{"list":"other","total":64,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2210.03629","title":"ReAct: Synergizing Reasoning and Acting in Language Models","created":"2022-10-06","cited_by_count":8695},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2301.12597","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","created":"2023-01-30","cited_by_count":6137},{"id":"2502.13923","title":"Qwen2.5-VL Technical Report","created":"2025-02-19","cited_by_count":5587},{"id":"1706.04599","title":"On Calibration of Modern Neural Networks","created":"2017-06-14","cited_by_count":4960},{"id":"2205.11916","title":"Large Language Models are Zero-Shot Reasoners","created":"2022-05-24","cited_by_count":4374},{"id":"1612.00837","title":"Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering","created":"2016-12-02","cited_by_count":2516},{"id":"2207.05221","title":"Language Models (Mostly) Know What They Know","created":"2022-07-11","cited_by_count":1856},{"id":"2305.10355","title":"Evaluating Object Hallucination in Large Vision-Language Models","created":"2023-05-17","cited_by_count":1729},{"id":"2209.07753","title":"Code as Policies: Language Model Programs for Embodied Control","created":"2022-09-16","cited_by_count":1210},{"id":"2005.04118","title":"Beyond Accuracy: Behavioral Testing of NLP models with CheckList","created":"2020-05-08","cited_by_count":1006},{"id":"1705.08500","title":"Selective Classification for Deep Neural Networks","created":"2017-05-23","cited_by_count":852},{"id":"2302.09664","title":"Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generation","created":"2023-02-19","cited_by_count":819},{"id":"2401.06209","title":"Eyes Wide Shut? Exploring the Visual Shortcomings of Multimodal LLMs","created":"2024-01-11","cited_by_count":735},{"id":"2504.05299","title":"SmolVLM: Redefining small and efficient multimodal models","created":"2025-04-07","cited_by_count":237},{"id":"2410.07073","title":"Pixtral 12B","created":"2024-10-09","cited_by_count":179},{"id":"2408.12637","title":"Building and better understanding vision-language models: insights and future directions","created":"2024-08-22","cited_by_count":173},{"id":"2106.08261","title":"Physion: Evaluating Physical Prediction from Vision in Humans and Machines","created":"2021-06-15","cited_by_count":153},{"id":"2407.06581","title":"Vision language models are blind: Failing to translate detailed visual features into words","created":"2024-07-09","cited_by_count":147},{"id":"1908.05656","title":"PHYRE: A New Benchmark for Physical Reasoning","created":"2019-08-15","cited_by_count":137},{"id":"2103.02438","title":"Deep Adaptive Design: Amortizing Sequential Bayesian Experimental Design","created":"2021-03-03","cited_by_count":106},{"id":"1603.02729","title":"Revisiting Active Perception","created":"2016-03-08","cited_by_count":94},{"id":"1604.03670","title":"Interactive Perception: Leveraging Action in Perception and Perception in Action","created":"2016-04-13","cited_by_count":78},{"id":"2306.15668","title":"Physion++: Evaluating Physical Scene Understanding that Requires Online Inference of Different Physical Properties","created":"2023-06-27","cited_by_count":54},{"id":"1611.01843","title":"Learning to Perform Physics Experiments via Deep Reinforcement Learning","created":"2016-11-06","cited_by_count":47},{"id":"2411.08027","title":"LLMPhy: Parameter-Identifiable Physical Reasoning Combining Large Language Models and Physics Engines","created":"2024-11-12","cited_by_count":30},{"id":"2601.03555","title":"SCRIBE: Structured Mid-Level Supervision for Tool-Using Language Models","created":"2026-01-07","cited_by_count":21},{"id":"2411.15477","title":"Towards Robust Evaluation of Unlearning in LLMs via Data Transformations","created":"2024-11-23","cited_by_count":20},{"id":"2309.08182","title":"Using Large Language Model to Solve and Explain Physics Word Problems Approaching Human Level","created":"2023-09-15","cited_by_count":16},{"id":"1910.05672","title":"Optic-Net: A Novel Convolutional Neural Network for Diagnosis of Retinal Diseases from Optical Tomography Images","created":"2019-10-13","cited_by_count":15},{"id":"2509.23292","title":"Learning How to Use Tools, Not Just When: Pattern-Aware Tool-Integrated Reasoning","created":"2025-09-27","cited_by_count":15},{"id":"2508.15124","title":"Side Effects of Erasing Concepts from Diffusion Models","created":"2025-08-20","cited_by_count":13},{"id":"2606.00305","title":"Bridging Reasoning Trajectories in On-Policy Distillation via Near-Future Guidance","created":"2026-05-29","cited_by_count":13},{"id":"2412.14368","title":"Beyond Math: Stories as a Testbed for Memorization-Constrained Reasoning in LLMs","created":"2024-12-18","cited_by_count":12},{"id":"2601.06853","title":"DAGGER: