Hacker News new | past | comments | ask | show | jobs | submit | from login
TAIS – a framework for autonomous scientific discovery (paperswithcode.com)
3 points by nopromisessir 26 days ago | past | 1 comment
New Method Fine-Tunes LLMs with 10x Less Data, Even Rivals In-Context Learning (paperswithcode.com)
4 points by lineshogan 5 months ago | past | 1 comment
Accelerating Innovation in 6G Research: Real-Time SDR for Rapid Prototyping (paperswithcode.com)
2 points by teleforce 7 months ago | past
DemoFusion: Democratising High-Resolution Image Generation with No $$$ (paperswithcode.com)
2 points by gaborcselle 9 months ago | past
Exploring an LM to Generate Prolog Predicates from Mathematics Questions (paperswithcode.com)
5 points by wseqyrku 10 months ago | past
Think Twice Before Detecting GAN-Generated Fake Images from Their Spectra (paperswithcode.com)
4 points by woolion 11 months ago | past
RankVicuna: Open Source Zero-Shot Listwise Document Reranking (paperswithcode.com)
17 points by alexmolas 11 months ago | past | 5 comments
Thought Propagation: An analogical approach to complex reasoning with LLMs (paperswithcode.com)
56 points by amilios 11 months ago | past | 13 comments
Low-Resource Languages Jailbreak GPT-4 (paperswithcode.com)
3 points by amilios 11 months ago | past
LLMs trained on “A is B” fail to learn “B is A” (paperswithcode.com)
120 points by saliagato on Sept 23, 2023 | past | 158 comments
Qwen-VL: A Frontier Large Vision-Language Model with Versatile Abilities (paperswithcode.com)
3 points by belter on Aug 25, 2023 | past
Papers with Code State-of-the-Art Benchmarks (paperswithcode.com)
4 points by bcjordan on Aug 13, 2023 | past
Code Generation on HumanEval Leaderboard (paperswithcode.com)
2 points by bcjordan on Aug 13, 2023 | past
A Differential Datalog Interpreter (paperswithcode.com)
1 point by MLIR on July 31, 2023 | past | 2 comments
RepoFusion: Training Code Models to Understand Your Repository (paperswithcode.com)
2 points by geox on July 7, 2023 | past
From Zero to Hero:Harnessing Transformers for Zero- and Few-Shot Biomedical NER (paperswithcode.com)
2 points by nikolamilosevic on June 28, 2023 | past
Automaton and Cognition: Structured Thoughts Automaton (paperswithcode.com)
4 points by tristanvdb on June 21, 2023 | past | 1 comment
PyTorch has won: 59% of papers use it vs. 5% for TensorFlow (paperswithcode.com)
4 points by rkrzr on May 19, 2023 | past | 2 comments
StarCoder: May the Source Be with You (paperswithcode.com)
3 points by PaulHoule on May 11, 2023 | past | 1 comment
Transformers (paperswithcode.com)
1 point by tosh on May 1, 2023 | past
Most Language Models Can Be Poets Too (paperswithcode.com)
1 point by Der_Einzige on April 29, 2023 | past
Making AI Less “Thirsty”: The Secret Water Footprint of AI Models (paperswithcode.com)
2 points by geox on April 14, 2023 | past | 1 comment
Large Language Models perform autonomous scientific research (paperswithcode.com)
1 point by og_kalu on April 12, 2023 | past
MMLU Benchmark (Multi-Task Language Understanding) (paperswithcode.com)
2 points by ZeljkoS on March 30, 2023 | past
Detecting Virtual Learning Disengagement Using Convolutional Network Autoencoder (paperswithcode.com)
1 point by Jimmc414 on March 3, 2023 | past
ST-Moe: Designing Stable and Transferable Sparse Expert Models (paperswithcode.com)
1 point by sharemywin on Feb 21, 2023 | past | 1 comment
Device JNEEG to convert Jetson Nano to brain-Computer interfaces. Short report (paperswithcode.com)
1 point by Mark_Frenk on Jan 27, 2023 | past | 1 comment
Evaluating the Cost of Atomic Operations on Modern Architectures (paperswithcode.com)
2 points by rck on Jan 18, 2023 | past
Cramming: Training a Language Model on a Single GPU in One Day (paperswithcode.com)
2 points by tosh on Dec 30, 2022 | past
“Most language models can be poets too ” (paperswithcode.com)
1 point by Der_Einzige on Dec 4, 2022 | past

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: