{"list":"other","total":55,"rows":[{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2309.06180","title":"Efficient Memory Management for Large Language Model Serving with PagedAttention","created":"2023-09-12","cited_by_count":5944},{"id":"2204.05862","title":"Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback","created":"2022-04-12","cited_by_count":3720},{"id":"2406.09246","title":"OpenVLA: An Open-Source Vision-Language-Action Model","created":"2024-06-13","cited_by_count":2887},{"id":"2408.00118","title":"Gemma 2: Improving Open Language Models at a Practical Size","created":"2024-07-31","cited_by_count":1998},{"id":"2306.02858","title":"Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding","created":"2023-06-05","cited_by_count":1471},{"id":"2105.03023","title":"DExperts: Decoding-Time Controlled Text Generation with Experts and Anti-Experts","created":"2021-05-07","cited_by_count":441},{"id":"1806.07011","title":"VirtualHome: Simulating Household Activities via Programs","created":"2018-06-19","cited_by_count":415},{"id":"2311.01378","title":"Vision-Language Foundation Models as Effective Robot Imitators","created":"2023-11-02","cited_by_count":349},{"id":"1709.02540","title":"The Expressive Power of Neural Networks: A View from the Width","created":"2017-09-08","cited_by_count":320},{"id":"1606.05336","title":"On the Expressive Power of Deep Neural Networks","created":"2016-06-16","cited_by_count":306},{"id":"2302.08399","title":"Large Language Models Fail on Trivial Alterations to Theory-of-Mind Tasks","created":"2023-02-16","cited_by_count":292},{"id":"1602.04485","title":"Benefits of depth in neural networks","created":"2016-02-14","cited_by_count":250},{"id":"1802.07740","title":"Machine Theory of Mind","created":"2018-02-21","cited_by_count":226},{"id":"2202.06417","title":"A Contrastive Framework for Neural Text Generation","created":"2022-02-13","cited_by_count":225},{"id":"2210.13312","title":"Neural Theory-of-Mind? On the Limits of Social Intelligence in Large LMs","created":"2022-10-24","cited_by_count":220},{"id":"2405.09711","title":"STAR: A Benchmark for Situated Reasoning in Real-World Videos","created":"2024-05-15","cited_by_count":213},{"id":"2308.10168","title":"Head-to-Tail: How Knowledgeable are Large Language Models (LLMs)? A.K.A. Will LLMs Replace Knowledge Graphs?","created":"2023-08-20","cited_by_count":168},{"id":"2309.10105","title":"Understanding Catastrophic Forgetting in Language Models via Implicit Inference","created":"2023-09-18","cited_by_count":144},{"id":"2407.12404","title":"Analyzing the Generalization and Reliability of Steering Vectors","created":"2024-07-17","cited_by_count":143},{"id":"2402.10058","title":"Towards Safer Large Language Models through Machine Unlearning","created":"2024-02-15","cited_by_count":139},{"id":"2406.00045","title":"Personalized Steering of Large Language Models: Versatile Steering Vectors Through Bi-directional Preference Optimization","created":"2024-05-28","cited_by_count":118},{"id":"2306.00924","title":"Minding Language Models' (Lack of) Theory of Mind: A Plug-and-Play Multi-Character Belief Tracker","created":"2023-06-01","cited_by_count":95},{"id":"2107.05612","title":"A Persistent Spatial Semantic Representation for High-level Natural Language Instruction Execution","created":"2021-07-12","cited_by_count":91},{"id":"2310.17722","title":"Large Language Models as Generalizable Policies for Embodied Tasks","created":"2023-10-26","cited_by_count":86},{"id":"2401.08743","title":"MMToM-QA: Multimodal Theory of Mind Question Answering","created":"2024-01-16","cited_by_count":85},{"id":"2305.12798","title":"Word Embeddings Are Steers for Language Models","created":"2023-05-22","cited_by_count":70},{"id":"2402.02992","title":"Decoding-time Realignment of Language Models","created":"2024-02-05","cited_by_count":67},{"id":"2410.01707","title":"Interpretable Contrastive Monte Carlo Tree Search Reasoning","created":"2024-10-02","cited_by_count":64},{"id":"2410.22108","title":"Protecting Privacy in Multimodal Large Language Models with MLLMU-Bench","created":"2024-10-29","cited_by_count":64},{"id":"2310.12962","title":"An Emulator for Fine-Tuning Large Language Models using Small Language Models","created":"2023-10-19","cited_by_count":61},{"id":"2503.19206","title":"Overtrained Language Models Are Harder to Fine-Tune","created":"2025-03-24","cited_by_count":58},{"id":"2410.05695","title":"Unlocking the Capabilities of Thought: A Reasoning Boundary Framework to Quantify and Optimize Chain-of-Thought","created":"2024-10-08","cited_by_count":56},{"id":"2408.12574","title":"MuMA-ToM: Multi-modal Multi-Agent Theory of Mind","created":"2024-08-22","cited_by_count":51},{"id":"2501.13453","title":"Spurious Forgetting in Continual Learning of Language Models","created":"2025-01-23","cited_by_count":51},{"id":"2102.12321","title":"AGENT: A Benchmark for Core Psychological Reasoning","created":"2021-02-24","cited_by_count":42},{"id":"2504.16053","title":"LongMamba: Enhancing Mamba's Long Context Capabilities via Training-Free Receptive Field Enlargement","created":"2025-04-22","cited_by_count":42},{"id":"2402.12343","title":"Emulated Disalignment: Safety Alignment for Large Language Models May Backfire!","created":"2024-02-19","cited_by_count":37},{"id":"2310.19619","title":"Towards A Holistic Landscape of Situated Theory of Mind in Large Language Models","created":"2023-10-30","cited_by_count":32},{"id":"1505.05957","title":"Joint Inference of Groups, Events and Human Roles in Aerial Videos","created":"2015-05-22","cited_by_count":30},{"id":"1901.06085","title":"Theory of Minds: Understanding Behavior in Groups Through Inverse Planning","created":"2019-01-18","cited_by_count":30},{"id":"2307.07063","title":"Bootstrapping Vision-Language Learning with Decoupled Language Pre-training","created":"2023-07-13","cited_by_count":28},{"id":"2502.15910","title":"Modality-Aware Neuron Pruning for Unlearning in Multimodal Large Language Models","created":"2025-02-21","cited_by_count":26},{"id":"2306.14325","title":"The Neuro-Symbolic Inverse Planning Engine (NIPE): Modeling Probabilistic Social Inferences from Linguistic Inputs","created":"2023-06-25","cited_by_count":23},{"id":"2502.06710","title":"Learning Musical Representations for Music Performance Question Answering","created":"2025-02-10","cited_by_count":17},{"id":"2503.02103","title":"Superficial Self-Improved Reasoners Benefit from Model Merging","created":"2025-03-03","cited_by_count":16},{"id":"2310.03291","title":"Expedited Training of Visual Conditioned Language Generation via Redundancy Reduction","created":"2023-10-05","cited_by_count":15},{"id":"2411.10606","title":"AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment","created":"2024-11-15","cited_by_count":12},{"id":"2502.13363","title":"Pretrained Image-Text Models are Secretly Video Captioners","created":"2025-02-19","cited_by_count":11},{"id":"2402.10416","title":"Grounding Language about Belief in a Bayesian Theory-of-Mind","created":"2024-02-16","cited_by_count":8},{"id":"2501.15773","title":"Is It Navajo? Accurate Language Detection in Endangered Athabaskan Languages","created":"2025-01-27","cited_by_count":3}],"next_cursor":null}