{"list":"other","total":66,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"id":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288},{"id":"2004.05150","title":"Longformer: The Long-Document Transformer","created":"2020-04-10","cited_by_count":3413},{"id":"2307.15818","title":"RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control","created":"2023-07-28","cited_by_count":3080},{"id":"2011.10566","title":"Exploring Simple Siamese Representation Learning","created":"2020-11-20","cited_by_count":2866},{"id":"2211.09800","title":"InstructPix2Pix: Learning to Follow Image Editing Instructions","created":"2022-11-17","cited_by_count":2611},{"id":"2304.08818","title":"Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models","created":"2023-04-18","cited_by_count":1476},{"id":"2110.08207","title":"Multitask Prompted Training Enables Zero-Shot Task Generalization","created":"2021-10-15","cited_by_count":1470},{"id":"2105.01601","title":"MLP-Mixer: An all-MLP Architecture for Vision","created":"2021-05-04","cited_by_count":1446},{"id":"2309.08600","title":"Sparse Autoencoders Find Highly Interpretable Features in Language Models","created":"2023-09-15","cited_by_count":1420},{"id":"1610.01644","title":"Understanding intermediate layers using linear classifier probes","created":"2016-10-05","cited_by_count":1353},{"id":"2310.01405","title":"Representation Engineering: A Top-Down Approach to AI Transparency","created":"2023-10-02","cited_by_count":1336},{"id":"1711.11279","title":"Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)","created":"2017-11-30","cited_by_count":1319},{"id":"2103.03206","title":"Perceiver: General Perception with Iterative Attention","created":"2021-03-04","cited_by_count":1104},{"id":"2312.06681","title":"Steering Llama 2 via Contrastive Activation Addition","created":"2023-12-09","cited_by_count":1085},{"id":"2209.10652","title":"Toy Models of Superposition","created":"2022-09-21","cited_by_count":971},{"id":"2308.10248","title":"Steering Language Models With Activation Engineering","created":"2023-08-20","cited_by_count":922},{"id":"2008.08186","title":"Prevalence of Neural Collapse during the terminal phase of deep learning training","created":"2020-08-18","cited_by_count":719},{"id":"2301.00493","title":"Argoverse 2: Next Generation Datasets for Self-Driving Perception and Forecasting","created":"2023-01-02","cited_by_count":707},{"id":"2109.12098","title":"CLIPort: What and Where Pathways for Robotic Manipulation","created":"2021-09-24","cited_by_count":622},{"id":"2406.04093","title":"Scaling and evaluating sparse autoencoders","created":"2024-06-06","cited_by_count":553},{"id":"2104.10133","title":"Large Scale Interactive Motion Forecasting for Autonomous Driving : The Waymo Open Motion Dataset","created":"2021-04-20","cited_by_count":537},{"id":"2312.14150","title":"DriveLM: Driving with Graph Visual Question Answering","created":"2023-12-21","cited_by_count":536},{"id":"1712.09707","title":"Deep learning for universal linear embeddings of nonlinear dynamics","created":"2017-12-27","cited_by_count":494},{"id":"2310.01412","title":"DriveGPT4: Interpretable End-to-end Autonomous Driving via Large Language Model","created":"2023-10-02","cited_by_count":461},{"id":"2203.08063","title":"MotionCLIP: Exposing Human Motion Generation to CLIP Space","created":"2022-03-15","cited_by_count":408},{"id":"2102.06701","title":"Explaining Neural Scaling Laws","created":"2021-02-12","cited_by_count":363},{"id":"2312.07488","title":"LMDrive: Closed-Loop End-to-End Driving with Large Language Models","created":"2023-12-12","cited_by_count":305},{"id":"2207.05844","title":"Wayformer: Motion Forecasting via Simple & Efficient Attention Networks","created":"2022-07-12","cited_by_count":280},{"id":"1703.04394","title":"Zero-Shot Learning -- The Good, the Bad and the Ugly","created":"2017-03-13","cited_by_count":255},{"id":"2205.05124","title":"Extracting Latent Steering Vectors from Pretrained Language Models","created":"2022-05-10","cited_by_count":225},{"id":"2305.14909","title":"Leveraging