| 3961. |
Transformers Meet Neural Algorithmic Reasoners (arxiv.org) |
|
1 point by rntn on Dec 30, 2024 | hide | past | pdf | discuss
|
|
| 3962. |
Efficient Generative Modeling with Residual Vector Quantization-Based Tokens (arxiv.org) |
|
1 point by PaulHoule on Dec 29, 2024 | hide | past | pdf | discuss
|
|
| 3963. |
Modeling health trajectories with a transformer-based deep learning model (arxiv.org) |
|
1 point by PaulHoule on Dec 29, 2024 | hide | past | pdf | discuss
|
|
| 3964. |
ReAct: Synergizing Reasoning and Acting in Language Models (arxiv.org) |
|
3 points by sebg on Dec 28, 2024 | hide | past | pdf | discuss
|
|
| 3965. |
Empirical Study of Test Generation with LLM's (arxiv.org) |
|
40 points by nickpsecurity on Dec 28, 2024 | hide | past | pdf | 36 comments
|
|
| 3966. |
A Many Objective Problem Where Crossover Is Provably Indispensable (arxiv.org) |
|
1 point by crete on Dec 28, 2024 | hide | past | pdf | discuss
|
|
| 3967. |
Frontier AI systems have surpassed the self-replicating red line (arxiv.org) |
|
1 point by blacktulip on Dec 28, 2024 | hide | past | pdf | 1 comment
|
|
| 3968. |
Measuring and Understanding LLM Identity Confusion (arxiv.org) |
|
21 points by _____k on Dec 28, 2024 | hide | past | pdf | 1 comment
|
|
| 3969. |
Armada: Augmented Reality for Robot Manipulation and Robot-Free Data Acquisition (arxiv.org) |
|
6 points by sandwichsphinx on Dec 28, 2024 | hide | past | pdf | discuss
|
|
| 3970. |
Explaining Large Language Models Decisions Using Shapley Values (arxiv.org) |
|
89 points by veryluckyxyz on Dec 28, 2024 | hide | past | pdf | 19 comments
|
|
| 3971. |
The Famine of Forte: Few Search Problems Greatly Favor Your Algorithm (2016) (arxiv.org) |
|
1 point by pizza on Dec 28, 2024 | hide | past | pdf | discuss
|
|
| 3972. |
Rethinking Uncertainty Estimation in Natural Language Generation (arxiv.org) |
|
1 point by sroussey on Dec 27, 2024 | hide | past | pdf | discuss
|
|
| 3973. |
Language Model as Visual Explainer (arxiv.org) |
|
5 points by PaulHoule on Dec 27, 2024 | hide | past | pdf | discuss
|
|
| 3974. |
DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts LMs (arxiv.org) |
|
2 points by doener on Dec 27, 2024 | hide | past | pdf | discuss
|
|
| 3975. |
Towards Unsupervised Learning Scheme for Efficiently Solving Parameterized MIPS (arxiv.org) |
|
1 point by crete on Dec 27, 2024 | hide | past | pdf | discuss
|
|
| 3976. |
Are Language Models Actually Useful for Time Series Forecasting? (arxiv.org) |
|
7 points by cl42 on Dec 27, 2024 | hide | past | pdf | 7 comments
|
|
| 3977. |
When Every Token Counts: Optimal Segmentation for Low-Resource Language Models (arxiv.org) |
|
1 point by PaulHoule on Dec 27, 2024 | hide | past | pdf | discuss
|
|
| 3978. |
Improving feature interactions at Pinterest under industry constraints (arxiv.org) |
|
1 point by PaulHoule on Dec 26, 2024 | hide | past | pdf | discuss
|
|
| 3979. |
Deliberation in Latent Space via Differentiable Cache Augmentation [pdf] (arxiv.org) |
|
9 points by lawrenceyan on Dec 26, 2024 | hide | past | pdf | discuss
|
|
| 3980. |
Monolith: Real Time Recommendation System with Collisionless Embedding Table (arxiv.org) |
|
1 point by ianrahman on Dec 26, 2024 | hide | past | pdf | discuss
|
|
| 3981. |
Phi-4 Technical Report (arxiv.org) |
|
2 points by veryluckyxyz on Dec 25, 2024 | hide | past | pdf | discuss
|
|
| 3982. |
AlphaPruning: Using Heavy-Tailed Self Regularization for Improved LLM Pruning (arxiv.org) |
|
1 point by selimthegrim on Dec 25, 2024 | hide | past | pdf | discuss
|
|
| 3983. |
Brain-to-Text Benchmark '24 (arxiv.org) |
|
2 points by UCdallasGA on Dec 24, 2024 | hide | past | pdf | discuss
|
|
| 3984. |
LearnLM (arxiv.org) |
|
2 points by UCdallasGA on Dec 24, 2024 | hide | past | pdf | discuss
|
|
| 3985. |
Arbitrary-Steps Image Super-Resolution via Diffusion Inversion (arxiv.org) |
|
3 points by ChrisArchitect on Dec 23, 2024 | hide | past | pdf | discuss
|
|
| 3986. |
A High-Performance In-Browser LLM Inference Engine (arxiv.org) |
|
1 point by UCdallasGA on Dec 23, 2024 | hide | past | pdf | discuss
|
|
| 3987. |
Adversarial policies beat superhuman Go AIs (2023) (arxiv.org) |
|
306 points by amichail on Dec 23, 2024 | hide | past | pdf | 139 comments
|
|
| 3988. |
Offline Reinforcement Learning for LLM Multi-Step Reasoning (arxiv.org) |
|
111 points by belter on Dec 23, 2024 | hide | past | pdf | 9 comments
|
|
| 3989. |
SWE-Bench+: Enhanced Coding Benchmark for LLMs (arxiv.org) |
|
3 points by zeroonetwothree on Dec 23, 2024 | hide | past | pdf | discuss
|
|
| 3990. |
Selective Adapter Freezing for Memory-Efficient Fine-Tuning of Language Models (arxiv.org) |
|
2 points by PaulHoule on Dec 22, 2024 | hide | past | pdf | discuss
|
|
|
| More |
