Wang Bowei

observerw

observerw

AI & ML interests

LLM; RTL Design; HDL (Hardware Description Language) Generation; DSL (Domain Specific Language) Generation; Reinforcement Learning; Constraint Decoding;

Recent Activity

upvoted a collection 6 days ago

Qwen3.5

updated a bucket 7 days ago

observerw/main

published a bucket 7 days ago

observerw/main

View all activity

Organizations

None yet

upvoted a collection 6 days ago

Qwen3.5

Collection

21 items • Updated Mar 9 • 1.47k

upvoted a paper 2 months ago

SWE-Master: Unleashing the Potential of Software Engineering Agents via Post-Training

Paper • 2602.03411 • Published Feb 3 • 39

upvoted a paper 4 months ago

DAComp: Benchmarking Data Agents across the Full Data Intelligence Lifecycle

Paper • 2512.04324 • Published Dec 3, 2025 • 159

upvoted an article 5 months ago

Article

Training and Finetuning Sparse Embedding Models with Sentence Transformers v5

Jul 1, 2025

•

137

upvoted a paper 5 months ago

Stronger Together: On-Policy Reinforcement Learning for Collaborative LLMs

Paper • 2510.11062 • Published Oct 13, 2025 • 29

upvoted 2 collections 7 months ago

Inference-free IR model

Collection

Online-inference-free sparse encoding IR models trained by OpenSearch. Combination of efficiency and search relevance. • 4 items • Updated Jun 18, 2025 • 7

jina-code-embeddings

Collection

high quality code embeddings trained from code generation models • 7 items • Updated Feb 27 • 14

upvoted a collection 12 months ago

Qwen3

Collection

84 items • Updated Dec 31, 2025 • 1.74k

upvoted a paper 12 months ago

ChiseLLM: Unleashing the Power of Reasoning LLMs for Chisel Agile Hardware Development

Paper • 2504.19144 • Published Apr 27, 2025 • 4

upvoted a collection 12 months ago

ChiseLLM-v1.0

Collection

ChiseLLM: Reasoning LLMs optimized for Chisel code generation • 5 items • Updated Mar 2 • 2

Wang Bowei

AI & ML interests

Recent Activity

Organizations

observerw's activity

Training and Finetuning Sparse Embedding Models with Sentence Transformers v5