| 4741. |
LazyLLM: Dynamic Token Pruning for Efficient Long Context LLM Inference (arxiv.org) |
|
2 points by usernamesdf on Aug 2, 2024 | hide | past | pdf | discuss
|
|
| 4742. |
Why knowledge overshadowing causes LLMs to hallucinate despite training on truth (arxiv.org) |
|
2 points by thoughtpeddler on Aug 2, 2024 | hide | past | pdf | 1 comment
|
|
| 4743. |
Interpreting LLM outputs reveals the "token noise" effect (arxiv.org) |
|
2 points by behnamoh on Aug 2, 2024 | hide | past | pdf | discuss
|
|
| 4744. |
Human-Like Episodic Memory for Infinite Context LLMs (arxiv.org) |
|
2 points by wslh on Aug 1, 2024 | hide | past | pdf | discuss
|
|
| 4745. |
Eyeballvul: A future-proof benchmark for vulnerability detection in the wild (arxiv.org) |
|
1 point by wslh on Aug 1, 2024 | hide | past | pdf | discuss
|
|
| 4746. |
Beating GPT-4o and Claude 3.5 on SWE-bench Lite through repeated sampling (arxiv.org) |
|
5 points by aglazer on Aug 1, 2024 | hide | past | pdf | discuss
|
|
| 4747. |
The Llama 3 Herd of Models (arxiv.org) |
|
1 point by GaggiX on Aug 1, 2024 | hide | past | pdf | discuss
|
|
| 4748. |
Things Come from Having Many Good Models (arxiv.org) |
|
2 points by PaulHoule on Aug 1, 2024 | hide | past | pdf | discuss
|
|
| 4749. |
Meta-Rewarding Language Models:Self-Improving Alignment with LLM-as-a-Meta-Judge (arxiv.org) |
|
2 points by sssummer on Aug 1, 2024 | hide | past | pdf | discuss
|
|
| 4750. |
From pixels to planning: scale-free active inference (arxiv.org) |
|
1 point by vlotar on Aug 1, 2024 | hide | past | pdf | discuss
|
|
| 4751. |
Algorithmic Language Models with Neurally Compiled Libraries (arxiv.org) |
|
2 points by PaulHoule on Aug 1, 2024 | hide | past | pdf | discuss
|
|
| 4752. |
Baidu's Improving Retrieval Augmented Language Model with Self-Reasoning (arxiv.org) |
|
66 points by a-s-k-af on Aug 1, 2024 | hide | past | pdf | 4 comments
|
|
| 4753. |
Do AI Safety Benchmarks Measure Safety Progress? (arxiv.org) |
|
1 point by hendrycks on Aug 1, 2024 | hide | past | pdf | discuss
|
|
| 4754. |
Scaling Exponents Across Parameterizations and Optimizers (arxiv.org) |
|
2 points by johnsutor on Jul 31, 2024 | hide | past | pdf | discuss
|
|
| 4755. |
Deep-Tempest: Using Deep Learning to Eavesdrop on HDMI (arxiv.org) |
|
86 points by _____k on Jul 31, 2024 | hide | past | pdf | 15 comments
|
|
| 4756. |
Machine Unlearning in Generative AI: A Survey (arxiv.org) |
|
1 point by tzury on Jul 31, 2024 | hide | past | pdf | discuss
|
|
| 4757. |
Efficient Execution of Structured Language Model Programs (arxiv.org) |
|
3 points by fzliu on Jul 30, 2024 | hide | past | pdf | discuss
|
|
| 4758. |
From Explicit Cot to Implicit Cot: Learning to Internalize Cot Step by Step (arxiv.org) |
|
2 points by jasondavies on Jul 30, 2024 | hide | past | pdf | discuss
|
|
| 4759. |
Deep-Tempest:Using Deep Learning to Eavesdrop on HDMI (arxiv.org) |
|
5 points by quxinxin on Jul 30, 2024 | hide | past | pdf | discuss
|
|
| 4760. |
Diffusion Training from Scratch on a Micro-Budget (arxiv.org) |
|
208 points by fzliu on Jul 30, 2024 | hide | past | pdf | 27 comments
|
|
| 4761. |
Beyond Deepfake Images: Detecting AI-Generated Videos [pdf] (arxiv.org) |
|
3 points by gnabgib on Jul 29, 2024 | hide | past | pdf | discuss
|
|
| 4762. |
Looking into Black Box Code Language Models (arxiv.org) |
|
2 points by PaulHoule on Jul 29, 2024 | hide | past | pdf | discuss
|
|
| 4763. |
Trillion-Parameter Sequential Transducers for Generative Recommendations (arxiv.org) |
|
4 points by potench on Jul 29, 2024 | hide | past | pdf | discuss
|
|
| 4764. |
Stretching Each Dollar: Diffusion Training from Scratch on a Micro-Budget (arxiv.org) |
|
3 points by tosh on Jul 29, 2024 | hide | past | pdf | discuss
|
|
| 4765. |
Recursive Introspection: Teaching Language Model Agents How to Self-Improve (arxiv.org) |
|
5 points by mnk47 on Jul 27, 2024 | hide | past | pdf | discuss
|
|
| 4766. |
The Opportunities and Risks of Foundation Models (2021) (arxiv.org) |
|
1 point by fzliu on Jul 27, 2024 | hide | past | pdf | discuss
|
|
| 4767. |
Text-Guided Shape Free Object Inpainting with Diffusion Model (arxiv.org) |
|
2 points by fzliu on Jul 27, 2024 | hide | past | pdf | discuss
|
|
| 4768. |
Sparse vs. Contiguous Adversarial Pixel Perturbations in Multimodal Models [pdf] (arxiv.org) |
|
1 point by thunderbong on Jul 26, 2024 | hide | past | pdf | discuss
|
|
| 4769. |
Learning to Rank for Maps at Airbnb (arxiv.org) |
|
1 point by PaulHoule on Jul 25, 2024 | hide | past | pdf | discuss
|
|
| 4770. |
The Next Decade in AI: Four Steps Towards Robust Artificial Intelligence (2020) (arxiv.org) |
|
1 point by Anon84 on Jul 25, 2024 | hide | past | pdf | discuss
|
|
|
| More |