Pre-trained Large Language Models to Construct and Utilize World Models for Model-based Task Planning","created":"2023-05-24","cited_by_count":207},{"id":"2309.16292","title":"DiLu: A Knowledge-Driven Approach to Autonomous Driving with Large Language Models","created":"2023-09-28","cited_by_count":207},{"id":"1710.11379","title":"Latent Space Oddity: on the Curvature of Deep Generative Models","created":"2017-10-31","cited_by_count":174},{"id":"1601.03764","title":"Linear Algebraic Structure of Word Senses, with Applications to Polysemy","created":"2016-01-14","cited_by_count":165},{"id":"2311.10813","title":"A Language Agent for Autonomous Driving","created":"2023-11-17","cited_by_count":164},{"id":"2105.00470","title":"On Feature Decorrelation in Self-Supervised Learning","created":"2021-05-02","cited_by_count":160},{"id":"2307.07162","title":"Drive Like a Human: Rethinking Autonomous Driving with Large Language Models","created":"2023-07-14","cited_by_count":160},{"id":"2309.16534","title":"MotionLM: Multi-Agent Motion Forecasting as Language Modeling","created":"2023-09-28","cited_by_count":156},{"id":"2301.06051","title":"DSVT: Dynamic Sparse Voxel Transformer with Rotated Sets","created":"2023-01-15","cited_by_count":122},{"id":"2204.00673","title":"Learnable latent embeddings for joint behavioral and neural analysis","created":"2022-04-01","cited_by_count":117},{"id":"2003.02236","title":"Forecasting Sequential Data using Consistent Koopman Autoencoders","created":"2020-03-04","cited_by_count":115},{"id":"2306.06344","title":"Language-Guided Traffic Simulation via Scene-Level Diffusion","created":"2023-06-10","cited_by_count":111},{"id":"2112.15121","title":"On the Role of Neural Collapse in Transfer Learning","created":"2021-12-30","cited_by_count":100},{"id":"2406.04267","title":"Transformers need glasses! Information over-squashing in language tasks","created":"2024-06-06","cited_by_count":91},{"id":"2307.07947","title":"Language Conditioned Traffic Generation","created":"2023-07-16","cited_by_count":87},{"id":"2404.10179","title":"Scaling Instructable Agents Across Many Simulated Worlds","created":"2024-03-13","cited_by_count":71},{"id":"2310.17642","title":"Drive Anywhere: Generalizable End-to-end Autonomous Driving with Multi-modal Foundation Models","created":"2023-10-26","cited_by_count":59},{"id":"2402.01618","title":"Style Vectors for Steering Generative Large Language Model","created":"2024-02-02","cited_by_count":56},{"id":"2405.17767","title":"Linguistic Collapse: Neural Collapse in (Large) Language Models","created":"2024-05-28","cited_by_count":38},{"id":"2306.00966","title":"The Hidden Language of Diffusion Models","created":"2023-06-01","cited_by_count":34},{"id":"2305.03302","title":"High-Fidelity 3D Face Generation from Natural Language Descriptions","created":"2023-05-05","cited_by_count":33},{"id":"2305.15614","title":"Reverse Engineering Self-Supervised Learning","created":"2023-05-24","cited_by_count":33},{"id":"2310.12970","title":"Real-Time Motion Prediction via Heterogeneous Polyline Transformer with Relative Pose Encoding","created":"2023-10-19","cited_by_count":33},{"id":"2406.03008","title":"DriVLMe: Enhancing LLM-based Autonomous Driving Agents with Embodied and Social Experiences","created":"2024-06-05","cited_by_count":27},{"id":"2110.09741","title":"Trajectory Prediction with Linguistic Representations","created":"2021-10-19","cited_by_count":13},{"id":"2206.10041","title":"MPA: MultiPath++ Based Architecture for Motion Prediction","created":"2022-06-20","cited_by_count":13},{"id":"2403.11057","title":"Large Language Models Powered Context-aware Motion Prediction in Autonomous Driving","created":"2024-03-17","cited_by_count":13},{"id":"2305.01777","title":"Representation Learning via Manifold Flattening and Reconstruction","created":"2023-05-02","cited_by_count":11},{"id":"2306.10840","title":"RedMotion: Motion Prediction via Redundancy Reduction","created":"2023-06-19","cited_by_count":6}],"next_cursor":null}