Distractor-Aware Graph Generation for Executable Reasoning in Math Problems","created":"2026-01-11","cited_by_count":9},{"id":"2206.09203","title":"Interactive Visual Reasoning under Uncertainty","created":"2022-06-18","cited_by_count":8},{"id":"2503.05786","title":"FedMentalCare: Towards Privacy-Preserving Fine-Tuned LLMs to Analyze Mental Health Status Using Federated Learning Framework","created":"2025-02-27","cited_by_count":8},{"id":"2607.07907","title":"Multimodal Unlearning Across Vision, Language, Video, and Audio: Survey of Methods, Datasets, and Benchmarks","created":"2026-07-08","cited_by_count":7},{"id":"2404.07410","title":"Improving Shift Invariance in Convolutional Neural Networks with Translation Invariant Polyphase Sampling","created":"2024-04-11","cited_by_count":6},{"id":"2510.03898","title":"Read Between the Lines: A Benchmark for Uncovering Political Bias in Bangla News Articles","created":"2025-10-04","cited_by_count":6},{"id":"2603.27187","title":"Omni-Modal Dissonance Benchmark: Systematically Breaking Modality Consensus to Probe Robustness and Calibrated Abstention","created":"2026-03-28","cited_by_count":6},{"id":"2605.13414","title":"TRIAGE: Evaluating Prospective Metacognitive Control in LLMs under Resource Constraints","created":"2026-05-13","cited_by_count":6},{"id":"2502.18536","title":"FilterRAG: Zero-Shot Informed Retrieval-Augmented Generation to Mitigate Hallucinations in VQA","created":"2025-02-25","cited_by_count":5},{"id":"2508.16838","title":"If We May De-Presuppose: Robustly Verifying Claims through Presupposition-Free Question Decomposition","created":"2025-08-22","cited_by_count":5},{"id":"2509.14275","title":"FedMentor: Domain-Aware Differential Privacy for Heterogeneous Federated LLMs in Mental Health","created":"2025-09-16","cited_by_count":5},{"id":"2602.17469","title":"Cross-Lingual Sentiment Misalignment: Auditing Multilingual Language Models for Inversion Risk, Dialectal Representation, and Affective Stability","created":"2026-02-19","cited_by_count":5},{"id":"2509.16538","title":"VC-Inspector: Advancing Reference-free Evaluation of Video Captions with Factual Analysis","created":"2025-09-20","cited_by_count":4},{"id":"2602.02952","title":"UAT-LITE: Inference-Time Uncertainty-Aware Attention for Pretrained Transformers","created":"2026-02-03","cited_by_count":4},{"id":"2608.21031","title":"PhysCaP: Grounding Code-as-Policy Agent with Physics-Informed Exploration","created":"2026-08-21","cited_by_count":4},{"id":"2506.10202","title":"Q2E: Query-to-Event Decomposition for Zero-Shot Multilingual Text-to-Video Retrieval","created":"2025-06-11","cited_by_count":3},{"id":"2603.21165","title":"Many Dialects, Many Languages, One Cultural Lens: Evaluating Multilingual VLMs for Bengali Culture Understanding Across Historically Linked Languages and Regional Dialects","created":"2026-03-22","cited_by_count":3},{"id":"2605.08647","title":"AgentCollabBench: Diagnosing When Good Agents Make Bad Collaborators","created":"2026-05-09","cited_by_count":3},{"id":"2607.23492","title":"To Erase, or Not to Erase: Robust Training-Free Concept Erasure with Preservation aware Adaptive Ranked Subspace Expansion","created":"2026-07-26","cited_by_count":3},{"id":"2302.06134","title":"RFC-Net: Learning High Resolution Global Features for Medical Image Segmentation on a Computational Budget","created":"2023-02-13","cited_by_count":2},{"id":"2605.27858","title":"DecomposeRL: Learning to Ask Useful, Informative, and Diverse Questions for Semi-Supervised, Traceable Claim Verification","created":"2026-05-27","cited_by_count":2},{"id":"2606.20959","title":"Right Knowledge, Wrong Answer: Characterizing Parametric Temporal Conflict in Open-Weight Language Models","created":"2026-06-18","cited_by_count":2},{"id":"2606.21943","title":"Modularized Reinforcement Learning on LLMs: From MDP Creation to Exploration and Learning","created":"2026-06-20","cited_by_count":2},{"id":"2606.29315","title":"Hierarchical Experimentalist Agents","created":"2026-06-28","cited_by_count":2},{"id":"2607.04409","title":"Learning Task-Sufficient World Models by Synergizing Agentic Exploration and Structured Modeling","created":"2026-07-05","cited_by_count":2},{"id":"2608.22335","title":"Register Shifts Break LLM Safety: A Bengali Benchmark with Culturally Grounded Harms","created":"2026-08-23","cited_by_count":1},{"id":"2609.06490","title":"OracleZoom: On-Policy Self-Distillation Inspired Reference-Constrained Recursive Image Super Resolution","created":"2026-09-06","cited_by_count":1},{"id":"2609.06922","title":"BEFORE THE FLIP: Measuring Hidden Score Shifts In Quantized Vision Language Models Before The Answer Changes for Visual Question Answering","created":"2026-09-07","cited_by_count":1}],"next_cursor":null}