| 5761. |
Hallucination is inevitable: An innate limitation of large language models (arxiv.org) |
|
308 points by louthy on Feb 25, 2024 | hide | past | pdf | 474 comments
|
|
| 5762. |
Every model learned by gradient descent is approximately a kernel machine (2020) (arxiv.org) |
|
176 points by Anon84 on Feb 25, 2024 | hide | past | pdf | 136 comments
|
|
| 5763. |
How Susceptible Are Large Language Models to Ideological Manipulation? (arxiv.org) |
|
2 points by carlossouza on Feb 24, 2024 | hide | past | pdf | discuss
|
|
| 5764. |
Studying Bias in GANs Through the Lens of Race (arxiv.org) |
|
1 point by pajop on Feb 24, 2024 | hide | past | pdf | discuss
|
|
| 5765. |
What Artificial Neural Networks Can Tell Us About Human Language Acquisition (arxiv.org) |
|
2 points by EndXA on Feb 23, 2024 | hide | past | pdf | discuss
|
|
| 5766. |
More Agents Is All You Need (arxiv.org) |
|
2 points by anotherpaulg on Feb 23, 2024 | hide | past | pdf | discuss
|
|
| 5767. |
Synthetic images aid the recognition of human-made art forgeries (arxiv.org) |
|
29 points by evanb on Feb 23, 2024 | hide | past | pdf | 8 comments
|
|
| 5768. |
Boosting Latent Diffusion with Flow Matching (arxiv.org) |
|
1 point by lnyan on Feb 23, 2024 | hide | past | pdf | discuss
|
|
| 5769. |
Beyond A*: Better Planning with Transformers (arxiv.org) |
|
313 points by jonbaer on Feb 23, 2024 | hide | past | pdf | 120 comments
|
|
| 5770. |
YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information (arxiv.org) |
|
1 point by zerojames on Feb 23, 2024 | hide | past | pdf | discuss
|
|
| 5771. |
TrustScore: Reference-Free Evaluation of LLM Response Trustworthiness (arxiv.org) |
|
1 point by alastairr on Feb 23, 2024 | hide | past | pdf | discuss
|
|
| 5772. |
Rethinking Large Language Model Architectures for Sequential Recommendations (arxiv.org) |
|
2 points by PaulHoule on Feb 23, 2024 | hide | past | pdf | discuss
|
|
| 5773. |
Show HN: Verified Multi-Step Synthesis Using LLMs and MCTS (arxiv.org) |
|
1 point by namin on Feb 23, 2024 | hide | past | pdf | discuss
|
|
| 5774. |
Experimental Analysis of Large-Scale Learnable Vector Storage Compression (arxiv.org) |
|
1 point by PaulHoule on Feb 22, 2024 | hide | past | pdf | discuss
|
|
| 5775. |
LILO: Learning Interpretable Libraries by Compressing and Documenting Code (arxiv.org) |
|
2 points by PaulHoule on Feb 22, 2024 | hide | past | pdf | discuss
|
|
| 5776. |
Coercing LLMs to do and reveal almost anything (arxiv.org) |
|
12 points by arbesman on Feb 22, 2024 | hide | past | pdf | 1 comment
|
|
| 5777. |
Bridging empirical-theoretical gap in neural network formal language learning (arxiv.org) |
|
68 points by puttycat on Feb 22, 2024 | hide | past | pdf | 31 comments
|
|
| 5778. |
LongRoPE: Extending LLM Context Window Beyond 2M Tokens (arxiv.org) |
|
142 points by nojito on Feb 22, 2024 | hide | past | pdf | 46 comments
|
|
| 5779. |
A Language Agent For Autonomous Driving (2023) (arxiv.org) |
|
1 point by optimalsolver on Feb 22, 2024 | hide | past | pdf | discuss
|
|
| 5780. |
Speculative Streaming: Fast LLM Inference Without Auxiliary Models (arxiv.org) |
|
2 points by jonbaer on Feb 22, 2024 | hide | past | pdf | discuss
|
|
| 5781. |
Unsupervised Evaluation of Code LLMs with Round-Trip Correctness (arxiv.org) |
|
2 points by PaulHoule on Feb 21, 2024 | hide | past | pdf | discuss
|
|
| 5782. |
On-the-Fly Syntax Highlighting: Generalisation and Speed-Ups (arxiv.org) |
|
2 points by PaulHoule on Feb 21, 2024 | hide | past | pdf | discuss
|
|
| 5783. |
Neural Network Diffusion (arxiv.org) |
|
223 points by vagabund on Feb 21, 2024 | hide | past | pdf | 86 comments
|
|
| 5784. |
How Many Views Are Needed to Reconstruct an Unknown Object Using NeRF? (arxiv.org) |
|
1 point by PaulHoule on Feb 21, 2024 | hide | past | pdf | discuss
|
|
| 5785. |
Do Large Code Models Understand Programming Concepts? A Black-Box Approach (arxiv.org) |
|
1 point by PaulHoule on Feb 21, 2024 | hide | past | pdf | 1 comment
|
|
| 5786. |
UFO: A UI-Focused Agent for Windows OS Interaction (arxiv.org) |
|
1 point by PaulHoule on Feb 21, 2024 | hide | past | pdf | discuss
|
|
| 5787. |
Unit Test Generation Using Generative AI: A Comparative Analysis (arxiv.org) |
|
2 points by PaulHoule on Feb 21, 2024 | hide | past | pdf | discuss
|
|
| 5788. |
ScreenAgent: A Vision Language Model-Driven Computer Control Agent (arxiv.org) |
|
1 point by PaulHoule on Feb 21, 2024 | hide | past | pdf | discuss
|
|
| 5789. |
VideoPrism: A Foundational Visual Encoder for Video Understanding (arxiv.org) |
|
2 points by ashvardanian on Feb 21, 2024 | hide | past | pdf | discuss
|
|
| 5790. |
DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open LLMs (arxiv.org) |
|
3 points by ororm on Feb 21, 2024 | hide | past | pdf | discuss
|
|
|
| More |
