🔄 In a Training Loop

Xinping Zhao

Yuki131

·

AI & ML interests

LLMs, RAG, Embedding, Reranker——A Pokémon Trainer on a journey to become a Pokémon Master.

Recent Activity

liked a dataset 3 days ago

lightonai/embeddings-fine-tuning

liked a model 3 days ago

omai-research/milco-650m

liked a model 3 days ago

LiquidAI/LFM2.5-Encoder-350M

View all activity

Organizations

upvoted a collection 5 days ago

Sentence Transformers v5.4 integrations

See https://huggingface.co/blog/multimodal-sentence-transformers • 37 items • Updated 6 days ago • 6

upvoted a paper 6 days ago

A New Role for Relevance: Guiding Corpus Interaction in Agentic Search

Paper • 2607.24223 • Published 8 days ago • 92

upvoted 2 papers 12 days ago

Beyond Relevance-Centric Retrieval: Rubric-Oriented Document Set Selection and Ranking

Paper • 2607.19747 • Published 13 days ago • 31

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

Paper • 2607.20145 • Published 13 days ago • 74

upvoted a collection 17 days ago

DenseOn & LateOn

A collection of open state-of-the-art single and multi-vector models for English retrieval • 9 items • Updated 4 days ago • 13

upvoted a paper 18 days ago

RESOURCE2SKILL: Distilling Executable Agent Skills from Human-Created Multimodal Resources

Paper • 2606.29538 • Published 19 days ago • 142

upvoted 3 articles 18 days ago

Article

NVIDIA Nemotron 3 Embed Ranks #1 Overall on RTEB, Advancing Agentic Retrieval

nvidia

•

18 days ago

• 58

Article

Build a Domain-Specific Embedding Model in Under a Day

nvidia

•

Mar 20

• 77

Article

One Adapter, Both Modalities: Field Notes from Building and Serving a Multimodal Reranker

lightonai

•

18 days ago

• 19

upvoted 2 papers 19 days ago

Ring-Zero: Scaling Zero RL to a Trillion Parameters for Emergent Reasoning

Paper • 2607.12395 • Published 21 days ago • 99

KnowAct-GUIClaw: Know Deeply, Act Perfectly, Personal GUI Assistant with Self-Evolving Memory and Skill

Paper • 2607.12625 • Published 20 days ago • 80

upvoted a paper 26 days ago

Quantifying and Expanding the Theoretical Capacity of Late-Interaction Retrieval Models

Paper • 2607.05803 • Published 28 days ago • 10

upvoted a collection about 1 month ago

Merino — unified embedding + reranker models

One model for both halves of RAG retrieval; a strong default per size. Contact baa.ai for the optimal pick for your corpus. • 10 items • Updated Jun 30 • 2

upvoted an article about 1 month ago

Article

Introducing the Ettin Reranker Family

tomaarsen

•

May 19

• 56

upvoted a collection about 1 month ago

Ettin Rerankers

8 items • Updated May 19 • 10

upvoted a paper about 1 month ago

Qwen-AgentWorld: Language World Models for General Agents

Paper • 2606.24597 • Published Jun 23 • 154

upvoted 2 collections about 1 month ago

Lychee-KaLM-Reranker

4 items • Updated 11 days ago • 1

Lychee-KaLM-Reranker

13 items • Updated 25 days ago • 1

upvoted 2 papers about 1 month ago

EvoEmbedding: Evolvable Representations for Long-Context Retrieval and Agentic Memory

Paper • 2606.21649 • Published Jun 19 • 35

KaLM-Reranker-V1: Fast but Not Late Interaction for Compressed Document Reranking

Paper • 2606.22807 • Published Jun 22 • 49