| 4771. |
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
|
|
| 4772. |
Avoiding Model Collapse via Accumulating Real and Synthetic Data (arxiv.org) |
|
5 points by igorkraw on Jul 24, 2024 | hide | past | pdf | 1 comment
|
|
| 4773. |
MOMAland: Benchmarks for Multi-Objective Multi-Agent Reinforcement Learning (arxiv.org) |
|
3 points by jonbaer on Jul 24, 2024 | hide | past | pdf | discuss
|
|
| 4774. |
A Multimodal Automated Interpretability Agent (arxiv.org) |
|
83 points by el_duderino on Jul 24, 2024 | hide | past | pdf | 7 comments
|
|
| 4775. |
Alice's Adventures in a Differentiable Wonderland (updated and in print) (arxiv.org) |
|
3 points by sscardapane on Jul 24, 2024 | hide | past | pdf | 1 comment
|
|
| 4776. |
ChatBCG – Can AI Read Your Slide Decks? (arxiv.org) |
|
5 points by rob313 on Jul 23, 2024 | hide | past | pdf | discuss
|
|
| 4777. |
Reconstructing Training Data from Models Trained with Transfer Learning (arxiv.org) |
|
1 point by belter on Jul 23, 2024 | hide | past | pdf | discuss
|
|
| 4778. |
On the Design and Analysis of LLM-Based Algorithms (arxiv.org) |
|
2 points by Sajarin on Jul 23, 2024 | hide | past | pdf | discuss
|
|
| 4779. |
When in Doubt, Cascade: Towards Building Efficient and Capable Guardrails (arxiv.org) |
|
2 points by PaulHoule on Jul 23, 2024 | hide | past | pdf | discuss
|
|
| 4780. |
Domain-Aware Fine-Tuning of Foundation Models (arxiv.org) |
|
12 points by PaulHoule on Jul 23, 2024 | hide | past | pdf | discuss
|
|
| 4781. |
Operationalizing a Threat Model for Red-Teaming Large Language Models (arxiv.org) |
|
2 points by dapurv5 on Jul 23, 2024 | hide | past | pdf | 1 comment
|
|
| 4782. |
Vulnerability Detection with Code Language Models: How Far Are We? (arxiv.org) |
|
1 point by wslh on Jul 23, 2024 | hide | past | pdf | discuss
|
|
| 4783. |
Attention in SRAM on Tenstorrent Grayskull (1.5x SRAM, 30x cheaper than H100) (arxiv.org) |
|
3 points by molli on Jul 23, 2024 | hide | past | pdf | 1 comment
|
|
| 4784. |
Spectra: A Comprehensive Study of Ternary, Quantized, and FP16 Language Models (arxiv.org) |
|
2 points by fzliu on Jul 23, 2024 | hide | past | pdf | discuss
|
|
| 4785. |
Does Refusal Training in LLMs Generalize to the Past Tense? (arxiv.org) |
|
2 points by geox on Jul 21, 2024 | hide | past | pdf | 1 comment
|
|
| 4786. |
Unexpected Benefits of Self-Modeling in Neural Systems (arxiv.org) |
|
2 points by rcoppolo on Jul 21, 2024 | hide | past | pdf | 1 comment
|
|
| 4787. |
Exploring FPGA designs for MX and beyond (arxiv.org) |
|
2 points by matt_d on Jul 21, 2024 | hide | past | pdf | discuss
|
|
| 4788. |
Bright: A Realistic and Challenging Benchmark for Reasoning-Intensive Retrieval (arxiv.org) |
|
1 point by veryluckyxyz on Jul 21, 2024 | hide | past | pdf | discuss
|
|
| 4789. |
Human-like object concept representations emerge naturally in multimodal LLMs (arxiv.org) |
|
5 points by rntn on Jul 20, 2024 | hide | past | pdf | discuss
|
|
| 4790. |
Building AI Agents for Autonomous Clouds: Challenges and Design Principles (arxiv.org) |
|
2 points by slimshetty on Jul 20, 2024 | hide | past | pdf | 1 comment
|
|
| 4791. |
Deep Learning to Eavesdrop on HDMI from Unintended Electromagnetic Emanations (arxiv.org) |
|
4 points by transpute on Jul 20, 2024 | hide | past | pdf | discuss
|
|
| 4792. |
Scaling Granite Code Models to 128K Context (arxiv.org) |
|
2 points by belter on Jul 19, 2024 | hide | past | pdf | discuss
|
|
| 4793. |
Reliable Reasoning Beyond Natural Language (arxiv.org) |
|
1 point by triska on Jul 19, 2024 | hide | past | pdf | discuss
|
|
| 4794. |
Q-Sparse: All Large Language Models Can Be Fully Sparsely-Activated (arxiv.org) |
|
5 points by quxinxin on Jul 19, 2024 | hide | past | pdf | discuss
|
|
| 4795. |
Mixture of A Million Experts: PEER (parameter efficient expert retrieval) (arxiv.org) |
|
2 points by mnoorfawi on Jul 18, 2024 | hide | past | pdf | discuss
|
|
| 4796. |
The Conversational Persuasiveness of LLMs: A Randomized Controlled Trial (arxiv.org) |
|
1 point by throwaway71271 on Jul 18, 2024 | hide | past | pdf | discuss
|
|
| 4797. |
Training LLMs to cite the pretraining data (arxiv.org) |
|
1 point by mkhalifa on Jul 18, 2024 | hide | past | pdf | 1 comment
|
|
| 4798. |
Multi-Agent Reinforcement Learning Based Variable Speed Limit Controllers (arxiv.org) |
|
3 points by Luc on Jul 17, 2024 | hide | past | pdf | discuss
|
|
| 4799. |
Re-Thinking Inverse Graphics with Large Language Models (arxiv.org) |
|
1 point by lnyan on Jul 17, 2024 | hide | past | pdf | discuss
|
|
| 4800. |
SpreadsheetLLM: Encoding Spreadsheets for Large Language Models (arxiv.org) |
|
190 points by goplayoutside on Jul 17, 2024 | hide | past | pdf | 69 comments
|
|
|
| More |
