Reasoning Model is Stubborn: Diagnosing Instruction Overriding in Reasoning Models
Paper
•
2505.17225
•
Published
•
65
Doohyuk Jang
jadohu
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
about 2 months ago
Revisiting Multi-Agent Debate as Test-Time Scaling: A Systematic Study
of Conditional Effectiveness
updated
a Space
about 2 months ago
ReasoningTrap/README
authored
a paper
about 2 months ago
Reasoning Model is Stubborn: Diagnosing Instruction Overriding in
Reasoning Models
Organizations
authored
a
paper
about 2 months ago
authored
3
papers
4 months ago
PromptKD: Distilling Student-Friendly Knowledge for Generative Language Models via Prompt Tuning
Paper
•
2402.12842
•
Published
LANTERN: Accelerating Visual Autoregressive Models with Relaxed Speculative Decoding
Paper
•
2410.03355
•
Published
LANTERN++: Enhanced Relaxed Speculative Decoding with Static Tree Drafting for Visual Auto-regressive Models
Paper
•
2502.06352
•
Published