Fengshenbang-LM

non-profit

https://github.com/IDEA-CCNL/Fengshenbang-LM

Activity Feed Request to join this org

AI & ML interests

If you are searching chinese NLP pretrained model, Fengshenbang-LM is all your need! NLP, Pretrain models, Big models, Chinese domain, Fengshenbang-LM

Recent Activity

wanng authored a paper 24 days ago

E2A-Bench: Benchmarking Evidence-to-Action Reliability in Financial Chart Reasoning

wanng authored a paper 24 days ago

CoWork-X: Experience-Optimized Co-Evolution for Multi-Agent Collaboration System

wanng submitted a paper 24 days ago

E2A-Bench: Benchmarking Evidence-to-Action Reliability in Financial Chart Reasoning

View all activity

authored 2 papers 24 days ago

E2A-Bench: Benchmarking Evidence-to-Action Reliability in Financial Chart Reasoning

Paper • 2609.14302 • Published 27 days ago • 3

CoWork-X: Experience-Optimized Co-Evolution for Multi-Agent Collaboration System

Paper • 2602.05004 • Published Feb 4

submitted 2 papers to Daily Papers 24 days ago

E2A-Bench: Benchmarking Evidence-to-Action Reliability in Financial Chart Reasoning

Paper • 2609.14302 • Published 27 days ago • 3

Learning Sparse Decision Trees via Transformer Variational Auto-Encoders

Paper • 2609.01430 • Published Sep 1 • 2

authored a paper about 1 month ago

Learning Where Outcomes Change:Credit-Addressable Reasoning for Multimodal Geometry

Paper • 2608.30457 • Published Aug 31 • 7

submitted a paper to Daily Papers about 1 month ago

Learning Where Outcomes Change:Credit-Addressable Reasoning for Multimodal Geometry

Paper • 2608.30457 • Published Aug 31 • 7

authored 3 papers about 1 month ago

LongWoF-Bench: Evaluating EvoMap Genes for Verifiable Long-Workflow Tasks

Paper • 2608.23200 • Published Aug 24 • 7

AutoResearch: Insight In, Hallucination Out

Paper • 2608.17906 • Published Aug 23 • 24

Simple-OPD: Demystifying Warm-up for On-policy Distillation

Paper • 2608.06802 • Published Aug 7 • 1

submitted 2 papers to Daily Papers about 2 months ago

LongWoF-Bench: Evaluating EvoMap Genes for Verifiable Long-Workflow Tasks

Paper • 2608.23200 • Published Aug 24 • 7

AutoResearch: Insight In, Hallucination Out

Paper • 2608.17906 • Published Aug 23 • 24

authored a paper about 2 months ago

Route by Kinematics, Act by Observation: Kinematics-Supervised Expert Routing in MoE-Augmented VLA

Paper • 2607.26807 • Published Jul 29 • 1

authored a paper 3 months ago

Bayesian-Agent: Posterior-Guided Skill Evolution for LLM Agent Harnesses

Paper • 2606.08348 • Published Jun 6 • 17

authored 2 papers 4 months ago

WebRISE: Requirement-Induced State Evaluation for MLLM-Generated Web Artifacts

Paper • 2606.03220 • Published Jun 2 • 11

Smaller Models are Natural Explorers for Policy-Level Diversity in GRPO

Paper • 2605.30789 • Published Jun 2 • 27

in IDEA-CCNL/Erlangshen-MegatronBert-1.3B 4 months ago

支持1024的序列长度吗

#3 opened 4 months ago by

submitted a paper to Daily Papers 4 months ago

Bayesian-Agent: Posterior-Guided Skill Evolution for LLM Agent Harnesses

Paper • 2606.08348 • Published Jun 6 • 17

submitted a paper to Daily Papers 7 months ago

The Curse and Blessing of Mean Bias in FP4-Quantized LLM Training

Paper • 2603.10444 • Published Mar 11 • 14

authored 2 papers 9 months ago

ProFit: Leveraging High-Value Signals in SFT via Probability-Guided Token Selection

Paper • 2601.09195 • Published Jan 14 • 15

SIN-Bench: Tracing Native Evidence Chains in Long-Context Multimodal Scientific Interleaved Literature

Paper • 2601.10108 • Published Jan 15 • 7