{"total":15,"rows":[{"id":"2204.00598","title":"Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language","created":"2022-04-01","cited_by_count":513,"area":"lr"},{"id":"2212.09597","title":"Reasoning with Language Model Prompting: A Survey","created":"2022-12-19","cited_by_count":252,"area":"lr"},{"id":"2309.15402","title":"Navigate through Enigmatic Labyrinth A Survey of Chain of Thought Reasoning: Advances, Frontiers and Future","created":"2023-09-27","cited_by_count":184,"area":"lr"},{"id":"2501.03230","title":"Video-of-Thought: Step-by-Step Video Reasoning from Perception to Cognition","created":"2024-05-07","cited_by_count":153,"area":"lr"},{"id":"2207.12647","title":"Cross-Modal Causal Relational Reasoning for Event-Level Visual Question Answering","created":"2022-07-26","cited_by_count":57,"area":"lr"},{"id":"2310.15747","title":"Large Language Models are Temporal and Causal Reasoners for Video Question Answering","created":"2023-10-24","cited_by_count":51,"area":"lr"},{"id":"2202.04800","title":"The Abduction of Sherlock Holmes: A Dataset for Visual Abductive Reasoning","created":"2022-02-10","cited_by_count":38,"area":"lr"},{"id":"2203.14040","title":"Visual Abductive Reasoning","created":"2022-03-26","cited_by_count":30,"area":"lr"},{"id":"2207.12576","title":"WinoGAViL: Gamified Association Benchmark to Challenge Vision-and-Language Models","created":"2022-07-25","cited_by_count":20,"area":"lr"},{"id":"2501.01426","title":"Unifying Specialized Visual Encoders for Video Language Models","created":"2025-01-02","cited_by_count":10,"area":"lr"},{"id":"2511.16669","title":"Video-as-Answer: Predict and Generate Next Video Event with Joint-GRPO","created":"2025-11-20","cited_by_count":9,"area":"lr"},{"id":"2305.13903","title":"Let's Think Frame by Frame with VIP: A Video Infilling and Prediction Dataset for Evaluating Video Chain-of-Thought","created":"2023-05-23","cited_by_count":5,"area":"lr"},{"id":"2502.19409","title":"ImageChain: Advancing Sequential Image-to-Text Reasoning in Multimodal Large Language Models","created":"2025-02-26","cited_by_count":4,"area":"lr"},{"id":"2304.02313","title":"Personality-aware Human-centric Multimodal Reasoning: A New Task, Dataset and Baselines","created":"2023-04-05","cited_by_count":2,"area":"lr"},{"id":"2412.19304","title":"Perceive, Query & Reason: Enhancing Video QA with Question-Guided Temporal Queries","created":"2024-12-26","cited_by_count":2,"area":"lr"}],"next_cursor":null}