- MagicLens: Self-Supervised Image Retrieval with Open-Ended Instructions - [Arxiv] [QA]
- GraspXL: Generating Grasping Motions for Diverse Objects at Scale - [Arxiv] [QA]
- Human-compatible driving partners through data-regularized self-play reinforcement learning - [Arxiv] [QA]
- Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models - [Arxiv] [QA]
- Asymmetric and trial-dependent modeling: the contribution of LIA to SdSV Challenge Task 2 - [Arxiv] [QA]
- Retrieval-Enhanced Knowledge Editing for Multi-Hop Question Answering in Language Models - [Arxiv] [QA]
- Top-$k$ Classification and Cardinality-Aware Prediction - [Arxiv] [QA]
- RH20T-P: A Primitive-Level Robotic Dataset Towards Composable Generalization Agents - [Arxiv] [QA]
- SAID-NeRF: Segmentation-AIDed NeRF for Depth Completion of Transparent Objects - [Arxiv] [QA]
- Semantic Map-based Generation of Navigation Instructions - [Arxiv] [QA]
- Behavior Trees in Industrial Applications: A Case Study in Underground Explosive Charging - [Arxiv] [QA]
- Genetic Quantization-Aware Approximation for Non-Linear Operations in Transformers - [Arxiv] [QA]
- DenseNets Reloaded: Paradigm Shift Beyond ResNets and ViTs - [Arxiv] [QA]
- Keypoint Action Tokens Enable In-Context Imitation Learning in Robotics - [Arxiv] [QA]
- Swarm Characteristics Classification Using Neural Networks - [Arxiv] [QA]
- GrINd: Grid Interpolation Network for Scattered Observations - [Arxiv] [QA]
- Self-Improved Learning for Scalable Neural Combinatorial Optimization - [Arxiv] [QA]
- Improving Adversarial Data Collection by Supporting Annotators: Lessons from GAHD, a German Hate Speech Dataset - [Arxiv] [QA]
- GlORIE-SLAM: Globally Optimized RGB-only Implicit Encoding Point Cloud SLAM - [Arxiv] [QA]
- WaterJudge: Quality-Detection Trade-off when Watermarking Large Language Models - [Arxiv] [QA]
- Croissant: A Metadata Format for ML-Ready Datasets - [Arxiv] [QA]
- Lamarckian Inheritance Improves Robot Evolution in Dynamic Environments - [Arxiv] [QA]
- Model Stock: All we need is just a few fine-tuned models - [Arxiv] [QA]
- Interpreting Key Mechanisms of Factual Recall in Transformer-Based Language Models - [Arxiv] [QA]
- SineNet: Learning Temporal Dynamics in Time-Dependent Partial Differential Equations - [Arxiv] [QA]
- Papers for 2024
- Papers for 2023
- Papers for 2022
- Papers for 2021
- Papers for 2020
- Papers for 2019
- Papers for 2018
- Papers for 2017
- Papers for 2016
- Papers for 2015
- Papers for 2014
- Papers for 2013
- Papers for 2012
- Papers for 2010
- Papers for 2009
This project is made possible through the generous support of Anthropic, who provided free access to the Claude-2.1
API.