Starstrek

Stars321123

Stars321

AI & ML interests

Recent Activity

upvoted a paper about 15 hours ago

T2I-R1: Reinforcing Image Generation with Collaborative Semantic-level and Token-level CoT

liked a Space 1 day ago

Qwen/Qwen3-Demo

upvoted an article 1 day ago

How to Build an MCP Server with Gradio

View all activity

Organizations

None yet

Stars321123's activity

upvoted a paper about 15 hours ago

T2I-R1: Reinforcing Image Generation with Collaborative Semantic-level and Token-level CoT

Paper • 2505.00703 • Published 2 days ago • 26

upvoted an article 1 day ago

Article

How to Build an MCP Server with Gradio

4 days ago

• 65

upvoted 2 papers 3 days ago

UniversalRAG: Retrieval-Augmented Generation over Multiple Corpora with Diverse Modalities and Granularities

Paper • 2504.20734 • Published 5 days ago • 55

Reinforcement Learning for Reasoning in Large Language Models with One Training Example

Paper • 2504.20571 • Published 5 days ago • 76

upvoted a collection 5 days ago

Qwen3

Collection

27 items • Updated 1 day ago • 498

upvoted 2 papers 6 days ago

BitNet v2: Native 4-bit Activations with Hadamard Transformation for 1-bit LLMs

Paper • 2504.18415 • Published 8 days ago • 40

TTRL: Test-Time Reinforcement Learning

Paper • 2504.16084 • Published 11 days ago • 100

upvoted a paper 7 days ago

Perspective-Aware Reasoning in Vision-Language Models via Mental Imagery Simulation

Paper • 2504.17207 • Published 10 days ago • 28

upvoted a paper 8 days ago

PHYBench: Holistic Evaluation of Physical Perception and Reasoning in Large Language Models

Paper • 2504.16074 • Published 11 days ago • 35

upvoted an article 8 days ago

Article

Tiny Agents: a MCP-powered agent in 50 lines of code

9 days ago

• 207

upvoted 4 papers 9 days ago

Contrastive Localized Language-Image Pre-Training

Paper • 2410.02746 • Published Oct 3, 2024 • 38

Breaking the Modality Barrier: Universal Embedding Learning with Multimodal LLMs

Paper • 2504.17432 • Published 10 days ago • 38

WALL-E: World Alignment by Rule Learning Improves World Model-based LLM Agents

Paper • 2410.07484 • Published Oct 9, 2024 • 51

WALL-E 2.0: World Alignment by NeuroSymbolic Learning improves World Model-based LLM Agents

Paper • 2504.15785 • Published 12 days ago • 18

upvoted a paper 11 days ago

X-Teaming: Multi-Turn Jailbreaks and Defenses with Adaptive Multi-Agents

Paper • 2504.13203 • Published 18 days ago • 30

upvoted 2 papers 12 days ago

Analyzing LLMs' Knowledge Boundary Cognition Across Languages Through the Lens of Internal Representations

Paper • 2504.13816 • Published 15 days ago • 17

NodeRAG: Structuring Graph-based RAG with Heterogeneous Nodes

Paper • 2504.11544 • Published 18 days ago • 41

upvoted a collection 15 days ago

Gemma 3 QAT

Collection

Quantization Aware Trained (QAT) Gemma 3 checkpoints. The model preserves similar quality as half precision while using 3x less memory. • 19 items • Updated 16 days ago • 26

upvoted an article 15 days ago

Article

Cohere on Hugging Face Inference Providers 🔥

18 days ago

• 124

upvoted a paper 16 days ago

ReTool: Reinforcement Learning for Strategic Tool Use in LLMs

Paper • 2504.11536 • Published 18 days ago • 60