Revisiting Complete Reasoning Traces for Post-Training
Paper • 2609.07103 • Published • 23
Jaehui Hwang
j-jaehui
AI & ML interests
None yet
Recent Activity
authored a paper 7 days ago
Revisiting Complete Reasoning Traces for Post-Training authored a paper 7 days ago
Beneath the Surface of Chains-of-Thought: A Mechanistic Interpretation of Reasoning Operations in LLMs authored a paper 7 days ago
On-Policy Delta Distillation for Multilingual Math ReasoningOrganizations
authored 6
papers 7 days ago
Beneath the Surface of Chains-of-Thought: A Mechanistic Interpretation of Reasoning Operations in LLMs
Paper • 2609.04753 • Published • 17
On-Policy Delta Distillation for Multilingual Math Reasoning
Paper • 2608.05802 • Published • 33
What Defines Good Reasoning in LLMs? Dissecting Reasoning Steps with Multi-Aspect Evaluation
Paper • 2510.20603 • Published
MuCo: Multi-turn Contrastive Learning for Multimodal Embedding Model
Paper • 2602.06393 • Published • 5
Similarity of Neural Architectures using Adversarial Attack Transferability
Paper • 2210.11407 • Published
submitted a
paper to Daily Papers 7 days ago
upvoted a paper 10 days ago
authored a
paper about 2 months ago
upvoted a paper about 2 months ago