Length Penalties Make Chain-of-Thought Less Monitorable
Paper • 2607.09786 • Published • 6
🔄 In a Training Loop
Urro
urroxyz
AI & ML interests
computational linguistics major 🤖🔎ðŸ”
i am autistic. if i come off rude, i probably didn't mean to. please feel free to ask me for clarification.
Recent Activity
upvoted a paper about 10 hours ago
Length Penalties Make Chain-of-Thought Less Monitorable updated a collection 1 day ago
WTF GENIUS PAPERSOrganizations
upvoted a paper about 10 hours ago
updated a
collection 1 day ago
upvoted a paper 1 day ago
updated a
collection 1 day ago
upvoted a paper 1 day ago
upvoted 2
papers 2 days ago
commented a
paper 2 days ago
upvoted 5
papers 2 days ago
MuScriptor: An Open Model for Multi-Instrument Music Transcription
Paper • 2607.08168 • Published • 12
Know Before Fix: QA-Driven Repository Knowledge Acquisition for Software Issue Resolution
Paper • 2607.11111 • Published • 12
Blind-Spots-Bench: Evaluating Blind Spots in Multimodal Models
Paper • 2607.08317 • Published • 28
SynthDocBench: Controlled Benchmark for Long-Context Visual Document Understanding
Paper • 2607.10400 • Published • 66
Read It Back: Pretrained MLLMs Are Zero-Shot Reward Models for Text-to-Image Generation
Paper • 2607.11886 • Published • 73
commented a
paper 4 days ago
updated a
collection 4 days ago
commented a
paper 5 days ago
upvoted 4
papers 5 days ago
Phone Segmentation and Recognition through Phonological Activation Mapping
Paper • 2607.09020 • Published • 7
Towards Mechanistically Understanding Why Memorized Knowledge Fails to Generalize in Large Language Model Finetuning
Paper • 2607.08393 • Published • 15
Self-Guided Test-Time Training for Long-Context LLMs
Paper • 2607.09415 • Published • 15
KronQ: LLM Quantization via Kronecker-Factored Hessian
Paper • 2607.07964 • Published • 29