| 4051. |
Arctic-Embed 2.0: Multilingual Retrieval Without Compromise (arxiv.org) |
|
2 points by fzliu on Dec 10, 2024 | hide | past | pdf | discuss
|
|
| 4052. |
Can OpenAI o1 outperform humans in higher-order cognitive thinking? [pdf] (arxiv.org) |
|
2 points by bikenaga on Dec 10, 2024 | hide | past | pdf | discuss
|
|
| 4053. |
Training LLMs to Reason in a Continuous Latent Space (arxiv.org) |
|
283 points by omarsar on Dec 10, 2024 | hide | past | pdf | 114 comments
|
|
| 4054. |
Flow Matching Guide and Code (arxiv.org) |
|
3 points by lnyan on Dec 10, 2024 | hide | past | pdf | discuss
|
|
| 4055. |
PyPIM: Integrating Digital Processing-in-Memory from Microarchitectural Design (arxiv.org) |
|
2 points by pauloxnet on Dec 10, 2024 | hide | past | pdf | 1 comment
|
|
| 4056. |
LightLLM: A Versatile Large Language Model for Predictive Light Sensing (arxiv.org) |
|
1 point by PaulHoule on Dec 9, 2024 | hide | past | pdf | discuss
|
|
| 4057. |
GhostRNN: Reducing State Redundancy in RNN with Cheap Operations (arxiv.org) |
|
2 points by PaulHoule on Dec 9, 2024 | hide | past | pdf | discuss
|
|
| 4058. |
Semantic Retrieval at Walmart (arxiv.org) |
|
2 points by sonabinu on Dec 9, 2024 | hide | past | pdf | 1 comment
|
|
| 4059. |
Transformers Struggle to Learn to Search (arxiv.org) |
|
2 points by omarsar on Dec 9, 2024 | hide | past | pdf | discuss
|
|
| 4060. |
The Llama 3 Herd of Models (arxiv.org) |
|
1 point by cloudsql on Dec 9, 2024 | hide | past | pdf | discuss
|
|
| 4061. |
Reinforcement Learning: An Overview (arxiv.org) |
|
6 points by killme2008 on Dec 9, 2024 | hide | past | pdf | 1 comment
|
|
| 4062. |
RoboHanger: Learning Generalizable Robotic Hanger Insertion for Diverse Garments (arxiv.org) |
|
1 point by sandwichsphinx on Dec 9, 2024 | hide | past | pdf | discuss
|
|
| 4063. |
RL, But Don't Do Anything I Wouldn't Do (arxiv.org) |
|
1 point by optimalsolver on Dec 8, 2024 | hide | past | pdf | 2 comments
|
|
| 4064. |
Vulnerability of LLM Benchmarks: Do They Accurately Reflect True LLM Performance (arxiv.org) |
|
2 points by sandwichsphinx on Dec 8, 2024 | hide | past | pdf | discuss
|
|
| 4065. |
The Alignment Problem from a Deep Learning Perspective (arxiv.org) |
|
3 points by occamschainsaw on Dec 8, 2024 | hide | past | pdf | discuss
|
|
| 4066. |
Amplifying human performance in combinatorial competitive programming (arxiv.org) |
|
2 points by bmc7505 on Dec 7, 2024 | hide | past | pdf | discuss
|
|
| 4067. |
Reverse Thinking Makes LLMs Stronger Reasoners (arxiv.org) |
|
2 points by Anon84 on Dec 7, 2024 | hide | past | pdf | discuss
|
|
| 4068. |
Gradient Routing: Masking Gradients to Localize Computation in Neural Networks (arxiv.org) |
|
2 points by Eugeleo on Dec 7, 2024 | hide | past | pdf | discuss
|
|
| 4069. |
Enhancing Mathematical Reasoning in LLMs with Background Operators (arxiv.org) |
|
1 point by triska on Dec 7, 2024 | hide | past | pdf | discuss
|
|
| 4070. |
Densing Law of LLMs (arxiv.org) |
|
1 point by cyp0633 on Dec 7, 2024 | hide | past | pdf | discuss
|
|
| 4071. |
Mapping the Podcast Ecosystem with the Structured Podcast Research Corpus (arxiv.org) |
|
2 points by avyfain on Dec 6, 2024 | hide | past | pdf | discuss
|
|
| 4072. |
Intriguing Properties of Robust Classification (arxiv.org) |
|
1 point by lamename on Dec 6, 2024 | hide | past | pdf | discuss
|
|
| 4073. |
FlashAttention on a Napkin:A Diagrammatic Approach to Deep Learning IO-Awareness (arxiv.org) |
|
5 points by mpweiher on Dec 6, 2024 | hide | past | pdf | discuss
|
|
| 4074. |
Compressing Large Language Models Using Low Rank and Low Precision Decomposition (arxiv.org) |
|
2 points by westurner on Dec 5, 2024 | hide | past | pdf | 1 comment
|
|
| 4075. |
PowerGraph: A power grid benchmark dataset for graph neural networks (arxiv.org) |
|
2 points by sandwichsphinx on Dec 5, 2024 | hide | past | pdf | discuss
|
|
| 4076. |
Distinguishing Ignorance from Error in LLM Hallucinations (arxiv.org) |
|
2 points by micrum on Dec 4, 2024 | hide | past | pdf | discuss
|
|
| 4077. |
Generative Agent Simulations of 1k People (arxiv.org) |
|
1 point by amrrs on Dec 4, 2024 | hide | past | pdf | discuss
|
|
| 4078. |
The Surprising Effectiveness of Test-Time Training for Abstract Reasoning (arxiv.org) |
|
1 point by surprisetalk on Dec 4, 2024 | hide | past | pdf | discuss
|
|
| 4079. |
OpenHumanVid: Large-Scale High-Quality Dataset Enhancing Human-Centric Video Gen (arxiv.org) |
|
2 points by sandwichsphinx on Dec 4, 2024 | hide | past | pdf | discuss
|
|
| 4080. |
Effective Strategies for Mitigating Hallucinations in LLMs for Data Analytics (arxiv.org) |
|
2 points by micrum on Dec 3, 2024 | hide | past | pdf | discuss
|
|
|
| More |
