Papers World Knowledge
“World Knowledge” 태그가 달린 논문 818편 · 필터 해제
HRSeg: High-Resolution Visual Perception and Enhancement for Reasoning Segmentation
The reasoning segmentation task involves segmenting objects within an image by interpreting implicit user instructions, which may encompass subtleties such as contextual cues and open-world knowledge. Despite significant…
Reasoning SegmentationWorld KnowledgeComparing Apples to Oranges: A Dataset & Analysis of LLM Humour Understanding from Traditional Puns to Topical Jokes
Humour, as a complex language form, is derived from myriad aspects of life, whilst existing work on computational humour has focussed almost exclusively on short pun-based jokes. In this work, we investigate whether the …
Common Sense ReasoningWorld KnowledgeKEN: Knowledge Augmentation and Emotion Guidance Network for Multimodal Fake News Detection
In recent years, the rampant spread of misinformation on social media has made accurate detection of multimodal fake news a critical research focus. However, previous research has not adequately understood the semantics …
Fake News DetectionMisinformationWorld KnowledgeVideo Event Reasoning and Prediction by Fusing World Knowledge from LLMs with Vision Foundation Models
Current video understanding models excel at recognizing "what" is happening but fall short in high-level cognitive tasks like causal reasoning and future prediction, a limitation rooted in their lack of commonsense world…
Future predictionLarge Language ModelVideo UnderstandingWorld Knowledge+1DreamVLA: A Vision-Language-Action Model Dreamed with Comprehensive World Knowledge
Recent advances in vision-language-action (VLA) models have shown promise in integrating image generation with action prediction to improve generalization and reasoning in robot manipulation. However, existing methods ar…
Image GenerationMultimodal ReasoningRobot ManipulationVision-Language-Action+1A Semi-supervised Scalable Unified Framework for E-commerce Query Classification
Query classification, including multiple subtasks such as intent and category prediction, is vital to e-commerce applications. E-commerce queries are usually short and lack context, and the information between labels can…
ClassificationWorld KnowledgeMIRAGE: A Benchmark for Multimodal Information-Seeking and Reasoning in Agricultural Expert-Guided Conversations
We introduce MIRAGE, a new benchmark for multimodal expert-level reasoning and decision-making in consultative interaction settings. Designed for the agriculture domain, MIRAGE captures the full complexity of expert cons…
World KnowledgeFrom 2D to 3D Cognition: A Brief Survey of General World Models
World models have garnered increasing attention in the development of artificial general intelligence (AGI), serving as computational frameworks for learning representations of the external world and forecasting future s…
Autonomous DrivingScene GenerationSpatial ReasoningWorld KnowledgeMulti-Preference Lambda-weighted Listwise DPO for Dynamic Preference Alignment
While large-scale unsupervised language models (LMs) capture broad world knowledge and reasoning capabilities, steering their behavior toward desired objectives remains challenging due to the lack of explicit supervision…
Informativenessreinforcement-learningReinforcement LearningWorld KnowledgeImpliRet: Benchmarking the Implicit Fact Retrieval Challenge
Retrieval systems are central to many NLP pipelines, but often rely on surface-level cues such as keyword overlap and lexical semantic similarity. To evaluate retrieval beyond these shallow signals, recent benchmarks int…
BenchmarkingRetrievalSemantic SimilaritySemantic Textual Similarity+1AutoVLA: A Vision-Language-Action Model for End-to-End Autonomous Driving with Adaptive Reasoning and Reinforcement Fine-Tuning
Recent advancements in Vision-Language-Action (VLA) models have shown promise for end-to-end autonomous driving by leveraging world knowledge and reasoning capabilities. However, current VLA models often struggle with ph…
Action GenerationAutonomous DrivingTrajectory PlanningVision-Language-Action+1MMMG: A Massive, Multidisciplinary, Multi-Tier Generation Benchmark for Text-to-Image Reasoning
In this paper, we introduce knowledge image generation as a new task, alongside the Massive Multi-Discipline Multi-Tier Knowledge-Image Generation Benchmark (MMMG) to probe the reasoning capability of image generation mo…
Image GenerationMultimodal ReasoningText to Image GenerationText-to-Image Generation+1ConTextTab: A Semantics-Aware Tabular In-Context Learner
Tabular in-context learning (ICL) has recently achieved state-of-the-art (SOTA) performance on several tabular prediction tasks. Previously restricted to classification problems on small tables, recent advances such as T…
In-Context LearningWorld KnowledgeRoCA: Robust Cross-Domain End-to-End Autonomous Driving
End-to-end (E2E) autonomous driving has recently emerged as a new paradigm, offering significant potential. However, few studies have looked into the practical challenge of deployment across domains (e.g., cities). Altho…
Autonomous DrivingDomain AdaptationDomain GeneralizationWorld KnowledgeReCogDrive: A Reinforced Cognitive Framework for End-to-End Autonomous Driving
Although end-to-end autonomous driving has made remarkable progress, its performance degrades significantly in rare and long-tail scenarios. Recent approaches attempt to address this challenge by leveraging the rich worl…
Autonomous DrivingImitation LearningNavSimQuestion Answering+1Serendipitous Recommendation with Multimodal LLM
Conventional recommendation systems succeed in identifying relevant content but often fail to provide users with surprising or novel items. Multimodal Large Language Models (MLLMs) possess the world knowledge and multimo…
Recommendation SystemsWorld KnowledgeVid2Sim: Generalizable, Video-based Reconstruction of Appearance, Geometry and Physics for Mesh-free Simulation
Faithfully reconstructing textured shapes and physical properties from videos presents an intriguing yet challenging problem. Significant efforts have been dedicated to advancing such a system identification problem in t…
Computational EfficiencyWorld KnowledgeQuantifying Cross-Modality Memorization in Vision-Language Models
Understanding what and how neural networks memorize during training is crucial, both from the perspective of unintentional memorization of potentially sensitive information and from the standpoint of effective knowledge …
Machine UnlearningMemorizationWorld KnowledgeTIIF-Bench: How Does Your T2I Model Follow Your Instructions?
The rapid advancements of Text-to-Image (T2I) models have ushered in a new phase of AI-generated content, marked by their growing ability to interpret and follow user instructions. However, existing T2I model evaluation …
BenchmarkingInstruction FollowingWorld KnowledgeProbing the Geometry of Truth: Consistency and Generalization of Truth Directions in LLMs Across Logical Transformations and Question Answering Tasks
Large language models (LLMs) are trained on extensive datasets that encapsulate substantial world knowledge. However, their outputs often include confidently stated inaccuracies. Earlier works suggest that LLMs encode tr…
In-Context LearningNegationQuestion AnsweringWorld Knowledge