Sergiu Han

hgsg

·

https://sergiudm.github.io/

sergiudm

AI & ML interests

NLP, agent

Recent Activity

liked a model 4 days ago

moonshotai/Kimi-K3

liked a model 4 days ago

tencent/HiLS-Attention-7B

liked a model 6 days ago

ATH-MaaS/OvisOCR2

View all activity

Organizations

upvoted a collection about 1 month ago

DeepSpec

12 items • Updated Jun 28 • 81

upvoted a paper about 1 month ago

LoopCoder-v2: Only Loop Once for Efficient Test-Time Computation Scaling

Paper • 2606.18023 • Published Jun 16 • 210

upvoted 2 papers about 2 months ago

VisualClaw: A Real-Time, Personalized Agent for the Physical World

Paper • 2606.16295 • Published Jun 15 • 28

Harness Updating Is Not Harness Benefit: Disentangling Evolution Capabilities in Self-Evolving LLM Agents

Paper • 2605.30621 • Published May 28 • 23

upvoted a collection about 2 months ago

Mistral Medium 3.5

Our first flaship models handling instruction-following, reasoning, and coding in a single set of opened-weights. • 2 items • Updated Apr 29 • 20

upvoted a paper about 2 months ago

AutoMedBench: Towards Medical AutoResearch with Agentic AI Models

Paper • 2606.01961 • Published Jun 3 • 28

upvoted 2 papers 2 months ago

StepAudio 2.5 Technical Report

Paper • 2605.23463 • Published May 22 • 49

AutoResearchClaw: Self-Reinforcing Autonomous Research with Human-AI Collaboration

Paper • 2605.20025 • Published May 19 • 191

upvoted an article 3 months ago

Article

Forge: Scalable Agent RL Framework and Algorithm

MiniMax-AI

•

Feb 13

• 156

upvoted 2 collections 3 months ago

Qwen2.5-VL

Vision-language model series based on Qwen2.5 • 10 items • Updated Mar 2 • 567

Ling 2.6

Ling-2.6 series is designed for real-world agents that require fast responses, strong execution, and high token efficiency, with several sized SKUs. • 6 items • Updated Jun 22 • 13

upvoted an article 3 months ago

Article

NEO-unify: Building Native Multimodal Unified Models End to End

sensenova

•

Mar 5

• 172

upvoted a paper 3 months ago

VLAA-GUI: Knowing When to Stop, Recover, and Search, A Modular Framework for GUI Automation

Paper • 2604.21375 • Published Apr 23 • 19

upvoted a collection 3 months ago

DeepSeek-V4

6 items • Updated Jun 27 • 764

upvoted 2 papers 4 months ago

ClawArena: Benchmarking AI Agents in Evolving Information Environments

Paper • 2604.04202 • Published Apr 5 • 37

Your Agent, Their Asset: A Real-World Safety Analysis of OpenClaw

Paper • 2604.04759 • Published Apr 6 • 24

upvoted a collection 4 months ago

Gemma 4

16 items • Updated 10 days ago • 1.06k

upvoted a paper 4 months ago

Omni-SimpleMem: Autoresearch-Guided Discovery of Lifelong Multimodal Agent Memory

Paper • 2604.01007 • Published Apr 2 • 31

upvoted a collection 4 months ago

Trinity-Large-Thinking

5 items • Updated Apr 10 • 32

upvoted a paper 4 months ago

Cheers: Decoupling Patch Details from Semantic Representations Enables Unified Multimodal Comprehension and Generation

Paper • 2603.12793 • Published Mar 13 • 38