Beneath the Surface of Chains-of-Thought: A Mechanistic Interpretation of Reasoning Operations in LLMs
Paper • 2609.04753 • Published • 12
Seogyeong Jeong
sg-jeong28
·
AI & ML interests
None yet
Recent Activity
authored a paper about 18 hours ago
Beneath the Surface of Chains-of-Thought: A Mechanistic Interpretation of Reasoning Operations in LLMs upvoted a paper about 21 hours ago
Beneath the Surface of Chains-of-Thought: A Mechanistic Interpretation of Reasoning Operations in LLMs upvoted a paper about 21 hours ago
Retrieve, Don't Retrain: Extending Vision Language Action Models to New Tasks at Test TimeOrganizations
None yet
authored a
paper about 18 hours ago
upvoted 4
papers about 21 hours ago
Beneath the Surface of Chains-of-Thought: A Mechanistic Interpretation of Reasoning Operations in LLMs
Paper • 2609.04753 • Published • 12
Retrieve, Don't Retrain: Extending Vision Language Action Models to New Tasks at Test Time
Paper • 2606.15631 • Published • 17
On-Policy Delta Distillation
Paper • 2607.15161 • Published • 39
Verification-Aware Training for Speculative Decoding
Paper • 2608.30135 • Published • 10
submitted a
paper to Daily Papers 1 day ago
upvoted a paper 1 day ago
authored 3
papers 1 day ago
LLM-C3MOD: A Human-LLM Collaborative System for Cross-Cultural Hate Speech Moderation
Paper • 2503.07237 • Published
MUG-Eval: A Proxy Evaluation Framework for Multilingual Generation Capabilities in Any Language
Paper • 2505.14395 • Published • 7
MSTS: A Multimodal Safety Test Suite for Vision-Language Models
Paper • 2501.10057 • Published • 10