| 5551. |
The Unreasonable Ineffectiveness of the Deeper Layers (arxiv.org) |
|
4 points by WithinReason on Mar 27, 2024 | hide | past | pdf | discuss
|
|
| 5552. |
Correcting misinformation on social media with a large language model (arxiv.org) |
|
2 points by CharlesW on Mar 27, 2024 | hide | past | pdf | discuss
|
|
| 5553. |
Characterization of Large Language Model Development in the Datacenter (arxiv.org) |
|
1 point by mfiguiere on Mar 26, 2024 | hide | past | pdf | discuss
|
|
| 5554. |
Encode Once and Decode in Parallel: Efficient Transformer Decoding (arxiv.org) |
|
2 points by PaulHoule on Mar 26, 2024 | hide | past | pdf | discuss
|
|
| 5555. |
GPT-4V(ision) Unsuitable for Clinical Care and Education: An Evaluation (arxiv.org) |
|
75 points by PaulHoule on Mar 26, 2024 | hide | past | pdf | 52 comments
|
|
| 5556. |
An overview of gradient descent optimization algorithms (2017) (arxiv.org) |
|
1 point by Anon84 on Mar 26, 2024 | hide | past | pdf | discuss
|
|
| 5557. |
ACDG-VTON: Accurate and Contained Diffusion Generation for Virtual Try-On (arxiv.org) |
|
2 points by PaulHoule on Mar 26, 2024 | hide | past | pdf | discuss
|
|
| 5558. |
Learning the greatest common divisor: explaining transformer predictions (arxiv.org) |
|
1 point by mfiguiere on Mar 25, 2024 | hide | past | pdf | discuss
|
|
| 5559. |
Is GPT-4 a good data analyst? (2023) (arxiv.org) |
|
63 points by CharlesW on Mar 25, 2024 | hide | past | pdf | 106 comments
|
|
| 5560. |
Epistemology of Language Models: Do Language Models Have Holistic Knowledge? (arxiv.org) |
|
1 point by rntn on Mar 25, 2024 | hide | past | pdf | discuss
|
|
| 5561. |
Generator-Guided Crowd Reaction Assessment (arxiv.org) |
|
1 point by PaulHoule on Mar 25, 2024 | hide | past | pdf | 1 comment
|
|
| 5562. |
Large Language Models: A Survey (arxiv.org) |
|
5 points by Anon84 on Mar 25, 2024 | hide | past | pdf | discuss
|
|
| 5563. |
Prompt Design and Engineering: Introduction and Advanced Methods (arxiv.org) |
|
1 point by Anon84 on Mar 25, 2024 | hide | past | pdf | discuss
|
|
| 5564. |
Enhancing Depression-Diagnosis-Oriented Chat with Psychological State Tracking (arxiv.org) |
|
1 point by PaulHoule on Mar 25, 2024 | hide | past | pdf | discuss
|
|
| 5565. |
Text Clustering with LLM Embeddings (arxiv.org) |
|
1 point by Anon84 on Mar 25, 2024 | hide | past | pdf | discuss
|
|
| 5566. |
Linearity of Relation Decoding in Transformer Language Models (arxiv.org) |
|
2 points by belter on Mar 25, 2024 | hide | past | pdf | discuss
|
|
| 5567. |
Thermometer: Towards Universal Calibration for Large Language Models (arxiv.org) |
|
1 point by PaulHoule on Mar 25, 2024 | hide | past | pdf | discuss
|
|
| 5568. |
Rotational Equilibrium: How Weight Decay Balances Learning Across NeuralNetworks (arxiv.org) |
|
2 points by veryluckyxyz on Mar 25, 2024 | hide | past | pdf | discuss
|
|
| 5569. |
LightIt: Illumination Modeling and Control for Diffusion Models (arxiv.org) |
|
2 points by PaulHoule on Mar 25, 2024 | hide | past | pdf | discuss
|
|
| 5570. |
Explorer: Exploration-Guided Reasoning for Textual Reinforcement Learning (arxiv.org) |
|
25 points by PaulHoule on Mar 24, 2024 | hide | past | pdf | 1 comment
|
|
| 5571. |
Perl: Parameter Efficient Reinforcement Learning from Human Feedback (arxiv.org) |
|
3 points by PaulHoule on Mar 24, 2024 | hide | past | pdf | discuss
|
|
| 5572. |
Rad-PHI2: Instruction Tuning Phi-2 for Radiology (arxiv.org) |
|
2 points by PaulHoule on Mar 24, 2024 | hide | past | pdf | discuss
|
|
| 5573. |
Climatic-Aware Terrain Generation with Geological Sketch Guidance (arxiv.org) |
|
6 points by anticensor on Mar 24, 2024 | hide | past | pdf | discuss
|
|
| 5574. |
The Expressive Power of Transformers with Chain of Thought (Revised) (arxiv.org) |
|
20 points by yawboakye on Mar 24, 2024 | hide | past | pdf | 1 comment
|
|
| 5575. |
Simulating Weighted Automata over Sequences and Trees with Transformers (arxiv.org) |
|
3 points by PaulHoule on Mar 23, 2024 | hide | past | pdf | discuss
|
|
| 5576. |
Exploring Language Model's Code Generation Ability with Auxiliary Functions (arxiv.org) |
|
2 points by PaulHoule on Mar 23, 2024 | hide | past | pdf | discuss
|
|
| 5577. |
Study on Persuasiveness of LLMs (arxiv.org) |
|
3 points by cataflam on Mar 22, 2024 | hide | past | pdf | discuss
|
|
| 5578. |
DenseFormer: Enhancing Information Flow in Transformers (arxiv.org) |
|
123 points by tipsytoad on Mar 22, 2024 | hide | past | pdf | 33 comments
|
|
| 5579. |
The Elements of Differentiable Programming (arxiv.org) |
|
131 points by leephillips on Mar 22, 2024 | hide | past | pdf | 77 comments
|
|
| 5580. |
The Myth of Software Portability and Implications for ML Progress (2023) (arxiv.org) |
|
3 points by tosh on Mar 22, 2024 | hide | past | pdf | discuss
|
|
|
| More |
