Nikita

PQlet's activity

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

upvoted a paper 5 days ago

When Punctuation Matters: A Large-Scale Comparison of Prompt Robustness Methods for LLMs

Paper • 2508.11383 • Published 9 days ago • 38

upvoted a paper 12 days ago

SONAR-LLM: Autoregressive Transformer that Thinks in Sentence Embeddings and Speaks in Tokens

Paper • 2508.05305 • Published 17 days ago • 44

upvoted a paper about 1 month ago

A Survey on Latent Reasoning

Paper • 2507.06203 • Published Jul 8 • 89

upvoted a paper about 2 months ago

Heeding the Inner Voice: Aligning ControlNet Training via Intermediate Features Feedback

Paper • 2507.02321 • Published Jul 3 • 39

upvoted 4 papers 2 months ago

DreamBoothDPO: Improving Personalized Generation using Direct Preference Optimization

Paper • 2505.20975 • Published May 27 • 36

Confidence Is All You Need: Few-Shot RL Fine-Tuning of Language Models

Paper • 2506.06395 • Published Jun 5 • 130

Image Reconstruction as a Tool for Feature Analysis

Paper • 2506.07803 • Published Jun 9 • 29

ImageReFL: Balancing Quality and Diversity in Human-Aligned Diffusion Models

Paper • 2505.22569 • Published May 28 • 55

upvoted a paper 3 months ago

cadrille: Multi-modal CAD Reconstruction with Online Reinforcement Learning

Paper • 2505.22914 • Published May 28 • 35

upvoted 3 papers 5 months ago

Hogwild! Inference: Parallel LLM Generation via Concurrent Attention

Paper • 2504.06261 • Published Apr 8 • 111

When Less is Enough: Adaptive Token Reduction for Efficient Image Representation

Paper • 2503.16660 • Published Mar 20 • 73

One-Step Residual Shifting Diffusion for Image Super-Resolution via Distillation

Paper • 2503.13358 • Published Mar 17 • 96

upvoted 3 papers 6 months ago

A Primer on the Inner Workings of Transformer-based Language Models

Paper • 2405.00208 • Published Apr 30, 2024 • 10

LLM-Microscope: Uncovering the Hidden Role of Punctuation in Context Memory of Transformers

Paper • 2502.15007 • Published Feb 20 • 175

SynthDetoxM: Modern LLMs are Few-Shot Parallel Detoxification Data Annotators

Paper • 2502.06394 • Published Feb 10 • 90

upvoted an article 7 months ago

view article

Article

Finally, a Replacement for BERT: Introducing ModernBERT

By and 14 others •

Dec 19, 2024

• 679

upvoted a paper 10 months ago

CLEAR: Character Unlearning in Textual and Visual Modalities

Paper • 2410.18057 • Published Oct 23, 2024 • 210

upvoted an article 10 months ago

view article

Article

Understanding InstaFlow/Rectified Flow

By •

Oct 6, 2023

• 31

upvoted a paper 10 months ago

Mechanistic Permutability: Match Features Across Layers

Paper • 2410.07656 • Published Oct 10, 2024 • 20

upvoted a collection 11 months ago

🔍 Interpretability & Analysis of LMs

Collection

Outstanding research in LM interpretability and evaluation, summarized • 127 items • Updated 3 days ago • 112