Songhao Wu

shwu's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a paper 7 days ago

IQuest-Q1: Advancing Foundation Capabilities for Agentic CLI Systems

Paper • 2610.30949 • Published 9 days ago • 104

upvoted a paper 10 days ago

SpecMRL: Redesign Matryoshka Representation Learning within Parametric Spectrum

Paper • 2610.26824 • Published 12 days ago • 89

submitted a paper to Daily Papers 10 days ago

SpecMRL: Redesign Matryoshka Representation Learning within Parametric Spectrum

Paper • 2610.26824 • Published 12 days ago • 89

upvoted a paper 18 days ago

Inducing Process Supervision from Outcome-Only Reinforcement Learning

Paper • 2609.36641 • Published Sep 29 • 23

upvoted a paper 23 days ago

Periodic Weak Spots: Phase Sensitivity from Chunked KV-Cache Compression

Paper • 2609.36322 • Published Sep 28 • 120

liked a model about 1 month ago

IQuestLab/IQuest-Q1

Text Generation • 320B • Updated Sep 29 • 5.04k • 150

upvoted a paper 4 months ago

LatentMoE: Toward Optimal Accuracy per FLOP and Parameter in Mixture of Experts

Paper • 2601.18089 • Published Jan 26 • 1

authored a paper 5 months ago

Redesign Mixture-of-Experts Routers with Manifold Power Iteration

Paper • 2606.12397 • Published Jun 10 • 91

upvoted a paper 5 months ago

Redesign Mixture-of-Experts Routers with Manifold Power Iteration

Paper • 2606.12397 • Published Jun 10 • 91

submitted a paper to Daily Papers 5 months ago

Redesign Mixture-of-Experts Routers with Manifold Power Iteration

Paper • 2606.12397 • Published Jun 10 • 91

commented 2 papers 5 months ago

Your UnEmbedding Matrix is Secretly a Feature Lens for Text Embeddings

Paper • 2606.07502 • Published Jun 5 • 100 •

8

Your UnEmbedding Matrix is Secretly a Feature Lens for Text Embeddings

Paper • 2606.07502 • Published Jun 5 • 100 •

8

authored 3 papers 5 months ago

From 1,000,000 Users to Every User: Scaling Up Personalized Preference for User-level Alignment

Paper • 2503.15463 • Published Mar 19, 2025 • 1

PolarQuant: Leveraging Polar Transformation for Efficient Key Cache Quantization and Decoding Acceleration

Paper • 2502.00527 • Published Feb 1, 2025 • 3

Your UnEmbedding Matrix is Secretly a Feature Lens for Text Embeddings

Paper • 2606.07502 • Published Jun 5 • 100

upvoted 2 papers 5 months ago

PolarQuant: Leveraging Polar Transformation for Efficient Key Cache Quantization and Decoding Acceleration

Paper • 2502.00527 • Published Feb 1, 2025 • 3

Your UnEmbedding Matrix is Secretly a Feature Lens for Text Embeddings

Paper • 2606.07502 • Published Jun 5 • 100

submitted a paper to Daily Papers 5 months ago

Your UnEmbedding Matrix is Secretly a Feature Lens for Text Embeddings

Paper • 2606.07502 • Published Jun 5 • 100

upvoted a paper 5 months ago

DelTA: Discriminative Token Credit Assignment for Reinforcement Learning from Verifiable Rewards

Paper • 2605.21467 • Published May 20 • 100

upvoted a paper 9 months ago

Learning beyond Teacher: Generalized On-Policy Distillation with Reward Extrapolation

Paper • 2602.12125 • Published Feb 12 • 70