via LLM Reasoning
Paper • 2507.00833 • Published • 1 -
IGen: Scalable Data Generation for Robot Learning from Open-World Images
Paper • 2512.01773 • Published • 1
-
X-Coder: Advancing Competitive Programming with Fully Synthetic Tasks, Solutions, and Tests
Paper • 2601.06953 • Published • 47 -
Dr. Zero: Self-Evolving Search Agents without Training Data
Paper • 2601.07055 • Published • 22 -
Controlled Self-Evolution for Algorithmic Code Optimization
Paper • 2601.07348 • Published • 115
-
DataFlow: An LLM-Driven Framework for Unified Data Preparation and Workflow Automation in the Era of Data-Centric AI
Paper • 2512.16676 • Published • 222 -
Webscale-RL: Automated Data Pipeline for Scaling RL Data to Pretraining Levels
Paper • 2510.06499 • Published • 33 -
FLAMES: Improving LLM Math Reasoning via a Fine-Grained Analysis of the Data Synthesis Pipeline
Paper • 2508.16514 • Published • 1 -
Seed-Coder: Let the Code Model Curate Data for Itself
Paper • 2506.03524 • Published • 8
-
OpenMMReasoner: Pushing the Frontiers for Multimodal Reasoning with an Open and General Recipe
Paper • 2511.16334 • Published • 96 -
Parallel-R1: Towards Parallel Thinking via Reinforcement Learning
Paper • 2509.07980 • Published • 105 -
ParaThinker: Native Parallel Thinking as a New Paradigm to Scale LLM Test-time Compute
Paper • 2509.04475 • Published • 3 -
Stabilizing Reinforcement Learning with LLMs: Formulation and Practices
Paper • 2512.01374 • Published • 107
-
TiDAR: Think in Diffusion, Talk in Autoregression
Paper • 2511.08923 • Published • 129 -
Diffusion Language Models are Super Data Learners
Paper • 2511.03276 • Published • 132 -
What Makes Diffusion Language Models Super Data Learners?
Paper • 2510.04071 • Published -
LLaDA2.0: Scaling Up Diffusion Language Models to 100B
Paper • 2512.15745 • Published • 90
-
Rank-GRPO: Training LLM-based Conversational Recommender Systems with Reinforcement Learning
Paper • 2510.20150 • Published • 7 -
Tiny Model, Big Logic: Diversity-Driven Optimization Elicits Large-Model Reasoning Ability in VibeThinker-1.5B
Paper • 2511.06221 • Published • 135 -
We-Math 2.0: A Versatile MathBook System for Incentivizing Visual Mathematical Reasoning
Paper • 2508.10433 • Published • 146 -
Stabilizing Reinforcement Learning with LLMs: Formulation and Practices
Paper • 2512.01374 • Published • 107
-
FuseAI/FuseO1-DeepSeekR1-QwQ-SkyT1-32B-Preview
33B • Updated • 51 • 129 -
Wait, We Don't Need to "Wait"! Removing Thinking Tokens Improves Reasoning Efficiency
Paper • 2506.08343 • Published • 54 -
Thinking-Free Policy Initialization Makes Distilled Reasoning Models More Effective and Efficient Reasoners
Paper • 2509.26226 • Published • 34
-
PaddlePaddle/PaddleOCR-VL
Image-Text-to-Text • 1.0B • Updated • 8.32k • 1.62k -
nanonets/Nanonets-OCR2-3B
Image-Text-to-Text • 4B • Updated • 277k • 507 -
deepseek-ai/DeepSeek-OCR
Image-Text-to-Text • 3B • Updated • 2.81M • 3.27k -
MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing
Paper • 2509.22186 • Published • 165