Ruizhe Li

rzdiversity's activity

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

authored a paper 1 day ago

When Does Correction Become Repair? Mechanistic Auditing of Internal Interventions in Tool-Using LLMs

Paper • 2609.36138 • Published 6 days ago • 6

upvoted a paper 1 day ago

When Does Correction Become Repair? Mechanistic Auditing of Internal Interventions in Tool-Using LLMs

Paper • 2609.36138 • Published 6 days ago • 6

submitted a paper to Daily Papers 1 day ago

When Does Correction Become Repair? Mechanistic Auditing of Internal Interventions in Tool-Using LLMs

Paper • 2609.36138 • Published 6 days ago • 6

authored a paper 3 days ago

See it, Say it, Sorted: Mechanistic Diagnosis and Parameter-Space Mitigation of Emergent Misalignment in LLMs

Paper • 2609.34970 • Published 6 days ago • 4

upvoted a paper 3 days ago

See it, Say it, Sorted: Mechanistic Diagnosis and Parameter-Space Mitigation of Emergent Misalignment in LLMs

Paper • 2609.34970 • Published 6 days ago • 4

submitted a paper to Daily Papers 3 days ago

See it, Say it, Sorted: Mechanistic Diagnosis and Parameter-Space Mitigation of Emergent Misalignment in LLMs

Paper • 2609.34970 • Published 6 days ago • 4

authored 3 papers 29 days ago

Locked at the Entrance, Open Inside: Where RLVR Narrows the Solution Space

Paper • 2608.29188 • Published Aug 29 • 11

Orthogonal Hierarchical Decomposition for Structure-Aware Table Understanding with Large Language Models

Paper • 2602.01969 • Published Feb 2

Marco-Bench-MIF: On Multilingual Instruction-Following Capability of Large Language Models

Paper • 2507.11882 • Published Jul 16, 2025 • 1

upvoted a paper 29 days ago

Locked at the Entrance, Open Inside: Where RLVR Narrows the Solution Space

Paper • 2608.29188 • Published Aug 29 • 11

submitted a paper to Daily Papers 29 days ago

Locked at the Entrance, Open Inside: Where RLVR Narrows the Solution Space

Paper • 2608.29188 • Published Aug 29 • 11

authored a paper 9 months ago

Spurious Rewards Paradox: Mechanistically Understanding How RLVR Activates Memorization Shortcuts in LLMs

Paper • 2601.11061 • Published Jan 16 • 8

upvoted a paper 9 months ago

Spurious Rewards Paradox: Mechanistically Understanding How RLVR Activates Memorization Shortcuts in LLMs

Paper • 2601.11061 • Published Jan 16 • 8

submitted a paper to Daily Papers 9 months ago

Spurious Rewards Paradox: Mechanistically Understanding How RLVR Activates Memorization Shortcuts in LLMs

Paper • 2601.11061 • Published Jan 16 • 8

authored a paper over 1 year ago

Attributing Response to Context: A Jensen-Shannon Divergence Driven Mechanistic Study of Context Attribution in Retrieval-Augmented Generation

Paper • 2505.16415 • Published May 22, 2025 • 1

upvoted a paper over 1 year ago

Attributing Response to Context: A Jensen-Shannon Divergence Driven Mechanistic Study of Context Attribution in Retrieval-Augmented Generation

Paper • 2505.16415 • Published May 22, 2025 • 1

liked a model over 1 year ago

PULSE-ECG/PULSE-7B

Image-Text-to-Text • 7B • Updated Oct 28, 2024 • 875 • 38

authored 3 papers almost 2 years ago

Latent Space Factorisation and Manipulation via Matrix Subspace Projection

Paper • 1907.12385 • Published Jul 26, 2019 • 1

Large Language Models are Efficient Learners of Noise-Robust Speech Recognition

Paper • 2401.10446 • Published Jan 19, 2024

It's Never Too Late: Fusing Acoustic Information into Large Language Models for Automatic Speech Recognition

Paper • 2402.05457 • Published Feb 8, 2024