Parameter Lab

parameterlab's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Articles

mgubri 

updated a collection 1 day ago

🫗 Leaky Thoughts

Collection

Data of the "Leaky Thoughts: Large Reasoning Models Are Not Private Thinkers" paper • 1 item • Updated 1 day ago

tommaso-green 

published a dataset 4 days ago

parameterlab/leaky_thoughts

Updated 5 days ago • 23 • 1

ahmedheakl 

authored a paper 5 days ago

Guaranteed Guess: A Language Modeling Approach for CISC-to-RISC Transpilation with Testing Guarantees

Paper • 2506.14606 • Published 6 days ago • 11

tommaso-green 

updated a dataset 5 days ago

parameterlab/leaky_thoughts

Updated 5 days ago • 23 • 1

ahmedheakl 

authored a paper 16 days ago

VideoMolmo: Spatio-Temporal Grounding Meets Pointing

Paper • 2506.05336 • Published 17 days ago • 8

haritzpuerto 

updated a collection 17 days ago

🔎 C-SEO

Collection

3 items • Updated 17 days ago

haritzpuerto 

updated a dataset 17 days ago

parameterlab/c-seo-results

Updated 17 days ago • 204

haritzpuerto 

published a dataset 17 days ago

parameterlab/c-seo-results

Updated 17 days ago • 204

haritzpuerto 

updated a collection 17 days ago

🔎 C-SEO

Collection

3 items • Updated 17 days ago

haritzpuerto 

updated a dataset 17 days ago

parameterlab/c-seo-bench

Viewer • Updated 17 days ago • 16.4k • 196 • 1

haritzpuerto 

updated a collection 18 days ago

🔎 C-SEO

Collection

3 items • Updated 17 days ago

haritzpuerto 

published a dataset 18 days ago

parameterlab/c-seo-bench

Viewer • Updated 17 days ago • 16.4k • 196 • 1

ahmedheakl 

authored a paper 25 days ago

SVRPBench: A Realistic Benchmark for Stochastic Vehicle Routing Problem

Paper • 2505.21887 • Published 26 days ago • 14

haritzpuerto 

posted an update 25 days ago

view post

Post

299

📜 Accepted at ACL 2025! Fine-Tuning on Diverse Reasoning Chains Drives Within-Inference CoT Refinement in LLMs
We propose to fine-tune LLMs to generate diverse chains of thought (DCoT) in a single inference step. This enables within-inference refinement of the cots, no external feedback needed!
🔗 https://arxiv.org/abs/2407.03181

🚀

1

1

+

Reply

coallaoh 

authored 6 papers 26 days ago

Calibrating Large Language Models Using Their Generations Only

Paper • 2403.05973 • Published Mar 9, 2024

Do Deep Neural Network Solutions Form a Star Domain?

Paper • 2403.07968 • Published Mar 12, 2024

Scaling Up Membership Inference: When and How Attacks Succeed on Large Language Models

Paper • 2411.00154 • Published Oct 31, 2024

CLIP Behaves like a Bag-of-Words Model Cross-modally but not Uni-modally

Paper • 2502.03566 • Published Feb 5 • 2

Intermediate Layer Classifiers for OOD generalization

Paper • 2504.05461 • Published Apr 7 • 1

Diffusion Classifiers Understand Compositionality, but Conditions Apply

Paper • 2505.17955 • Published about 1 month ago • 21