| 5491. |
Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks (arxiv.org) |
|
3 points by max-andr on Apr 5, 2024 | hide | past | pdf | 1 comment
|
|
| 5492. |
DeepMind: Mixture-of-Depths: Dynamically allocating compute in transformers (arxiv.org) |
|
2 points by alecco on Apr 5, 2024 | hide | past | pdf | 1 comment
|
|
| 5493. |
Machine Learning on Blockchain Data: A Systematic Mapping Study (arxiv.org) |
|
2 points by PaulHoule on Apr 4, 2024 | hide | past | pdf | discuss
|
|
| 5494. |
Language models as compilers: Simulating pseudocode execution (arxiv.org) |
|
170 points by milliondreams on Apr 4, 2024 | hide | past | pdf | 52 comments
|
|
| 5495. |
Towards High-Quality Text-to-3D Generation via Geometric Diffusion (arxiv.org) |
|
1 point by PaulHoule on Apr 4, 2024 | hide | past | pdf | discuss
|
|
| 5496. |
Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena (arxiv.org) |
|
1 point by tosh on Apr 4, 2024 | hide | past | pdf | discuss
|
|
| 5497. |
Rule-based NLP system beats LLM for analysis of psychiatric clinical notes (arxiv.org) |
|
120 points by PaulHoule on Apr 4, 2024 | hide | past | pdf | 19 comments
|
|
| 5498. |
Approaching Human-Level Forecasting with Language Models (arxiv.org) |
|
3 points by p1esk on Apr 4, 2024 | hide | past | pdf | discuss
|
|
| 5499. |
Mixture-of-Depths: Dynamically allocating compute in transformers (arxiv.org) |
|
4 points by dekuma on Apr 4, 2024 | hide | past | pdf | discuss
|
|
| 5500. |
Do language models plan ahead for future tokens? (arxiv.org) |
|
3 points by tosh on Apr 4, 2024 | hide | past | pdf | discuss
|
|
| 5501. |
Mixture-of-Depths: Dynamically allocating compute in transformer language models (arxiv.org) |
|
5 points by GaggiX on Apr 4, 2024 | hide | past | pdf | 2 comments
|
|
| 5502. |
LLMs and the "token noise" effect (arxiv.org) |
|
1 point by behnamoh on Apr 3, 2024 | hide | past | pdf | discuss
|
|
| 5503. |
Emotion Detection with Transformers: A Comparative Study (arxiv.org) |
|
2 points by PaulHoule on Apr 3, 2024 | hide | past | pdf | discuss
|
|
| 5504. |
Scrutinizing the Trustworthiness of Efficient LLMs Under Compression (arxiv.org) |
|
2 points by PaulHoule on Apr 3, 2024 | hide | past | pdf | discuss
|
|
| 5505. |
On the measure of intelligence (2019) (arxiv.org) |
|
2 points by kaycebasques on Apr 3, 2024 | hide | past | pdf | 1 comment
|
|
| 5506. |
Exposing Vulnerabilities of LLMs via Global Scale Prompt Hacking Competition (arxiv.org) |
|
2 points by mpweiher on Apr 3, 2024 | hide | past | pdf | discuss
|
|
| 5507. |
Octopus v2: On-device language model for super agent (arxiv.org) |
|
91 points by lawrencechen on Apr 3, 2024 | hide | past | pdf | 17 comments
|
|
| 5508. |
Wait, It's All Token Noise? Always Has Been: Interpreting LLM Behavior (arxiv.org) |
|
2 points by behnamoh on Apr 3, 2024 | hide | past | pdf | discuss
|
|
| 5509. |
Bigger Is Not Always Better: Scaling Properties of Latent Diffusion Models (arxiv.org) |
|
2 points by nisarggg on Apr 3, 2024 | hide | past | pdf | discuss
|
|
| 5510. |
ReALM: Reference Resolution as Language Modeling (arxiv.org) |
|
140 points by mfiguiere on Apr 2, 2024 | hide | past | pdf | 15 comments
|
|
| 5511. |
Monitoring AI-Modified Content: Impact of ChatGPT on AI Conference Peer Reviews (arxiv.org) |
|
1 point by bookofjoe on Apr 2, 2024 | hide | past | pdf | discuss
|
|
| 5512. |
Conformer-Based Speech Recognition on Extreme Edge-Computing Devices (arxiv.org) |
|
2 points by gok on Apr 2, 2024 | hide | past | pdf | discuss
|
|
| 5513. |
Evolution of RAG (arxiv.org) |
|
1 point by milliondreams on Apr 2, 2024 | hide | past | pdf | discuss
|
|
| 5514. |
Tutorial on Diffusion Models for Imaging and Vision (arxiv.org) |
|
2 points by qwertyforce on Apr 2, 2024 | hide | past | pdf | discuss
|
|
| 5515. |
Wolf: Large Language Model Framework for CXR Understanding (arxiv.org) |
|
1 point by PaulHoule on Apr 2, 2024 | hide | past | pdf | discuss
|
|
| 5516. |
ReALM: Reference Resolution as Language Modeling (arxiv.org) |
|
12 points by frizlab on Apr 2, 2024 | hide | past | pdf | 1 comment
|
|
| 5517. |
Model Stock: All we need is just a few fine-tuned models (arxiv.org) |
|
1 point by tosh on Apr 2, 2024 | hide | past | pdf | discuss
|
|
| 5518. |
The Unreasonable Ineffectiveness of the Deeper Layers (arxiv.org) |
|
2 points by srirangr on Apr 2, 2024 | hide | past | pdf | discuss
|
|
| 5519. |
Magis: LLM-Based Multi-Agent Framework for GitHub Issue ReSolution (arxiv.org) |
|
3 points by anticensor on Apr 2, 2024 | hide | past | pdf | discuss
|
|
| 5520. |
ReALM: Reference Resolution as Language Modeling (arxiv.org) |
|
2 points by davidbarker on Apr 1, 2024 | hide | past | pdf | discuss
|
|
|
| More |
