| 4861. |
Review of Mechanistic Interpretability for Transformer-Based Language Models (arxiv.org) |
|
2 points by belter on Jul 7, 2024 | hide | past | pdf | discuss
|
|
| 4862. |
Reasoning in Large Language Models: A Geometric Perspective (arxiv.org) |
|
214 points by belter on Jul 7, 2024 | hide | past | pdf | 171 comments
|
|
| 4863. |
An Efficient NAS-Based Approach for Handling Imbalanced Datasets (arxiv.org) |
|
1 point by PaulHoule on Jul 7, 2024 | hide | past | pdf | discuss
|
|
| 4864. |
MobileLLM: Optimizing Sub-Billion Parameter Language Models for On-Device Use (arxiv.org) |
|
3 points by tosh on Jul 7, 2024 | hide | past | pdf | discuss
|
|
| 4865. |
T-FREE Tokenizer-Free LLMs via Sparse Representation Memory-Efficient Embeddings (arxiv.org) |
|
3 points by Bluestein on Jul 6, 2024 | hide | past | pdf | discuss
|
|
| 4866. |
Data curation via joint example selection (arxiv.org) |
|
3 points by jonbaer on Jul 6, 2024 | hide | past | pdf | discuss
|
|
| 4867. |
Can LLMs Generate Visualizations with Dataless Prompts? (arxiv.org) |
|
3 points by PaulHoule on Jul 6, 2024 | hide | past | pdf | discuss
|
|
| 4868. |
Verif.ai: Open-Source Generative Q&A System with Referenced Answers (arxiv.org) |
|
2 points by nikolamilosevic on Jul 6, 2024 | hide | past | pdf | discuss
|
|
| 4869. |
ConvNet vs Transformer, Supervised vs CLIP (arxiv.org) |
|
2 points by fzliu on Jul 6, 2024 | hide | past | pdf | discuss
|
|
| 4870. |
Spurious Reconstruction of Visual Perception from Brain Activity (arxiv.org) |
|
1 point by DanielleMolloy on Jul 5, 2024 | hide | past | pdf | 1 comment
|
|
| 4871. |
LLM Agents can Autonomously Exploit One-day Vulnerabili-ties [pdf] (arxiv.org) |
|
4 points by gsky on Jul 5, 2024 | hide | past | pdf | 1 comment
|
|
| 4872. |
Improve Mathematical Logic in Language Models by Automated Process Supervision (arxiv.org) |
|
2 points by bryanrasmussen on Jul 4, 2024 | hide | past | pdf | 1 comment
|
|
| 4873. |
LLMMatDesign – Gen AI for Materials (arxiv.org) |
|
4 points by socratic1 on Jul 4, 2024 | hide | past | pdf | discuss
|
|
| 4874. |
Radiology Report Generation and Evaluation with Layman's Terms (arxiv.org) |
|
1 point by PaulHoule on Jul 4, 2024 | hide | past | pdf | discuss
|
|
| 4875. |
GraphReader: Building Graph-Based Agent to Enhance Long-Context Abilities of LLM (arxiv.org) |
|
2 points by theptip on Jul 4, 2024 | hide | past | pdf | discuss
|
|
| 4876. |
Mental Modeling of Reinforcement Learning Agents by Language Models (arxiv.org) |
|
7 points by piecerough on Jul 3, 2024 | hide | past | pdf | discuss
|
|
| 4877. |
Reducing the Memory Footprint of 3D Gaussian Splatting (arxiv.org) |
|
2 points by PaulHoule on Jul 3, 2024 | hide | past | pdf | discuss
|
|
| 4878. |
ColPali: Efficient Document Retrieval with Vision Language Models (arxiv.org) |
|
2 points by alphabetting on Jul 2, 2024 | hide | past | pdf | discuss
|
|
| 4879. |
UniGen: Unified Modeling for Generating Autonomous Driving Scenarios (arxiv.org) |
|
1 point by ra7 on Jul 2, 2024 | hide | past | pdf | discuss
|
|
| 4880. |
AI Agents That Matter (arxiv.org) |
|
4 points by randomwalker on Jul 2, 2024 | hide | past | pdf | discuss
|
|
| 4881. |
MoonshotAI unveils Kimi's large-scale LLM serving architecture (arxiv.org) |
|
18 points by slothfulhamster on Jul 2, 2024 | hide | past | pdf | 1 comment
|
|
| 4882. |
Generalist Lightweight Model for Various Information Extraction Tasks (arxiv.org) |
|
1 point by PaulHoule on Jul 2, 2024 | hide | past | pdf | discuss
|
|
| 4883. |
xLSTM-UNet can be an Effective 2D and 3D Medical Image Segmentation Backbone (arxiv.org) |
|
2 points by tosh on Jul 2, 2024 | hide | past | pdf | discuss
|
|
| 4884. |
Large language models have developed a higher-order theory of mind (arxiv.org) |
|
17 points by some-unique-x on Jul 2, 2024 | hide | past | pdf | 4 comments
|
|
| 4885. |
Segment Any Text (arxiv.org) |
|
1 point by jasondavies on Jul 2, 2024 | hide | past | pdf | discuss
|
|
| 4886. |
FTTN: Feature-Targeted Testing for Numerical Properties of Matrix Accelerators (arxiv.org) |
|
2 points by matt_d on Jul 2, 2024 | hide | past | pdf | discuss
|
|
| 4887. |
The Factorization Curse: Which Tokens You Predict Underlie the Reversal Curse (arxiv.org) |
|
1 point by ijk on Jul 1, 2024 | hide | past | pdf | discuss
|
|
| 4888. |
What is the best model? Application-driven Evaluation for Large Language Models (arxiv.org) |
|
1 point by PaulHoule on Jul 1, 2024 | hide | past | pdf | discuss
|
|
| 4889. |
The Remarkable Robustness of LLMs: Stages of Inference? (arxiv.org) |
|
2 points by belter on Jun 30, 2024 | hide | past | pdf | discuss
|
|
| 4890. |
Newswire: A large-scale structured database of a century of historical news (arxiv.org) |
|
165 points by h2odragon on Jun 30, 2024 | hide | past | pdf | 39 comments
|
|
|
| More |
